Article Per Year (5 Year)
p-Index From 2020 - 2025
0.408
P-Index
This Author published in this journals
All Journal JOIV : International Journal on Informatics Visualization
Tareq, Mustafa
Unknown Affiliation
Computer Science & IT

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

Found 2 Documents
Search

 1 
An Enhanced Routing Protocol For Vehicular Ad Hoc Networks With Swarm Intelligent Tareq, Mustafa; Farhan, Yasir Hadi; Nafea, Mohammed Mansoor
JOIV : International Journal on Informatics Visualization Vol 9, No 3 (2025)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.9.3.3298

Abstract

A Vehicular Ad Hoc Network (VANET) is a transient network of wireless mobile nodes operating without centralized administration or pre-existing infrastructure. VANETs are a subset of Mobile Ad Hoc Networks (MANETs) designed to facilitate vehicular communication. This allows vehicles to communicate directly with roadside devices or with each other. These networks are appropriate for applications like infotainment services, traffic control, and accident avoidance since they are dynamic, decentralized, and highly flexible. However, their lack of established infrastructure presents serious difficulties, especially when preserving dependable routing and energy efficiency. Path selection in VANETs usually attempts to limit the number of intermediary nodes required to reach a destination to reduce latency and possible points of failure. However, as the distance between nodes increases, so does the required transmission power, directly impacting the network's energy consumption. As a result, energy-efficient routing is crucial to maintain network longevity and performance. This paper introduces the Bee Destination Sequenced Distance Vector Routing (B-DSDV) protocol, utilizing swarm intelligence principles via the Artificial Bee Colony (ABC) algorithm to enhance energy efficiency within a DSDV framework. This integration incorporates the Bee Algorithm into the discovery mechanism of DSDV to identify the most accessible node and the shortest route based on node distances. The algorithm assesses both the power levels of nodes and their distances to others. Route selection is optimized by considering the power consumption of intermediate nodes between the source and destination. Performance evaluation of the B-DSDV protocol is compared with established protocols, demonstrating its effectiveness in selecting high-power optimal paths and improving overall performance. The simulation results were conducted based on average throughput, average energy consumption, average end-to-end delay, and packet delivery ratio performance metrics. We conducted a simulation study using Network Simulator (NS) version 2.35 to evaluate the performance metrics of the routing protocols. Regarding energy consumption, the B-DSDV protocol achieved superior results, approximately 0.10% concerning packet size, compared to other protocols.
Sample An Improved Lite-Yolov4 Object Detection Model for Mobile Augmented Reality Mansoor Nafea, Mohammed; Siok Yeeb, Tan; Tareq, Mustafa; Ahmed Jubair, Mohammed; Fatikhan Ataalla, Abdalrahman
JOIV : International Journal on Informatics Visualization Vol 9, No 6 (2025)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.9.6.3341

Abstract

Augmented reality (AR) enhances user experiences by overlaying digital information on real-world objects or places. Augmented reality makes unprecedentedly immersive experiences possible in marketing, industry, education, entertainment, fashion, and healthcare. While current augmented reality methods can identify 3D items in their environment, the recognition of tiny, complex objects remains a problem for most object detection methods. In addition, object detection is a key in computer vision and AR systems. The Object detection process aims to classify and localize objects in applications like face detection, text detection, and people counting. Many natural features detection models were proposed, like YOLO, YOLO-LITE, and YOLOv4-tiny. However, the detection of objects from natural images remains a challenging task, often compromising accuracy or requiring longer processing times. To overcome these challenges, this article suggests a novel method that combines the strengths of YOLO-LITE and YOLOv4-tiny into a hybrid model. The suggested model name is LITE-YOLOv4, which stands for “LITE-You Only Look Once Version 4. The model design depends on YOLO-LITE as a backbone. LITE-YOLOv4 uses a feature pyramid network to extract feature maps of various sizes. It also utilizes a "shallow and narrow" convolution layer to optimize its object detection capability. The proposed model aims to achieve a speed and accuracy balance, making it suitable for use in AR apps on portable devices and PCs without GPUs. LITE-YOLOv4 achieved a mean average precision (mAP) of 52.6% on the PASCAL VOC dataset and 33.3% on the COCO dataset. The suggested model achieved a respectable speed, which is 20 frames per second (FPS). LITE-YOLOv4 provides better accuracy and reasonable computational time than state-of-the-art non-GPU models.
Co-Authors Ahmed Jubair, Mohammed Farhan, Yasir Hadi Fatikhan Ataalla, Abdalrahman Mansoor Nafea, Mohammed Nafea, Mohammed Mansoor Siok Yeeb, Tan