A
Akm Ashiquzzaman
Researcher at Chonnam National University
Publications - 23
Citations - 412
Akm Ashiquzzaman is an academic researcher from Chonnam National University. The author has contributed to research in topics: Deep learning & Convolutional neural network. The author has an hindex of 7, co-authored 22 publications receiving 280 citations. Previous affiliations of Akm Ashiquzzaman include University of Asia and the Pacific & University of Dhaka.
Papers
More filters
Posted Content
Handwritten Arabic Numeral Recognition using Deep Learning Neural Networks
TL;DR: A novel algorithm based on deep learning neural networks using appropriate activation function and regularization layer is proposed, which shows significantly improved accuracy compared to the existing Arabic numeral recognition methods.
Proceedings ArticleDOI
Handwritten Arabic numeral recognition using deep learning neural networks
TL;DR: In this article, the authors proposed a novel algorithm based on deep learning neural networks using appropriate activation function and regularization layer, which shows significantly improved accuracy compared to the existing Arabic numeral recognition methods.
Book ChapterDOI
Reduction of Overfitting in Diabetes Prediction Using Deep Learning Neural Network
Akm Ashiquzzaman,Abdul Kawsar Tushar,Md. Rashedul Islam,Dongkoo Shon,Kichang Im,Jeong-Ho Park,Dong-Sun Lim,Jong-Myon Kim +7 more
TL;DR: A reliable prediction system for the disease of diabetes is presented using a dropout method to address the overfitting issue and the proposed neural network outperforms other state-of-art methods in better prediction scores for the Pima Indians Diabetes Data Set.
Book ChapterDOI
A Novel Transfer Learning Approach upon Hindi, Arabic, and Bangla Numerals Using Convolutional Neural Networks
TL;DR: This model is presented for the recognition of handwritten numerals in Indic languages using convolutional neural networks with backpropagation for error reduction and dropout for data overfitting and closely matched other state-of-the-art methods using only a fraction of time used by the state of thearts.
Proceedings ArticleDOI
An efficient method for improving classification accuracy of handwritten Bangla compound characters using DCNN with dropout and ELU
TL;DR: This work proposes a novel method of recognition of compound characters in Bangla language using deep convolutional neural networks (DCNN) and efficient greedy layer-wise training approach and introduction of dropout technology mitigates data overfitting and Exponential Linear Unit (ELU) is introduced to tackle the vanishing gradient problem during training.