Article Per Year (5 Year)
p-Index From 2021 - 2026
2.332
P-Index
This Author published in this journals
All Journal Informatika Mulawarman: Jurnal Ilmiah Ilmu Komputer Knowledge Engineering and Data Science JIKO (Jurnal Informatika dan Komputer) PENDIPA Journal of Science Education Jurnal Teknologi Terapan METIK JURNAL JISKa (Jurnal Informatika Sunan Kalijaga) Journal of Innovation Information Technology and Application (JINITA) PLAKAT : Jurnal Pelayanan Kepada Masyarakat Prosiding Seminar Nasional Rekayasa Teknologi Industri dan Informasi ReTII Adopsi Teknologi dan Sistem Informasi
Gubtha Mahendra Putra
Informatics Department, Engineering Faculty, Mulawarman University, Samarinda, 75123, Indonesia
Aerospace Engineering Humanities Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Education Electrical & Electronics Engineering Energy Engineering Environmental Science Industrial & Manufacturing Engineering Library & Information Science Materials Science & Nanotechnology Mathematics Mechanical Engineering Physics Social Sciences Transportation

Published : 13 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 13 Documents
Search

 1   2 
Facial Image-Based Autism Detection Using ConvNeXt Tiny: A Lightweight Deep Learning Approach for Early Screening Putut Pamilih Widagdo; Muhammad Bambang Firdaus; Gubtha Mahendra Putra; Akhmad Irsyad
Journal of Innovation Information Technology and Application (JINITA) Vol 7 No 2 (2025): JINITA, December 2025
Publisher : Politeknik Negeri Cilacap

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35970/jinita.v7i2.2848

Abstract

This study proposes a deep learning model using the ConvNeXt Tiny architecture to detect autism spectrum disorder (ASD) from facial images, addressing the need for an early, efficient, and accessible diagnostic tool. The model integrates facial image preprocessing techniques like Contrast Limited Adaptive Histogram Equalization (CLAHE) and data augmentation, with facial segmentation performed by MTCNN. The ConvNeXt Tiny model is trained using transfer learning and evaluated through metrics such as accuracy, precision, recall, and F1-score, and compared with traditional CNN models like ResNet50 and EfficientNet-B0. The results demonstrate that the proposed model outperforms ResNet50 and EfficientNet in all evaluation metrics, achieving a classification accuracy of 84%. It also demonstrates a balanced performance across both classes (autistic and non-autistic), with high precision and recall for both, leading to a high F1-score. Furthermore, the model's computational efficiency makes it suitable for web and mobile applications, enabling scalable and real-time screening for ASD in children. The study's contributions include the development of a novel, lightweight ASD classification system, a comparative analysis of ConvNeXt with other CNN models, and the creation of a prototype for early ASD detection. This approach not only provides a promising alternative to conventional diagnostic methods but also sets the groundwork for further research and practical implementation in clinical settings.
Peningkatan Kemampuan Analisis Statistik Kuantitatif Pada Riset Eksperimen Dengan Metode Workshop Fahrul Agus; Gubtha Mahendra Putra; Zanu Alfandi Kamil; Iswanto Arifin; Okta Ihza Gifari
Plakat : Jurnal Pelayanan Kepada Masyarakat Vol 4, No 2 (2022): Plakat: Jurnal Pelayanan Kepada Masyarakat
Publisher : Fakultas Ilmu Sosial dan Ilmu Politik, Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30872/plakat.v4i2.8954

Abstract

Riset merupakan kegiatan akademik yang wajib dilakukan oleh mahasiswa tugas akhir di Program Studi Informatika, Fakultas Teknik Universitas Mulawarman, Samarinda Kalimantan Timur. Riset eksperimen memerlukan pengetahuan dan pemahaman yang kuat di bidang Statistik. Pelajaran Matematika dan Statistika termasuk materi yang sulit dipahami di kalangan mahasiswa di beberapa perguruan tinggi. Pelatihan atau workshop ini betujuan untuk melakukan penguatan kembali (recharging) serta peningkatan pengetahuan peserta tentang ilmu pengetahuan, konsep dan aplikasi Statistik Kuantitatif untuk riset eksperimen. Pelatihan dilakukan dengan cara pembelajaran secara langsung di dalam kelas. Monitoring pelatihan dilakukan dengan observasi selama kegiatan berlangsung, sedangkan evaluasi dilakukan melalui survey kepada peserta. Bobot penilaian oleh peserta terhadap materi, narasumber, fasilitas pelatihan dan peningkatan kemampuan diukur dengan Skala Likert. Pelatihan dilaksanakan dengan 38 peserta dan observasi monitoring menunjukkan dinamika peserta dan fasilitator yang aktif dan lancar. Hasil evaluasi kegiatan pelatihan menunjukkan materi, narasumber, fasilitas pelatihan dan peningkatan kemampuan telah memenuhi kebutuhan peserta dengan persentase rata-rata sebesar 99.7%. Evaluasi juga menunjukkan bahwa sebesar 64% peserta menyatakan peningkatan pengetahuan yang sangat tinggi, 31% menilai tinggi dan 5% menyatakan sedang. Students in the Department of Informatics at the Faculty of Engineering, Mulawarman University, Samarinda, East Kalimantan, are required to conduct research for their final project. Strong statistical expertise and understanding are necessary for conducting experimental research. Many universities' students report having trouble understanding math and statistics classes. The purpose of this training is to deepen and broaden participants' understanding of scientific principles and the uses of quantitative statistics in experimental research. Direct learning takes place during the training in the classroom. Evaluation of training is done through surveys given to participants, while monitoring is done by observing during the activity. A Likert Scale was used to gauge how seriously the participants took the content, resource people, training facilities, and capacity building. 38 people attended the training, and monitoring observations revealed the dynamics of fluent and active participants and facilitators. According to the findings of the evaluation of training activities, an average percentage of 99.7% of the participants' needs were met by the training materials, resource people, training facilities, and capacity building. Additionally, the evaluation revealed that 64% of participants rated the level of knowledge gain as very high, 31% as high, and 5% as moderate.
Validitas dan Efektivitas Media Karibu Dayak Berbasis Genially pada Materi Klasifikasi Makhluk Hidup SMP Ru'iyah Ru'iyah; Elsje Theodora Maasawet; Ruqqoyah Nasution; Dora Dayu Rahma Turista; Sri Purwati; Gubtha Mahendra Putra; Marwah Ulwatunnisa
PendIPA Journal of Science Education Vol 10 No 2 (2026): April - June
Publisher : UNIB Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33369/pendipa.10.2.576-585

Abstract

This study was motivated by students' difficulties in understanding the classification of living things, monotonous science learning, and the limited use of learning media at SMP Negeri 2 Samarinda. The study aimed to determine the validity, practicality, and effectiveness of Genially-based learning media integrated with Dayak Kenyah local wisdom for seventh-grade students. The research employed the Research and Development (R&D) method using the 4D model (Define, Design, Develop, and Disseminate). Data were collected through validation sheets, practicality questionnaires, activity observation sheets, and learning outcome tests. The results showed that the learning media achieved a very valid category with an Aiken’s V value of 0.897, a very practical category with an Aiken’s V value of 0.876, and a very feasible category with a percentage of 86.6%. The media was also proven effective, as indicated by an average student activity score of 92%, a paired sample t-test significance value of 0.000, and an N-Gain score of 0.41, which falls into the moderate category. Therefore, the Genially-based learning media integrated with Dayak Kenyah local wisdom is suitable for use in science learning on the topic of the classification of living things.
Co-Authors Anam, M Khairul Anton Prafanto Arinda Mulawardani Kustiawan Awang Harsa Kridalaksana Budiman, Edy Dary Daris Abdurrahman Dedi Cahyadi Elsje Theodora Maasawet Fahrul Agus Fahrul Agus Fandy Haviluddin Haviluddin Herman Santoso Pakpahan Indah Fitri Astuti Irsyad, Akhmad Iswanto Arifin Marwah Ulwatunnisa Muhammad Bambang Firdaus Muhammad Bambang Firdaus Muhammad Wisdan Pratama Putra Nariza Wanti Wulan Sari Novianti Puspitasari Okta Ihza Gifari Puspitasari, Novianti Putut Pamilih Widagdo Rayner Alfred Reza Wardhana Rima Yustika Hasnida Rosmasari Rosmasari Ru'iyah Ru'iyah Ruqqoyah Nasution Setyadi, Hario Jati Solly Aryza Sri Purwati Suryani Junita Patandianan Taghfirul Azhima Yoga Siswa Taruk, Medi Turista, Dora Dayu Rahma Yumami, Eva Zanu Alfandi Kamil