Article Per Year (5 Year)
p-Index From 2021 - 2026
0.92
P-Index
This Author published in this journals
All Journal ILKOM Jurnal Ilmiah Indonesian Journal of Data and Science Bioma : Jurnal Ilmiah Biologi LANCAH Jurnal Inovasi dan Tren
Dafa Fadhilah Hilmi
Universitas Negeri Malang
Agriculture, Biological Sciences & Forestry Biochemistry, Genetics & Molecular Biology Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Immunology & microbiology Mathematics Social Sciences Other

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
MORPHOLOGICAL CHARACTERIZATION OF BRAIN TUMOR TISSUE IN MRI IMAGES USING CNN AND TRANSFER LEARNING Dafa Fadhilah Hilmi; Aji Prasetya Wibawa; Ardha Ardhana Putra Agustavada; Abdullah Sholum; Felix Andika Dwiyanto
BIOMA : Jurnal Ilmiah Biologi Vol. 15 No. 1 (2026): April 2026
Publisher : Prodi Pendidikan Biologi, FPMIPATI, Universitas PGRI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26877/bioma.v15i1.3550

Abstract

This study evaluates the role of computational pattern recognition as an observational method for analyzing morphological characteristics of brain tumor tissue in MRI data. A total of 6,056 labeled MRI images, including glioma, meningioma, and pituitary tumor cases, were examined. The images were standardized to maintain uniform structural representation and processed using three convolutional-based architectures: a baseline CNN, MobileNetV2, and EfficientNet-B0. Model performance was assessed using accuracy, precision, recall, F1-score, AUC-ROC, and a confusion matrix. The findings show variation in identification performance across tumor categories, with pituitary tumors consistently recognized, while misclassification predominantly occurred between glioma and meningioma. Models based on transfer learning achieved stronger agreement with the reference labels than the baseline CNN, with MobileNetV2 demonstrating the most stable performance. The recurrence of similar misclassification patterns across models suggests the presence of shared morphological characteristics in MRI representations of certain tumor types. Overall, the results support the use of computational image analysis as a structured observational framework that enables consistent evaluation of brain tumor tissue morphology in MRI, providing complementary insights for biological interpretation.
Effect of Spatial, Intensity, and Hybrid Augmentation on Kidney CT Image Classification Ardha Ardhana Putra Agustavada; Aji Prasetya Wibawa; Dafa Fadhilah Hilmi; Abdullah Sholum; Felix Andika Dwiyanto
Indonesian Journal of Data and Science Vol. 7 No. 2 (2026): Indonesian Journal of Data and Science
Publisher : Yocto Brain

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56705/ijodas.v7i2.443

Abstract

Introduction: Kidney diseases remain a major global health challenge, and computed tomography (CT) provides detailed renal imaging that supports accurate diagnosis. Although data augmentation is commonly used to improve deep learning performance on limited medical datasets, the effects of different augmentation strategies on image characteristics and model learning behavior remain insufficiently understood. Method: This study evaluated spatial, intensity, and hybrid augmentation for kidney CT image classification using a custom CNN, MobileNetV2, and EfficientNet-B0. A public dataset containing 12,446 CT images across Normal, Cyst, Tumor, and Stone classes was partitioned using stratified sampling into training, validation, and test sets. Four scenarios—baseline, spatial, intensity, and hybrid augmentation—were evaluated across three independent random seeds using accuracy, precision, recall, F1-score, and AUC. Results and Discussion: The baseline achieved mean accuracies of 99.96%, 98.32%, and 94.06% for CNN, MobileNetV2, and EfficientNet-B0, respectively. Intensity augmentation slightly improved CNN accuracy to 99.99% and consistently produced smaller performance degradation and more stable convergence than spatial and hybrid augmentation. Spatial and hybrid transformations generally reduced classification performance, indicating that excessive geometric changes may disrupt diagnostically relevant anatomical features. Conclusion: Baseline training provided the best overall performance, while intensity augmentation was the most effective augmentation strategy, demonstrating that preserving anatomically meaningful image characteristics is more important than indiscriminately increasing data diversity.
Analisis Konsep Rancangan Produk Kartu Saku P3K Berbasis QR Code untuk Meningkatkan Nilai Fungsional, Ergonomi, dan Estetika Nabila Putri Aprilia Nur Cahyanti; Wardatul Elsa Bilbina; Putri Hajar Syalsabilah; Bertrand Okthaddeus; Vira Febrianti; Dafa Fadhilah Hilmi; Nashifa Maisun Nuhita; Ahmad Raziqi
LANCAH: Jurnal Inovasi dan Tren Vol. 3 No. 2 (2025): JUNI-NOVEMBER
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ljit.v3i2.5957

Abstract

This study aims to develop a functional, ergonomic P3K pocket card design that meets user needs and is in line with the latest product design developments. This P3K pocket card is designed as a practical health education medium for emergency use. The methods used are a combination of structured literature studies and a qualitative descriptive approach. The research involved a comprehensive review of scientific publications focusing on product design, ergonomics, and health technology from 2020 to 2025. This review aims to integrate important findings regarding function, aesthetics, ergonomics, and value of use in formulating the design principles of the P3K pocket card. Ergonomic principles (ease of use) and aesthetics (visual appeal) are the main focus of the design. The results of the study show that the proposed P3K Pocket Card design is able to effectively integrate clinical functions (essential P3K information), modern design aesthetics, and ergonomics (ease of carrying and access). This design produces an educational medium that is not only practical and accessible, but also increases the potential for P3K knowledge transfer among the general public and non-medical personnel.
Analisis Konsep Rancangan Produk NutriFarm Website Sebagai Inovasi Peternakan Masa Depan Vira Febrianti; Dafa Fadhilah Hilmi; Nashifa Maisun Nuhita; Ahmad Raziqi Raziqi; Devy Dwi Arianty; Izzatu Salisah Mafatihurrohmah; Maura Y’nauri Yasmin Hidayat; Hikam Muta’aly Al Isyraq
LANCAH: Jurnal Inovasi dan Tren Vol. 3 No. 2 (2025): JUNI-NOVEMBER
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ljit.v3i2.5959

Abstract

This study aims to review the latest literature on livestock nutrition, feed management, and digital technology developments in animal husbandry, and how these findings support the development of the NutriFarm Website as a web-based nutrition management platform. The results show that the main problems in livestock farming, especially on a small scale, include nutritional imbalances, high rates of metabolic diseases such as hypocalcemia due to calcium deficiency, and low literacy among farmers in feed management. On the other hand, digital technologies such as the Internet of Things (IoT), decision support systems, and feed automation have been proven to improve livestock efficiency and health, but their adoption remains low due to limited access and complexity of use. The literature synthesis confirms that simple and accessible digital platforms, such as the NutriFarm Website, have the potential to be practical solutions to help farmers calculate nutritional requirements, understand feed composition, and prevent diseases related to nutritional imbalances. This study concludes that the NutriFarm Website not only improves feed management efficiency but also strengthens farmer education and encourages the adoption of technology to support productivity and sustainability in Indonesia's livestock sector.  
Lightweight Deep Learning Models for Lung Disease Classification Using Chest X-ray Images Abdullah Sholum; Aji Prasetya Wibawa; Ardhana Putra Agustavada; Dafa Fadhilah Hilmi; Felix Andika Dwiyanto
ILKOM Jurnal Ilmiah Vol 18, No 2 (2026)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v18i2.3351.302-319

Abstract

Lung disease classification from chest X-ray images using deep learning has attracted significant attention due to its potential to support rapid and automated medical diagnosis. However, many deep learning models require high computational resources, limiting their applicability in resource-constrained environments. This study evaluates the effectiveness of lightweight deep learning architectures for lung disease classification using chest X-ray images consisting of COVID-19, Normal, and Pneumonia classes. Three architectures were comparatively analyzed, including a baseline Convolutional Neural Network (CNN), EfficientNetV2, and MobileNetV2. All models were trained and evaluated under identical preprocessing and experimental conditions using a dataset of 697 chest X-ray images with a 60:20:20 split ratio for training, validation, and testing. Experimental results show that EfficientNetV2 and MobileNetV2 achieved classification accuracy up to 0.99 with AUC-ROC values approaching 1.0. In terms of computational efficiency, both lightweight architectures reduced trainable parameters by approximately 99.3% compared to the baseline CNN, decreasing from 576,851 to 3,843 trainable parameters through transfer learning with frozen pretrained layers. MobileNetV2 achieved this performance with 0.613 GFLOPs and a model size of 9,435 KB, while EfficientNetV2 required 0.781 GFLOPs and 15,993 KB. Although EfficientNetV2 demonstrated slightly more stable performance, MobileNetV2 provided the most effective trade-off between classification accuracy and computational efficiency, making it more suitable for deployment in resource-constrained healthcare environments. These findings demonstrate the feasibility of lightweight deep learning architectures for efficient and reliable lung disease classification from chest X-ray images
Co-Authors Abdullah Sholum Ahmad Raziqi Ahmad Raziqi Raziqi Aji Prasetya Wibawa Ardha Ardhana Putra Agustavada Ardhana Putra Agustavada Bertrand Okthaddeus Devy Dwi Arianty Felix Andika Dwiyanto Hikam Muta’aly Al Isyraq Izzatu Salisah Mafatihurrohmah Maura Y’nauri Yasmin Hidayat Nabila Putri Aprilia Nur Cahyanti Nashifa Maisun Nuhita Putri Hajar Syalsabilah Vira Febrianti Wardatul Elsa Bilbina