Research and Projects

Research Projects:

Abstract:  Multi-label classification (MLC) is a machine learning approach where each instance may belong to more than one class at the same time. Due to overlapping classes and label-label correlation, solving MLC is very challenging. Further, class imbalance and computational time complexity are also considered significant issues. In this dissertation, we have proposed two novel multi-label classifiers to address the issues mentioned earlier, termed as Label-Cardinality based Divide-and-conquer strategy for Multi-label classification (LCDC-MLC) and Median based Divide-and-conquer strategy for Multi-label Classification (MDC-MLC). LCDC-MLC takes label-cardinality into account for recovering data imbalance and employs the divide-and-conquer approach for resolving the time-complexity issue. MDC-MLC considers median value-based label-cardinality to solve the hierarchical-structure imbalance problem and applies the divide-and-conquer technique to determine the aforementioned issues. The experimental results on several benchmark data sets show that our proposed classifier, LCDC-MLC, is competitive with other state-of-the-art Multi-label classification approaches.

Keywords: Multi-label classification, Multi-label learning, Label Cardinality, Divide-and-conquer algorithm.

Supervised by:  Dr. Reshma Rastogi (Associate Professor at SAU) and Ment0r: Mr. Sanjay Kumar (Senior PhD Scholar at SAU)

Abstract: Sign Language is the mode of communication among the deaf and dumb. However, integrating them into the main stream is very difficult as the majority of the society is unaware of their language. So, to bridge the communication gap between the hearing and speech impaired and the rest in Bangladesh, we conducted a research find out a way for better communication between deaf-mute people and ordinary people. There are many existing methods related to Sign Language Recognition in order to achieve this goal. To achieve our goal, we used Convolutional Neural Network (CNN). This research work aim is to apply the concept of Convolutional Neural Network (CNN) for developing a model which can be able to recognize the Bengali Sign Language. Hope in the future, this model can be helping as an interpreter. [Presentation Link]

Supervised by:  Shahed Khan (Former Lecturer at BAIUST) 

Previous Academic Projects: