Muhammad Alfariz Rasyid
Unknown Affiliation

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

Real-Time Driver Microsleep Detection Using Lightweight MobileViT and Haar Cascade Syahada Mawarda Hutagalung; Muhammad Alfariz Rasyid; Supiyandi; Aidil Halim Lubis
Jurnal Ilmiah Informatika dan Komputer Vol. 2 No. 2 (2025): Desember 2025
Publisher : CV.RIZANIA MEDIA PRATAMA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69533/j5k7v326

Abstract

Microsleep is a brief and involuntary loss of awareness that increases the risk of driving accidents. This study proposes a real-time microsleep detection system using Haar Cascade for eye localization and the lightweight MobileViT-XXS model for eye-state classification. The model was trained on a public dataset and achieved a training accuracy of 99.49%, a test accuracy of 98%, and a real-time accuracy of 90–94%. A microsleep event is detected when the eyes remain closed for ≥ 2 seconds. While the method performs well under controlled conditions, real-time testing revealed technical limitations such as sensitivity to lighting variation, non-frontal head pose, and motion, which affect detection stability and represent common robust-vision challenges. Despite these limitations, the system runs efficiently on CPU-only hardware and demonstrates strong potential as a lightweight early-warning system to support driving safety. Future research may explore expanding dataset diversity, improving environmental adaptation, and deploying the system on embedded or mobile platforms to enhance robustness and scalability.
Traffic Congestion Modeling and Simulation in Front of the University of North Sumatra (USU) Campus Using an Agent-Based Modeling Approach Muhammad Alfariz Rasyid; Hutagalung, Syahada Mawarda; Muhammad Fajar Dermawan
JITCoS : Journal of Information Technology and Computer System Vol. 1 No. 2 (2025): Volume 1 Number 2, December 2025
Publisher : CV. Multimedia Teknologi Kreatif

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65230/jitcos.v1i2.41

Abstract

Traffic congestion around the entrance of the University of North Sumatra (USU) campus represents a major issue influenced by several factors, including the presence of street vendors, illegal vehicle parking, public transport (angkot) that frequently stops without proper order, and the movement of both vehicles and pedestrians crossing the road. This research aims to construct and simulate the traffic situation in that area using an Agent-Based Modeling (ABM) approach, which was manually developed through the Python programming language. Each type of vehicle motorcycle, car, public transport, and pedicab is modeled as an individual agent that exhibits specific behaviors such as varying speed, stopping probability, and pause duration, based on observational data obtained from CCTV recordings of the Medan City Transportation Agency’s ATCS system. The simulation covers two main traffic directions, namely Jalan Setia Budi and Jalan Jamin Ginting, and evaluates several intervention scenarios such as adding designated bus stops, organizing street vendors, and managing pedestrian crossings. The outcomes demonstrate that applying a combination of these interventions increases the average vehicle speed by approximately 15-20% compared to the initial condition, implying that the proper management of roadside activities and environmental control significantly reduce traffic congestion. The ABM method proves capable of realistically illustrating traffic dynamics and can serve as a valuable analytical tool for evaluating transportation policies within campus zones and other urban areas.