Internet of Things - IoT

IoT is paving way for an era of intuitive human-machine interactivity i.e., simultaneously connecting billions of devices for an intelligent internet. The future of IoT has the potential to be limitless. Advances to the industrial internet will be accelerated through increased network agility, integrated artificial intelligence (AI) and the capacity to deploy, automate, orchestrate and secure diverse use cases at hyper-scale. The potential is not just in enabling billions of devices simultaneously but leveraging the huge volumes of actionable data which can automate diverse business processes. As networks and IoT platforms evolve to overcome these challenges, through increased capacity and AI, service providers will edge furthermore into IT and web-scale markets [ref].

We at SPCRC are working on much innovative cutting edge IoT applications. We develop optimal algorithms, deploy the algorithms in real-time IoT devices and validate its performance. IoT lab of SPCRC in general works on Embedded Systems, signal processing and ML. We have collaboration with international industries and many exciting projects are to forward in future.

We are undoubtedly becoming ‘smarter’ in various aspects of our daily life, with IoT and machine learning (ML) playing a crucial role in this. Well known thought leaders like Bill Gates and Dr Judith Dayhoff (author of ‘Neural Network Architectures: An Introduction’) say that the IoT has given our physical inanimate world a digital nervous system. IoT has really exploded over the past three years, demonstrating its potential in applications ranging from wearables and automated cars to smart homes and smart cities, creating an impact everywhere. Machine learning is basically a part of computer science that makes any system smart enough to learn on its own without actually being programmed for that task. It helps a system or device learn in the same way as humans learn by themselves. As we learn any type of system on the basis of our experience and the knowledge that is gained after analysing it, machines too can analyse and study the behaviour of a system or its output data and then learn how to take different decisions on that basis.

The main purpose behind ML is to automate the development of different analytical models to enable algorithms to continuously learn with the help of available data. Google’s self-driving vehicle is one such development that uses different ML techniques with IoT to create a completely autonomous vehicle. It combines the advanced features of different modern cars (like speech recognition, lane assistance, adaptive cruise control, parking assistants and navigators). [ref]

Internet of Things has become a global phenomenon that has the potential to change the way we live by revolutionising our interaction with everyday objects. The number of objects covered under IoT is expected to reach a mammoth 50 billion by the year 2025! Just as the smartphone revolution changed our perception of handheld mobile devices, smart cities are set to be the next big upgrade that will change our perception of living in general. A big chunk of the smart city plan ranging from managing traffic and automating household devices to keeping people safe relies heavily of IoT. Needless to say that your house will no longer be made from just brick and mortar but will essentially be a computer system with sensors and actuators which will not just listen to your commands, but also learn from you in order to automate tasks without you lifting so much as a finger! The IoT lab in SPCRC is a congregation of cool nerds who like to eat embedded systems in breakfast and machine learning in lunch so that dumb monotonic systems can be made smarter before dinner!

With the number of IoT devices increasing everyday, a big challenge of providing constant and sufficient power to them has paved its way to the desks of the researchers. The number of connected IoT objects is expected to reach 50 billion by the end of 2025; how will such a vast eco-system be powered and maintained? Surely not all of these devices would draw power from mains! In fact in many IoT use cases, the sensor nodes are deployed in places where mains power is unavailable leaving only batteries available for use. The research on data reduction techniques is therefore a very relevant topic today wherein various signal processing as well as machine learning algorithms are developed to extend the lifetime of IoT nodes without compromising much on the data that is to be collected by the system.

Pioneers in this field