NewsProjects

Smart Transportation Systems for Comprehensive Mobility of Persons with Disabilities in NEOM-like Smart Cities Across Saudi Arabia — KSA Vision 2030

Elhosseini

September 4, 2026

2 Min Read

135 Views

0 Comments

This funded research project investigates intelligent transportation systems designed to improve mobility, accessibility, safety, and independence for persons with disabilities in future smart-city environments. The project integrates artificial intelligence, machine learning, deep learning, computer vision, reinforcement learning, acoustic intelligence, traffic optimization, and accessibility-aware routing to develop more inclusive urban transportation solutions aligned with KSA Vision 2030.

Project at a Glance

Publications & Research Outputs

1. Sound-Based Vehicle Diagnostics & Emergency Recognition

Toward Inclusive Smart Cities: Sound-Based Vehicle Diagnostics, Emergency Signal Recognition, and Beyond

Machines, 2025, 13, 258
DOI: 10.3390/machines13040258

The work develops sound-based vehicle-fault and emergency-signal recognition for inclusive ITS environments, including new acoustic datasets and machine-learning models.

2. Adaptive Traffic-Light Management

Adaptive Traffic Light Management for Mobility and Accessibility in Smart Cities

Sustainability, 2025, 17, 6462
DOI: 10.3390/su17146462

The paper proposes the H-ATLM system using DDPG reinforcement learning for dynamic traffic control, reporting congestion reductions of up to 50%, throughput improvements of up to 149%, and clearance-time reductions of up to 84%.

3. Mobility-Aid Detection & Accessibility-Aware Routing

A Hybrid YOLOv10—Faster R-CNN Framework for Mobility-Aid Detection and Traffic Optimization in Disability-Inclusive Smart Cities

Alexandria Engineering Journal, 2025, 129, 1279–1298
DOI: 10.1016/j.aej.2025.08.044

This work integrates YOLOv10 and Faster R-CNN for wheelchair/crutch detection with traffic-severity prediction and accessibility-aware route optimization. It reports 99.4% mAP for general mobility aids, 100% recall, and a 17.3% reduction in disabled-user travel time under peak congestion.

Most importantly for your project page, its contribution statement explicitly credits:

4. Explainable Audio-Based ITS

From Sensors to Insights: Interpretable Audio-Based Machine Learning for Real-Time Vehicle Fault and Emergency Sound Classification

Machines, 2025, 13, 888
DOI: 10.3390/machines13100888

The study develops an interpretable acoustic-ML framework using MFCCs, Mel spectrograms, Chroma features, SHAP, Boruta, ANOVA, and ensemble learning for vehicle faults and emergency sounds.