Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) Bulletin of Electrical Engineering and Informatics
Rosniza Roslan
Universiti Teknologi MARA
Computer Science & IT Electrical & Electronics Engineering Engineering

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

Found 2 Documents
Search

 1 
Automated segmentation and detection of T1-weighted magnetic resonance imaging brain images of glioma brain tumor Nur Hanina Izani Muhammad Zaihani; Rosniza Roslan; Zaidah Ibrahim; Khyrina Airin Fariza Abu Samah
Bulletin of Electrical Engineering and Informatics Vol 9, No 3: June 2020
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (527.118 KB) | DOI: 10.11591/eei.v9i3.2079

Abstract

There are numerous studies on brain imaging applications.  The statistics in Malaysia showed that glioma is one of the most common type disease in brain tumor.  Glioma brain tumor is an abnormal growth of glial cells inside the brain tissues which known as cerebral tissues.  Radiologist commonly used Magnetic Resonance Imaging (MRI) image sequences to diagnose the brain tumor.  However, manual examination of the brain tumor diagnosis by radiologist is difficult and time-consuming task as tumors are occurred in variability of shape and appearance.  They will also inject a gadolinium contrast agent to enhance the image modality which will give the side effects to the patients.  Therefore, this paper presents an automated segmentation and detection of MRI brain images using Sobel edge detection and mathematical morphology operations.  The total of 30 glioma T1-Weighted MRI brain images are obtained from Brain Tumor Image Segmentation Benchmark (BRATS).  The results of segmentation and detection are quantitatively evaluated by using Area Overlap which produced the accuracy rate of 80.2% and shows that the presented methods are promising.
Multi-stage hybrid YOLO-driven and MobileNetV2-CNN variants for robust fish freshness classification Raseeda Hamzah; Rosniza Roslan; Amni Munira Khidir; Lala Septem Riza
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 15, No 4: August 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v15.i4.pp3660-3671

Abstract

This study presents a multi-stage hybrid representation learning framework for robust fish freshness classification to address the critical challenge of reliable quality assessment in unpreserved food supply chains. The proposed pipeline operates in two stages: stage-1 employs you only look once (YOLO)v8n as feature-gated detector to validate inputs and eliminate non-fish images, while stage-2 leverages transfer-learned MobileNetV2 variants enhanced with convolutional neural network (CNN) layers, fine-tuning, adaptive learning rate schedulers, and expanded fully connected layers for hierarchical classification into three freshness classes i.e., highly fresh, fresh, and not fresh. The framework has been trained and evaluated on two curated datasets comprising 4,500 fish and non-fish images and 11,111 freshness-labeled including augmented dataset to increase diversity. The experimental results showed significant improvements. The best performance model transfer learning (TL)-MobileNetV2 + CNN + fine-tuning achieved 98.07% training accuracy and 67.72% validation accuracy on 80:20 split, and training accuracy of 97.57%, validation accuracy of 97.21% through 10-fold cross-validation. The comparative benchmarking confirmed that dual-stage design outperformed baseline MobileNetV2 and YOLOv5s models across precision, recall, and F1-score. The findings highlighted significant value of integrating detection-driven validation with transfer-learning classification, and propose new benchmark for intelligent freshness monitoring. For future work, this study aims to explore attention-based models, data integration, and species diversity.
Co-Authors Amni Munira Khidir Khyrina Airin Fariza Abu Samah Lala Septem Riza Nur Hanina Izani Muhammad Zaihani Raseeda Hamzah Zaidah Ibrahim