Article Per Year (5 Year)
p-Index From 2020 - 2025
5.701
P-Index
This Author published in this journals
All Journal Sainteks Prosiding Seminar Nasional Sains Dan Teknologi Fakultas Teknik Techno (Jurnal Fakultas Teknik, Universitas Muhammadiyah Purwokerto) JUITA : Jurnal Informatika Proceeding Seminar LPPM UMP Tahun 2014 PROSIDING SENATEK FAKULTAS TEKNIK UMP PAEDAGOGIA JRST (Jurnal Riset Sains dan Teknologi) KACANEGARA Jurnal Pengabdian pada Masyarakat CYBERNETICS JURIKOM (Jurnal Riset Komputer) JPPM (Jurnal Pengabdian dan Pemberdayaan Masyarakat) JTIM : Jurnal Teknologi Informasi dan Multimedia REMIK : Riset dan E-Jurnal Manajemen Informatika Komputer Jurnal Sistem Komputer dan Informatika (JSON) Jurnal Generic Proceedings Series on Physical & Formal Sciences Dulang: Jurnal Pengabdian Kepada Masyarakat Techno Jutech: Jurnal Teknologi Informasi Prosiding University Research Colloquium Jurnal Sistem Informasi Prosiding Seminar Nasional Hasil-hasil Penelitian dan Pengabdian Pada Masyarakat Jurnal Aplikasi Sistem Informasi dan Elektronika Jurnal Pengabdian Kepada Masyarakat Kalam
Hindayati Mustafidah
Informatic Engineering, Universitas Muhammadiyah Purwokerto
Humanities Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Mechanical Engineering Medicine & Pharmacology Public Health Social Sciences Other

Published : 117 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : JURIKOM (Jurnal Riset Komputer)

 1 
Perbandingan MobileNetV2, DenseNet121, InceptionV3, dan Xception pada Klasifikasi Citra Panel Surya Bersih dan Berdebu Nugroho, Aswin Mulyo; Mustafidah, Hindayati; Fitriani, Maulida Ayu; Supriyono, Supriyono
JURIKOM (Jurnal Riset Komputer) Vol. 12 No. 4 (2025): Agustus 2025
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v12i4.8688

Abstract

The buildup of dust on solar panels can greatly diminish energy output, lower system efficiency, and raise operational expenses. A productive way to tackle this problem is to utilize image classification through Convolutional Neural Network (CNN) techniques. This study examines the classification capabilities of four CNN models, namely MobileNetV2, DenseNet121, InceptionV3, and Xception, using transfer learning. These models leverage pre-trained weights from large datasets such as ImageNet to accelerate convergence and improve generalization. The dataset of images utilized in this research is obtained from Kaggle and includes pictures of both clean and dusty solar panels. The dataset was divided into training, validation, and testing subsets using a stratified approach to ensure balanced class distribution across all subsets. During training, class weighting was used to address potential class imbalance. The models were developed using TensorFlow with multi-GPU support, optimized using the AdamW optimizer, and fine-tuned to enhance performance. Model evaluation was conducted using accuracy, precision, recall, and F1-score metrics. Among all the architectures evaluated, the Xception model achieved the best performance with an accuracy of 90.52%, outperforming MobileNetV2 with an accuracy of 87.92%, DenseNet121 with 89.78%, and InceptionV3 which achieved 87.73%. These results indicate that modern CNN-based models can effectively recognize relevant visual patterns to detect dust on solar panels.
Perbandingan MobileNetV2, DenseNet121, InceptionV3, dan Xception pada Klasifikasi Citra Panel Surya Bersih dan Berdebu Nugroho, Aswin Mulyo; Mustafidah, Hindayati; Fitriani, Maulida Ayu; Supriyono, Supriyono
JURNAL RISET KOMPUTER (JURIKOM) Vol. 12 No. 4 (2025): Agustus 2025
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v12i4.8688

Abstract

The buildup of dust on solar panels can greatly diminish energy output, lower system efficiency, and raise operational expenses. A productive way to tackle this problem is to utilize image classification through Convolutional Neural Network (CNN) techniques. This study examines the classification capabilities of four CNN models, namely MobileNetV2, DenseNet121, InceptionV3, and Xception, using transfer learning. These models leverage pre-trained weights from large datasets such as ImageNet to accelerate convergence and improve generalization. The dataset of images utilized in this research is obtained from Kaggle and includes pictures of both clean and dusty solar panels. The dataset was divided into training, validation, and testing subsets using a stratified approach to ensure balanced class distribution across all subsets. During training, class weighting was used to address potential class imbalance. The models were developed using TensorFlow with multi-GPU support, optimized using the AdamW optimizer, and fine-tuned to enhance performance. Model evaluation was conducted using accuracy, precision, recall, and F1-score metrics. Among all the architectures evaluated, the Xception model achieved the best performance with an accuracy of 90.52%, outperforming MobileNetV2 with an accuracy of 87.92%, DenseNet121 with 89.78%, and InceptionV3 which achieved 87.73%. These results indicate that modern CNN-based models can effectively recognize relevant visual patterns to detect dust on solar panels.
Co-Authors . Suwarsito Abdul Azis Abdul Kadir Hasani Abu Khaer Firman Ades Galih Anto Adi Imantoyo Aditia, Rudi Aditya Hadi Wijaya, Aditya Hadi Agung Purwo Wicaksono Agung Purwo Wicaksono Agung Supriyono Ahmad Ahmad Ahmad Yatiman Aji Dwi Setyabudi Aji, Panji Andika Mustiko Akbar Wiraisy Akhsin Rifai Aman Suyadi Aman Suyadi Aman Suyadi Amrisa Yanri Rahmadhani Andi Kurniawan Anis Shofiyani Anton Suroto Ardhine Attafaqquf Arif Mukhamal Bangkit Nurdiyansah Beny Pradana Betharia Wahyu Rizdawaty Cahyono Purbomartono Citra Aristy Yusliani Dany Candra Febrianto Darwan, Darwan Dede Rubianto Dedi Mulyawan, Dedi Dedi Suprayogi Denis Pratama Alwan Azzami Dimara Kusuma Hakim Dimara Kusuma Hakim Dimas Anugerah Adibrata Dini Agustina Dini Siswani Mulia Dodi Ghani Setiawan Dwi Aryanto Dwi Aryanto Dwi Ayanto Dwi Cahyanto Yoni Dwiky Putra Hardiawan Eka Setyaningsih Eri Zuliarso Erik Kurniawan Fardhian Dwi Saputra Feri Wibowo Fitriani, Maulida Ayu Gunadi, Ilham H Harjono Habib Wisnu Pratama Habibullah Al Faruq Halimah, Fitri Nur Harjono, H Hendrik Prawijaya Hirzi Nur Hadyan Ibnu Hazim Alfatih Jaka Purwa Nugraha, Jaka Purwa Jefri Setiawan Khotimul Anwar Luthfatul Adlhiyah Mahmud, Annisa Kayla Azzira Manshur Awalludin Martono Akbar Rahmadi Mawaddah Isfa Apriliyani Mochamad Tegar Utomo Moh Aya Sofia Mr. Harjono, Mr. Mr. Suwarno, Mr. Muftikhah, Muftikhah Muhamad Zaeni Budiastanto Muhammad Hamka Muhammad Hamka Mustika Ratnaningsih Purbowati Mu’ammirotus Sholihah Ning Rahayu Noor Adi Pamungkas Nugraha, Habib Rosyid Pandu Nugroho, Aswin Mulyo Nurhidayah Nurhidayah Opik Taofik Pajar Sidiq Pandu Priambadha Prista Amanda Putri Purnomo Purnomo Purwana Abdi Pujangga Putri Fitria Aprilliani Rakhmat Wijayanto, Rakhmat Ratna Kartikawati Ratna Kartikawati Reza Satria Ridho Muktiadi Rifqi Al Mubarok Rizka Putriyanti Rizky Maulana Yusuf Rodiah Pawesti Mayasari S Suwarsito SANTOSA, DWI Saputri, Devi Selvia Nur Rohman Septian Ari Wibowo Sigit Sugiyanto SUPRIYONO Supriyono Supriyono Susi Kurniasih Suwarno Suwarno Suwarno Suwarno Suwarsito, S Syahrul Hakim Tito Pinandita Tito Pinandita Wahyu Agung Ciptadi Wahyu Giri Pambudi Giarto Yuni Wiwiet Wiharti Yusuf, Rizky Maulana