Projects

Here I present a list of my projects. I tried to add the basic information of each of these projects with papers/reports.


Research Projects:


Mobile Phone based Solution for MicroCredit in Rural Bangladesh:
[Report: PDF]

Microcredit was introduced in Bangladesh in early Seventies and since then, it has been considered as one of the principal means of socio-economic development in many parts of rural Bangladesh. However, the impacts of Microcredit are not always positive and the ultimate objectives are very often found to be missing in reality. We conducted a field study at the district of Jamalganj in Sylhet. From our study we could come to know some facts why Microcredit operations are not being successful there. We therefore propose a mobile phone based solutions to those problems.







A Computer Game-based Approach for Increasing Fluency in the Speech of Autistic Children: 
( submitted to a conference) [draft]


Autism is a complex developmental disability that typically appears during the first three years of life. This is the result of a neurological disorder that affects the functioning of human brain. Children diagnosed with autism often are self-absorbed and seem to exist in a private world where they are unable to successfully communicate and interact with others. Sometimes they have difficulties in developing language skills and understanding what others say to them. They also might have difficulties in communicating non-verbally, such as through hand gestures, eye contact, and facial expressions. What actually causes verbal and nonverbal communication difficulties in autism is not yet known, but it is thought that an individual’s brain development was affected either before, during or after birth and thus the communication control centre was somehow impaired. Depending on the individual, the type of communication difficulties experienced will vary. Some individuals with autism can speak fairly fluently while others may not be able to speak at all. In this project we have developed a system that helps an autistic child for  increasing his or her fluency in speaking. Besides, we also present results of our experiments using the proposed Gaming Software with the autistic children of Autism Welfare Foundation (AWF) at Dhaka, over the past 3 months.



-------------------------------------------------------------------------------------------------------------------------------------------------

Increasing Intelligibility in the Speech of Autistic Children: 
(The ACM Symposium on Applied Computing (ACM SAC), 2011,Taiwan [to appear]) [Poster]
(IEEE Symposium on Multimedia (ISM) 2010, Workshop on Multimedia in E-Learning, Taiwan) [PDF]


Autism is a disorder of neural development which affects about one in every 150 kids on average. One of the major complexities regarding autistic children in social communication is the speech disorder.  The problems related to speech disorder fall into different categories and unintelligibility in speech is one of them. Although  there  is  no  definite medicine  or  treatment  for  autism, doctors, therapists, and special teachers can help kids with autism overcome  many  difficulties  by  different  physical  and psychological  therapies.  In  this project we have demonstrated our newly developed interactive computer game which will be helpful in increasing intelligibility in the speeches of autistic children and can  be  used  as  a  therapy  besides  the  traditional  approaches. During our five months of intervention with the autistic

children of Autism Welfare Foundation (AWF) at Dhaka, we checked the effectiveness of this therapy and got some encouraging results.


-------------------------------------------------------------------------------------------------------------------------------------------------

Detecting Turns in Conversational Dialogs:
(Manuscript under preparation)




In our conversational dialogs, we exchange turns. We get the silent clues of when we start talking and when we have to stop. This clues are very important to understand for conversation. However, there is no definite rule for guessing the turns. In many cases, we detect the turns based on pause, duration of speech, eye contact and facial expressions. While talking over telephone or such other media, we need to pick these clues solely from the speech. This require some cognitive computation which is inherent in most of the human being. But for their special pattern of thoughts, autistic children very often demonstrate poor performances in picking up turns. So, in this project we analyze the speech and try to mine the turns from conversational dialogs. Our aim is to devise an intelligent system which will signal one for taking turns based on the speech of his partner(s). This system is expected to help the autistic children to improve their turn-taking abilities. We experiment on duration of pause, frequency of the speech, zero-crossing etc. to determine turns. We are now trying to find out the optimal ensembling of this decisions to get the best output.


-------------------------------------------------------------------------------------------------------------------------------------------------

Development of the Sense of Turn-Taking in Autistic Children by Interactive Computer Games:
(Manuscript under preparation)


Abnormalities in social communication are considered as the principle characteristics of autism spectral disorder. Due to the abnormal cerebral structure, people with autism generally demonstrate poor performances while communicating to other people in the society. Speech is considered as one of the prime means of communication and people suffering from autism are very often found to have problems with their speeches. For example, the sense of taking proper turns during conversational dialogues is very often missing in them. This problem is even more frequent in their childhood when the skills of communication grow in them. In our ongoing intervention, we have prepared a number of interactive computer games for improving the skills of turn taking in autistic children and with different experimental setups; we analyzed their performances over a number of participants.


-------------------------------------------------------------------------------------------------------------------------------------------------


A-Class: A Classroom Software with the Support for Diversity in Aptitudes of Autistic Children:
( IEEE Symposium on Computer and Informatics (ISCI), Malaysia, 2011)
(
Third National Seminar on Computer and Information Technology (NSCIS) 2010, Khulna, Bangladesh.) [draft PDF]



The  burgeoning  growth  of  the  e-Learning  technologies  implies  the  fact  that  the  future  education system will  largely  depend upon  the  electronic devices  and computer aided  technologies.  It  has  already  been proved that the computer aided teaching techniques are much more effective for the children than the traditional teaching system in most of the cases. A large number of software has been designed to assist the teachers in the classroom to teach and evaluate the students. Although those software systems are good enough for a class with normal (neurotypical) children, those very often fail to address the special needs of the autistic children. Hence, the autistic children face various challenges in participating with neurotypicals in the same classroom. We have addressed  this  problem  by  designing  and  implementing  an  intelligent  classroom  software,  named “A-Class”, which  takes care of  the diversity of  tastes among  the autistic children of a classroom and helps  the  teacher  to teach in a class participated by both autistic and neurotypical children. In this project, design and implement  A-Class, based upon our five months of intervention with the autistic children at Autism Welfare Foundation (AWF) in Dhaka.

-------------------------------------------------------------------------------------------------------------------------------------------------

Mobile Phone Based Real Time Bio-Surveillance for Developing Regions:
[Research ongoing]

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
[manuscript under preparation]


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
[
AINA' 11 at DMWPC Workshop, Biopolis, Singapore]






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.









-------------------------------------------------------------------------------------------------------------------------------------------------

Cutting a Convex Polyhedron out of a Sphere:
  [pdf]
(JCCGG '09, WALCOM '10 and Graphs and Combinatorics, Springer )






Given a convex polyhedron P of n vertices inside a sphere Q, we give an O(n^3)-time algorithm that cuts P out of Q by using guillotine cuts and has cutting cost O((log n)^2) times the optimal.

This is the first algorithm for cutting a 3D geometric shape from another 3D geometric shape.

-------------------------------------------------------------------------------------------------------------------------------------------------

Vindictive Voronoi Diagrams and Stabbing Delaunay Circles:
[pdf]
(in International Symposium on Voronoi Diagrams (ISVD), 2010, Canada)




In this paper we consider the following problem: Given a set of n Player1 sites in the plane and their Delaunay triangulation D, place minimum possible Player2 sites such that in the resulting Delaunay triangulation D' of the sites of both Players, the neighborship between Player1 sites are as less as possible. We first consider placing minimum number of Player2 sites such that no two Player1 sites are neighbors in D'. We show that to isolate a Player1 site p, two Player2 sites are both necessary and sufficient if p is in the convex hull of D, otherwise three Player2 sites are both necessary and sufficient. This gives a liner time algorithm to individually isolate all Player1 sites by 3n−h Player2 sites, where h is the number of sites in the convex hull of D. Then we give two more algorithms for this problem. The next algorithm runs also in linear time and uses 3(n−1)−h Player2 sites, but is much simpler. Our next algorithm uses 5|M| sites, where |M| is the size of a maximum matching in D, and runs in O( p root(nm)) time, where m is the number of edges of D. Then we consider isolating sites by components, where a component in D' is a maximal connected subset of sites of the same player. We show that it is possible to place n Player2 sites such that in D0 the number of components among Player1 sites is higher than that among Player2 sites. The above problems are related to at least two existing well known research topics: Voronoi games, where the strategy of each of the two players is to place sites such that in the resulting Voronoi diagram some certain criteria is optimized for each player, and proximity graphs, where this problem is known as minimum stabbing set of Delaunay circles. Our bound of 5|M| for the first problem would work better than known bound for the minimum stabbing set of Delaunay circles if M has a smaller size.

-------------------------------------------------------------------------------------------------------------------------------------------------



Cutting a Cornered Convex Polygon out of a Circle: [pdf]

( in ICCIT '09 and Journal of Computers (JCP) )





The problem of cutting a convex polygon P out of a piece of planar material Q with minimum total cutting length is a well studied problem in computational  geometry. Researchers studied several variations of the problem, such as P and Q are convex or non-convex polygons and the cuts are line cuts or ray cuts. In this paper we consider yet another variation of the problem where Q is a circle and P is a convex polygon such that P is bounded by a half circle of Q and all the cuts are line cuts. We give two algorithms for solving this problem. Our first algorithm is an O(log n)-approximation algorithm with O(n) running time, where n is the number of edges of P. The second algorithm is a constant factor approximation algorithm with approximation ratio 6.48 and running time O(n^3).


-------------------------------------------------------------------------------------------------------------------------------------------------

Searching for the Centers of Spheres and Ellipsoids: [pdf]
(in ACT '09, India)

Biedl et al. first posed the problem of finding the center of a circle, starting from a point on the boundary and using a limited number of operations. They presented an open problem for searching the center of an ellipse in their paper. Later, Burr et al. solved that problem. However, in both of their works, they considered the searching space to be two dimensional. As a result their strategies do well on a plane. But in reality the searching space is three dimensional in most of the cases. In those cases we need an efficient strategy to find out the center of a sphere or in some cases, the center of an ellipsoid. In this paper, we have approached the problems of searching the center of a sphere and an ellipsoid. We have proposed here four different strategies for finding the center of a sphere. We have also proposed the strategy of searching the center of an ellipsoid.


-------------------------------------------------------------------------------------------------------------------------------------------------


Policy requirements to ensure security in enterprise grid security systems:[pdf]
(in CSA '09, Korea)

Addressing some vital security issues in enterprise grid technologies is particularly important from the software industry’s viewpoint. Enterprise grid computing systems do face unique security challenges, ranging from preventing access control attacks to ensuring encapsulation and safe object reuse to masquerading and brute-force attacks. Hence, the security requirements for enterprise grid system are also unique. In this paper, we presented the unique security issues and security requirements encountered in enterprise grid systems. We also devise appropriate security policies to address the enterprise grid security requirements.




Computer Graphics:
------------------------------------------------------------------------------------------------------------------------------
  • Pen Fight
Pen Fight is a popular game among the children. In this game two pens are put on a table and the players hit the opponent's pen with their own pen. We simulated this game using the Open Graphics Library (OpenGL) in C++. We implemented different sophisticated techniques of graphics like textures, lightings, shadows, shades, smooth camera, collision detection etc.


Computer Interfacing:
------------------------------------------------------------------------------------------------------------------------------
  • Voice Activated Remote Home Maintenance System
In this project we interfaced PC with mobile phone using blue tooth technology and detected voice commands using Microsoft Speech Tools. Then we interfaced TV, Fan and Light we PC parallel port to work according to that signal. This project was accepted in the 1st International Conference on Information Systems and Web-based Applications (ISWBAS), Nepal.

[more to be added]

Comments