Claim Missing Document
Check
Articles

Found 12 Documents
Search

Lightweight Enhancement Module for Efficient Sea Turtle Species Detection under Illumination Variation Yuliana Mose; Alex Copernikus Andaria; Hebron Prasetya; Muhamad Dwisnanto Putro
Indonesian Journal of Electrical Engineering and Informatics (IJEEI) Vol 14, No 2: June 2026
Publisher : IAES Indonesian Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52549/ijeei.v14i2.7399

Abstract

Sea turtle monitoring is crucial for maintaining ecosystem balance, although traditional methods are costly and inefficient. Object detection provides a foundation for autonomous monitoring by localizing sea turtles in their natural habitat. At the same time, recent deep learning models can operate in real-time. On the other hand, underwater detection remains challenging due to extreme illumination, underwater blur, and underwater distortions, which obscure key features from the background. To address these issues, this work proposes a new sea turtle detector, based on a modified YOLOv12-nano model that incorporates a lightweight enhancement module to improve robustness under diverse illumination. The network introduced Efficient Spatial Convolution (ESC) at the end of the backbone to improve the representation of high-level features. It involves Dual Spatial Convolution (DSC) to improve backbone feature extraction with a large kernel size while preserving efficiency. The Lite module is designed to enrich feature diversity and selectively enhance the quality of high-level features. These modifications significantly enhance detection performance under diverse underwater lighting conditions. The proposed network achieves higher precision than the original YOLOv12-nano while maintaining efficiency, making it well-suited for deployment on low-cost devices.
Social Media Use, Cybersecurity Threats, and Psychological Distress: The Moderating Role of Social Support Among University Students Angelina Helda Semuruk; Windy Christy Tulung; Ingrid Novelia R Sembiring; Yuliana Mose; Agatha C E M Jamlean
Indonesian Journal of Education Research (IJoER) Vol. 7 No. 5 (2026): October
Publisher : Cahaya Ilmu Cendekia Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37251/ijoer.v7i5.3861

Abstract

Purpose of the study: This study examined the relationships of social media use and cybersecurity threats with depression, anxiety, and stress among university students in Manado, Indonesia. It also investigated whether perceived social support moderated the relationships between these digital stressors and the three dimensions of psychological distress. Methodology: A quantitative cross-sectional design was employed with 300 university students in Manado, comprising 154 students from private universities and 146 from public universities. Participants were selected through random sampling. Data were collected using structured questionnaires and analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM) with SmartPLS. Main Findings: Social media use was positively associated with depression (β = 0.353, p < 0.001), anxiety (β = 0.305, p < 0.001), and stress (β = 0.353, p < 0.001). Cybersecurity threats were positively associated with depression (β = 0.144, p = 0.005), but not with anxiety or stress. Social support was negatively associated with all three outcomes and moderated the relationships between social media use and depression and stress. Novelty/Originality of this study: This study integrates social media use and cybersecurity threats within a single model while examining depression, anxiety, and stress as distinct psychological outcomes. The findings further demonstrate that the moderating role of social support is selective, occurring for depression and stress in relation to social media use but not for anxiety or cybersecurity-related pathways.