Md. Mijanur Rahman

Md. Mijanur Rahman, Shamim Ripon

Proper management of requirements is crucial to successful development software within limited time and cost. Nonfunctional requirements (NFR) are one of the key criteria to derive a comparison among various software systems. In most of software development NFR have be specified as an additional requirement of software. NFRs such as performance, reliability, maintainability, security, accuracy etc. have to be considered at the early stage of software development as functional requirement (FR). However, identifying NFR is not an easy task. Although there are well developed techniques for eliciting functional requirement, there is a lack of elicitation mechanism for NFR and there is no proper consensus regarding NFR elicitation techniques. Eliciting NFRs are considered to be one of the challenging jobs in requirement analysis. This paper proposes a UML use case based questionary approach to identifying and classifying NFR of a system. The proposed approach is illustrated by using a Point of Sale (POS) case study

Md. Ali Hossain, Md. Mijanur Rahman, Uzzal Kumar Prodhan et al.

This paper is concerned with the development of Back-propagation Neural Network for Bangla Speech Recognition. In this paper, ten bangla digits were recorded from ten speakers and have been recognized. The features of these speech digits were extracted by the method of Mel Frequency Cepstral Coefficient (MFCC) analysis. The mfcc features of five speakers were used to train the network with Back propagation algorithm. The mfcc features of ten bangla digit speeches, from 0 to 9, of another five speakers were used to test the system. All the methods and algorithms used in this research were implemented using the features of Turbo C and C++ languages. From our investigation it is seen that the developed system can successfully encode and analyze the mfcc features of the speech signal to recognition. The developed system achieved recognition rate about 96.332% for known speakers (i.e., speaker dependent) and 92% for unknown speakers (i.e., speaker independent).