CyPhyS+
A Cyber Physical System for Remote Health Monitoring of Old Age Patients.
CyPhyS+ is a project at Indian Institute of Science, funded by DeitY(Department of Information Technology), aims to be a model for future remote healthcare monitoring systems. Such a system should be easy to deploy and use as well as reliable and secure. It should provide two-way communication to facilitate sensing as well as control. Technology should be transparent to the end-users and must function without much user intervention. Elderly persons, the end-users we are aiming, are expected to be weak with many limitations on their physical ability. Therefore, wearable design and user interface aspects play major role in acceptability of such a system.
The backend infrastructure that stores information needs to provide preliminary analysis of received medical data and GUI to present it in a meaningful way to medical professionals. The communication infrastructure should guarantee integrity and reliability of data under adverse conditions.
We have considered a scenario of old age home that needs reliable, affordable and scalable healthcare solution. Further, this solution should support limited mobility such that daily activities of the inmates are not affected. The figure shown captures the scenario we are addressing. It is also possible to extend this for people who are home alone and need care. Idea is to remotely monitor the health of a person in a non intrusive and transparent manner.
CyPhyS+ Web
CyPhyS+ 2015 IEEE ICSC
CheepSync
A time synchronization service for resource constrained bluetooth le advertisers
Clock synchronization is highly desirable in distributed systems, including many applications in the Internet of Things and Humans. It improves the efficiency, modularity, and scalability of the system, and optimizes use of event triggers. For IoTH, BLE - a subset of the recent Bluetooth v4.0 stack - provides a low-power and loosely coupled mechanism for sensor data collection with ubiquitous units (e.g., smartphones and tablets) carried by humans. This fundamental design paradigm of BLE is enabled by a range of broadcast advertising modes. While its operational benefits are numerous, the lack of a common time reference in the broadcast mode of BLE has been a fundamental limitation. This article presents and describes CheepSync, a time synchronization service for BLE advertisers, especially tailored for applications requiring high time precision on resource constrained BLE platforms. Designed on top of the existing Bluetooth v4.0 standard, the CheepSync framework utilizes low-level timestamping and comprehensive error compensation mechanisms for overcoming uncertainties in message transmission, clock drift, and other system-specific constraints. CheepSync was implemented on custom designed nRF24Cheep beacon platforms (as broadcasters) and commercial off-the-shelf Android ported smartphones (as passive listeners). We demonstrate the efficacy of CheepSync by numerous empirical evaluations in a variety of experimental setups, and show that its average (single-hop) time synchronization accuracy is in the 10 μs range.
Cheep Sync : IEEE Communication Magazine (Vol 54 Issue 1 2016)
Road Traffic Sign Detection
Realtime Imge Classification of Road Trafic Signs using Beagle Bone for Driver Assistence.
This is a DIT(Department of Information and Technology, Gov. of INDIA) sponsored project that focuses on detection and Identification of Road Traffic Signs. An assisting technology, which can alert the driver of some important signs in real time. Detection of Signs are done is various steps, Theresholding/Transformation, Exterior Sign extraction, Colour identification, Interior Sign Extraction, Inner Sign Colour Identification and finally calculation of various Invariant Moments. Classification is done using a Balanced Tree classifier.
Medicinal Leaf Identification
Using Image Processing and Classification algorithms to Identify Leafs with known medinical values.
There's a huge importance in identifying leaves/herbs with medicinal value. The project "Medicinal Leaf Identification" aids in identification on leaves of such value. Initial objective of the project was to study and implement Invariant features of such leaves and to classify using a balanced tree classifier.