A
Abdullah S. Alharthi
Researcher at University of Manchester
Publications - 13
Citations - 159
Abdullah S. Alharthi is an academic researcher from University of Manchester. The author has contributed to research in topics: Gait (human) & Artificial neural network. The author has an hindex of 4, co-authored 11 publications receiving 74 citations. Previous affiliations of Abdullah S. Alharthi include St. Mary's University.
Papers
More filters
Journal ArticleDOI
Deep Learning for Monitoring of Human Gait: A Review
TL;DR: By most of the essential metrics, deep learning convolutional neural networks typically outperform shallow learning models and are attributed to the possibility to extract the gait features automatically in deep learning as opposed to the shallow learning from the handcrafted gait Features.
Journal ArticleDOI
Gait Spatiotemporal Signal Analysis for Parkinson’s Disease Detection and Severity Rating
TL;DR: The proposed models are resilient to noise and are computationally efficient for processing and classification of large longitudinal GRF signal datasets, therefore they can be useful for detecting deterioration in the postural balance and rating PD severity.
Proceedings ArticleDOI
Deep Learning for Ground Reaction Force Data Analysis: Application to Wide-Area Floor Sensing
TL;DR: Deep learning considerably achieved better classification results, compared to the shallow learning methods with the handcrafted features, which implies that for the purpose of automatic decision-making, it is beneficial to utilize deep learning methods to analyse GRF.
Book ChapterDOI
Deep learning in gait analysis for security and healthcare
Omar Costilla-Reyes,Ruben Vera-Rodriguez,Abdullah S. Alharthi,Syed U. Yunas,Krikor B. Ozanyan +4 more
TL;DR: Key conceptual and algorithmic facets of deep learning applied to gait analysis in two important contexts: security and healthcare are reviewed.
Proceedings ArticleDOI
Multi-modality fusion of floor and ambulatory sensors for gait classification
TL;DR: In a case study of gait classification from floor and ambulatory sensors, results with data from each modality are compared, showing non-linear classifiers are most efficient for fused features.