Article Per Year (5 Year)
p-Index From 2021 - 2026
2.978
P-Index
This Author published in this journals
All Journal Sinkron : Jurnal dan Penelitian Teknik Informatika Jurnal Pendidikan Teknologi Informasi dan Vokasional Jurnal Sains Teknologi dan Sistem Informasi Jurnal Pengabdian Masyarakat : Pemberdayaan, Inovasi dan Perubahan Engineering and Technology International Journal (EATIJ) JUPADAI : Jurnal Pengabdian Kepada Masyarakat JR : Jurnal Responsive Teknik Informatika The Indonesian Journal of Computer Science Jurnal Responsive Teknik Informatika Pelayanan Unggulan: Jurnal Pengabdian Masyarakat Terapan JUTEKDISI: Jurnal Teknologi Digital dan Sistem Informasi
Doni Syofiawan
Universitas Ibnu Sina
Religion Aerospace Engineering Agriculture, Biological Sciences & Forestry Humanities Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Mechanical Engineering Public Health Social Sciences Other

Published : 22 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 22 Documents
Search

 1   2   3 
Lightweight Deep Learning Models for Facial Expression Recognition in Inclusive Education Ilmi, Miftahul; Doni Syofiawan
Sinkron : jurnal dan penelitian teknik informatika Vol. 9 No. 4 (2025): Articles Research October 2025
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v9i4.15370

Abstract

Facial expression recognition is an essential component in the development of artificial intelligence-based learning systems, particularly in the context of inclusive education that involves students with special needs. This study aims to evaluate the performance of several lightweight deep learning architectures in detecting facial expressions with high accuracy while maintaining computational efficiency. Facial image data were obtained from both public datasets and newly collected samples, which were preprocessed through face cropping, normalization, and data augmentation. The dataset was split into 70% training, 15% validation, and 15% testing. Four lightweight deep learning architectures: MobileNetV2, MobileNetV3 (Small and Large), and EfficientNetB0, were employed as the primary models using transfer learning and fine-tuning approaches. Evaluation was conducted using accuracy, loss, precision, recall, and F1-score metrics, complemented by visualization through confusion matrices. The results indicate that MobileNetV2 achieved the best performance with a test accuracy of 92%, precision of 93%, recall of 91%, and F1-score of 92%, while maintaining a relatively lightweight parameter size of 2.26 million. EfficientNetB0 ranked second with 83% accuracy, followed by MobileNetV3-Large (77%), whereas MobileNetV3-Small demonstrated the lowest performance (45%). Confusion matrix analysis revealed recurring misclassification patterns for certain expressions, such as Happy often misclassified as Sad, and Neutral overlapping with Angry. This study confirms that MobileNetV2 is the most optimal architecture for implementing facial expression recognition systems in inclusive education environments, as it balances high accuracy with computational efficiency. These findings provide a solid foundation for developing intelligent applications that support adaptive interaction in the learning process..
EDUKASI PENGGUNAAN AI DAN MEDIA SOSIAL YANG BIJAK UNTUK MENCEGAH PERILAKU MENYIMPANG Ilmi, Miftahul; Syofiawan, Doni; Situmorang, Robert
Jurnal Pengabdian Masyarakat: Pemberdayaan, Inovasi dan Perubahan Vol 5, No 6 (2025): JPM: Pemberdayaan, Inovasi dan Perubahan
Publisher : Penerbit Widina, Widina Media Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59818/jpm.v5i6.2207

Abstract

The rapid growth of artificial intelligence (AI) and social media during the Fourth Industrial Revolution has influenced adolescent behavior, offering learning opportunities but also increasing risks of digital manipulation, harmful content, and privacy violations. Observations at SMP Permata Harapan 1 Batam revealed low digital literacy and ethical awareness, prompting the need for an educational intervention. This community service program (PKM), held on October 17, 2025, involved 128 students through needs assessment, module preparation, interactive theory sessions, and practical case analysis, evaluated using pre-tests, post-tests, and behavioral observations. Results showed a notable improvement in students’ understanding of AI, digital ethics, and data privacy, with an average increase of 28.5% and visible positive changes in online behavior. These findings demonstrate that integrating digital literacy and AI ethics effectively strengthens adolescents’ moral awareness, emphasizing the importance of embedding AI ethics within school curricula.ABSTRAKRevolusi Industri 4.0 mendorong peningkatan penggunaan kecerdasan buatan (AI) dan media sosial di kalangan remaja, yang meskipun memberi manfaat edukatif, juga membuka potensi perilaku menyimpang seperti manipulasi digital, penyebaran konten negatif, dan pelanggaran privasi. Observasi di SMP Permata Harapan 1 Batam menunjukkan rendahnya literasi digital dan etika penggunaan teknologi, sehingga diperlukan intervensi edukatif. Kegiatan Pengabdian kepada Masyarakat (PKM) ini dilaksanakan pada 17 Oktober 2025 dengan melibatkan 128 siswa kelas VIII dan IX melalui tahapan asesmen kebutuhan, penyusunan modul, penyampaian materi teori dengan media interaktif, serta praktik analisis kasus digital yang kemudian dievaluasi menggunakan pre-test, post-test, dan observasi sikap. Hasilnya menunjukkan peningkatan signifikan pada pemahaman konsep AI, etika digital, dan keamanan data pribadi dengan rata-rata peningkatan 28,5%, disertai perubahan perilaku seperti meningkatnya kehati-hatian dalam berbagi konten dan berkurangnya manipulasi digital. Temuan ini menegaskan bahwa edukasi berbasis literasi digital dan etika AI efektif meningkatkan kesadaran moral serta perilaku digital remaja, sehingga integrasi etika AI ke dalam kurikulum sekolah menjadi sangat penting untuk membangun budaya digital yang sehat, aman, dan bermoral.
Co-Authors Abd Basith, Abd Abd. Basith Afrina Afrina Afrina, Afrina Agus Suryadi Agus Suryadi Al Rusman Alex Sandri Sikumbang Ali Basriadi Arifin, Nofri Yudi Crystalia, Nike Didin Setyawan Enggar Adi Sulityo Fadila, Anisa Rizki Ismail Ismail Jackhon Pahala Simanjuntak Larisang Laurensius Setyabudhi, Albertus M. Abdul Nizal Martino, Hisar Gusdian Miftahul Ilmi Nizal, M. Abdul Novi Hendri Adi Putri, Weni Lestari rikson pandapotan tampubolon Robert Situmorang Ropianto, Muhammad Rusman, Al Sabtu Sabtu Sabtu, Sabtu Setyawan, Didin Sikumbang, Alex Sandri Situmorang, Robert Sufian, Indra Suraya Veza, Okta