U
Usman Qamar
Researcher at College of Electrical and Mechanical Engineering
Publications - 176
Citations - 2629
Usman Qamar is an academic researcher from College of Electrical and Mechanical Engineering. The author has contributed to research in topics: Feature selection & Rough set. The author has an hindex of 23, co-authored 161 publications receiving 1864 citations. Previous affiliations of Usman Qamar include University of the Sciences & National University of Science and Technology.
Papers
More filters
Journal ArticleDOI
TOM: Twitter opinion mining framework using hybrid classification scheme
TL;DR: This research paper presents an algorithm for twitter feeds classification based on a hybrid approach and shows that the proposed technique overcomes the previous limitations and achieves higher accuracy when compared to similar techniques.
Journal ArticleDOI
Using Blockchain for Electronic Health Records
TL;DR: The aim of this proposed framework is firstly to implement blockchain technology for EHR and secondly to provide secure storage of electronic records by defining granular access rules for the users of the proposed framework.
Journal ArticleDOI
IntelliHealth: A medical decision support application using a novel weighted multi-layer classifier ensemble framework
TL;DR: An ensemble framework with multi-layer classification using enhanced bagging and optimized weighting is presented and it is shown that ensemble framework achieved the highest accuracy, accuracy and F-Measure when compared with individual classifiers for all the diseases.
Journal ArticleDOI
Texture Classification Using Rotation- and Scale-Invariant Gabor Texture Features
TL;DR: Experimental results demonstrate the superiority of the proposed descriptor as compared to other methods considered in this letter, and suggest a novel approach to rotation and scale invariant texture classification.
Journal ArticleDOI
A semi-supervised approach to sentiment analysis using revised sentiment strength based on SentiWordNet
TL;DR: This research proposes a semi-supervised sentiment analysis approach that incorporates lexicon-based methodology with machine learning in order to improve sentiment analysis performance.