Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal SMARTICS Journal Journal of Electrical Engineering and Computer (JEECOM)
Fakhrunnia, Brahma Ratih Rahayu
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Energy

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

Found 2 Documents
Search

 1 
Pemanfaatan Metode Multiclass Support Vector Machine dalam Klasifikasi Penyakit Daun Kacang Tanah Fakhrunnia, Brahma Ratih Rahayu; Aziz, As'ad Shidqy; Sesoca, Jendra
SMARTICS Journal Vol 9 No 2 (2023): SMARTICS Journal (Oktober 2023)
Publisher : Universitas PGRI Kanjuruhan Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21067/smartics.v9i2.9077

Abstract

Peanuts are one type of agricultural crop from commodity crops that can provide additional income opportunities for farmers in Indonesia. In addition, the benefits of peanuts are as a source of protein and vegetable fat for human body, so they are also much needed by the food industry. However, in increasing soil productivity there is a decrease in quality and quantity caused by one of the factors, namely plant diseases. Efforts that can be made in maintaining peanut productivity are to prevent early by applying early detection technology. This study presents the application of digital image processing application-based technology using the Multiclass SVM One-Against-One (OAO) strategy to classify the types of leaf disease of peanut plants based on texture feature extraction on the diseased parts of peanut leaves using the Gray Level Co-Occurrence Matrix (GLCM) method. In the classification process using the M-SVM method the OAO strategy will use three kernels, namely polynomial kernel, linear kernel and RBF kernels. Based on the experimental results, the best accuracy is obtained, namely by using GLCM texture feature extraction with a distance of d = 1 and angle 90 degree of and classified using the M-SVM method, the OAO strategy with polynomial kernels provides the highest accuracy results, namely 96.39% for leaf spot class, 92.79% for leaf rust class, 96.39% for eye spot class and 100% for normal class
Performance Evaluation of YOLOv8-Pose for Vision-Based Fatigue Detection via Multi-Feature Behavioral Analysis Permatasari, Dinda Ayu; Lestari, Rifki Noviandra; Putra, Dimas Rossiawan Hendra; Fakhrunnia, Brahma Ratih Rahayu; Wahono, Wahyu Tri; Muallif, Mohammad
Journal of Electrical Engineering and Computer (JEECOM) Vol 8, No 3 (2026)
Publisher : Universitas Nurul Jadid

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33650/jeecom.v8i3.16982

Abstract

Driver fatigue is a significant contributor to road traffic accidents, motivating the development of non-invasive vision-based monitoring systems. This study evaluates a single-stage YOLOv8n-Pose approach for fatigue detection based on multiple behavioral indicators, including eye closure, a hand-at-mouth gesture as a yawning-related cue, and head tilt. Unlike conventional multi-stage approaches that require separate face detection and facial landmark extraction, the proposed approach jointly detects the facial region and estimates eight task-specific keypoints within a single inference process. The model was trained on 2,625 images representing variations in lighting conditions, subjects, accessories, and camera distance. Performance was evaluated using bounding-box and keypoint detection metrics, followed by live testing under different head orientations and camera distances. The model achieved a bounding-box mAP50 of 0.967 and a keypoint mAP50 of 0.817, with F1-scores of 0.90 for Eyes Open, 0.94 for Eyes Closed, and 0.97 for Hand-at-Mouth detection. Head-angle testing showed a monotonic decrease in ear-to-shoulder keypoint distance as the head tilted from the upright position, supporting its use as a head-tilt indicator within the tested conditions. Live testing identified an effective camera distance of 60–100 cm and an average processing rate of approximately 3.3–3.5 FPS. Error analysis identified backlighting as a source of incorrect eye-state predictions and hand occlusion as a cause of missed Hand-at-Mouth detections. These results demonstrate the potential of a single-stage pose-based approach for multi-indicator vision-based fatigue detection while highlighting the need for improved lighting robustness, diverse hand-pose training data, and higher inference efficiency.
Co-Authors Aziz, As’ad Shidqy Lestari, Rifki Noviandra Muallif, Mohammad PERMATASARI, DINDA AYU Putra, Dimas Rossiawan Hendra Sesoca, Jendra Wahono, Wahyu Tri