RESKOM: Jurnal Rekayasa Sistem Komputer

ANALYSIS OF ANTHRACHNOSE DISEASE DETECTION IN MELON PLANTS USING THE CONVOLUTIONAL NEURAL NETWORK (CNN) METHOD

2026-06-13T16:26:07+00:00

ANALISIS PENDETEKSIAN PENYAKIT ANTRAKNOSA PADA TANAMAN BUAH MELON DENGAN MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK (CNN)

Performance Evaluation of Whale Optimization Algorithm and Bald Eagle Search in Predictive Housing Price Modeling

2026-06-16T17:44:43+00:00

Accurate housing price prediction remains a critical challenge in real estate analytics, requiring models capable of capturing nonlinear relationships among structural, amenity, and economic features. This study evaluates the performance of the Whale Optimization Algorithm (WOA) and the Bald Eagle Search (BES) when integrated into a K-Nearest Neighbors (KNN) regression framework. Using a Kaggle housing dataset enriched with attributes such as area, bedrooms, bathrooms, and local economic indicators, the models were optimized and benchmarked against a baseline KNN. Experiments conducted in Google Colab assessed predictive accuracy using Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and the coefficient of determination (R²). Results show that the baseline KNN achieved an MAE of 193.97, RMSE of 265.23, and R² of 0.5705, reflecting moderate accuracy. The WOA-KNN model slightly increased MAE to 196.33 but reduced RMSE to 261.71, improving R² to 0.5818. Similarly, BES-KNN produced identical values to WOA-KNN, confirming comparable optimization outcomes. These findings demonstrate that metaheuristic-driven models enhance predictive stability and explanatory power, with WOA-KNN showing the most consistent error distribution. The study contributes to bridging the gap in comparative evaluations of WOA and BES, offering practical insights into the trade-off between exploration and exploitation strategies for reliable housing price forecasting.

Realtime Face Detection in Online Exam using Mobile Phone

2026-06-18T01:19:43+00:00

Currently, almost all human activities have been implemented with applications, one of which is the implementation of examinations, after the covid-19 pandemic, online examinations have begun to be widely used by many educational institutions, online examinations generally use computers that require a lot of devices and rooms for infrastructure. This research aims to create an online exam system that is simple and easy to do by utilising mobile devices. This system utilises the face recognition feature for security and minimises the occurrence of cheating with the method used is FaceNet. The system architecture is built with 3 different systems, namely, the training system and face detection uploaded to the server with the availability of API, the admin system made with Website-based, and the online exam system with mobile-based. The results of face detection carried out have been successful with an average percentage of 84.65%, face detection is carried out when going to do the exam and every 1 minute during the exam.

Analisis Manajemen Risiko Pada SITASI Menggunakan Framework OCTAVE Allegro

2026-06-19T08:31:20+00:00

Sistem Informasi Tugas Akhir (SITASI) merupakan sistem yang digunakan untuk mendukung pengelolaan proses tugas akhir mahasiswa, mulai dari pengajuan judul, penentuan dosen pembimbing, proses bimbingan, hingga pengelolaan data seminar dan sidang. Sebagai sistem yang menyimpan dan mengelola berbagai data penting akademik, SITASI memiliki potensi risiko yang dapat memengaruhi keamanan, integritas, dan ketersediaan informasi. Risiko tersebut dapat berasal dari kesalahan pengguna, kegagalan sistem, gangguan jaringan, maupun ancaman keamanan siber yang dapat menghambat proses akademik. Penelitian ini bertujuan untuk menganalisis manajemen risiko pada Sistem Informasi Tugas Akhir (SITASI) menggunakan framework Operationally Critical Threat, Asset, and Vulnerability Evaluation (OCTAVE) Allegro. Metode OCTAVE Allegro digunakan karena berfokus pada identifikasi aset informasi kritis, analisis ancaman, penilaian dampak risiko, serta penyusunan rekomendasi mitigasi yang sesuai dengan kebutuhan organisasi. Tahapan penelitian meliputi identifikasi aset informasi, penentuan kebutuhan keamanan, identifikasi ancaman dan kerentanan, analisis dampak, serta penentuan tingkat risiko berdasarkan konsekuensi yang ditimbulkan terhadap operasional sistem. Hasil analisis menunjukkan bahwa aset informasi kritis pada SITASI meliputi database akademik, server aplikasi, data pengguna, portal SITASI, dan dokumen konfigurasi sistem. Risiko dengan tingkat prioritas tertinggi yang teridentifikasi adalah serangan ransomware pada server database dengan skor risiko 40, kebocoran data akibat celah SQL Injection dengan skor risiko 39, serta downtime sistem pada periode penggunaan tinggi dengan skor risiko 38. Berdasarkan hasil tersebut, direkomendasikan penerapan pengendalian berupa Web Application Firewall (WAF), parameterized query, strategi backup 3-2-1, segmentasi jaringan, penguatan keamanan endpoint, serta peningkatan kapasitas infrastruktur sistem. Dengan penerapan framework OCTAVE Allegro, organisasi diharapkan dapat mengelola risiko keamanan informasi secara lebih efektif sehingga keamanan, keandalan, dan keberlangsungan layanan Sistem Informasi Tugas Akhir dapat terjaga dengan baik.

Smart Campus Analytics for Machine Learning Approaches to Student Stress, Anxiety, and Depression Prediction

2026-06-24T20:03:35+00:00

Accurate prediction of student depression levels is a critical challenge in educational analytics, requiring models capable of capturing nonlinear relationships among demographic, behavioral, and academic features. This study evaluates the performance of the Particle Swarm Optimization (PSO) algorithm when integrated into a K‑Nearest Neighbors (KNN) framework for regression and classification tasks. Using a student mental health dataset enriched with attributes such as sleep duration, screen time, physical activity, CGPA, and attendance, the models were optimized and benchmarked against a baseline KNN. Experiments conducted in Google Colab assessed predictive accuracy using Mean Squared Error (MSE), Coefficient of Determination (R²), and classification metrics including Confusion Matrix, Precision, Recall, and F1‑score. Results show that the baseline KNN achieved an accuracy of 61%, MSE of 7.86, and R² of 0.66, reflecting moderate predictive capability. The KNN‑PSO model, optimized to , improved accuracy to 64%, reduced MSE to 7.40, and increased R² to 0.68, demonstrating enhanced stability and explanatory power. These findings confirm that metaheuristic‑driven optimization strengthens the robustness of KNN models, yielding more reliable predictions across depression severity levels. The study contributes to bridging the gap in comparative evaluations of PSO‑based optimization for student mental health analytics, offering practical insights into the trade‑off between exploration and exploitation strategies for reliable predictive modeling.

Analisis Sentimen Ulasan Pengguna WhatsApp Indonesia pada Google Play Store Menggunakan Algoritma Naïve Bayes

2026-06-29T05:54:54+00:00

WhatsApp merupakan salah satu aplikasi pesan instan yang paling banyak digunakan di Indonesia, dengan jutaan ulasan pengguna yang tersedia di Google Play Store. Besarnya volume ulasan tersebut menjadikan analisis secara manual tidak memungkinkan untuk dilakukan, sehingga diperlukan pendekatan otomatis untuk memahami sentimen pengguna secara efisien. Penelitian ini bertujuan untuk menganalisis sentimen ulasan pengguna WhatsApp Indonesia di Google Play Store menggunakan algoritma Naive Bayes. Sebanyak 68.506 ulasan berbahasa Indonesia dikumpulkan melalui teknik web scraping menggunakan pustaka Google Play Scraper. Data kemudian melalui enam tahapan preprocessing meliputi cleaning, case folding, normalisasi, tokenizing, stopword removal, dan stemming. Pelabelan data dilakukan menggunakan pendekatan berbasis leksikon dengan memanfaatkan kamus InSet Lexicon yang terdiri atas 10.220 kata. Pembobotan fitur dilakukan menggunakan metode Term Frequency-Inverse Document Frequency dengan 5.000 fitur, dan data dibagi dengan rasio 80% data latih dan 20% data uji. Hasil klasifikasi Multinomial Naive Bayes menunjukkan bahwa sentimen negatif mendominasi dengan persentase 46,45%, diikuti sentimen positif sebesar 27,79%, dan sentimen netral sebesar 25,76%. Model yang dibangun menghasilkan akurasi sebesar 70,72%, dengan nilai precision 71,54%, recall 70,72%, dan F1-score 68,55%. Temuan ini mengindikasikan bahwa sebagian besar pengguna WhatsApp di Indonesia cenderung mengungkapkan ketidakpuasan terkait permasalahan teknis seperti spam dan pemblokiran akun. Penelitian ini berkontribusi dalam memahami persepsi pengguna terhadap aplikasi komunikasi berskala besar dan memberikan wawasan yang berguna bagi pengembang WhatsApp dalam meningkatkan kualitas layanan aplikasi.

Analisis Manajemen Risiko IT Pada Sistem Informasi Apotek XYZ Menggunakan ISO 31000

2026-06-30T16:08:44+00:00

The advancement of information technology is unavoidable and necessary in all aspects of human life. The use of information technology makes work easier to perform, but it also introduces risks that can threaten the activities of an organization. Pharmacy X has implemented a Pharmacy Information System (PIS) to enhance pharmacy administrative services, such as prescription management, medication inventory, patient data entry, doctor scheduling, and payment processing. Through interviews, potential risks that could disrupt the business processes at the pharmacy were identified. This study aims to obtain the Risk Priority Number (RPN) to provide risk treatment recommendations for the Pharmacy Information System (PIS). The method used is ISO 31000 to measure the level of risk. The research stages include risk identification, risk analysis, RPN calculation, risk evaluation, and risk treatment. This study results in a ranking of risks from highest to lowest that can be used as a reference for evaluation, treatment, and recommendations to mitigate those risks