K
Khan Muhammad
Researcher at Sejong University
Publications - 234
Citations - 11822
Khan Muhammad is an academic researcher from Sejong University. The author has contributed to research in topics: Computer science & Convolutional neural network. The author has an hindex of 45, co-authored 186 publications receiving 6232 citations. Previous affiliations of Khan Muhammad include Islamia College University.
Papers
More filters
Journal ArticleDOI
Action Recognition in Video Sequences using Deep Bi-Directional LSTM With CNN Features
TL;DR: A novel action recognition method by processing the video data using convolutional neural network (CNN) and deep bidirectional LSTM (DB-LSTM) network that is capable of learning long term sequences and can process lengthy videos by analyzing features for a certain time interval.
Journal ArticleDOI
Multi-grade brain tumor classification using deep CNN with extensive data augmentation
TL;DR: A novel convolutional neural network (CNN) based multi-grade brain tumor classification system that is experimentally evaluated on both augmented and original data and results show its convincing performance compared to existing methods.
Journal ArticleDOI
Convolutional Neural Networks Based Fire Detection in Surveillance Videos
TL;DR: Experimental results on benchmark fire datasets reveal the effectiveness of the proposed framework and validate its suitability for fire detection in CCTV surveillance systems compared to state-of-the-art methods.
Journal ArticleDOI
Image based fruit category classification by 13-layer deep convolutional neural network and data augmentation
TL;DR: This study designed and validated a 13-layer convolutional neural network (CNN) that is effective in image-based fruit classification and observed using data augmentation can increase the overall accuracy.
Journal ArticleDOI
Efficient Deep CNN-Based Fire Detection and Localization in Video Surveillance Applications
TL;DR: This paper proposes an original, energy-friendly, and computationally efficient CNN architecture, inspired by the SqueezeNet architecture for fire detection, localization, and semantic understanding of the scene of the fire, which uses smaller convolutional kernels and contains no dense, fully connected layers.