Article Published in Referred Journals

Permanent URI for this collectionhttps://hdl.handle.net/10361/6617

Browse

Recent Submissions

Now showing 1 - 3 of 3
  • Thumbnail Image
    listelement.badge.dso-type Item ,
    Nano satellite: a new journey towards space science for Bangladesh
    (© 2016 Istanbul Technical University, 2016) Md. Khalilur, Rhaman; Shakil, Shifur Rahman; Tarannum, Narzu; Department of Computer Science and Engineering, BRAC University
  • Thumbnail Image
    listelement.badge.dso-type Item ,
    Eagle i-Bot: an eye-controlled system
    (© International Organization Of Scientific Research (IOSR), 2012-12) Md Khalilur, Rhaman; Meem, Mohona Gazi; Afrin, Onindita; Hassan, Md. Mahabub; Bhuiyan, Farazul Haque; Department of Computer Science and Engineering, BRAC University
    Hundreds of millions of people in the world are hand impaired in some way, and for many, there is no absolute solution. Operation of computers by physically disabled people; especially with hand impairment was quite impossible till now because use of hands plays a vital role in the use of mouse, touch pad and keyboard. We proposed a new system named as “Eagle i-Bot - An eye-controlled system” which has come with a feasible solution for this scenario. With this system, computers and robots can be controlled by the pair of eyes’ movement or iris movement and voice commands control all the mouse events. This system works with image processing system based on Voila-Jones algorithm and modified Ada-boost algorithms along with java robot class and sphinx-4 frameworks. In this paper, this system is described including software and hardware aspects, algorithms that are used and scopes where Eagle i-Bot can be used.
  • Thumbnail Image
    listelement.badge.dso-type Item ,
    Recurrent neural network classifier for three layer conceptual network and performance evaluation
    (© 2010 ACADEMY PUBLISHER, 2010-01) Md. Khalilur, Rhaman; Endo, Tsutomu; Department of Computer Science and Engineering
    Natural language has traditionally been handled using symbolic computation and recursive processes. Classification of natural language by using neural network is a hard problem. Past few years several recurrent neural network (RNN) architectures have emerged which have been used for several smaller natural language problems. In this paper, we adopt Elman RNN classifier for disease classification for a doctor patient-dialog system. We find that the Elman RNN is able to find a representation for natural language. Contextual analysis in dialog is also a major problem. A three layers memory structure was adopted to address the challenge which we referred to as ”Three Layer Conceptual Network” (TLCN). This highly efficient network simulates the human brain by discourse information. An extended case structure framework is used to represent the knowledge. We used the same case frame structure to train and examine the RNN classifier. This system prototype is based on doctor-patients dialogs. The over all system performance achieved 84% accuracy. Disease identification accuracy depends on number of disease and number of utterances. The performance evaluation is also discussed in this paper.