Article Per Year (5 Year)
p-Index From 2021 - 2026
0.778
P-Index
This Author published in this journals
All Journal Sistemasi: Jurnal Sistem Informasi JOURNAL OF APPLIED INFORMATICS AND COMPUTING Jurnal Media Informatika
Muhammad Abdul Ghofur
Universitas Nahdlatul Ulama Sunan Giri
Computer Science & IT Electrical & Electronics Engineering

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
High Precision Deep Learning Model for Road Damage Classification using Transfer Learning Ghofur, Muhammad Abdul; Murdifin, Murdifin; Hardandrito, Awan Gumilang; 'Uyun, Shofwatul
Sistemasi: Jurnal Sistem Informasi Vol 14, No 6 (2025): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v14i6.5707

Abstract

Roads are critical infrastructure that frequently experience damage, directly impacting transportation safety and efficiency. Manual road damage inspection is time-consuming and resource-intensive, highlighting the need for automated, image-based approaches. This study compares two Convolutional Neural Network (CNN) architectures—MobileNetV2 with transfer learning and a custom-built CNN—for classifying road surface damage severity. The dataset consists of 1,800 road surface images evenly distributed across three categories: good, minor damage, and severe damage. All images were normalized, augmented, and resized, followed by evaluation using 5-Fold Cross-Validation to ensure robust performance. Experimental results show that MobileNetV2 achieved an accuracy of 98%, outperforming the custom CNN, which achieved 89%. These findings demonstrate the effectiveness of transfer learning in improving classification accuracy with limited data and highlight the potential of MobileNetV2 for efficient, real-time road damage detection systems that can be integrated into intelligent infrastructure monitoring solutions.
Analisis Perbandingan Kinerja Model ResNet50 Dan EfficientNet-B0 Dalam Klasifikasi Kerusakan Jalan Muhammad Abdul Ghofur; Ahmad Bahrul Ulum
Jurnal Media Informatika Vol. 6 No. 5 (2025): Edisi Sep - Oktober 2025
Publisher : Lembaga Dongan Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55338/jumin.v6i5.6843

Abstract

Kerusakan jalan memiliki dampak signifikan terhadap aspek keselamatan, kenyamanan, dan kelancaran transportasi. Namun, identifikasi kerusakan secara manual membutuhkan waktu, tenaga, serta sumber daya yang besar. Penelitian ini bertujuan mengembangkan sistem klasifikasi otomatis tingkat kerusakan jalan berbasis pengolahan citra digital dengan membandingkan kinerja dua arsitektur Convolutional Neural Network (CNN) pretrained, yaitu ResNet50 dan EfficientNet-B0. Dataset penelitian terdiri atas 1.800 citra permukaan jalan yang terbagi secara seimbang ke dalam tiga kategori, yaitu jalan baik, rusak ringan, dan rusak berat. Seluruh citra melalui tahap praproses berupa normalisasi dan penyesuaian ukuran agar sesuai dengan masukan model. Selanjutnya, metode transfer learning diterapkan pada model pretrained untuk memanfaatkan pengetahuan awal dari dataset berskala besar, sedangkan evaluasi kinerja dilakukan menggunakan K-Fold Cross Validation (K=5) guna meningkatkan reliabilitas serta mengurangi potensi bias. Hasil penelitian menunjukkan bahwa ResNet50 dan EfficientNet-B0 mampu mencapai akurasi hingga 99% dengan nilai Precision dan F1-Score yang tinggi. Temuan ini menegaskan keunggulan model pretrained dalam klasifikasi citra kerusakan jalan, sehingga ResNet50 dan EfficientNet-B0 direkomendasikan untuk pengembangan sistem deteksi kerusakan jalan secara real-time yang efisien serta dapat diintegrasikan ke dalam sistem monitoring infrastruktur berbasis teknologi cerdas.
Brain Tumor Classification in MRI Images Using Convolutional Neural Networks with Explainable Artificial Intelligence Muhammad Abdul Ghofur; Nirma Ceisa Santi; Hastie Audytra
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13594

Abstract

Brain tumors are a condition requiring rapid and accurate diagnosis. This study aims to enhance the transparency of Convolutional Neural Network (CNN)-based brain tumor classification models by implementing Explainable Artificial Intelligence (XAI) techniques, specifically Eigen-CAM and LIME. The models were developed using a transfer learning approach on ResNet50 and EfficientNetB0 architectures, utilizing a dataset of 3,000 MRI images categorized into glioma, meningioma, and pituitary tumor classes. Test results indicate that ResNet50 achieved the best performance, with accuracy, precision, recall, and F1-score values of 94%, while EfficientNetB0 achieved 93%. The application of 5-fold cross-validation improved the models' generalization capabilities and reduced the risk of overfitting. Visualizations using Eigen-CAM and LIME demonstrate that the models focus on relevant tumor regions, thereby increasing the transparency and reliability of MRI-based classification.
XAI Interpretation to Enhance Transparency in Skin Cancer Classification using CNN Muhammad Abdul Ghofur; Maria Ulfah Siregar; Ahmad Bahrul Ulum
SISTEMASI Vol 15, No 9 (2026): Sistemasi: Jurnal Sistem Informasi
Publisher : Universitas Islam Indragiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v15i9.6726

Abstract

Skin health is an important aspect of maintaining quality of life, while skin cancer requires early detection to support appropriate treatment. This study explores the application of Explainable Artificial Intelligence (XAI), particularly LIME and Eigen-CAM, to interpret the results of binary skin cancer classification into benign and malignant classes. Classification was performed using a transfer learning approach with ResNet50, VGG16, EfficientNetB0, and MobileNetV2 architectures on a dataset of 2,000 skin images, with an equal number of samples in both classes. Model performance was evaluated using 5-fold cross-validation to obtain more consistent performance estimates across the test data. The experimental results showed that ResNet50 achieved the highest accuracy of 86.90%, followed by VGG16 at 85.90%, MobileNetV2 at 84.90%, and EfficientNetB0 at 84.85%. Visualization using LIME and Eigen-CAM highlighted image regions that contributed to the model's predictions, providing additional insights into the basis of its classification decisions. These findings indicate that XAI can serve as an interpretative approach for improving the understanding of model predictions in binary skin cancer classification.
Co-Authors Ahmad Bahrul Ulum Ahmad Bahrul Ulum Hardandrito, Awan Gumilang Hastie Audytra Maria Ulfah Siregar Murdifin, Murdifin Nirma Ceisa Santi Shofwatul ‘Uyun