Research‎ > ‎

Location Based Systems and Spatio-Temporal Data Mining

Making OpenStreetMap for Bangladesh:

OpenStreetMap is considered to be the Wikipedia of maps. As the commercial maps are not freely available to use all the information, it has been a challenge to build cheap location

based software. With the increasing growth in the volume of users of 3rd Generation mobile phones, the location based services are becoming very much important. Bangladesh, being a developing region, has not public digital map which can be used for making meaningful software. Even the Google/Yahoo maps are not much rich in this country. Hence, I felt the necessity of building open source digital map for Bangladesh.

I started working on OpenStreetMap for Bangladesh in early 2010. I presented the State of Bangladesh in the annual meeting of OSM in Spain in July, 2010 with the OSI Travel Scholarship.  As a part of the scholarship, I received 5 GPS units from OpenStreetMap Foundation in January 2011 and with those I started mapping different places of the country. At the same time, with my group, I design different location-based services for Bangladesh. Our primary focus is upon the threatening problems of Bangladesh including natural disasters, traffic jam etc.

Mobile Phone Based Real Time Bio-Surveillance for Developing Regions:

The early detection of epidemics is immensely important for the public health sector of a country. For this, real time bio-surveillance has been put under rigorous research during the recent past. Although n the developing country, the improved hospital admission systems and health care systems give the option for gathering medical data comfortably, this become a challenging task for the developing regions where the medical resources are scarce, the health-care infrastructures are vulnerable and and technical support is very poor. To address this problem, Prof. Artur Dubrawski of Carnegie Mellon University  made a mobile phone based real-time bio-surveillance project. The central idea is to gather the medical data from the hospitals or health care centers by mobile phone using an easy mobile application, and then execute a multimodal data mining over the streaming data to detect whether the admission rate for a particular disease cross the threshold value using the T-Cube software made at Auton Lab of CMU. In that case, the system will generate an alert which can be disseminated over the region by mobile SMS using disaster response systems like "Sahana". This project has already been piloted over Srilanka and Tamil Nadu of India and has been proved successful. With Prof. Dubrawski and some other members of his team, I am working on running this program in Bangladesh. The potential challenges are the unavailability of a good digital map and lack of volunteers. We are actively working on getting solutions to these. On the other hand, I am trying to improve the detection system using Active Learning both over time and regional changes.

Exploiting Online Social Networks for Balancing Traffic Loads

The burgeoning growth of online social networks in today’s world has opened up a vista of opportunities for collaborative social efforts in developmental issues. Facebook, Twitter, MySpace, Orkut etc. are gradually becoming indispensable parts of our daily life. Different groups and communities are frequently being developed in these networks for people of different interests and addressing different issues. In parallel, the GPS and internet enabled mobile devices (for example, the third generation mobile phones) are intruding into the society in a rapid pace. Hence, location based collaborative services via social networks are no longer beyond the reach of urban people, who are, in general, considered to be closer to technology compared to the rural mass. In this project, we explore the opportunities of using the social networks as a medium for devising collaborative efforts for balancing the traffic loads in a congested city. The central idea is to share the status of a road by one user who is passing through it, with the members of his/her network community and then having a software tool that suggests which road should be free according to the given data. We have considered three different types of systems here and presented the corresponding advantages and pitfalls. First, we have considered the currently popular social networks and used the user’s personal “status updates” as the source of information for current traffic loads of a street. Then we have considered a new type of social network where the current position of each of the users will be shown on a city map and their statuses will help one visualize the current traffic loads of different streets. Finally, we consider a game over social networks where the users will get the motivation for putting right traffic status of a street from the virtual “credits” which will help them getting better positions in the game. We have also discussed the possibilities of replacing the virtual credits by real-life rewards for encouraging people to participate in these types of collaborative efforts. We are using OpenStreetMap for this.

Smart Blood Query: A Novel Mobile Phone Based Privacy-Aware Blood Donor Recruitment and Management System for Developing Regions

The growth in numbers and capacity of mobile devices such as mobile phones coupled with widespread availability of inexpensive range of services presents an unprecedented opportunity for mobile healthcare applications. Blood donation and transfusion service is one of the most complex management systems in health sector. Quality management of a Blood Transfusion Services (BTS) starts with safe blood donor recruitment (BDR) and donor care. In the South-East Asia Region (SEAR) almost all countries except Thailand depend heavily on replacement of blood from relatives and friends. In this project, we present location-aware mobile phone based blood donor recruitment, information retrieval and management system that aims at ensuring the quality of the blood and increasing the efficiency of operation management. Here an attempt has been made to leverage the ubiquity and power of the standard mobile phone as a lifesaving mobile health-care application, delivering more user convenience.