Ahmad Al Shami
Affiliation confirmed via AI analysis of OpenAlex, ORCID, and web sources.
Associate Professor / Computer Science
Also affiliated: Suez Canal University (2019); Higher Colleges of Technology (2019–2020); University of Warwick (2015–2016); Nottingham Trent University (2011–2014)
Research Areas
Links
Biography and Research Information
OverviewAI-generated summary
Ahmad Al Shami's research focuses on the application of machine learning and computer vision techniques to address societal and medical challenges. His work includes developing systems for crowd detection and social distancing, such as the "CrowdTracing" system. Al Shami has also investigated the use of advanced imaging techniques and machine learning for medical image classification, including applications in detecting skin lesions and segmenting X-ray images.
His research extends to the predictive analysis of social media use among journalists and the modification of emergency alert systems using TinyML. Al Shami has co-authored publications with colleagues at Southern Arkansas University, including Christian Young and Malak Bachri. His scholarly output is reflected in an h-index of 5, with 18 total publications and 55 citations.
Metrics
- h-index: 5
- Publications: 19
- Citations: 55
Positions
-
Associate Professor / Computer Science 2021–presentSouthern Arkansas University Computer Science ORCID
-
Assistant Professor 2016–2021Higher Colleges of Technology Computer and Information Science ORCID
Selected Publications
-
YO-SAM: YOLO-Guided Segment Anything Model (2026)
-
PH-SAM2: Persistent Homology-Guided Prompting of SAM2 for Zero-Shot Medical Image Segmentation (2026)
-
Persistent Homology and Segment Anything Model for Automated Zero-Shot Localized Medical X-ray Images Segmentation (PH-SAM) (2025)
-
Predicting the level of social media use among journalists: machine learning analysis (2024)
-
Modified AMBER Alerts System Using TinyML Processing (2023)
-
Vision Transformers for Medical Images Classifications (2022)
-
CrowdTracing: Overcrowding Clustering and Detection System for Social Distancing (2021)
-
CrowdTracing: Overcrowding Clustering and Detection System for Social Distancing (2021)
-
CrowdTracing: Overcrowding Clustering and Detection System for Social Distancing (2021)
Collaboration Network
Top Collaborators
- CrowdTracing: Overcrowding Clustering and Detection System for Social Distancing
- CrowdTracing: Overcrowding Clustering and Detection System for Social Distancing
- CrowdTracing: Overcrowding Clustering and Detection System for Social Distancing
- CrowdTracing: Overcrowding Clustering and Detection System for Social Distancing
- CrowdTracing: Overcrowding Clustering and Detection System for Social Distancing
- CrowdTracing: Overcrowding Clustering and Detection System for Social Distancing
- Persistent Homology and Segment Anything Model for Automated Zero-Shot Localized Medical X-ray Images Segmentation (PH-SAM)
- PH-SAM2: Persistent Homology-Guided Prompting of SAM2 for Zero-Shot Medical Image Segmentation
- YO-SAM: YOLO-Guided Segment Anything Model
- CrowdTracing: Overcrowding Clustering and Detection System for Social Distancing
- CrowdTracing: Overcrowding Clustering and Detection System for Social Distancing
- CrowdTracing: Overcrowding Clustering and Detection System for Social Distancing
- CrowdTracing: Overcrowding Clustering and Detection System for Social Distancing
- PH-SAM2: Persistent Homology-Guided Prompting of SAM2 for Zero-Shot Medical Image Segmentation
- YO-SAM: YOLO-Guided Segment Anything Model
- CrowdTracing: Overcrowding Clustering and Detection System for Social Distancing
- CrowdTracing: Overcrowding Clustering and Detection System for Social Distancing
- Vision Transformers for Medical Images Classifications
- Vision Transformers for Medical Images Classifications
- Predicting the level of social media use among journalists: machine learning analysis
- Predicting the level of social media use among journalists: machine learning analysis
- Predicting the level of social media use among journalists: machine learning analysis
- Predicting the level of social media use among journalists: machine learning analysis
- Persistent Homology and Segment Anything Model for Automated Zero-Shot Localized Medical X-ray Images Segmentation (PH-SAM)
Similar Researchers
Based on overlapping research topics