Author Archives: ramakrishnan6

Patient / Elderly care and notification system using indoor localization

Technology behind our project:

Indoor localization has been a popular topic of research in ubiquitous computing.

žOur aim is to use Wi-Fi based indoor localization techniques to locate movement of a person (patient/elderly person) over a period of time inside the house.
Our present design consists of installing 4 wifi routers at four corners of a house. The house can be divided into a virtual grid. Each grid would cover a particular area within the house. For example, grids 4,5,6,7 could be the kitchen or something like this. A mobile device can be used to read the signal strength of each access point in each grid of the house. By building a database of such signal strength values, we can assign signal strength signatures to each grid. Now we can successfully identify each corner of the house and locate our mobile device anywhere within the house.
Use cases for this technology:
1. žUse this technology to determine motion pattern of a patient/elderly over time.
2. žProfile his/her activity data and then use this data in future to find any deviation from normal behavior.
3. Report any abnormalities. Select a threshold value beyond which an activity if repeated or carried out in a way other then normal, will be termed as abnormal and will be reported to the observer. For example, if an elderly person is in the restroom for more than an hour although the usual time taken is just 30 minutes, it could indicate some emergency situation.
Presentation is given below..
– Siddharth Gupta
– Ramakrishnan C H

AgeLab : MIT trying to solve the problem of aging

The world’s population is aging at a staggering rate. The 50+ population is the fastest growing segment worldwide and predicted life-expectancies are at a historical high.

  • An American turns 50 once every seven seconds.
  • Within the next few years, 50% of the European Union’s population will be 65+.
  • By 2030, in Italy, retirees will outnumber active workers.
  • By 2050, the median age in Thailand will rise to 50.

Let’s see how MIT is going about solving this problem. Should Georgia Tech expand its Aware Home initiative to include some research in this area?

Visit the website to read more:

– Ramakrishnan

PlaceLab MIT: context-aware computing at home

This is an initiative by MIT and TIAX LLC to experiment with new research ideas and to create a test bed to prototype and test new products. This is very similar to the Aware Home initiative that we have at Georgia Tech. I thought of posting this here since it is relevent after the Aware Home visits and showcases similar experiments that are being conducted at other universities.

One of the experiments going on in PlaceLab is about context-aware computing. an excerpt from the website goes something like this:

“We believe that environmental sensors combined with wearable sensors may offer the most potential for automatic recognition of everyday activity to enable new generations of context-aware computing devices. We are developing algorithms that automatically detect some activities from portable biometric and motion sensors. We have created software that runs on PocketPC devices and can be used to collect data using context-aware experience sampling – where sensors automatically trigger a computing devices to ask a volunteer a set of questions in a particular situation. This software is being used both for studies of people and technology in natural environments such as homes and workplaces as well as to collect data needed to develop new context detection algorithms.”

Recognizing and remembering Activities - Memento

“Memento”  is a prototype context-triggered reminder system, which presents users with “3 best guesses” about what they are currently doing and lets them associate an audio reminder with the most appropriate choice. The system uses Hidden Markov Models and the MITes to infer activity context.

Prof. Gregory Abowd at Georgia Tech also worked on something very similar to this.

– Ramakrishnan