Claim Missing Document
Check
Articles

Found 12 Documents
Search

Facial Expression Detection of Autism Children Using ResNet-50 in Convolutional Neural Network Algorithm Prihatini, Ekawati; Muslimin, Selamat; Darmawan, Muhammad Rizki
Indonesian Journal of Artificial Intelligence and Data Mining Vol 8, No 3 (2025): November 2025
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v8i3.37755

Abstract

Facial expression detection in children with autism presents unique challenges due to limitations in verbal communication and social responses. This study develops a Convolutional Neural Network (CNN) model using the ResNet-50 architecture to improve the recognition accuracy of five expression categories: angry, fear, sad, neutral, and happy. A dataset of 3,030 images was divided into training and testing sets (60:40), with data augmentation and hyperparameter tuning applied using the Adam optimizer. The model achieved 89% validation accuracy and 84.49% testing accuracy, along with 86.78% precision and 80.69% recall. Evaluation on 25 test images showed an 84% success rate. These results indicate that ResNet‑50 effectively extracts facial features and classifies expressions with high accuracy, demonstrating potential as a communication aid in autism therapy. Future improvements include adding more diverse training data and optimizing model parameters.
Strengthening Small-Scale Snakehead (Channa Striata) Aquaculture through the Implementation of the IoT-Based “Channa Sense” Monitoring System Nyayu, Latifah Husni; Muslim, Muslim; Handayani, Ade Silvia; Salamah, Umul; Ardiansyah, Muhammad; Martini, Rita; Ariyanto, Rusman; Prihatini, Ekawati; Citra, Cinda Anugrah
Wikrama Parahita : Jurnal Pengabdian Masyarakat Vol. 10 No. 1 (2026): May 2026
Publisher : Universitas Serang Raya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30656/jpmwp.v10i1.11574

Abstract

Small-scale snakehead (Channa striata) farmers commonly rely on manual and periodic water quality monitoring, which often results in delayed responses to environmental fluctuations and high fry mortality rates. This community service program aimed to strengthen technological literacy and improve hatchery management practices through the implementation of an Internet of Things (IoT)-based “Channa Sense” real-time monitoring system. The intervention adopted a structured three-phase approach consisting of pre-implementation assessment, participatory workshop and system installation, and post-implementation evaluation. The program involved 37 participants representing farmers, entrepreneurs, and community members, with baseline data collected from 30 small-scale farmers across Palembang, Indralaya, and Musi Banyuasin. Pre-intervention findings showed that 56.76% of participants were unaware of the technology and none had prior experience with digital monitoring systems. Following experiential learning activities, 64.86% of participants reported a moderate to full understanding of the system, and recognition of Channa Sense as a water quality monitoring device increased from 13.51% to 60.42%. At the partner hatchery (Kandang Om Bobby), real-time monitoring reduced fry mortality from approximately 40% to 5–10%, representing a survival improvement of 30–35%. The findings indicate that participatory and context-adapted IoT interventions can effectively bridge digital literacy gaps while generating measurable operational benefits in small-scale aquaculture. However, adoption intentions remained moderate due to cost and maintenance concerns. Continued mentoring, cost optimization, and cooperative-based implementation strategies are recommended to ensure long-term sustainability and broader community uptake