Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Media Jurnal Informatika Bakti Sekawan : Jurnal Pengabdian Masyarakat
Augustin, Kartarina
Unknown Affiliation
Religion Humanities Civil Engineering, Building, Construction & Architecture Computer Science & IT Health Professions Social Sciences Other

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

Found 2 Documents
Search

 1 
Peningkatan Kompetensi Guru SMAN 7 Mataram dalam Melaksanakan Pembelajaran dengan Pendekatan Deep Learning Azwar, Muhamad; Hariyadi, I Putu; Azhar, Raisul; Priyanto, Dadang; Adil, Ahmat; Santoso, Heroe; Syahrir, Moch.; Augustin, Kartarina; Zulkipli, Zulkipli; Darma, I Made Yadi; Asroni, Ondi; Qulub, Mudawil; Azhar, Lalu Zazuli; Widyawati, Lilik; Anas, Andi Sofyan
Bakti Sekawan : Jurnal Pengabdian Masyarakat Vol. 5 No. 2 (2025): Desember
Publisher : Puslitbang Sekawan Institute Nusa Tenggara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35746/bakwan.v5i2.852

Abstract

The capability of educators to respond to the dynamics of 21st-century education is a primary determinant in establishing a high-quality learning environment. Based on initial findings at SMAN 7 Mataram, a disparity was identified between the urgency of applying varied learning models and the reality in the field, which still relies heavily on conventional, teacher-centered approaches. This situation implies minimal active student participation and suboptimal stimulation of critical thinking skills or Higher Order Thinking Skills (HOTS). This community service program was initiated to escalate teacher capacity at SMAN 7 Mataram, specifically in designing Deep Learning-based schemes. The implementation approach adopted the Participatory Action Research (PAR) method, involving the full attention of 70 teachers through a series of phases, ranging from preparation and implementation to evaluation and mentoring. Key interventions included training on compiling Deep Learning-oriented Lesson Plans and teaching simulations. Program effectiveness was measured through questionnaires, lesson plan document reviews, and observations. Evaluation data showed a substantial positive impact, marked by an increase in conceptual understanding of Deep Learning indicators (40%), 6C principles (40%), the teacher's function as a facilitator (32%), and the application of authentic assessment (40%). In terms of implementation, the quality of lesson plans accommodating student-centered activities surged significantly from 30% in the pre-activity phase to 100% after the activity. It can be concluded that this program effectively boosts teachers' pedagogical competence comprehensively and encourages the transformation of teaching practices in the classroom to become more dynamic.
Autism Classification Using MobileNetV3 Feature Extraction and K-Nearest Neighbor Algorithm Husaini, Rahayun Amrullah; Pratama, Gede Yogi; Latif, Kurniadin Abd.; Zulfikri, Muhammad; Augustin, Kartarina
Media Jurnal Informatika Vol 17, No 2 (2025): Media Jurnal Informatika
Publisher : Teknik Informatika Universitas Suryakancana Cianjur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35194/mji.v17i2.5934

Abstract

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder characterized by difficulties in social interaction, communication, and repetitive behaviors. Early detection of ASD is crucial; however, conventional diagnostic methods rely heavily on clinical observation and expert assessment, which can be time-consuming and resource-intensive. Along with the rapid development of artificial intelligence, especially in computer vision and machine learning, automated image-based approaches have gained attention as alternative tools for ASD screening. This study proposes a hybrid classification approach that integrates MobileNetV3 as a feature extraction model with the K-Nearest Neighbor (KNN) algorithm for autism classification using facial image data. Unlike previous CNN–KNN approaches, this study specifically explores the use of MobileNetV3’s lightweight architecture to generate compact and discriminative facial features, which are then classified using KNN to evaluate its effectiveness in low-complexity and resource-efficient settings. This design highlights the novelty of combining an optimized lightweight CNN with a distance-based classifier for autism detection from facial images. The dataset used in this research was obtained from Kaggle and consists of 2,940 labeled facial images of children categorized into Autism and non-Autism classes. This study proposes a hybrid classification approach that combines MobileNetV3 as a lightweight feature extraction model with the K-Nearest Neighbor (KNN) algorithm for autism classification. Experimental evaluations were conducted over multiple independent runs to improve statistical reliability, and model performance was assessed using accuracy, precision, recall, and F1-score. The results indicate that the proposed hybrid model achieves satisfactory and consistent performance while maintaining computational efficiency. These findings suggest that integrating lightweight deep learning models with classical machine learning algorithms can provide an effective and resource-efficient approach for autism classification, with potential applicability as a supportive tool for early ASD screening rather than a definitive clinical diagnosis.
Co-Authors Ahmat Adil Andi Sofyan Anas Azhar, Lalu Zazuli Azhar, Raisul Darma, I Made Yadi Hariyadi, I Putu Husaini, Rahayun Amrullah Kurniadin Abd Latif Lilik Widyawati Muhamad Azwar, Muhamad Ondi Asroni Pratama, Gede Yogi Qulub, Mudawil Santoso, Heroe Syahrir, Moch. Zulfikri, Muhammad Zulkipli Zulkipli