Article Per Year (5 Year)
p-Index From 2020 - 2025
0.408
P-Index
This Author published in this journals
All Journal International Journal of Artificial Intelligence Research Knowledge Engineering and Data Science
Manga’, Abdul Rachman
Unknown Affiliation
Computer Science & IT Electrical & Electronics Engineering Engineering

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

Found 2 Documents
Search

 1 
Optimal Strategy for Handling Unbalanced Medical Datasets: Performance Evaluation of K-NN Algorithm Using Sampling Techniques Salim, Yulita; Utami, Aulia Putri; Manga’, Abdul Rachman; Aziz, Huzain; Admojo, Fadhila Tangguh
Knowledge Engineering and Data Science Vol 7, No 2 (2024)
Publisher : Universitas Negeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17977/um018v7i22024p176-186

Abstract

This study addresses the critical role of medical image classification in enhancing healthcare effectiveness and tackling the challenges of imbalanced medical datasets. It focuses on optimizing classification performance by integrating Canny edge detection for segmentation and Hu-moment feature extraction and applying oversampling and undersampling techniques. Five diverse medical datasets were utilized, covering Alzheimer’s and Parkinson’s diseases, COVID-19, brain tumours, and lung cancer. The K-Nearest Neighbors (K-NN) algorithm was implemented to enhance classification accuracy, aiming to develop a more robust framework for medical image analysis. The evaluation, conducted using cross-validation, demonstrated notable improvements in key metrics. Specifically, oversampling significantly enhanced lung cancer detection accuracy, while undersampling contributed to balanced performance gains in the COVID-19 class. Metrics, including accuracy, precision, recall, and F1-score, provided insights into the model’s effectiveness. These findings highlight the positive impact of data balancing techniques on K-NN performance in imbalanced medical image classification. Continued research is essential to refine these techniques and improve medical diagnostics.
Evaluation of VGG16 Performance in Multi-Input and Multi-Class Classification of Toraja Buffalo Breeds Manga’, Abdul Rachman; Nanda, As'syahrin; Salim, Yulita
International Journal of Artificial Intelligence Research Vol 8, No 1.1 (2024)
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v8i1.1.1203

Abstract

Traditional image classification research has focused on single-input and multiclass approaches. However, these approaches often fail to capture the complexity and diversity of real-world image data. To address the complexity and more diverse variation in data, as well as to improve the classification accuracy of various categories, a multi-input image approach is utilized. With a multi-input multi-class approach, a Transfer Learning model based on VGG16 is trained to identify objects from various perspectives and classify them into one of many predefined classes. The VGG16 architecture in the multi-input and multi-class classification of Toraja Buffalo breeds demonstrates excellent results with an average accuracy of 93.33%. The "Kerbau Lotong Boko" and "Kerbau Bonga Ulu" classes achieved 100% accuracy, while other classes showed high precision, recall, and F1 scores. Despite fluctuations in accuracy and loss during training, the model successfully achieved good convergence and generalization. This research is significant in the field of image classification by introducing a multi-input method capable of capturing richer and more diverse information from complex objects such as Toraja buffalo. It demonstrates that CNN architectures like VGG16 can be adapted to handle more complex classification tasks using a multi-input approach.
Co-Authors Admojo, Fadhila Tangguh Aziz, Huzain Nanda, As'syahrin Salim, Yulita Utami, Aulia Putri