Claim Missing Document
Check
Articles

Found 17 Documents
Search

Klasifikasi Kanker Payudara Berbasis Deep Learning Menggunakan Vision Transformer dengan Teknik Augmentasi Data Citra Ardiyansyah, Muhamad Salman; Umbara, Fajri Rakhmat; Melina, Melina
JURNAL RISET KOMPUTER (JURIKOM) Vol. 12 No. 3 (2025): Juni 2025
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v12i3.8619

Abstract

Breast cancer ranks among the leading causes of death in women worldwide. Early detection through mammographic image analysis plays a crucial role in increasing survival rates. However, manual interpretation of mammograms requires expert knowledge and is prone to errors. This study aims to develop a breast cancer classification model using mammography images based on the Vision Transformer (ViT) architecture without employing transfer learning. The dataset used is the Digital Database for Screening Mammography (DDSM), consisting of two categories: benign and malignant. To address class imbalance, undersampling and data augmentation techniques (flipping, rotation, cropping, and noise injection) were applied. All images were normalized and resized to 224×224 pixels to match the ViT input requirements. The model was trained for five epochs with a batch size of 16. Evaluation on the test data was conducted using seven metrics: accuracy, precision, recall, F1-score, Matthews Correlation Coefficient (MCC), Cohen’s Kappa Score, and Area Under the Curve (AUC). The results show that the model achieved an accuracy of 92.50%, precision of 90.48%, recall of 95.00%, F1-score of 92.68%, MCC of 85.11%, Kappa Score of 85.00%, and AUC of 95.75%. These findings indicate that the Vision Transformer is highly effective for mammographic image classification and holds potential as a reliable tool for automated breast cancer diagnosis support.
Prediksi Risiko Kesehatan Mental Mahasiswa Menggunakan Klasifikasi Naive Bayes Sumantri, Fithra Aditya; Chrisnanto, Yulison Herry; Melina, Melina
JURNAL RISET KOMPUTER (JURIKOM) Vol. 12 No. 3 (2025): Juni 2025
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v12i3.8648

Abstract

The mental health of university students is a growing concern as academic, emotional, and social pressures contribute to increased psychological risks. This study aims to classify mental health risk levels Low, Medium, and High among students using the Naïve Bayes classification algorithm. A dataset consisting of 1,000 entries and 11 key variables was utilized, covering academic, psychological, and behavioral factors. The preprocessing stage included data cleaning, label encoding, normalization, and rule-based labeling to determine the target classes. Model training and testing were conducted using stratified data splitting to preserve class distribution. The initial model achieved a classification accuracy of 88,67%, with macro average F1-score of 0.87 and weighted average F1-score of 0.88. Grid Search optimization with k-fold cross-validation was applied but showed no significant improvement, indicating the model was already in optimal configuration. Furthermore, probabilistic analysis revealed that Sleep Quality and Study Stress Level were the most influential features in predicting mental health risks. The findings suggest that Naïve Bayes is effective for multi-class classification with interpretable results. This research contributes to early detection efforts and offers a foundation for targeted interventions in university mental health management.
Rancang Bangun AWS Node Untuk Monitoring Lingkungan Berbasis Lora AS923-2 Guna Mendukung Penelitian Integrated Smart Farming Di Laboratorium Inacos Universitas Tekom Melina, Melina; Darlis, Denny; Ardianto Primadhi, Rizki
eProceedings of Applied Science Vol. 9 No. 1 (2023): Februari 2023
Publisher : eProceedings of Applied Science

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

ikatakan memiliki cuaca dan iklim yang khusus dan rumit. karena Indonesia berada pada daerah garis khatulistiwa, berbatasan dengan dua samudera yaitu Samudera Hindia dan Samudera Pasifik [1]. Keunikan cuaca dan iklim yang dimilikinya ini juga menyebabkan kondisi cuaca akan sangat berpengaruh terhadap kondisi Lingkungan. Maka pengamatan cuaca sangat diperlukan untuk dijadikan bahan memperkirakan cuaca pada waktu yang akan datang. Data cuaca juga bisa dimanfaatkan untuk instasi yang membutuhkan data cuaca seperti salah satunya pada bidang pertanian dan perkebunan [2]. Untuk mengukur cuaca dengan sistem pengamatan secara otomatis maka dibuatlah AWS [3]. Rancang bangun AWS menggunakan Lora AS923-2 sebagai pemanfaatan teknologi Lora AS923-2 untuk keperluan lingkungan penelitian. Melalui pemanfaatan Integrated Smart Farming Sistem dapat memberikan nilai tambah ekonomi dan mendorong perekonomian pertumbuhan saat ini dan dapat memanfaatkan sejumlah kecil perangkat tertentu [2]. Untuk merancang suatu sistem Automatic Weather Station dengan menggunakan modul komunikasi wireless untuk mempermudah pemantauan cuaca pada lingkungan dan lahan perkebunan pemodelan sistem ini menggunakan sensor suhu dan kelembaban, sensor tekanan udara, sensor cahaya, sensor curah hujan, sensor arah angin, serta kecepatan angin. Dari semua node data akan dikirimkan ke gateway untuk dipantau [4].Kata kunci — lingkungan, integrated smart farming, authomatic weather station, lora-AS923-2
QUESTION BANK SECURITY USING RIVEST SHAMIR ADLEMAN ALGORITHM AND ADVANCED ENCRYPTION STANDARD Monica, Taris; Hadiana, Asep Id; Melina, Melina
JIKO (Jurnal Informatika dan Komputer) Vol 7, No 3 (2024)
Publisher : Universitas Khairun

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33387/jiko.v7i3.8654

Abstract

Data security is essential. Educational question banks at vocational high schools (SMK) contain confidential information that could be misused if not properly secured. This research aims to ensure students question bank data and develop a responsive web platform for Pusdikhubad Cimahi Vocational School by implementing the integration of the Advanced Encryption Standard (AES) and Rivest Shamir Adleman (RSA) cryptographic algorithms through the encryption and decryption process. AES is a symmetric key cryptography algorithm, while RSA is an encryption algorithm based on using public keys to encrypt the keys required by AES-256. The integration of these two algorithms aims to ensure data confidentiality, prevent manipulation, and facilitate access to exam materials by authorized parties. This research shows that the process of encrypting and decrypting question data using a combination of RSA and AES was successfully carried out on the question bank system. Avalanche Effect testing shows that the RSA and AES 256-bit encryption has an Avalanche Effect level of 49.99%. Apart from that, the system feasibility test using black box testing results shows that the SIFILE system has a percentage level of 100%. It is hoped that the results of this research can serve as a data security system at Pusdikhubad Cimahi Vocational School and other educational institutions to secure the question bank from unauthorized access
Prediksi Curah Hujan Menggunakan Metode Bi-LSTM dan GRU Berbasis Data Iklim Abdillah, Fajrul; Hadiana, Asep Id; Melina, Melina
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2305

Abstract

As a tropical country, Indonesia faces great challenges in predicting rainfall due to increasingly dynamic climate change. This study aims to predict rainfall in an urban area in West Java with tropical climate characteristics using deep learning methods, namely Bidirectional Long Short-Term Memory (Bi-LSTM) and Gated Recurrent Unit (GRU) based on climate data collected from local meteorological stations. The results show that the Bi-LSTM method provides more stable prediction performance with a Mean Absolute Error (MAE) value of 0.0108 and a Root Mean Squared Error (RMSE) of 0.0158. In contrast, the GRU method produced variable performance with higher MAE and RMSE values in some test scenarios. The main findings of this study indicate that the BiLSTM model has a higher level of accuracy, making it an effective information technology solution to support disaster mitigation and agricultural sector planning in climatically complex regions.
Klasifikasi Penyakit Monkeypox dengan XGBoost dan SMOTE untuk Penanganan Data Tidak Seimbang Illawati, Adinda Rahma; Hadiana, Asep Id; Melina, Melina
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2349

Abstract

Monkeypox merupakan penyakit menular yang penyebarannya cepat dan memerlukan sistem deteksi dini yang akurat. Penelitian ini bertujuan mengembangkan model klasifikasi penyakit monkeypox dengan mengatasi permasalahan ketidakseimbangan data. Metode yang digunakan adalah Extreme Gradient Boosting (XGBoost) yang dikombinasikan dengan teknik Synthetic Minority Over-sampling Technique (SMOTE). Evaluasi model menggunakan Confusion Matrix dengan hasil akurasi 69%, presisi sebesar 0.69, recall sebesar 0.93, dan F1-score sebesar 0.79. Selain itu, nilai Area Under Curve - Receiver Operating Characteristic (AUC-ROC) mencapai 0.68. Penelitian ini menunjukkan bahwa kombinasi SMOTE dan XGBoost dapat mengatasi ketidakseimbangan data dan meningkatkan deteksi kelas minoritas, sehingga memberikan kontribusi dalam pengembangan sistem deteksi dini penyakit menular secara lebih akurat dan efisien.
Evaluasi Kualitas Klaster Wilayah Rawan Bencana Menggunakan K-Means dengan Silhouette dan Elbow Method Sudrajat, Risqi; Hadiana, Asep Id; Melina, Melina
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2379

Abstract

Natural disasters such as floods, earthquakes, and landslides are recurring threats in Cirebon City, West Java. This study aims to classify disaster-prone areas using the K-Means algorithm based on 1,144 incident data from Open Data Jabar. The data were grouped into three clusters, namely safe, moderate, and dangerous. Cluster quality was evaluated using the Silhouette Score and Elbow Method. The results of this study show that the model without normalization produced a score of 0.6804, reflecting good cluster separation. Conversely, the application of MinMaxScaler normalization significantly reduced the model's performance, with a score of 0.3900. The main contribution of this study is to show that data normalization can disrupt the natural pattern of risk distribution, thereby reducing the quality of clustering. Therefore, the selection of pre-processing techniques needs to be adjusted to the characteristics of local data. It is hoped that this study can be the basis for the development of a more adaptive and data-driven disaster mitigation decision support system.