Abstract :

Road Safety Remains A Critical Global Challenge, Particularly For Limited-mobility Road Users Such As Elderly Pedestrians, Individuals With Disabilities, Wheelchair Users, And People With Temporary Physical Impairments. These Groups Face Disproportionately Higher Risks Due To Slower Reaction Times, Restricted Movement, Reduced Situational Awareness, And Inadequate Infrastructure Support. With The Rapid Adoption Of Intelligent Transportation Systems And Machine Learning–based Safety Solutions, Predictive Models Have Shown Promise In Detecting Risks And Preventing Accidents. However, Most Existing Systems Operate As Black Boxes, Limiting Trust, Transparency, And Real-world Acceptance, Especially In Safety-critical Environments. This Research Proposes An Explainable Artificial Intelligence (XAI)–driven Framework Integrated With Support Vector Machine (SVM) Models To Enhance Road Safety For Limited Mobility Users. The Proposed Approach Focuses On Interpretable Decision-making That Allows Stakeholders; Including Traffic Authorities, Caregivers, And End Users, To Understand Why Certain Safety Alerts Or Risk Classifications Are Generated. By Combining SVM S Strong Classification Capabilities With XAI Techniques Such As Feature Attribution And Rule-based Explanations, The System Ensures High Accuracy While Maintaining Transparency. The Framework Processes Multimodal Data, Including Pedestrian Movement Patterns, Environmental Conditions, Traffic Density, And Assistive Device Signals, To Predict Hazardous Scenarios In Real Time. The Explain Ability Layer Improves Accountability, Supports Regulatory Compliance, And Increases User Trust By Clearly Communicating The Reasoning Behind Predictions. Experimental Evaluations Demonstrate That The XAI-enabled SVM Model Not Only Improves Predictive Reliability But Also Enhances Usability And Ethical Acceptance Compared To Conventional Black-box Approaches. This Research Highlights The Importance Of Explain Ability In AI-based Road Safety Systems And Presents A Scalable, Interpretable Solution Aimed At Protecting One Of The Most Vulnerable Populations In Modern Transportation Ecosystems.

Published:

01-5-2026

Issue:

Vol. 26 No. 5 (2026)

Page Nos:

36-42

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite