The objectives of this project are – i) Development of WBANs consisting of smart wearable bio- multifunctional sensors relevant for AD prediction, ii) Development of an edge-fog-cloud intelligence layer capable of running AI-ML models required for efficient prediction of AD, iii) Ensuring reliable and secure transmission of sensed data to the edge-fog intelligence layer with an added focus to data privacy, iv) Development of an ensemble learning model for prediction, early detection and monitoring of AD, with near real-time feedback, v) Development of a user-friendly graphical interface for different actors associated with the whole work.

The objectives of this project are – i) Developing wearable sensor-based expert system to detect accidental falls of aged human beings using advanced machine learning algorithms, ii) Developing an Android App to notify regarding detected falls, iii) Creating a database of health parameters of elderly person probable of falling, which will help us in future to predict fall. This work will involve the development of a BSN-based system to detect accidental falls of human beings. Employing advanced machine learning algorithms, the system will fuse data from multiple sensors and becomes over-sure before inferring that a fall has occurred.

The proposed project has mainly four broad objectives. First, we aim to develop sensors-based system for early detection of landslide. Second, we plan to develop early prediction algorithm using machine learning approaches based on the gathered sensor data. Third, we target development of self-sustained by utilizing energy harvesting circuits sensor nodes to monitor landslides. Fourth, we aim development of hilly terrain communication network from sensor node to hub and subsequently to a base terminal. Corresponding to each of these objectives, steps have been accordingly planned out. Four set of sensors would be integrated on a rod that is to be placed inside the soil. Evaluation of degree of the hazard caused by the landslide would be carried out to identify training parameters for machine learning ML based prediction.

This project focuses on designing a automated system for real time monitoring and detection of leakages and bursts in water transmission pipelines using LoRa-based wireless communication, cloud computing and data analytics techniques. For accurate detection of leaks and bursts, features resultant in data because of geographical conditions of hilly regions will be incorporated in data analytics method. At first, the complete system will be tested on a test bed by imitating transmission pipelines system by considering hilly region issues. After that, the system will be implemented as pilot project in collaboration with PHE Department, Shillong.