M
M. A. H. Akhand
Researcher at Khulna University of Engineering & Technology
Publications - 83
Citations - 738
M. A. H. Akhand is an academic researcher from Khulna University of Engineering & Technology. The author has contributed to research in topics: Artificial neural network & Computer science. The author has an hindex of 10, co-authored 68 publications receiving 388 citations. Previous affiliations of M. A. H. Akhand include University of Fukui.
Papers
More filters
Journal ArticleDOI
Discrete Spider Monkey Optimization for Travelling Salesman Problem
TL;DR: An effective variant of SMO to solve TSP called discrete SMO (DSMO), where every spider monkey represents a TSP solution where Swap Sequence and Swap Operator based operations are employed, which enables interaction among monkeys in obtaining the optimal T SP solution.
Journal ArticleDOI
Facial Emotion Recognition Using Transfer Learning in the Deep CNN
TL;DR: A novel pipeline strategy is introduced, where the training of the dense layer(s) is followed by tuning each of the pre-trained DCNN blocks successively that has led to gradual improvement of the accuracy of FER to a higher level.
Journal ArticleDOI
Optimization of University Course Scheduling Problem using Particle Swarm Optimization with Selective Search
TL;DR: A novel PSO-based method is investigated for solving highly constrained UCSP in which basic PSO operations are transformed to tackle combinatorial optimization task of UCSP and a few new operations are introduced to PSO to solve UCSP efficiently.
Proceedings ArticleDOI
Genetic algorithm based fuzzy decision support system for the diagnosis of heart disease
TL;DR: The experiments carried out with real-life data set show the effectiveness of the proposed genetic algorithm based fuzzy decision support system for predicting the risk level of heart disease.
Proceedings ArticleDOI
Convolutional neural network training with artificial pattern for Bangla handwritten numeral recognition
TL;DR: A CNN based method has been investigated for Bangla handwritten numeral recognition and is shown to outperform other existing methods while tested on a popular Bangla benchmark handwritten dataset.