Author Archives: Hussain Fakhruddin

Apple HomePod vs Amazon Echo: How Well Does Apple’s New Connected Speaker Stack Up?

The smart home speaker market is no longer a straight shootout between Amazon Echo and Google Home. At this year’s Worldwide Developers Conference (WWDC), Apple made its rather-delayed entry into the the domain of connected speakers – by announcing the multi-featured Apple HomePod (it will hit the markets in December). Given that more than 100 million smart speakers will be shipped by 2024, generating revenues of more than $14 million, the HomePod does have ample scopes to make a mark in this market. For that to happen though, it has to match up to the challenge of Amazon Echo (primarily), which debuted in 2014, and is currently by far the most popular AI-based smart speaker in the market (has a 3X lead over Google Home). We will here do an Apple HomePod vs Amazon Echo analysis, and try to determine which of these connected speakers comes out on top:

(Note: Amazon Echo has been in existence for over a couple of years, while Apple HomePod is yet to be launched. The comparison, if required, will be updated after the latter is commercially released)

  1. Speakers & Microphones

    Apple HomePod has been positioned primarily as a high-quality audio device – and it certainly has the edge as far as the built-in microphones and sound configuration architecture (upgraded Sonos-like speakers) are concerned. Each of the 7 tweeter speakers of the HomePod has its very own ‘custom amplifier’ setup (along with the 4” woofer). The single woofer (2.5”)+speaker combination of Amazon Echo rather pales in comparison with the much more advanced setup of Apple’s speaker. Also, Homepod has six far-field microphones (Amazon Echo has seven), along with a low-frequency mic. Casual listeners might not quite get the subtle improvements in sound quality that the HomePod will offer – but for the discerning users, it can well be a significant factor.

  2. Visual appeal

    By 2020, nearly 3 out of every 4 homes in the United states will have connected speakers (at least one). In other words, smart speakers are well on their way to becoming mainstream – and physically, they need to blend well with the actual room decors of end-users. Once again, Apple HomePod – with its typically minimalistic designs – would have the edge. It is less tall than the Amazon Echo (<7” compared to >9”) and is covered with the speaker grille. There is a glowing area at the top, just like Alexa blue that glows on the Amazon Echo when it is being talked to. The Echo is rather too conspicuous with its crisp cylindrical structure – and can tend to stick out in a room.

  3. Processor performance

    Apple HomePod is powered by the proprietary A8 chip (which debuted on iPhone 6/6 Plus a couple of years ago). It will allow the new speaker to deliver superior-quality audio performance, customized for different locations/rooms – thanks to the capability to analyze spatial data. Amazon Echo, which has the powerful DM3725CUS100 digital media processor, generally offers the same audio quality everywhere, and is not affected by locational changes. Make no mistake though – the audio quality of Amazon Echo is excellent, and the HomePod – with all its elaborate settings – will have a tough job of surpassing that.

  4. Utility as a well-rounded smart home device

    The Cupertino company has tried to avoid a head-on tussle with Amazon Echo, by positioning the HomePod as a ‘music first’ smart speaker (Siri was referred to as ‘musicologist’), and focusing primarily on the audio features of the device. There is built-in support for the HomeKit platform, allowing users to adjust room temperatures, switch on/off lights and other appliances, access weather information and perform other smart home tasks. There is no HomeKit-like hub for Amazon Echo, which relies on its third-party set of ‘Skills’, to provide a vast range of services for connected homes. Still, it seems that the target group of users for the two smart speakers will be different – those more interested in AI home assistants (with audio as an afterthought) will go for Amazon Echo, while people who are more concerned with the music/sound capabilities will consider the Apple HomePod.

Note: Amazon has also partnered with Samsung for the integration of SmartThings in Echo.

     5. Siri vs Alexa

Apple’s much-loved AI digital assistant Siri is getting smarter with time. It can offer contextual search options, translation services and a selection of other advanced features to HomePod users – tasks that Amazon’s Alexa is not equipped to perform. For regular web searches, information access and even timer-setting activities, the efficiency levels of Alexa and Siri are roughly the same (although the HomePod will be more likely to accurately understand voice commands in a crowded, noisy room). Alexa is a powerful AI digital assistant, but Siri on HomePod has the potential to be just a bit better.

     6. Trigger words

Amazon Echo offers greater options to users, when it comes to choice of ‘wake words’ or ‘trigger words’ to activate the device. ‘Alexa’ is, of course, the default word to ‘wake up the device’, but people can also use ‘Echo’, ‘Amazon’ and even ‘Computer’ (added in January 2017; a nod to ‘Star Trek’ fans, perhaps?) to get started in Echo. On the other hand HomePod will have the single ‘Hey Siri’ phrase to start up the HomePod. Not only are the options to ‘call’ the Amazon speaker more, it also seems natural to say its ‘wake words’ repeatedly, than having to say ‘Hey Siri’ (or, for that matter, ‘Ok Google’ for Google Home) many times.

    7. Platform and device compatibility

Although the usability of Apple HomePod will be limited to the iOS platform only (Amazon Echo can be paired with both Apple and Android phones), the extensive range of popular Apple home devices (iPhones and iPods and Macbooks and iPads) hand an advantage to the former. It will that much more easily integrable in the regular setup of smart devices used by people. Amazon Echo, on its part, has only its own speaker for playing music through (the smaller Echo Dot can be attached with speakers via 3.5 mm ports or via Bluetooth). Apple also has the option of enabling transfer of music/video files from the HomePod to Apple TV (as Google does for Home and Chromecast). If this feature is indeed incorporated, using Apple’s speaker would become really easy.

   8. Support for music stores

Amazon Echo fairly blows away the HomePod in terms of third-party music support. Users can stream music from Audible, Pandora, TuneIn, Spotify and iHeartRadio, in addition to Amazon Music and Prime Music, on the Echo speaker. In contrast, the HomePod will only have Apple Music to start things off. The audio experience on the new speaker will be more customized and (hopefully) of a better quality – but the sheer range of music support on the Echo makes it win this round hands-down.

   9. Multi-room functionality

Apple HomePod has this, while Amazon Echo does not. Apple announced the AirPlay 2 wifi standard last month – and that will ensure smooth multi-room support for the smart speaker in particular, and the HomeKit platform in general. Amazon Echo, in its present form, does not have any such comparable feature. However, there is a corollary to this: the support for third-party apps is very limited on AirPlay 2 (understandably, with it being a new standard). For regular single-room functions, the Echo does not have any such limitations.

Note: Multi-room support is offered by Google Home as well.

  10. Integration with third-party applications

Google Home arrived last year, and already has a fairly impressive list of supported third-party apps. Amazon Echo, by virtue of being the oldest player in the market – offers even more in this regard, with support for regular, essential applications like Sky News, National Rail and Uber. Apple HomePod is the new kid on the block, and it will take some time to build a network of supported apps. It can be reasonably expected that between now and December, there will be news of several new apps becoming available on the HomePod. For the moment though, it’s advantage to Echo in this context.

   11. Market share

The stranglehold that Amazon Echo has over the worldwide smart speaker market won’t make things easy for the HomePod. On average, 7 out of every 10 connected speakers sold is an Echo device – and there are, at present, well over 8 million people using this home speaker. The combined sales figure of Amazon Echo and Google Home will nudge towards 25 million units by the end of this year – a significant figure in a market that is not really wide yet. However, the smart home market is expanding rapidly – and if the Apple HomePod is as good as many tech enthusiasts feel it has the potential to be, there will be a market for it.

   12. The price factor

Apple has always been a company that makes ‘premium products’ (let’s forget about the icky iPhone 5C for the moment!). The Cupertino tech giant has retained that approach for the upcoming HomePod, which will be priced at a hefty $349 in the American market, nearly double the price tag of $179 for Amazon Echo. What’s more – for the consumer looking for a smart speaker that offers plenty of cool functions as well as an affordable price, Google Home ($129) can seem to be the best alternative. The cost of the smaller Amazon Echo Dot (second generation) is as low as $50. Apple has been trying to market the HomePod as much more than a smart speaker (hence the focus on audio/music, and less emphasis on Siri/AI capabilities) – but the much higher price point will be barrier for customer adoption – particularly since similar (and arguably, equally good) devices are available at much cheaper rates.

Compared to Amazon Echo, the form factor of the Apple HomePod has a slightly more bulky feel about it (Homepod weighs 5.5 pounds, while the weight of Echo is only 2.3 pounds). The more advanced mic and speaker setup of HomePod should offer better audio quality – but it remains to be seen whether that will be enough to motivate users to fork out the considerably higher price. There are no rooms for doubting that HomePod has several top-class features – but managing the steep price tag will be a big challenge. At the moment, it appears that HomePod will find favour among those who are already invested in the Apple device ecosystem, while for others, Amazon Echo (or Google Home) will remain the preferred choice.

We are still months away from the launch of Apple HomePod. A lot can change in the interim, and the new speaker might well get new features that enhance its overall attractions.

 

 

Drones In Agriculture: 15 Key Facts & Trends

 

An analysis of the use of drones in agriculture

 

The popularity of drone technology is soaring higher every quarter. The total number of drones produced this year is expected to reach 3 million – marking a ~40% YoY increase over 2016. Revenues from the usage of drones is climbing rapidly too, and according to a recent Gartner report, will go beyond $11 billion by the end of 2020. Agriculture has emerged as one of the most important fields for the application of drone technology, with the focus squarely on refinement and advancements in precision farming standards. The CAGR of the agricultural drone market is estimated to hover around 28% for the next 4-5 years – with its value nearing the $3000 million mark by 2021. In what follows, we will highlight on some latest trends and points of interest related to farming drones and their uses:

  1. Smarter crop planting

    Drones have the capacity to generate big savings for farmers. A classic instance of this is related to the task of planting seeds/crops on fields. Automated unmanned aerial vehicles (UAVs) are increasingly being used to place nutrients as well as pods/seeds in the soil – making the overall process much quicker (compared to manual planting), and bringing down the average expenses of planting by a whopping 85%. Planting drones can deliver uptake rates of up to 70%-75%, and are ideal for ensuring better sustainability of crops.

  2. Evolution of farming drones

    Till as late as 2015, the functions of drones in agriculture were limited. Most drones were simplistic imaging devices, and were used to take hi-res photos of farmlands. The aerial images were referred to by farmers to get an idea of crop health, weeding requirements and other basic farming activities. Things have changed a lot over the last few quarters, and the latest agricultural drones are all about delivering ‘actionable intelligence’ to users. NIR (near-infrared) sensors are being used to create accurate crop health maps, by tracking the green vegetation mass around crop areas. Also known as NDVI (Normalized Differentiation Vegetation Index) maps, these reports help in identifying areas where there are chances of yield losses. Aerial photography is still an important feature of farming drones – but the latter are currently used for many other purposes as well.

  3. Types of drones for agriculture

    Drones have come a long way from being mere recreational gadgets, with mediocre flight planning power and lowly payload capacities (range also used to be a factor). At present though, drones are finding extensive adoption in many fields of business, with agriculture being one of the most important domains. Farming drones can broadly be classified under two heads – multi-rotor drones and fixed-wing drones. The former is particularly useful in scenarios where low-altitude flying is required to capture high-quality crop photos and related information. Fixed-wing UAVs, on the other hand, do not require prior landing/takeoff plans, can start and end flights vertically, and are generally much easier to manage.

  4. The cost advantage

    One of the main drivers of the proliferation of drone technology in the agricultural sector has been the extremely competitive cost levels. The average farmer can purchase many types of smart farming drones at sub-$1000 levels – which is considerably cheaper than hiring manned aircrafts for crop photography (the hourly rental rates of aircrafts are likely to be higher than the price of drones). The images captured by drones are typically of higher resolution than those taken with the help of satellite imaging tools. Drones experience minimal interference in their flight paths too – thanks to the fact that they move under the clouds. On both the quality as well as the cost fronts, agricultural drones offer significant advantages to farmers and investors.

  5. Flying high

    Depending on their precise nature and objective(s), the height at which farming drones fly varies from 50 meters to 100 meters. The Federal Aviation Administration (FAA) mandates that UAVs cannot move beyond the edge of line of sight (in the US, special permits might be required for drones flying at a height of >120 meters). In addition, there are other national-level rules and regulations that the drone operators have to abide by. The average wingspan of an agricultural drone is around 1.2 meters, and its weight varies in the 1.5-2.0 kgs range.

  6. Components of farming drones

    Agricultural drones follow automated flight paths (artificial intelligence drones are, by definition, ‘unmanned’). Open-source programs are typically used to autopilot these drones – and they have several other important components. At the core of farming drones are cutting-edge microelectromechanical (MEMS) sensors – which receive/transmit data to and from the farmlands on a real-time basis. Different types of sensors are used – ranging from regular pressure sensors, to the more advanced gyrometers, accelerometers and magnetometers. To improve locational accuracy, powerful GPS modules are built-in, while high-capacity processors are used to power the drones. Small digital radio(s) are generally attached to agricultural drones as well.

  7. Facilitating smart irrigation

    Wastage of water is a point of concern for practically every crop-grower. The efficiency of traditional irrigation system is hardly ever more than 40% or 50% – implying that an alarming amount of water is wasted during every crop-cycle. Farming drones do their bit to improve the standards of irrigation in fields. Users, with the help of the thermal and multispectral sensors of these drones, can pinpoint the areas of the fields that have to be watered (heat signature is collected, along with information on the energy generated by crops). As already mentioned earlier, crop vegetation indices are also calculated by the drones – to keep farmers informed about the general health of crops.

  8. Distance of flight

    The range of flight of a drone varies with its size and built-in features/purposes. Fixed-wing agricultural drones generally have more coverage capabilities than the multi-rotor models – with the former requiring less than an hour (~50 minutes) to cover 12 square kilometers. The average flight times of fixed-wing drones are higher as well. Spot-checking entire farming lands is time-consuming and often inaccurate when done manually (particularly for large fields where simple perimeter checking is insufficient). Drones have enough in-built flight capacities to perform micro-surveillance of all types of agricultural fields – quickly and way more accurately.

  9. How do agricultural drones work?

    We have already talked about the key components of farming drones. Let us now quickly get an idea of how these UAVs function. The flight path of a drone is created by the user on a ground control device (a laptop or a smartphone). The line of flying – indicating the total area that has to be scouted/surveyed by the drone – is drawn on a map (Google Maps), and the information is transferred/uploaded wirelessly from the ground control tool to the UAV. The drone follows this flight path, and the user has the option to perform manual overrides in case any sudden emergency crops up (for instance, an aircraft appearing in the drone’s path). The takeoff and landing of AI-based farming drones are, of course, autonomous and can be monitored remotely.

  10. Uses of drones in agriculture

    The primary objective of using drone technology in agriculture is pretty much straightforward: increasing overall output levels and enhancing crop quality standards, while maintaining input requirements and optimizing all available resources. Apart from crop planting and smart irrigation, drones have already started to be used to tasks like crop monitoring/scouting (through high-quality time-series animations), crop health assessment (with NIR sensors as well as visible lights for tracking plant health and detecting sicknesses), in-depth soil analysis (with the help of 3D maps) and crop spraying (distributing liquid chemicals evenly on the farmlands, after real-time ground scanning and distance calculations). Drainage systems can be monitored with drones as well, while tracking the health and grazing habits of livestock is also a possibility. Farming drones also help users draw up detailed prescription maps to manage variable rate crop prescriptions. Yield loss risks are minimized as well.

  11. Main challenges for farming drones

    For all its merits, agricultural drones are still new – and some uncertainties still remain over their utility and efficiency levels. Farmers need to keep themselves updated with the latest changes and updates in the drone regulations of their respective countries. Correctly deploying drones in a farm also represents a challenge, while the overall costs of integration have to be managed too. Another serious point of concern is the distinctly ordinary battery performance of most farming drones (which puts their coverage abilities under a cloud). What’s more – unless an agricultural drone actually offers end-to-end problem detection, information transfer, detailed analytics and prescriptive action suggestions (as opposed to simple aerial photography only), neither investors nor end-users would be willing to check it out. Drones in agriculture have evolved greatly, but there is still a long way to go.

  12. Hardware and software

    Between 2017 and 2024, the volume of shipments of farming drone hardware and software will grow at a CAGR of more than 13%. The value of the drone hardware market will reach $200 million (up from ~$60 million in 2016), while that of drone software will be more than $50 million. One of the main factors behind the relatively faster rate of growth of the hardware segment is the higher costs of the device components. While multi-rotor and fixed-wing drones are both popular, shipments of hybrid drones (primarily used for covering large agricultural fields) are also increasing at a steady rate.

  13. Different views offered by drones

    The type of information generated by drones can be customized to suit the exact requirements of the modern-day ‘smart farmer’. Broadly speaking, three different ‘views’ can be obtained from farming drones. The first view takes care of repeated monitoring requirements of a crop or a particular section of the field, on a daily, weekly or monthly basis. The second (and perhaps the most common) view deals with regular crop monitoring from above – for tracking crop health, identifying problems (soil dryness, plant diseases, fungal attacks, etc.), and suggesting satisfactory remedial actions. The other view of farming drones is all about distinguishing between healthy and sick plants with the help of multispectral images (which combine data from visible and infrared spectrums). All the drone views and services are available on-demand (unlike most satellite imaging techniques), near-real-time – and high on quality.

  14. Drone are user-friendly

    While they bring in technological innovation in a big way to farming techniques, agricultural drones are typically very easy to manage. These UAVs can be seamlessly integrated in the crop-monitoring routine in farmlands, the operations and controls are simple (and becoming even simpler as the drone technology develops further), and deployments can be done promptly, on an ‘as-and-when-required’ basis. The sheer range of services that farming drones can deliver makes them highly valuable for users – and in most cases, there are no reliability or safety-related concerns either. The upfront investment is not exorbitant, which adds to the convenience of the farmers. Agricultural UAVs, when optimally deployed, can also lead to hefty savings – justifying its already reasonable cost levels.

Note: The cost of drones with many highly advanced capabilities can be as high as $3500/ €3000. The immediacy of the services of agricultural drones is a big advantage.

    15. USA at the forefront

The United States has a healthy lead in the worldwide market of farming drones. Last year, one-third of the total revenue generated from drones in agriculture came from the US alone. Countries in the Asia-Pacific (APAC) are also reporting rapidly increasing adoption of farming drones in particular, and precision agriculture/smart agriculture in general. In the European markets too, agricultural drones are increasingly finding favour. Chinese company DJI – the company whose first farming drone raised a staggering $75 million – is the undisputed leader, with nearly 37% share in the American drone market. Trimble Navigation, AeroVironment, GoPro and DroneDeploy are some of the other biggies involved in making agricultural drones. The space is getting more and more competitive.

Thanks to the enhanced water-resistance of farming drones, they can be used in practically all types of weather conditions (there is an outside chance of heavy rains distorting drone images though). Their value lies in the ability to add a dedicated ‘what is happening right now’ layer to on-field monitoring – ensuring that farmers are always kept in the loop. Agricultural drones typically save time and money of users, and learning to use them is not much of a challenge – provided that adequate training is available. Smart agriculture is becoming more data-driven than ever before…and drones can indeed play a mighty important role in taking farming standards to the next level.

 

 

Artificial Intelligence 3.0: 13 Things To Know About Deep Learning

 

Deep learning: Features and capabilities

 

Amazon, Google, Netflix, Facebook, MIT researchers – the lineup of ‘Deep Learning’ (DL) users is expanding every quarter. The yearly market revenue from deep learning software for enterprise applications is expected to go beyond the $10.5 billion mark by 2024 – up from the sub-$110 million figure in 2015. As per a recent study, the total annual income from all types of deep learning tools (software+hardware) is set to touch $100 billion by the end of 2024. The buzz around deep learning is enormous – and the technology has well and truly emerged from the realms of science fiction and ‘just that tool that is very good at the ‘Go’ board game’.

Before we get into analyzing the main points of interest about ‘deep learning’, it would be prudent to get its concept clear. Although the terms ‘artificial intelligence’, ‘machine learning’ and ‘deep learning’ are often used synonymously, the three are far from being one and the same. In essence, ‘deep learning’ can be referred to as Artificial Intelligence 3.0 (third-gen artificial intelligence, if you will) – a subset of ‘Machine Learning’, which itself is a subset of the broad concept of AI. While AI is all about creating programs that help machines display ‘human-like intelligence’, ‘machine learning’ refines things, extracting features from a starting object (picture or text or audio or other forms of media) and then forming a descriptive/predictive model. ‘Deep learning’ adds another layer of efficiency and sophistication, by doing away with feature extraction step, and enabling the analysis of objects with the help of customized deep learning algorithms. To sum up:

Artificial Intelligence → Machine Learning → Deep Learning

Let us now turn our attentions to some interesting facts to get a better understanding of the ‘deep learning’ technology:

  1. Not a new concept

    Although the breakthroughs in ‘deep learning’ are often viewed as part of a recent phenomenon, the actual concept is not exactly a new one. In 1965, the first ‘deep learning’ algorithms (perceptrons with several layers for supervised learning) were created – and the concept was used by London’s World School Council later on. Ivakhnenko and Lapa were the creators of this first DL algo. The computer identification setup in which the idea was used was called ‘Alpha’. Of course, the technology has evolved greatly from those days – and is currently right at the heart of internet of things (IoT).

Note: The origin of the term ‘artificial intelligence’ can also be traced back to more than 60 years ago. It was coined at the 1956 Dartmouth Conferences by a team of computer scientists.

  1. Works like the human brain

    The way in which ‘deep learning’ models are trained has a lot in common with the working mechanism of our brains. Hence, the underlying computing model in DL applications can be explained through neural networks (artificial). Data is seamlessly transferred/transmitted within these networks by automated neurons. The neural network of a ‘deep learning’ model ‘learns’ things on the basis of gaining ‘experience’ from sample data and observations – and the behaviour of the neurons undergo changes as the model gets more ‘experienced’. The principal purpose of the neural network in particular, and the DL model in general, is the accurate calculation of unknown functions (e.g., differentiating between a cat and a rabbit) from labeled data. As DL gets more and more advanced, correctly identifying the differences between relatively similar objects is becoming possible.

  2. Input requirements

    The value of deep learning lies in its accuracy. In select use cases, the performance of DL software can be much higher than human capabilities. However, there are two primary conditions for the optimal performance of deep learning applications. High-power graphic processing units (GPUs), which have a large number of built-in processors, are required for working with DL software. That, in turn, brings the importance of parallel training for GPUs to the fore. Secondly, for the results generated by deep learning to be of any real value, the actual volume of ‘labeled data’ or ‘sample data’ has to be huge. It’s similar to basic statistics – the greater the ‘sample’ size is, the better will be the ability of a model to predict from the ‘population’ or the real-world.

Note: For a complicated and potentially risky task like autonomous (driverless) driving, hundreds of thousands of pictures and videos have to be fed to the concerned DL algorithm.

  1. The importance of structured data

    In the previous point, the value of large sample data for deep learning models was highlighted. It has to be kept in mind that the data we are talking about here refers only to ‘structured data’ and not just any random pieces of sound or text or photos. When a business plans to implement deep learning in its IT system – it has to make sure about the availability of huge collections of such structured, organized data first. The deep learning technology processes this data to arrive at judgements (which can vary from voice identifications, to reading traffic signals, or anticipating the opponent’s next move in a board game).

  2. Availability of deep learning frameworks

    There are plenty of misplaced notions and myths about deep learning. For starters, it is often considered that DL is a tool for academicians and researchers only, and only people with advanced degrees and decades of experience can sink their teeth into it. The actual scenario is almost the reverse – with deep learning having multifarious practical uses, and there are plenty of infrastructures, networks and frameworks that can be utilized for DL training and implementation. What’s more – many of these frameworks can be used by academicians as well as developers without any problems whatsoever. The easy availability of extensive documentation on DL frameworks eases the learning curve for developers further. Many of the existing frameworks are free-to-use as well.

Note: Theano, TensorFlow and Caffe are some of the central frameworks that are used for deep learning models.

  1. Way of working

    The overall function of deep learning models can be explained in two broad steps. In the first, the suitable algorithms are created – after thorough analysis and ‘learnings’ from the available data (remember, feature extraction is here automated, unlike in machine learning). The major characteristics and traits of the object under scrutiny can be described by this algorithm. These DL algorithms are then used in Step 2, for the identification of and predictions from objects on a real-time basis. The nature and quality of the training set/sample dataset determines the quality of algorithms generated – and that, in turn, affects the accuracy/efficiency of the output.

  2. Expenses involved

    As the scopes of artificial intelligence are expanding, the revenue-earning capacities of ‘insights-driven businesses’ (those that rely heavily on IoT and AI-based processes) are going through the roof. On a year-on-year basis, the total investment on AI tools and processes this year will be a staggering 300% more than the corresponding figure in 2016 (according to a Forrester report). Investments on deep learning software and devices are also rising rapidly. DL, as things currently stand, is a fairly pricey technology – mainly due to the requirement of expensive GPUs in its architecture. The cost of only the GPU graphics card can run up to several thousands of US dollars. Add to this the fact that separate servers will be required for most of these cards – and it can be clearly understood that implementation of ‘deep learning’ architecture involves rather steep expenses indeed. Over the next few years though, as the technology becomes more commonplace and the component prices fall, things should become a lot more competitive.

  3. The importance of transfer learning

    If a separate deep learning model (training sets, algos, hardware, et all) had to be created for every different use case – that would have been a problem, both operationally as well as financially. Thankfully, ‘transfer learning’ considerably eases the pain in this regard. To put it simply, ‘transfer learning’ (TL) refers to the practice expanding the scope of a specialized DL model to another (preferably related) use case. Another way of explaining this would be bringing in the capability of one DL model to provide the requisite training to another one. A classic example of TL would be the ability to identify genders, and the detection of male and female voices. Apart from reducing the number of deep learning models required, TL also helps in bringing down the total volume of sample data needed (for the similar yet different purposes).

  4. Number of layers

    The underlying neural networks (‘deep neural networks’, or DNN) for deep learning setups typically have multiple layers. The simplest of them has 3 layers (input, output, and a hidden layer – where the processing of data takes place) – while more complex networks can have as many 140-150 layers. The ‘deep’ or ‘hidden’ layers in the neural network of a DL model removes the need for manual feature extraction from objects. Although we are still quite some way from it, experts from the field of software and app development feel that deep learning has the potential to completely replace all types of manual feature engineering in the tech space in future.

Note: Convolutional Neural Networks (CNNs) are a good example of the deep neural networks that are used for deep learning models.

    10. DL for business applications

Product recommendations, image tagging, brand identification (both own as well as that of competitors) and news aggregation are all examples of business tasks that can be powered by deep learning modules. The biggest example of DL implementation in businesses, however, have to be for the AI-powered chatbots. These bots, with the help of cutting-edge deep learning capabilities, can easily simulate human conversations – ensuring 24×7 customer services (without companies having to hire additional manpower). AI bots are particularly useful for ecommerce portals, can store, analyze and identify patterns in received information, and can even facilitate secure payments. By the end of this decade, 80% of all firms will be in favour of chatbot integration in their work-processes – a clear indication of the rapid ongoing developments in the deep learning technologies that will support the bots.

    11. Key layers of the systems

Like any high-end software system, a DL model has multiple important layers. The rules and algos created after ‘studying’ the sample structured data are known as ‘training algorithms’, all possible functions can be analyzed by these algorithms in the ‘hypothesis space’, and the target function is identified by a set of data points which are named ‘training data’. The component of the DL module that actually performs the necessary action (e.g., identification) is known as the ‘performance element’.

   12. The scalability is an advantage

The volume of ‘learning data’ required and the requirement/non-requirement of feature extraction manually are important points in any deep learning vs manual learning (ML) analysis (ML requires much smaller datasets than DL). Yet another advantage of deep learning over ML is the enhanced scalability of the former. The underlying algorithms in a DL model can easily scale up or down, depending on the volume and type of data under consideration – with the performance remaining unaffected at all times. In contrast, the performance and effectiveness of machine learning (can also be referred to as ‘shallow learning’) tends to become flat beyond a certain level.

  13. Deep learning use cases

From identifying sounds and fully automated voice recognitions, to applications that boost the powers of computer vision and bioinformatics – the fields in which deep learning can be implemented are seemingly endless. In the domain of electronic tools and services, DL has already proven to be a handy tool for automatic translations (audio) and listening. Detection of cancer cells has been facilitated by deep learning too (it has been implemented in a HD data microscope at the UCLA). Smart driving and industrial safety & automation are two other fields where DL has enormous scopes to grow. The technology will make national defences and important aerospaces safer than ever before.

There are no scopes for doubting the fact that deep learning is the most powerful component/subset of artificial intelligence. Provided that there are no problems in acquiring enough structured data samples, and adequate investments can be made for GPUs – organizations can easily opt to integrate DL in their systems (in the absence of these resources, machine learning would be the better alternative). However, for all its advanced, futuristic capabilities – DL models still require the support of human beings, to resolve any possible confusions. Deep learning takes computing powers to the next level…without quite being able to act as a perfect substitute of the human brain. Yet.

Thinking Beyond Mobile Apps: Are Bots The New Apps?

 

List of advantages of bots over apps

 

Bots are already big, and they are growing bigger. In 2016, the total investments on chatbots showed a ~230% YoY increase over the previous year. In comparison, spending on mobile applications grew by a relatively measly 65% during the same time-frame – adding substance to Microsoft CEO Satya Nadella’s much-talked-about comment about ‘bots being the new apps’. A recent study also found that, AI-powered chatbots are estimated to help in generating $20 million savings for businesses by the end of this year (the figure will grow to a massive $8 billion by 2020). Over here, we will highlight a few reasons why bots indeed have the potential to emerge as ‘the new apps’:

  1. Surging popularity of messaging apps

    The mobile app industry has entered the stage of maturity (mind you, it’s a relatively early maturity, and there are still plenty of growth opportunities). In the first quarter of 2015, the total number of active users (monthly) of the top four mobile messaging apps overtook that of the top four social networking applications, and since then, the gap has only grown wider. According to an Activate report, close to 3.6 billion people will have at least one messaging app installed in their smartphones by mid-2018. At a time when much is being written about the onset of ‘mobile app fatigue’ (on average, nearly 80% individuals use only 3-4 apps on their phones; only around 0.01% of all apps are expected to be financially successful next year), messaging apps are well and truly going against the trend – and their popularity is boosting the proliferation of chatbots.

  2. Immediate availability

    To use a new mobile app, some time has to be invested. You have to go to the app stores (Apple/Google), look up the app you need, download and install it on your device, (probably) register on it – and only then can you start using the application. In comparison, bots are a lot easier to get onboard. All that a person has to do is find the bot from within the messaging apps, and things are set for him/her to start chatting. Chatbots built on reliable platforms are ‘always on’, and have seamless access to the identity and preferences of users. While it generally takes a couple of minutes (at times, maybe more) to start using an app, bot-usage can be started in a matter of seconds. The ‘significantly quicker access’ is a critical factor.

  3. The artificial intelligence factor

    Artificial intelligence (AI) and machine learning have important roles in the current ‘chatbot revolution’. According to Forrester, there will be whopping 300% jump in investments on AI-based tools and resources this year (over 2016). ‘Intelligent automation’ is helping chatbots simulate actual human conversations in a better way – with just that required touch of empathy and personalization. Thanks to the rapid advances in AI standards, new-age bots can also store, analyze and identify patterns in user-data, and even carry out transactions (everything is automated within a single chat window). AI chatbots with optimized natural language processing (NLP) and clean, efficient UI can do everything that a mobile app can (and then some more!) – and they are generally much quicker too.

  4. Rise of the conversational UX

    There will be an amazing 2.2 million devices compatible with voice-recognition technology by 2020. At last year’s Google I/O conference, it was announced that 1 out of every 5 searches on Android apps (and, of course, the Google app) is voice-based. Chatbots serve as ideal platforms for developers to implement ‘conversational UX’ – powered by voice technology. Users can seek specific information/service, and the same can be instantly delivered by an ‘intelligent bot’. With the accuracy of speech recognition software tools increasing steadily (recent stats put the accuracy at 90%), the adoption of chatbots with ‘conversational UX’ is growing fast.

  5. Bots for all use cases

    ‘There’s an app for that’ might be an iconic phrase from Apple (the Cupertino company got a trademark on it in 2010) – but it is becoming clearer and clearer that apps cannot be used for every ubiquitous use-case. For instance, to book an appointment with a doctor or fixing up a session with a beautician, chatbots are much more convenient than downloading a full application. The average smartphone user would be much more likely to include the contact number of the concerned service provider (doctor, beautician, etc.) in their phonebooks – than bothering to install mobile apps for the same purpose. At present, the scenario is more like ‘there’s a bot for that!’

  6. Mobile apps to bots is a natural progression

    When the first-generation World Wide Web came along, no one had imagined that its popularity will be eclipsed by that of mobile apps one day (apps are considerably more popular than mobile web too). The shift from smartphone applications to smart chatbots is a natural progression too. In a way, bots can be referred to as the ‘third-generation communication platform’ (web being first-generation and apps being second-generation). Websites had yielded to the mobile operating systems – and the latter is now yielding to messaging platforms and the bot technology. It’s all in the flow of innovation and progress of technology.

  7. Bots facilitate two-way communication

    ‘Talking’ with a chatbot is just like interacting with an actual human being via live chat. For commercial and financial requirements in particular, this bi-directional conversation is of immense importance – and the interactions should be in a seamless flow, with users providing information and ‘receiving’ responses from the bots. With mobile apps though, this interaction is mostly one-way – with users having to provide most of the information. Responses are, more often than not, limited to push notifications and the occasional messages. Receiving data has emerged as a key element of smart platforms – and chatbots are way ahead of apps in this regard.

  8. Bots for business is a smart option

    People love to communicate with businesses via messaging and chatting. In the United States, close to 65% customers expressed their preference for chatbots (over actual human beings) for getting their service requests resolved. What’s more – businesses now need to be ‘available’ and ‘accessible’ to clients/stakeholders on a 24x7x365 basis. The option of having a round-the-clock call center team for live chatting is neither practically nor financially feasible – and bots offer an excellent alternative. High-quality chatbots meet the ‘five-9s rule of availability’ (available 99.999% of the time) – and they help businesses in increasing the reach of their brands in a big way.

  9. Easier to create; Quicker to deploy

    Creating a chatbot is, in essence, piggybacking a new software on an already existing, tried-and-tested messaging application (e.g., FB Messenger). A new bot can be conceptualized and built much more quickly than a mobile app – which requires a team of iOS/Android developers (depending on the chosen platform(s)), UI/UX experts and animators, and a reliable group of app testers. The overall app development phase, on average, stretches for 6-8 weeks – and the expenses are, understandably, much higher. There are several bot frameworks available as well, which further ease the task of creating and deploying a new chatbot (continuous feature integrations can be done by tweaking the backend). Bots require lower monetary and time investments – and this gives them a major advantage over apps.

Note: Different apps have different types of interfaces, and hence, the learning curve for users becomes a factor. Bots, on the other hand, brings in a layer uniformity or singularity – making it easier for people to start using an already familiar platform. The need to get acquainted with a large number of disparate app interfaces disappears.

    10. The growing app fatigue

Make no mistake…the app economy is not going to die out anytime soon. However, the fact remains that the ‘wow factor’ of mobile applications is diminishing rapidly – with new app installations becoming few and far between (in the United States, app downloads fell by 20% in 2016) and nearly 25% of all newly installed apps being discarded after single-use. On the Apple platform, 50% of the overall app store revenues are generated by 20-odd top developers – while the majority of indie developers are under the so-called ‘app poverty line’ (the difference is more noticeable in the Android ecosystem). As highlighted in the previous point, building times are higher for apps and promotional campaigns also involve significant expenses. The latest bots have cutting-edge features, rich conversational properties, and solid backend support – and as the app industry shows signs of slightly slowing down, they can emerge as a more than viable replacement.

   11. The smooth blend of entertainment with information

Bots typically offer a nice blend of interactive fun and practical utility – something that traditional mobile apps often cannot provide (a business app is serious, a storytelling app is fun, and so on). By October 2016, well over 3 million LINE@ accounts had been created by businesses to launch their bots – while the number of bot applications on Facebook Messenger had zoomed past the 50000 mark. In addition, chatbot platforms are gradually emerging from being ramped-up versions of interactive voice response (IVR) tools, to actual smart conversation (text-based or voice-based) platforms. The interactions are natural, often have fun, edgy elements about it, and can potentially be more engaging than mobile apps.

  12. Accessing information on the cloud is made easier

There are two ways to access the same information on the web. The first involves the hassles of actually searching on Google, parsing through the search results, opening links and going through the contents in them. The other, and much easier option, is to rely on an AI-powered bot for delivering the same information. It won’t be wrong to say that intelligent bots are doing all the hard work for users – who only have to place their queries, and get instant replies. This, in turn, is bringing down the ‘cognitive load’ placed on the users.

  13. Portable, scalable, distributable

How can you share a mobile app? There are apps like SHAREit and Xender for file/app transfers – but to use them, they have to be downloaded first. The need for installing an extra app for sharing makes the overall process long-drawn and rather cumbersome – particularly when compared to smart bots, which can be distributed much more easily. Bot sharing can be done directly from the underlying messaging platform, and they can be shared to, or linked with, social media with absolute ease. In select cases, one bot can also ‘recommend’ another bot. Scalability is yet another major advantage – with bots being ideal for both SMEs as well as large corporate houses. Chatbots are generally dynamic, and they are well-equipped to handle peak and low demand volumes without any glitch in performance.

 

The enhanced portability of bots also give it a major boost over apps. Right from mobile digital assistants like Google Now and Siri, to email accounts, smartwatches, vehicle infotainment systems and live chat environments – a bot system can reside practically anywhere. Mobile apps, in comparison, have to function within limited interfaces.

 

Satya Nadella’s ‘bots are the new apps’ prediction does have merit in it – with AI-based bots indeed promising superior performance and usability over traditional mobile apps for many purposes. However, it also has to be kept in mind that bots are not finished products per se, and (as the Tay disaster proved), there are still considerable room for improvements, greater stability and bug-free assurance. Mobile apps are way too popular to give way to bots overnight – and over the next few years, the two can easily co-exist. Let’s just say that, in the realm of technology, apps are the ‘present’, while bots indeed have the potential to become the ‘future’.

 

 

iOS 11 Is Coming: What’s New?

 

list of iOS 11 features

 

Another year, another new version of iOS. At the recently concluded Worldwide Developers Conference (WWDC ’17), Apple showcased the first beta of iOS 11 – the latest iteration of the platform. The first impressions of the platform have been mostly positive, with many experts hailing iOS 11 as the ‘biggest update ever‘. With the latest iOS 10 adoption figures worldwide pushing towards the 87% mark, there is ample evidence of users being more than interested in updating their iDevices to the newest version of the iOS platform. The second developer beta was released yesterday, and in today’s discussion, we will scan through the most interesting new features of iOS 11:

  1. Upgraded Messages app

    The built-in Messages application has received a couple of handy new features in the latest iteration of the iOS platform. There is an all-new app drawer, which can be swiped by users to share stuff (games or songs or emoticons or stickers) with their contacts. All the messages in iCloud gets auto-synced across all paired iPhones and Mac systems. People can now easily share files from Apple Music through Messages – and enjoy together.

  2. Lock Screen and Notification Center

    The two have become one and the same in iOS 11. After upgrading their devices, users will no longer see a separate Notifications Center. Instead, they can simply pull down the lock screen itself to check out all the notifications (including the ones that were missed earlier). This, according to early testers, would add to the convenience factor of iPhone owners – since notifications are now neatly organized and accessible at a single place. Swiping sideways displays the ‘Today’ view.

  3. ARKit for iOS

    This one is big news for iOS app developers and final users alike. At this year’s WWDC, Pokemon Go was used as a demo to showcase ARKit – the new software development kit that allows app and game makers to integrate cutting-edge augmented reality features in their software. In essence, the ARKit tool will help developers enrich the environment by placing virtual objects in the real-world – with the help of the native camera of iPhone/iPad. Support for augmented reality is probably going to be the single biggest new feature in this year’s iPhone 8.

Note: One of the launch partners of AR in iOS 11 will be Ikea.

 

  1. Smarter, better Siri

    Every recent iOS update seems to make improvements in Siri – and iOS 11 is set to push the envelope further. Apple’s mobile digital assistant will now speak in a more natural, human-like voice (male or female voice can be chosen), and will have the capability to translate queries made in English – into French, Chinese, Italian, German and Spanish. The artificial intelligence (AI) support for Siri has been enhanced, with the assistant now being able to offer interesting facts and tidbits about the songs played from Apple Music. Depending on the precise location of a user, search results and news are suggested to him/her (suggestions are also based on the interests of users). More refined ‘on-device learning’ will also help Siri in predicting the names of things (cities, films, etc.) that a person is going to type on the phone. The security standards of Siri have also been bumped up, with all conversations between users and the assistant being encrypted.

 

  1. New filters for Photos

    If you decide to get the new iPhone 8, you’ll have that much less reason to carry your DSLR camera everywhere. Multiple pro-level filters have been included in the revamped Photos app of iOS 11 – skin tones have been made more natural, and users also have the option of applying special filters for classic effects.

 

For the fan of photography, the fun does not end with the new Photos filter. iOS 11 will be coming with a revolutionary ‘Live Photos’ feature – to let people create fun ‘bounces’ and ‘loops’ with the pictures they take. The ‘long exposure’ feature helps in snapping photos with unmatched effects and tones. With the latest version of iOS, Apple has certainly raised its game as far as photography with smartphones is concerned.

 

Note: In iOS 11, Photos will be stored in the .HEIF format, while videos will be created in the .HEVC format. The new compression image/video compression standards will cut down on the space required to store these files – without compromising on the quality in any way.

 

  1. Changes in Control Center

    The Control Center in the iOS 11 platform has become more customizable than ever before. Users can now do a lot of things – right from adding Home controls and voice memos, to managing playlists and changing the volume – directly from the Control Center. 3D Touch, which debuted on iPhone 6S a couple of years back, is now available in the Control Center, making user actions faster and more responsive. The focus is clearly on giving iPhone-owners a ‘more personal experience’.

 

  1. Apple Pay comes to Messages

    Imagine being able to send or receive money from another person from inside the Messages app (no third-party apps involved). The upcoming version of iOS will bring precisely that functionality to the hands of users – by integrating Apple Pay inside Messages. With the help of this peer-to-peer payments feature, people will be able to request for, or receive from others, payments in a completely secure manner. The transferred amount gets stored in Apple Pay Cash and can be used to make other payments online (or in mobile applications) and even sent to bank accounts. This new feature might well place a challenge for established players like Vemmo.

 

Note: To start things off, both Apple Pay Cash and peer-to-peer payments will be available only to US users.

 

  1. CoreML for machine learning

    Along with ARKit, CoreML is yet another all-new futuristic tool that iOS 11 would place in the hands of third-party iPhone app developers. The latter will be able to use the CoreML framework to seamlessly integrate advanced machine learning modules in their new applications (thereby making the apps more ‘intelligent’). GameplayKit, Vision and Foundation (for NLP) are all supported by CoreML – and it also saves power and reduces the total amount of memory footprint.

  2. One-handed typing feature

    The Quicktype Keyboard will be a really useful addition in the iOS 11 platform. With it, users will be able to type quickly and accurately, by using one hand (there are plenty of times when using both hands for typing is simply not possible). The keys will move nearer to the thumb of the user to enable this one-handed typing, after the Quicktype Keyboard is activated by long-pressing the emoji key on the default keyboard. Who said typing isn’t possible when you are holding a cup of tea in one hand?

 

Note: The Do Not Disturb feature of iOS 11 is worth a separate mention too. Upgraded iPhones will be able to detect when users are driving – and will let them concentrate by sending automated responses to everyone who might be trying to call or send messages (app notifications will be muted too).

  10. Airplay 2

iOS 11 will do its bit towards creating ‘smarter homes’. Airplay 2 has been billed as one of the most interesting new additions in the platform – and just like Sonos, it will be enable multi-room support for home speakers. In other words, Airplay 2 will allow users to play the same music in different rooms of the house simultaneously (on smart, compatible speakers). Through Siri as well as Apple Music, the home audio will be controllable from Apple TV with the help of Airplay 2. Music on multiple speakers can be synced to start together, and volume levels can be adjusted easily. With biggies like Bower & Wilkins and Beats already confirming support for Apple HomeKit, this feature has the potential to become very popular.

 11. Redesigned App Store

For the first time ever since its launch, the Apple App Store has been redesigned – with the Cupertino company referring to to the revamped App Store as ‘designed for discovery’. There will be separate, dedicated ‘Apps’ and ‘Games’ tabs, that will showcase the latest and the most popular applications under the two categories respectively (in-app purchases for already installed will also be shown). When the App Store will be first opened, the ‘Today’ tab will come up with lists and collections (updated daily) and informative tutorials. Each new app will have its very own ‘story’ – and applications will have their product pages too.

 12. Shared playlists in Apple Music

Apple has paved the way for iPhone-owners to enjoy music with their friends, and discover great new music with the latter’s help. A person can now check out the entire playlists of his/her friends (no prior permissions required) – while stations and albums can also be shared within networks. Siri, as already highlighted above, has enhanced music curation capabilities as well. Discovering new artists and enjoying the best of Apple Music have never been this easy.

 13. More powerful Apple Maps

For years, Apple Maps have been (rightly) considered to be not as good as Google Maps – but the Cupertino company is pulling up in a big way. There are significant upgrades in Apple Maps in iOS 11 – with detailed, accurate navigational information available from the ‘Lane Guidance’ section. Yet another high point of the rejigged Apple Maps is the built-in ‘Indoor Maps’ feature. Users can now take a sneak peek inside select shopping malls, major airports and other locations. Information about speed limits can also be read off the new Apple Maps.

 14. iPad gets many new features

After iOS 9 had launched split-screen multitasking for iPad, iOS 10 had no iPad-specific features. The latest iteration of the platform, however (and rather expectedly), has a large number of new features and functionalities for the tablet. The ‘Files app’ keeps all the files on your iPad neatly organized – ensuring easy searchability and access. Files stored in iCloud Drive and Dropbox can also be maintained with the Files app. iOS 11 has finally brought in the drag-and-drop functionality to the iPad, while the multitasking feature has been significantly improved. There is a new Dock (mirroring the one present in Mac computers) – and from there, apps can be launched for multitasking. Apple Pencil – launched in 2015 – has also received new features like inline drawing, instant markup and instant notes. Apple does not seem to have any plans of giving up on the iPad line anytime soon.

 

While the new features of iOS 11 have mostly come in for high praise from software and app developers as well as general Apple enthusiasts, there have been some concern over the decision to discontinue Twitter and Facebook integrations (for third-party applications). The update will be available on iPhone 5S and later, iPad Mini 2 and later, iPad Air, first and second-gen 12.9” iPad Pro (along with its 9.7” and 10.5” variants) and the sixth-generation iPod Touch. Support for iPhone 5 and iPhone 5C (including legacy apps) has been stopped.

 

2017 marks the ten-year anniversary of the iPhone – and Apple has made sure that this year’s iOS update has enough new features and add-ons to live up to the user-expectations. It will debut on the iPhone 8 this September. Over the course of the next developer and public betas of iOS 11, we will get to know what other features are added (or maybe, removed?) to the platform before its final release.

 

 

Top 12 Tips to Choose The Best Chatbot Platform

Guideline for choosing chatbot platform

 

The importance of chatbots in the field of business is rising at a rapid pace. A recent TechEmergence study estimated that, over the next few years, bots will emerge as the single largest category of artificial intelligence-based applications. In 2016 alone, well over 30000 new branded chatbots were launched – and by the end of this decade, nearly 86% of all ‘customer conversations with businesses’ will take place without human management (i.e., will be automated). For low-level interactions and transactions in particular, 7 out of every 10 people prefer conversing with a bot instead of humans.

The growing popularity of chatbots has, in turn, made the task of selecting a good bot platform more critical than ever before. A chatbot can only be as good as its platform – and over here, we will provide some important tips and pointers for selecting the best chatbot platform for your business:

 

  1. Round-the-clock availability

    A big factor behind the growing adoption rate of AI chatbots is the ‘always on’ nature of these applications. The platform you select should, as a rule of thumb, ensure 24×7 availability of the chatbot for customer interactions. According to experts, a high-quality chatbot framework should abide by the ‘five nine-s rule’ of availability (available 99.999% of the time). Downtimes should be minimal, response speeds should be high, and there should not be any risks of sudden failures/crashes. A chatbot platform has to be customer-oriented and highly reliable.

  2. Neat, uncluttered user-interface

    A bot platform should allow users to set up new, smart chatbots quickly. If the UI of the platform is overly complicated, that objective is likely to be defeated – and a fair amount of time will be lost while trying to ‘learn’ how the platform is to be operated. Businesses should always go for chatbot frameworks that have simple, streamlined UIs, user-friendly controls and architecture, and proper tutorials/manuals. Integration with Facebook Messenger is a desired feature for many bot platforms, while analytics information should be easily available. Users who do not have much prior coding experience should also find it easy to launch intelligent bots on the platform easily.

 

Note: In most cases, it is advisable to go for a chatbot platform that offers cross-platform support. OnSequel is a good example of such a platform.

 

  1. In sync with the nature of business

    It’s easy to not look beyond Facebook Messenger, when it comes to choosing a bot platform. After all, it is by far the biggest framework – and has been estimated to reach the 2 billion users mark by 2018. However, it should be kept in mind that the size of a bot framework is directly proportional to the degree of competition your bot (created on it) has to cope up with (FB Messenger already has close to 35000 bots). For startups and other companies at an early stage in their lifecycles, going for a smaller platform is a better option (something like Telegram fits the bill perfectly). This strategy will allow these ‘new’ businesses to reach out to a wide cross-section of audiences. For larger, more mature businesses, using a biggie like FB Messenger to target an already identified customer-base makes more sense.

 

  1. Scalability is vital

    The volume of interactions with a chatbot does not remain the same at all times. If the bot platform you selected is not properly scalable – the chatbot might end up showing glitches at the time of high demand, while you may have to cough up unnecessary money (as capital expenditure) during low demand periods/idle times. To tackle this issue, look out for a platform that has dynamic scaling properties. The bot created on it should be able to handle fluctuating demand/interaction volumes with ease – and its functionality should never be affected. It is impossible to accurately predict the number of people logging in at any time – and the platform needs to be able to manage this uncertainty.

 

  1. Consider the type of chatbot required

    There are plenty of multi-featured chatbot platforms available at present – and not all of them offer similar bot development solutions. As the business owner, the onus is on you to determine the type of chatbot that your business requires, and select the platform accordingly. If you are looking for a ‘conversational chatbot’ that would simulate conversations and keep users engaged (maybe act as a substitute of the FAQ page of a website), choose a platform that uses Artificial Intelligence Markup Language (or, AIML). On the other hand, you might need a ‘transactional chatbot’, which will help customers to achieve certain specific goals (food ordering, ticket buying, etc.). Find out the precise bot requirement for your business, and then start to look for a suitable platform.

 

Note: If you wish to launch your chatbot as quickly as possible, go for a ‘no programming platform’. Many existing platforms are supported by the biggest tech companies – with Wit.ai (Facebook) and Api.ai (Google) being classic examples.

 

  1. Support for multiple languages

    Depending on the nature of chatbots to be set up, and also for maintaining higher productivity levels, developers might need to use heterogeneous programming languages. A chatbot platform should, hence, support multiple languages – like Python, C#, Node.js, and other related technologies. Modern-day enterprises do not, generally, use the same language for all their development tasks – and developers typically prefer using the language(s) they are best acquainted with. Platforms that are language-specific are limited in nature, and not of much use.

 

Note: Search for platforms that will allow your bot to be easily accessible through all the leading social media channels, and messaging/voice platforms. Slack, Facebook and Skype are some channels via which customers often try to connect with chatbots.

 

  1. Ease of development and testing

    The tools and features of a chatbot platform are the biggest indicators of its usability. A snazzy, elegantly designed platform is all very fine – but unless there is a proper integrated environment for creating the chatbot, problems might crop up. A platform should ideally be able to help users during the development, debugging and deployment stages – ensuring optimal performance and high productivity. In particular, testers should be able to perform integration and unit tests with ease, while creating mock objects should not be a problem either. Scaffolding codes, readymade templates and quick start wizards are all useful in boosting the overall pace of chatbot development. The platform you choose should have a built-in emulator as well, for testing.

 

  1. Profile of target audience

    Once again, if you are looking to make a bot that maximizes the social reach of your business, Facebook Messenger should be the go-to platform. However, if you need to target any particular niche category, other alternatives can be considered. For instance, if millennials are to be targeted, Kik would probably be the best bot framework (around 70% of its users fall in the 13-24 age group). The nature of promotional and marketing strategies planned should also influence the choice of bot platform. Make sure that your chosen framework supports smooth integration with third-party applications, for enhanced functionality. You should also take into account whether the bot has to be monetized or not.

 

  1. Integration capabilities

    Artificial intelligence standards are becoming increasingly refined – and with that, the demands on chatbots are growing fast. To be able to satisfy customers and carry out interactions without a hitch, a bot should be easily integrable with transaction services, analytics data, research tools and other behavioural resources. The natural language processing (NLP) has to be of the highest order, to ensure smooth, contextual chatbot conversations. The interface of the bot platform should support two-way transfer of images, files and other attachments (apart from, of course, text-based communications). The nature of interactions between a user and a chatbot can be diverse, and a well-rounded bot platform has to support everything.

 

Note: Button clicks, option selection, and even data sorting should be included in the overall list of interactions supported by a chatbot.

  10. Security and audit

Unless the authentication standards of a bot platform are robust enough, using it can be downright risky. More and more people are sharing personal, sensitive, confidential data through chatbots – and users have to make sure that there are no chances of unauthorized access/hacks of such information. It would be a good idea to always stick with platforms that support the oAuth authentication protocol. In addition, it should be easy to audit the performance of enterprise chatbots at any point in time. The underlying platform has to let administrators monitor the activities happening on a chatbot, and have the option of ‘rich logging’ (the logs must be available directly from the dashboard). Constant monitoring/auditing is very important for maintaining the quality of chatbots over time, and resolving errors/problems on the fly.

  11. Compatible with DevOps standards

It is no longer sufficient for a bot framework to only offer the necessary automation endpoints and basic functionalities. The adoption of DevOps standards is increasing steadily (2016 was named by Gartner as the ‘Year of the DevOps’) across enterprises across the globe. The bot platform you are planning to use should allow continuous, seamless integration and delivery – which, in turn, would ensure smooth automation and easier deployment of the technology. Developers should face no difficulties while trying to integrate the DevOps mechanism in their AI chatbots.

 

Note: Over 30% SMEs have already implemented DevOps practices across their entire business. Large enterprises are also fast warming up to the mechanism.

  12. The cost factor

There are many self-service platforms out there (as an alternative to delegating the task to third-party mobile app companies, or having an in-house team to build a chatbot from scratch). The cost structures vary across platforms – and users need to have a pre-determined budget and allocation level, to prevent expenses from spiralling upwards. Make sure that your platform has a free-to-use basic plan, and the charges are based only on the active machine timings of the bot (instead of static, monthly charges which might include significant idle times). Check the plan limits (i.e., maximum interactions) and the corresponding monthly expenses. Depending on your budget, requirements from the bot, and features of the platforms you have shortlisted – make an informed choice.

 

Ideally, your chatbot platform should not be reliant on proprietary technology, and should function in accordance with the industry standards (for REST endpoints, JSON is the standard). The bot(s) you create should be able to take the initiative and start conversations with customers, and should be capable of performing tasks both synchronously and asynchronously (this enhances the scalability of the bot application). Embedding a chatbot on a mobile app should also be a breeze. The presence of so many chatbot platforms has, without doubt, made the task of finding the ‘right’ one just a tad trickier – but with due care and proper research, you can zero in on the framework that would be best suited for your purposes.

 

Facebook launched the Messenger 2.0 platform at this year’s F8 developer conference (April 18-19). A couple of weeks later, Parl.Ai – an advanced AI evaluation and training tool – was launched. Google, meanwhile, released its very own chatbots analytics tool (Chatbase) last month. Chatbot frameworks in particular, and bot technology in general, is evolving rapidly – and your business needs to keep up with it.

 

 

 

 

Smart Agriculture: 13 Trends To Watch Out For

Smart agriculture IoT trends

 

In 2006, there were 6.6 billion people in the world. Cut to 2050, and this global population figure will move beyond the 9.5 billion mark. A United Nations FAO (Food and Agriculture Organization) report predicted that the overall volume of food production worldwide will have to increase by nearly 70% in 2050 – in comparison with 2006 – to keep up with (read: feed) the rapidly swelling global population. The need of the hour is to consistently increase agricultural productivity levels – and the importance of ‘smart agriculture‘ comes into focus here.

Before moving on to the latest data, stats and insights from the domain of smart agriculture, a couple of terms need to be explained. Firstly, the concept of ‘big data farming’ refers to the utilization of big data to make more informed farming decisions – that, in turn, bolster production and profit figures. On the other hand, ‘precision agriculture’ is the technique of closely monitoring the variability in crop yields (within single fields and across multiple fields), and tackling such changes effectively. Both of these concepts are vital for understanding the essence of smart, information technology-driven farming. Let us now turn our attentions on some important smart agriculture trends and statistics to look out for in 2017 and beyond:

Size of the market

On a year-on-year basis, the global smart farming industry grew by nearly 6% in 2016, with it value going beyond the $10 billion mark. In the next ten years, the smart agriculture market is expected to witness a 4X growth (by the end of 2026, it will be a $40+ billion market). The hardware component of the industry will be at the forefront of this growth, with more than 50% share in the overall technological solutions for agriculture. The CAGR of smart agriculture for the 2016-2026 period has been estimated to hover around 11.5% – a mighty impressive stat in itself. The variable rate technology segment of smart agriculture will, in particular, grow rapidly.

Key drivers of the market

As mentioned above, ‘enhanced agricultural productivity’ is the main reason for the steady growth in demand for smart farming. A closer analysis of the market reveals several other factors that are contributing to the need for using technology in agriculture. Greenhouse farming practices have gone up significantly in recent years, food demand levels (and shortages) have been increasing, there is a definite need for smarter livestock management, and irrigation management (i.e., preventing wastage of water) has emerged as a critical issue. Individual farmers as well as corporate farming entities are increasingly looking out for solutions that can help them in producing top-quality crops, while minimizing costs and making optimal use of available technological resources. As such, adoption of smart farming practices is increasing across the world.

Note: As the global population is escalating (and the demand for food is increasing), the percentage of workforce employed in the primary sector (agricultural labourers) is going down. In this scenario, smart farming is the best possible way to improve, and maintain, productivity levels.

Growth of IoT in agriculture

Apart from productivity, ‘greater efficiency’ is the other main objective of smart agriculture. To attain these targets, IoT (internet of things) is quickly making its way in this sector. According to a recent BI Intelligence report, more than 75 million IoT devices will be installed (for agriculture) by the end of this decade – a rise of 150% from the 30 million figure in 2015. The average volume of big data generated and managed by individual farms will also show a staggering increase between 2017 (<0.5 million data points) and 2050 (>4.0 million data points). Consistent application of technology is resulting in more agricultural information being generated than ever before – and these insights are helping in bolstering productivity and efficiency.

Note: John Deere – a worldwide leader in agricultural machinery production – has already started to implement IoT sensors and other web-enabled tools in its tractors. Just like the fast-growing ‘connected cars’ market, ‘connected tractors’ are growing in popularity too.

Components of smart farming

The broad concept of ‘smart farming’ is made up of several, equally important technologies. Mobile applications can now be used by farmers to remotely track and manage yields, costs and other important farm metrics, sensing technologies (on-field sensors) have proved mighty useful, both hardware tools and software solutions have increased in popularity, and smart positioning technologies (GPS) have done their bit towards making agricultural practices smarter. The importance of communication technology – via the cellular platform – cannot be overemphasized either. Telematics (i.e., the transmission of information over long ranges) has been a key component of smart farming as well, as have been the advanced data analytics tools and platforms. Each of these technologies are evolving every quarter – and smart farming as a whole is becoming more advanced, as a result.

North America to remain the market leader

At the start of this year, North America – with a $5000 million smart agriculture market – was the clear worldwide leader in this sector. Between now and 2026, this market will grow at a CAGR of a shade under 10%, reaching $16 billion by the end of that year. In terms of actual pace of growth though, Asia Pacific markets (excluding Japan) will become the leader, with a CAGR of 13.7%. In Latin American countries, the CAGR of technology-aided agriculture will be more than 12% too. Europe, Middle East and Africa are also progressing rapidly in terms of growth in smart farming standards.

Smart water management

A Beecham Research report found that close to 70% of the total fresh water supply in world is used up by the agricultural sector. That, in turn, underlines the importance of optimizing irrigation management with technology, and cutting down on wastage of water resources. According to OnFarm, smart farming helped in reducing the total amount of water required (for irrigation) in a farm by as much as 8%. Technology has helped in bringing down per-acre energy costs by nearly $6 as well. There have also been gains in terms of fertilizer cost reduction. On average, yields have increased by nearly 2% due to smart farming – and this figure is expected to grow in a big way in the next 8-10 years or so.

Note: In the United States, the average cereal-per-hectare yield is 7340 kgs. That is close to double of the global average figure (3850 kgs).

Hardware components to lead smart farming

Between 2017 and 2022, there will be a surge in the usage of hardware tools and devices for smart agriculture across the world. In particular, VRT (variable rate technology) tools and GPS receivers will fuel the growth in this segment, while smart steering and guidance systems will also have hefty demands from farmers. The purpose of using advanced hardware on farmlands is easy enough: minimization of inputs/resources, upgradation of quality, and maximization of output. According to experts from the field of technology, the constant betterment in the standard of automation and control systems is playing a vital role in the growth of smart farming.

Rising investments

As interest in smart agriculture is growing and its benefits are becoming more and more apparent – investments in this sector are increasing too. In 2016, CropX (an American smart farming solution provider company) was invested upon by Lab IX and Robert Bosch Venture Capital GmbH. Many well-known OEMs of sensor devices are coming up with customized tracking tools and equipments – designed according to the precise nature, size and requirements of each farm. The collaboration between Trimble Navigation and Avidor High Tech France, Precision AG and Agrinetix (in November 2016) is an important example of the several high-profile partnerships that are being struck up between different companies involved in the overall smart agriculture value chain. Corporates are prepared to spend more on agricultural technology, knowing that the returns can be potentially big.

Drones are taking flight

On ‘connected farms’, drones (or, Unmanned Aerial Vehicles) are gaining in importance as useful tools for crop data generation and general surveillance of cultivation lands. Over the last couple of years, quite a few agricultural solution provider companies have included drones in their services – a clear indication of the latter’s popularity and utility in smart farming. Since drones are not particularly expensive and are (generally) easily manageable, they are finding ready acceptance as a key component of IoT-enabled farming tools. Capturing images from fields is the primary function of drones in agriculture. Since these tools have boosted both the volume and the accuracy of farming data, decision-making has also become more informed than before.

Understanding the smart agriculture ecosystems

Farmers and farm managers are, of course, the end-users of smart farming technologies. Technology providers are the ‘suppliers’ in this market – in charge of coming up with innovative software applications/mobile apps, M2M tools, sensors and tracking devices, communication channels, data analytics tools and other smart equipments for the users. OEMs like John Deere, who provide tractors and combines and sprayers are important stakeholders here, as are the ‘influencers’ (who have key decision-making authorities, including price-setting). With the advancement of technology, smart farming is becoming increasingly diversified – with players from different industries (retail, finance, chemicals, engineering etc.) joining the ecosystem in the last few quarters.

Fish farming on the fast track of growth

The benefits of smart agriculture has expanded to different types of firms. While indoor horticulture offers the best opportunities for precision agriculture, fish farming is another field that has started to show big benefits from the implementation of smart technology. Right from GPS tools to track the migration of fishes and selecting the best locations for fishing, tracking feeding patterns and detecting probable diseases – everything can now be done with the help of advanced tech devices/monitors/sensors. Information about the water quality can also be generated. Livestock management, farm vehicle management and dairy management are three other sectors that show high adoption rates of smart farming methods.

Note: Cotton, maize, soybeans and corn are some important crops that are being brought under the purview of smart farming in the United States. With greater use of technology and resultant productivity/supply improvements – it is expected that prices will remain under control in the long-run.

Barriers to growth

For all its advantages, smart agriculture is still at a nascent stage – with penetration levels on the lower side at present. A recent Trimble report showed that basic data services are used in only 1 out of every 4 farms in the world. In the US, less than 40% of the maize and corn acres actually employ precision farming techniques. The cost-factor remains an important barrier (setting up the required infrastructure requires significant upfront investment by farm-owners). The general uncertainties about data security in particular, and the impact of politics and weather elements on agriculture in general, are also important points of concern. Broadband and wifi network coverage in rural farm areas far from being uniformly strong, while there is still room for more specialized software solutions to come in. Confusions over the sensor standards, data ownership and cellular communication standards also lead to many farms staying away from initiating smart agricultural practices. Installations of IoT devices in farms also suffers from the problem of fragmentation. The good thing is, familiarity with IT tools and best practices is growing – and over time, most of these problems would hopefully be ironed out.

Growing opportunities

The scope of IoT is expanding rapidly, and the onus is on the farm owners to understand, access, and implement this ‘intelligence’ in their day-to-day farming practices (e.g., tractors or irrigation systems). The partnership between Dacom and Orange Business Services have shown that there are considerable opportunities for leading mobile network operators to collaborate with agri equipment manufacturers. Similarly, M2M platform owners can get into mutually beneficial deals with manufacturers of sensor devices (given the importance of embedded SIMs in sensors that would be used in rural areas). Both the hardware and software segments of the market are set to become more refined in the foreseeable future. All of these will contribute to, at the end of the day, greater productivity, sustainability, reliability and optimized farming.

Earlier this year, the ‘Internet of Food and Farm 2020’ (IoF2020) was launched to speed up the implementation of IoT standards and practices in farming, and push up the overall adoption of smart agriculture in Europe. The four-year project (2017-2020) has users from the arable farming, meat production, vegetables, fruits and dairy farming sectors, and as many as 19 use cases in total.

Usage of technology in agriculture is not something entirely new. The first gas tractors and chemical fertilizers were used way back in the 19th century, and satellites were used for farming from the later half of the 20th century. GPS sensors were included in tractors by John Deere in 2001. Technology has come a long way since then – web-enabled tools and services are becoming more and more commonplace, and interest in IoT is at an all-time high. With traditional farming methods likely to fall woefully short of meeting the escalating food demands, farmers are increasingly turning towards smart agriculture. This is one domain that is likely to soar further in future.

 

 

 

The Other Side Of Chatbots: Risks & Disadvantages

 

List of chatbot risks and disadvantages

 

Round-the-clock ‘availability’ is one of the most important prerequisites of modern-day businesses, according to nearly 52% people (as reported in a recent research). This requirement can be best fulfilled by artificial intelligence (AI)-powered chatbots, that can simulate human conversations, and serve as the first point of interaction between organizations and customers. Apart from acting as the ‘virtual spokesperson’ of businesses, chatbots also help in significant reduction in expenses. By 2022, it has been estimated that the annual savings owing to the use of AI bots will be more than $8 billion. However, like any other form of innovative technology, chatbots come with a few disadvantages and potential risks. We will here focus on them:

  1. The problem of rogue chatbots

    With advanced machine learning capabilities, chatbots are increasingly becoming adept at ‘imitating’ human conversations. That, however, can prove to be a double-edged sword – since hackers can easily create bots that pose as buyers or suppliers, to strike up conversations with the in-house personnel of businesses. Over the course of a chat, this ‘rogue bot’ can convince users to share personal information and/or sign up for unauthorized/inappropriate, malicious content. Other forms of phishing attacks can also be launched by hackers through these bots. As a rule of thumb, users should stay away from sharing confidential information (say, credit card details) on a bot – until its security is verified. Links supposedly sent by vendors/buyers should be treated with caution as well.

Note: Users of the Tinder app have already been affected by a malware bot, posing as a female user.

  1. Bots can be too mechanical

    For all the advances in artificial intelligence and predictive behaviour (helping in more intuitive, contextual chats) – chatbots remain, in essence, glorified mechanical robots. They are pre-programmed by developers, and can handle queries/comments from humans only as long as the overall conversation flows in the ‘expected path’. As soon as something else – that has not been fed into the bot program – is asked, the chatbot’s performance gets affected. In most such instances, the program tries to manage the situation by putting forth more qualifying questions, which can be: a) repetitive and b) irritating for the customer. To be of practical use, a chatbot has to be capable of handling different scenarios and resolving queries as quickly as possible.

   3. Risks of using standard web protocols

While the chatbot revolution definitely has more than its fair share of innovative features, there is one significant downside. These programs (built on platforms like Slack, Facebook Messenger, WhatsApp or SMS) typically use open Internet protocols, that have been in existence for long – and can be targeted by professional hackers relatively easily. In fact, chatbots have been referred to as the ‘next big cyber crime target’ precisely for this reason. Using chatbots with standard protocols is particularly risky in the financial sector (e.g., banks). To tackle these security ‘threats’ and ‘vulnerabilities‘, most financial institutions currently ensure that all types of data transmissions take place through reliable HTTPS protocols. Transport Level Authentication (TLA) is another cutting-edge technique for financial sector chatbots to enhance data security standards.

 

Note: Robust security is essential for bots that support speech recognition (voice technology) as well as the ones that are purely text-based.

 

  1. Probable confusions affecting buying decisions

    A big advantage of chatbots is that they allow buyers to check out products right inside the chatbox – doing away with the need to actually visit stores (or browsing through the different item categories on online shopping portals). However, a closer examination suggests that confusions can crop up in this regard. A person might ask a chatbot to show shirts of a particular size – and the computer program would show all items in that category. The customer has to narrow down the displayed range by mentioning his/her favourite colour, sleeves, collar and material. The process can be time-consuming (defeating the very essence of chatbots somewhat) – and it might well happen that the bot ultimately fails to show the product that a customer is looking for. This, in turn, obviously affects the purchase decision of the latter. For some cases, actually checking out the available stock yields a more satisfactory result than simply dealing with chatbots.

 

  1. Low-level job openings being eaten up

    ‘Intelligent chatbots’ are ideal for low-level, repetitive jobs at organizations. Since they are programmed and have the latest AI support, these chatbots can do such ‘menial’ jobs much faster than human workers. While that is great from the business productivity perspective, a serious problem raises its head…about chatbots being likely to displace human workers from low-level positions in future. The threat is particularly serious in developing countries like India, where nearly 1.5 lakh new employees join the BPO sector every year. From the demand-side too, bots seem to have an upper-hand over humans – with 44% users in the United States stating their preference for chatbots (instead of humans) for customer services. While those at senior-level positions are not at risk, openings for ‘online marketers’ and ‘customer relationship managers’ are likely to dry up over the long-run.

 

Note: Chatbots are fairly easy to make for developers, thanks to the presence of the various bot development frameworks. The cost of making chatbots is not very high either.

 

  1. Increased personalization can be a problem

    Chatbots are becoming more ‘chatty’ than ever before. Ask Eva, the web chatbot made by Senseforth, whether she likes you – and it will shoot back with a cool ‘am still learning’ response. There are bots that can relate typing in capital letters to greater urgency – and accordingly, hand over the chat to a human employee. Things like personal food preferences, addresses, favourite dresses and a lot more are being shared on chatbots…at times without even realizing that the conversation is taking place with a piece of manipulatable software, and not a fellow human being. Deliberate impersonation can also be an issue. AI-powered chatbots typically store customer data for analysis and greater personalization in future – and there remains a risk of this data being ‘stolen’ by a third-party attacker, and used against the concerned individuals/businesses. An intelligent, friendly chatbot need not necessarily be a good one!

 

  1. Fails the Turing Test

    AI chatbot programs are supposed to simulate human behaviour closely. How good are they at doing this? While reports keep coming in about the witty replies and efficient responses of bots – the fact remains that most chatbots do not pass the famous Turing Test (conducted to gauge the ‘intelligence’ of machines). This brings up the risk of conversations being unfulfilling for potential buyers – inferior to what a traditional two-way conversation between humans would have been. To minimize these problems, experts recommend preparing chatbots in a way that they can introduce humans in the conversation – as and when required (with a message like ‘I am your AI robot. Let me connect you with our executive’). Chatbots might be very, very ‘intelligent’…but they cannot think for themselves. At least, not yet.

 

Note: The relatively ‘meh’ performance of Facebook M has shown once again that chatbot technology still has a long way to go.

   8. Can be manipulated through social engineering attacks

‘Hitler was right’. That was what Microsoft Tay – the ambitious ‘AI with zero chills’ bot – started to tweet within a day of its launch in March 2016 (in a canned ‘Repeat after me…’ series of tweets). The bot had to be suspended – and when it was re-launched a week later, there were trouble again, as Tay started to constantly tweet ‘You are too fast, please take a rest’ – multiple times per second. The entire Tay episode serves as a classic example of how AI chatbots can be manipulated into an engine for spewing out racist, sexist and other offensive content. Developers have to be very careful while designing the security of computer programs. If any loopholes/bugs remain, things can go pear-shaped very quickly. Microsoft Tay (ironically, ‘Tay’ stood for ‘thinking about you’) was an unmitigated social media disaster.

   9. Data handling on chatbot platforms

Although cloud security has become stronger than before, things are not quite foolproof yet. While using a chatbot, businesses have to be able to track the movement of data (provided by customers) – and follow a clear-cut policy on the location where and the duration for which the data will be stored. There cannot be any uncertainties over the identities of people who will be able to access the information (importance has to be given on ‘authorization’ and ‘authentication’) – and how the same would be used. In the medical and financial sectors in particular, the volume of sensitive personal information shared is high, and the importance of due diligence cannot be overemphasized. People should be able to ‘trust’ the chatbot (and consequently, ‘trust’ the business) while interacting with it.

  10. Lack of individuality and generic conversations

Natural language processing (NLP) is one of the pillars of AI chatbots – and there is no scope for doubting that these software programs can behave like humans while chatting with end-customers. However, most of the chatbots do not have a definite personality of their own – and hence, comes across as too generic and impersonal (the much sought-after ‘human touch’ is missing). In addition, chatbot programs do not (or are unable to) factor in feelings of empathy and emotion – which are often critical while interacting with clients. Software developers should ideally provide a nice little backstory to their chatbots, along with a basic sense of humour (emojis, maybe?) – which will make them more relatable to final users. If a customer wants to know about the bot, the latter should not feel stumped.

 

Note: The CNN chatbot is a good example of a bot functioning like a machine. It fails whenever anything beyond its pre-programmed script comes up in the conversation.

   11. Accuracy, trustability, accountability

Chatbots are still at a nascent stage. Mistakes in speech-recognition and NLP still happen rather frequently – and customer instructions are, as a result, not carried out properly. There are bots which are used to send out spammy, rejigged promotional content, which hurts the ‘digital trust’ factor of these tools. The onus is on chatbot developers to be fully transparent and frank about their AI programs – its features, capabilities and limitations. Developers/Brands also need to be fully accountable for the performance (good or bad) of their chatbots. To its credit, Microsoft came out and accepted full responsibility after the Tay fiasco. In a nutshell, the quality of service (QoS) still requires considerable improvement.

   12. The often-overlooked need for encryption

Encryption might be one of the first things that come to mind when it comes to digital data security – but many chatbots on public platforms (e.g., Facebook Messenger) are not secure enough in this regard. If a chatbot is deployed on a non-encrypted platform, data transmissions through it might be hijacked by unauthorized third-party agents. Access to company databases and other such private information should not be given to such unsecure chatbot platforms. Ideally, every conversation that takes place on a bot should be encrypted – and the deployment should be done on a secure platform. In the absence of proper channel encryption, chatbots can be soft targets.

 

There are chatbots that miss out on performing more tasks over and above what they actually do (the Fandango chatbot, for instance, should be able to handle payments). Apart from being aware of the disadvantages and likely risks of automated bots, it is also important for final users to have reasonable expectations from the technology (after all, a chatbot is never going to replicate all the functionalities of a premium smartphone!).

 

The chatbot revolution is far from being a fad. AI bots have already started to revolutionize the standard of customer communications, and things will become even ‘smarter’ in the foreseeable future. As discussed above, there are problems and chatbots are not perfect yet – but these issues should be gradually ironed out. What remains to be seen is whether the ‘bots are the new apps’ prophecy would be fulfilled anytime soon!

 

 

 

Bring Your Own Risk: Top 12 Risks Of BYOD Policy

BYOD risks

 

The ‘Bring-Your-Own-Device’ (or, BYOD) policy is increasingly being implemented in workplaces around the globe. A recent report showed that nearly 3 out of every 4 businesses worldwide either already practise BYOD policies, or have plans to implement it in the foreseeable future. Considering the many benefits of BYOD (productivity enhancement, lower costs, better mobility, etc.) – the rapid growth of this policy does not seem particularly surprising. The overall size of the BYOD market will swell to $181.4 billion by the end of this year.

While much has already been documented about the merits of implementing BYOD at workplaces, it is vital to not lose sight of the risks and potential problems with this policy. According to the heads of 78% firms around the world, security is the biggest point of concern with BYOD. In what follows, we will put the spotlight on some such probable BYOD risks:

 

  1. Latest security patches and updates not being installed

    There is no guarantee that all employees would actually have updated security patches and fixes on their devices. Smartphones and tablets with outdated software are more vulnerable to hack attacks – which can compromise the confidentiality of valuable corporate data. The problem gets more compounded for Android handsets – since the availability of the latest security updates depend on the OEMs and carriers on this platform. Unless employers can make sure that all the devices brought in by workers have the necessary ‘protections’, problems can always crop up.

 

Note: Companies need to have a policy that makes it mandatory for employees to regularly update the firewall/antivirus on their devices.

     2. Malware applications

It is next to impossible for organizations to keep a tab on the different types of mobile apps that employees choose to install in their handsets. Hackers can easily create applications with malware – and when people install them (often, app permissions are allowed without checking the details carefully), all official data present in the device gets exposed. In fact, such spyware apps can even be used by third-party agents to access servers and ‘steal’ important data stored therein. It is extremely important for businesses to have a proper ‘Mobile Application Management’ (MAM) standard in place – to minimize the chance of such risks (downloads from third-party app stores should be banned). The IT departments can also blacklist each and every suspicious app.

     3. The problem of stolen devices

On average, close to 70 million smartphones are misplaced or lost by users. Of more relevance to our current discussion is the stat that, nearly 4.5% of all smartphones issued by organizations to their employees are stolen every year – with almost 52% of such cases happening at the workplace itself. Now, every stolen device poses a security risk – since all the data stored in it can be accessed/used/manipulated by the perpetrator. While there are tools to remotely wipe off data from stolen devices, an Osterman Research report revealed that this is possible in less than 25% of all such lost smartphones.

 

Note: Most employees either do not protect their devices with passwords/passcodes. That makes ‘data stealing’ that much easier.  

 

  1. Using unsecured wifi access points

    Many personal devices are set up to connect to any open wifi network available. While organizations with BYOD policies, of course, have secure access points for employee handsets – connecting to other open wifi networks (at public places, hotels, restaurants, etc.) can be dangerous. Experts advise caution while using unsecured wifi at home as well. Using a malicious wifi network can lead to official tasks becoming visible to hackers (i.e., the network visibility can be unnecessarily increased) – and chances of ‘man-in-the-middle’ attacks become higher. To work around this risk, companies should make it compulsory for employees to use a virtual private network (VPN) while interacting with any official data on their personal handsets.

 

  1. Devices of departing workers

    Employees can leave a company at any time – and rather alarmingly, most BYOD-following companies do not have clearly-defined policies for such employees. As a result, sensitive corporate information remains in their devices – and that can easily fall in the wrong hands. The risks of such ‘data leakage’ is even greater when a person is terminated and leaves on unpleasant terms (since (s)he can deliberately five out the information with competitor firms). While it might not be practically feasible to ask employees who are leaving to wipe all data from their devices – at least business-related apps and files need to be erased. Once a person is no longer a part of a company, (s)he should not have access to any internal information of the latter.

 

  1. Jailbroken or rooted devices

    Many iDevice-owners jailbreak their handheld devices (China leads the way regarding jailbroken iPhones). On the other hand, close to 28% of all Android phones are ‘rooted’ by their users. When such jailbroken/rooted devices are brought under the BYOD-fold, they can ‘open up’ entire databases – providing a convenient entry point for hackers and cyber criminals. Native security restrictions become invalid, and users (with their administrator-level rights) might unknowingly install external malware applications. Prior to registering any device for corporate use, the IT security staff should ensure that it has not been jailbroken or rooted.

 

  1. Loss of control over data movements

    In 2016, close to 87% of businesses across the world faced cyber security threats in some form or the other (as per a Bitglass report). Since enterprises typically use both mobile storage and cloud storage for data transmission and maintenance – it becomes difficult after a point in time to keep track of the status of any particular information (i.e., data movements). There are third-party tools can perform this task – but their reliability remains an issue. As SaaS standards are becoming more advanced and reliance on cloud services are increasing, risks of data stealing (through ‘phishing’ and similar attacks), ‘data loss’ and lack of compliance are going up too. A whopping 90%+ organizations have serious concerns over cloud security.

 

Note: Last year, there was a three-fold increase in ransomware attacks on organizations.

 

  1. Lack of reimbursements to employees

    In a bid to minimize overall operating expenses, many companies stay away from providing full reimbursements to their employees (to cover BYOD costs). According to a Tech Pro Research report, 18% respondents receive a monthly stipend – while a measly 7%-8% employees actually receive full reimbursements. That, in turn, retains the ‘personal’ nature of the devices, with employees feeling greater freedom to use their favourite apps and games. Gaming, in particular, on a registered device (using the corporate network) can put additional bandwidth and storage pressure on the network. Productivity levels can also be hampered, if workers access social media sites or play games or chat on IM applications on their devices (using up available data resources as well).

 

  1. Line between personal device and company device being blurred

    With BYOD policies evolving over time, it is becoming increasingly difficult to demarcate between personal usage and official usage of a device. Employees are unlikely to react well to a ‘big brother’ attitude from organizations (i.e., full restrictions on the apps and activities permissible on devices). At any time, a company might feel the need to remotely wipe off the data on a device – and personal data might also get erased. If there are any glitches in the endpoint security standards of the BYOD policy and infrastructure, problems are likely to happen.

 

Note: Employees can also access/download malicious unauthorized content on their devices, particularly since data restrictions are (at most organizations with BYOD) minimal.

    10. Role of tech departments

8 out of every 10 employees feel that personal smartphones will have larger roles to plays in workplaces, in the near future. In such a scenario, the importance of maintaining diligent mobile device management (MDM) becomes immense – and the responsibility of ensuring the compliance lies on the tech/IT departments of organizations. The stats, however, paint a contradictory picture. Close to 18% workers report that they use personal handheld devices for officework – without the respective IT departments even being aware of it. More alarmingly, over 28% of tech departments prefer to gloss over active BYOD in workplaces. There is clearly a lack of surveillance – and that is increasing the vulnerabilities of BYOD in practice.

     11. Violation of network policies

Even if a company has a clear network access/usage policy – controlling which devices can access it – security threats remain. For the tech-savvy employees, it is fairly easy to use an alternative mechanism (generally in the form of third-party mobile apps) to access corporate databases, without the permission of the authorities. In the absence of set parameters (to monitor data access), confidential information can fall in the hands of unauthorized individuals. Network policies that are applicable only on wired LAN systems are not adequate for companies that allow BYOD.

    12. Probable increase in costs

One of the key drivers behind the growing popularity of BYOD is the chance of lowering overall costs. However, this advantage can very well be nullified – if large expenses become necessary for managing the different types of employee devices that are being used for corporate tasks. There is also the chance of an employee leaving AFTER the organization has spent money to provide him/her with a device and associated service plan(s). In such cases, the concerned organization ends up with sunk costs – which can be considerable.

 

BYOD allows employees to be ‘always on’, and provides an additional layer of flexibility to the working pattern of workers. The higher productivity levels achieved should also lead to greater employee-satisfaction. As discussed above, the policy has its fair share of risks and security threats – but fortunately, most of these problems can be effectively tackled. Organizations need to form and implement a thorough security policy and provide adequate training to workers – before granting the permission for BYOD. It is a dynamic, future-oriented technology and it is set to become mainstream in workplaces worldwide. The onus is on the users to make sure that BYOD does not, in any way, put corporate information in danger.