M
Mudassar Raza
Researcher at COMSATS Institute of Information Technology
Publications - 115
Citations - 2879
Mudassar Raza is an academic researcher from COMSATS Institute of Information Technology. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 23, co-authored 102 publications receiving 1722 citations. Previous affiliations of Mudassar Raza include University of Science and Technology of China.
Papers
More filters
Journal ArticleDOI
Brain tumor detection using statistical and machine learning method.
TL;DR: The presented approach outperformed as compared to existing approaches in segmentation and specificity, sensitivity, accuracy, area under the curve (AUC) and dice similarity coefficient (DSC) at the fused feature based level.
Journal ArticleDOI
An integrated design of particle swarm optimization (PSO) with fusion of features for detection of brain tumor
TL;DR: Initially the skull is removed through brain surface extraction (BSE) method and the skull removed image is then fed to particle swarm optimization (PSO) to achieve better segmentation and artificial neural network and other classifiers are utilized to classify the tumor grades.
Journal ArticleDOI
Detection of Brain Tumor based on Features Fusion and Machine Learning
TL;DR: An unsupervised clustering approach for tumor segmentation is proposed and a fused feature vector is used which is a mixture of Gabor wavelet features (GWF), histograms of oriented gradient (HOG), local binary pattern (LBP) and segmentation based fractal texture analysis (SFTA) features.
A Survey of Password Attacks and Comparative Analysis on Methods for Secure Authentication
TL;DR: This paper describes password attacks and comparative analysis of different authentication methods for awareness of attacks and selection of authentication method in a particular scenario.
Journal ArticleDOI
Hand-crafted and deep convolutional neural network features fusion and selection strategy: An application to intelligent human action recognition
Muhammad Attique Khan,Muhammad Attique Khan,Muhammad Sharif,Tallha Akram,Mudassar Raza,Tanzila Saba,Amjad Rehman +6 more
TL;DR: A novel HAR system which is based on the fusion of conventional hand-crafted features using histogram of oriented gradients (HoG) and deep features and an entropy-based feature selection technique to cope with the curse of dimensionality is proposed.