Article Per Year (5 Year)
p-Index From 2020 - 2025
0.408
P-Index
This Author published in this journals
All Journal Jurnal Ilmiah Teknik Elektro Komputer dan Informatika (JITEKI) International Journal of Robotics and Control Systems
Ahmed, Waleed Ali
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering

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

Found 2 Documents
Search

 1 
Accelerating Convergence in Data Offloading Solutions: A Greedy-Assisted Genetic Algorithm Approach Zulfa, Mulki Indana; Chrismawan, Stephen Prasetya; Hartoyo, Adhwa Moyafi; Nursakti, Wafdan Musa; Ahmed, Waleed Ali
International Journal of Robotics and Control Systems Vol 4, No 4 (2024)
Publisher : Association for Scientific Computing Electronics and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/ijrcs.v4i4.1652

Abstract

Data offloading, a technique that distributes data across the network, is crucial for alleviating congestion and enhancing system performance. One challenge in this process is optimizing web caching, which can be modeled as a dynamic knapsack problem in edge networks. This study introduces a Greedy-Assisted Genetic Algorithm (GA-Greedy) to tackle this challenge, accelerating convergence and improving solution quality. The greedy heuristic is integrated into the GA at two stages: during initialization to create a superior starting population, and at the end of each iteration to refine solutions generated through genetic operations. The GA-Greedy’s effectiveness was evaluated using the IRcache dataset, focusing on hit ratio—an indicator of successful cache accesses that reduces network load and speeds up data retrieval. Results show that GA-Greedy outperforms traditional GA and standalone greedy algorithms, especially with smaller cache sizes. For instance, with a 3K cache size, the half-greedy GA achieved a hit ratio of 0.55, compared to 0.2 for the pure GA and 0.1 for the greedy algorithm. Similarly, the full-greedy GA reached a hit ratio of 0.45. By enhancing convergence and guiding the search, GA-Greedy enables more efficient data distribution in edge networks, reducing latency and improving user experience.
Addressing Overfitting in Dermatological Image Analysis with Bayesian Convolutional Neural Network Zulfa, Mulki Indana; Aryanto, Andreas Sahir; Wijonarko, Bintang Abelian; Ahmed, Waleed Ali
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 10 No. 2 (2024): June
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v10i2.29177

Abstract

VGG, ResNet, and DenseNet are popular convolutional neural network (CNN) designs for transfer learning (TL), aiding dermatological image processing, particularly in skin cancer categorization. These TL-CNN models build extensive neural network layers for effective image classification. However, their numerous layers can cause overfitting and demand substantial computational resources. The Bayesian CNN (BCNN) technique addresses TL-CNN overfitting by introducing uncertainty in model weights and predictions. Research contributions are (i) comparing BCNN with three TL-CNN architectures in dermatological image processing and (ii) examining BCNN ability to mitigate overfitting through weight perturbation and uncertainty during training. BCNN uses flipout layers to perturb weights during training, guided by the KL divergence and Binary Cross Entropy (BCE) loss function. The dataset used is the ISIC Challenge 2017, categorized as malignant and benign skin tumors. The simulation results show that three TL-CNN architectures, namely VGG-19, ResNet-101, and DenseNet-201, obtained training accuracies of 96.65%, 100%, and 97.70%, respectively. However, all three were only able to achieve a maximum validation accuracy of around 78%. In contrast, BCNN can produce training and validation accuracy of 81.30% and 80%, respectively. The difference in training and validation accuracy values produced by BCNN is only 1.3%. Meanwhile, the three TL-CNN architectures are trapped in an overfitting condition with a difference in training and validation values of around 20%. Therefore, BCNN is more reliable for dermatological image processing, especially for skin cancer images.
Co-Authors Aryanto, Andreas Sahir Chrismawan, Stephen Prasetya Hartoyo, Adhwa Moyafi Mulki Indana Zulfa, Mulki Indana Nursakti, Wafdan Musa Wijonarko, Bintang Abelian