JURNAL MEDIA INFOTAMA

Perancangan Aplikasi Steganografi Pada Citra Digital Menggunakan Algoritma Diversity Untuk Keamanan Pesan

Aji Legawa — 2026-10-12

The rapid advancement of digital technology and internet communication necessitates robust information security mechanisms that not only protect message content but also conceal the existence of the communication itself. Steganography provides an effective approach by embedding secret messages within digital media, particularly digital images. This study aims to design of Steganography Application in Digital Images Using the Diversity Algorithm for Message Security. The research adopts an applied research methodology with a system design and implementation approach. The Diversity algorithm is employed to exploit variations in pixel color values for embedding message bits, resulting in a more randomized embedding pattern that is resistant to detection and analysis. The experimental results demonstrate that the proposed system is capable of embedding and extracting text messages accurately without degrading the original image information. Furthermore, the steno-image maintains high visual quality, indicating good imperceptibility of the embedded data. In conclusion, the developed application proves to be an effective and reliable solution for secure message transmission using digital image-based steganography.

Penerapan Metode Probabilitas Symetric Pada Sistem Pakar Untuk Mendiagnosa Penyakit Tanaman Jamur Tiram

Dicky Firmansyah — 2026-10-12

Oyster mushrooms are a highly sought-after cultivated commodity due to their high economic value and relatively easy cultivation process. However, various diseases often occur during cultivation, which can reduce the quality and yield of the crop. The main problem faced by farmers is limited knowledge in quickly and accurately recognizing disease symptoms. Therefore, a system is needed to assist in the automatic diagnosis of oyster mushroom diseases. This study aims to design and build an expert system for oyster mushroom disease diagnosis using the Symmetric Probability method with the PHP programming language and a MySQL database. This system is designed to assist users in identifying the type of disease based on the symptoms experienced by oyster mushrooms. The Symmetric Probability method is used to calculate the likelihood level of a disease based on the probability value of each symptom selected by the user. The results show that the expert system is capable of providing a diagnosis of oyster mushroom diseases, along with a percentage value of the disease probability and treatment solutions. This system can facilitate farmers and cultivators in obtaining diagnostic information quickly, effectively, and efficiently without having to rely directly on experts.

Sistem Informasi Pengarsipan Data Skripsi Di Fakultas Ilmu Sosial Universitas Dehasen Bengkulu Berbasis Web

Rafid Ula Penta — 2026-10-14

Archiving is an important part of document management, especially in universities that produce theses every year as proof of students' academic abilities. The Faculty of Social Sciences at Dehasen University in Bengkulu still archives theses manually, which causes various problems such as difficulty in searching for data, the risk of losing documents, and inefficient archive management processes. Therefore, an archiving information system is needed that can store, manage, and display thesis data in a structured and easily accessible manner. This study aims to design and develop a web-based thesis data archiving information system at the Faculty of Social Sciences, Dehasen University Bengkulu. The methods used include data collection through observation and interviews, as well as system design stages using a structured development model. The result of this research is a web-based information system that can facilitate the process of archiving, searching, and managing thesis data, especially in the Communication Science Study Program. With this system, the archiving process becomes more effective and efficient compared to the manual management system that was previously used.

Analisis Pengguna Terhadap Sistem Informasi Pelaporan Keuangan (SIPELUK) Pada Kantor Kecamatan Kelapa Gading

Defira Patricia Defira Patricia — 2026-10-14

Sistem Informasi Pelaporan Keuangan (SIPELUK) pada Kantor Kecamatan Kelapa Gading. Penelitian ini dilatarbelakangi oleh pentingnya pemanfaatan teknologi informasi dalam mendukung transparansi, akuntabilitas, dan efisiensi pelaporan keuangan pada instansi pemerintahan. Metode penelitian yang digunakan adalah deskriptif kuantitatif dengan teknik pengumpulan data melalui kuesioner dan dokumentasi tampilan aplikasi. Sampel penelitian berjumlah lima responden yang dipilih menggunakan teknik purposive sampling berdasarkan keterlibatan langsung dalam penggunaan atau pengelolaan SIPELUK. Data dianalisis secara deskriptif dengan menghitung nilai rata-rata pada setiap indikator penilaian. Hasil penelitian menunjukkan bahwa SIPELUK memperoleh penilaian sangat baik dari pengguna, dengan rata-rata skor 5,00 pada aspek kemudahan akses, formulir input data, percepatan pelaporan, kelancaran teknis, keakuratan laporan, dukungan fitur, dan manfaat transparansi. Temuan ini menunjukkan bahwa SIPELUK mampu mendukung proses pelaporan keuangan secara lebih efektif, efisien, dan terstruktur. Meskipun pengguna tidak mengalami kendala teknis yang berarti, pengembangan sistem tetap diperlukan melalui penambahan fitur barcode, notifikasi, serta pembaruan tampilan aplikasi agar lebih optimal sesuai kebutuhan pengguna.

Pembuatan Alat Kontrol Suhu Pada Kandang Ayam Berbasis Internet of Things (IoT)

Bima Kusuma Wardana — 2026-10-15

This study aims to design and build an Internet of Things (IoT)-based temperature control device for broiler chicken cages. The system was developed to help farmers monitor temperature and humidity in real time and control a heating device remotely through a smartphone. The hardware consists of an ESP8266 microcontroller, DHT11/DHT22 temperature and humidity sensor, relay module, 40-watt incandescent lamp as the heater, LCD 16x2 display, power supply, and supporting electronic components. The software was developed using Arduino IDE and integrated with the Blynk IoT platform for monitoring and manual control. The research method used was experimental design with black-box testing on sensor detection, data transmission, relay response, and Blynk application performance. The test results show that sensor data were received within 1.8-2.1 seconds, while commands from Blynk were received within 2.5-2.7 seconds. The relay response to the heater ranged from 1.5 to 1.9 seconds, and the Blynk display response ranged from 2.3 to 2.9 seconds. These results indicate that the proposed system works properly for real-time temperature monitoring and automatic/manual heating control in a small-scale broiler cage simulation.

Penerapan Snort Dalam Mendeteksi Penyerangan Pada Sistem Keamanan Jaringan Komputer SMKN 2 Seluma

Ade Manza Putra — 2026-10-16

This research focuses on deploying Snort as an Intrusion Detection System (IDS) to fortify the computer network security at SMK Negeri 2 Seluma, specifically targeting the protection of school servers and network infrastructure. Empirical testing demonstrated that the system successfully detected Ping of Death attacks by identifying anomalous Internet Control Message Protocol (ICMP) traffic, consequently generating high-priority alerts. During malware evaluation, Snort effectively flagged the EICAR Standard Anti-Virus Test File when accessed through PowerShell; however, it failed to recognize the payload when downloaded via a standard web browser. Furthermore, the system successfully identified simulated W32/ProxyBack trojan activity executed via HTTP CONNECT communications using PowerShell, triggering maximum-priority alerts to indicate a critical threat level.

Implemetasi Machine Learning Metode K-Nearest Neighbor Untuk Memprediksi Status Kelulusan Mahasiswa Program Studi Informatika Universitas Dehasen Bengkulu

AL Kausar AH — 2026-10-16

Student graduation rates are a key performance indicator that’s really crucial for the quality and reputation of a university. However, study delays and the risk of dropping out are still serious challenges for the Informatics Study Program at Dehasen University Bengkulu. This research focuses on tackling these issues by developing an early prediction system for student graduation status to help support more proactive academic decision-making. This research uses an Educational Data Mining (EDM) approach with the Knowledge Discovery in Databases (KDD) framework to process student academic datasets. It implements the K-Nearest Neighbor (KNN) algorithm. Based on the testing results with the hyperparameter K=5, the KNN model achieved an accuracy rate of 50%, which indicates that the decision boundary between students who pass and those who don't cannot be significantly separated by the numeric academic variables currently used. This finding suggests that further development is needed by adding latent variables or sociological data, as well as more specific feature selection techniques to better capture student behavior patterns and improve the model's performance in the future.

Analisis Performa Algoritma Hierarchical Clustering Untuk Identifikasi Pola Kematian Ikan Lele Pada Budidaya Lele Tiga Saudara

Agung Amanda Pratama — 2026-10-18

Tiga Saudara Catfish Farm in Bengkulu City has experienced varying mortality rates across different cultivation periods; however, these patterns have not been systematically analyzed using a data-driven approach. This study aims to identify catfish mortality patterns using Agglomerative Hierarchical Clustering (AHC) method. The dataset consisted of 90 days of operational records, including water temperature, pH levels, and feed types. The analytical process followed the Knowledge Discovery in Databases (KDD) framework, encompassing data preprocessing through One-Hot Encoding and Min–Max normalization, Euclidean distance calculation, and the implementation of the AHC algorithm using Single, Average, and Complete Linkage methods. The results indicate that the Average Linkage method achieved the best performance, with a Cophenetic Correlation Coefficient (CCC) value of 0.9789. The optimal number of clusters was determined to be four (k=4) based on a Silhouette Score of 0.8175. These four clusters represent distinct operational conditions within the farming system, namely Safe, Alert, Critical, and Recovery conditions. The findings further reveal that the use of alternative feed derived from bread waste contributed to a decline in water pH levels to a range of 6.0–6.8 and a significant increase in fish mortality, resulting in a total loss of 1,465 fish and an estimated financial loss of IDR 1,044,000 per production cycle. Model validity testing through White-Box Testing produced a CCC value of 0.9789 and a Silhouette Score of 0.8175, both exceeding the predetermined acceptance thresholds. Furthermore, system functionality testing through Black-Box Testing on 14 test cases within the AHC pipeline and Power BI dashboard demonstrated a 100% success rate. The clustering results were visualized through an interactive Microsoft Power BI dashboard, providing risk maps, daily mortality trends, and cluster distributions as decision-support tools for catfish farmers. This enables rapid identification of risk conditions and facilitates preventive actions before mass mortality events occur

Penerapan Deep Learning Untuk Klasifikasi Penyakit Mata Menggunakan Metode Convolutional Neural Network

Alfarida Dewi Aprilia — 2026-10-18

Eye diseases such as cataracts, diabetic retinopathy, and glaucoma are among the leading causes of visual impairment and can result in blindness if not detected at an early stage. The application of Deep Learning technology, particularly Convolutional Neural Networks (CNNs), provides an opportunity to support the automatic classification of eye diseases based on retinal fundus images. This study aims to develop an eye diseaseclassification model using the EfficientNetB0 architecture with a transfer learning approach. The dataset used was the Eye Diseases Classification dataset from Kaggle, consisting of 4,217 retinal fundus images categorized into four classes: Cataract, Diabetic Retinopathy, Glaucoma, and Normal. Before the training process, the images underwent preprocessing, including image resizing, normalization, and data augmentation. The model was trained using the Tensor Flow/Keras framework in the Google Colab environment and evaluated using accuracy, precision, recall, F1-score, and confusion matrix metrics. The experimental results showed that the proposed model achieved an overall accuracy of 73.23%. The Cataract class demonstrated the best performance, with a precision of 0.78, a recall of 0.92, and an F1-score of 0.84. In contrast, the Glaucoma class obtained the lowest recall of 0.36, indicating that the model still encountered difficulties in correctly identifying a considerable number of glaucoma images. Overall, the results indicate that the EfficientNetB0 architecture is capable of classifying eye diseases from retinal fundus images with satisfactory performance. However, increasing the dataset size, optimizing preprocessing techniques, and applying more extensive fine-tuning are recommended to further improve the model's performance, particularly in glaucoma classification

Sistem Informasi Penyewaan Kamar Kost Berbasis Web

Putri Fajar Wati — 2026-10-19

The management and rental transaction processes at Kost Lineska are currently conducted manually, resulting in inefficiencies in tenant data recording, difficulties in confirming room availability, and a risk of errors in rental payment bookkeeping. This study aims to design and develop Web-Based Boarding House Room Rental Information System that transforms the rental management process into a computerized system, making it easier, more accurate, transparent, and wellorganized. The system was developed using the PHP programming language and a MySQL database. The results of the study successfully produced an online boarding house rental application that supports two user access levels, namely administrators and tenants. Through this system, boarding house managers can manage room data, verify rental applications, update payment statuses, and view monthly rental reports. Meanwhile, tenants can register accounts, view available rooms, submit rental requests, upload proof of payment transfers, and independently print payment receipts. Based on functional testing using the Black Box Testing method, all features of the application were proven to operate properly and successfully without any system errors. Therefore, the system is considered highly feasible for supporting convenient and integrated boarding house rental management.

E-Commerce Produk Minuman Pada Toko Minumin

Bobby Dwi Saputra — 2026-10-20

Commerce for Beverage Products at Minumin Shop is a web-based system designed to support the online sales process of beverage products. This research was motivated by the existing sales process, which was still conducted manually, requiring customers to visit the store directly to view the menu, inquire about prices, and place orders. This condition resulted in inefficient service, increased the risk of order-recording errors, and complicated the management of product data, transactions, and sales reports. The objective of this study is to develop an e-commerce system that facilitates consumers in obtaining product information, placing orders, making payments, and monitoring order status online. The system development method employed was Rapid Application Development (RAD), consisting of the phases of requirements planning, user design, construction, and implementation. The system was developed using the PHP programming language and MySQL database. The results of the study indicate that the system is capable of performing its main features, including login, member registration, product categories, product details, shopping cart, checkout, payment processing, invoice generation, order status tracking, notifications, transaction history, as well as sales, payment, and sold-product reports. Based on the results of Black Box testing, all system functions operated in accordance with the expected outputs. Therefore, the system can assist the sales process at Minumin Shop by making it easier, faster, more structured, and more efficient.

Klasifikasi Parameter Penyebab Kecelakaan Lalu Lintas Dengan Algoritma Decission Tree Di Wilayah Polresta Kota Bengkulu

Ronna Mutiara Maheswari Wahyudi — 2026-10-22

The Traffic accidents are a complex issue influenced by multiple factors, including human behavior, vehicle conditions, road characteristics, and environmental conditions. Historically, traffic accident data maintained by the Police Department of Bengkulu City have been utilized primarily for descriptive reporting, limiting their potential to reveal comprehensive patterns of accident causation. This study aims to identify the dominant factors contributing to traffic accidents, implement the Decision Tree C4.5 algorithm for accident classification, and evaluate the performance of the resulting classification model. This study used the Knowledge Discovery in Databases (KDD) methodology. The dataset consisted of historical traffic accident records obtained from the Jurisdiction of Bengkulu City Police. Data processing was conducted using Python in the Google Collaboratory environment through several stages, including exploratory data analysis (EDA), data preprocessing, model development, and performance evaluation. The results demonstrate that the proposed model successfully identified relationships among accident causative factors through the construction of a decision tree, generating 20 classification rules. Road Surface Condition was identified as the most influential predictor, with a feature importance value of 0.30, followed by Special Information (0.15), Speed Limit at the Accident Location (0.13), and Lighting Condition (0.10). Model evaluation showed an overall accuracy of 65.2%, with a weighted average F1-score of 75.9%, indicating satisfactory performance in classifying the majority classes. However, the macro average F1-score of 28.9% suggests that the model's performance on minority classes remains limited due to class imbalance in the dataset. This study is expected to provide a data-driven foundation for developing more effective traffic accident prevention and mitigation strategies in the Jurisdiction of Bengkulu City Police.

Optimalisasi Pencarian Data Menggunakan Algoritma B-TREE

Muhammad Yusuf — 2026-10-22

The performance of the information system at the Regional Library Agency of Bengkulu Province currently experiences responsiveness constraints, particularly in the book and membership data retrieval processes. This high latency is triggered by an increasing volume of data that is still processed using linear scanning or a full table scan method on the database. Therefore, this study aims to optimize query execution time through the design and implementation of the B-Tree indexing algorithm within a MySQL database management system environment. The execution of this research adopts the stages of the Waterfall method to ensure a structured implementation without rebuilding the system from scratch. Testing was executed through two approaches: Black Box functionality testing to validate user interface precision, and Performance Testing to comparatively analyze computational execution times between non-indexed and indexed tables. Empirical experimental results on a population of 10,000 data rows prove that the implementation of the B-Tree algorithm yields highly significant computational efficiency. The average execution time for book data searches was successfully reduced from 2.9651 milliseconds to 0.5895 milliseconds, creating an 80.12% increase in efficiency. In member data retrieval, the execution time was compressed from an average of 5.8076 milliseconds to 0.7430 milliseconds, achieving an efficiency surge of 87.21%. In conclusion, the application of the B-Tree indexing technique is quantitatively proven to resolve data processing latency bottlenecks. This optimization solution enables library circulation services to operate much more responsively and consistently, with waiting times under one millisecond.

Implementasi Metode Weighted Agregated Sum Product Assesment (WASPAS) Untuk Seleksi Penerimaan Beasiswa Prestasi Pada SMA Negeri 7 Bengkulu Selatan

Ande Alfa Dela — 2026-10-23

Scholarships are a form of recognition provided as financial assistance to individuals or organizations based on their achievements and performance. The provision of merit-based scholarships aims to enhance the quality of students' learning and academic performance. However, one of the main challenges in the scholarship selection process is conducting objective evaluations, as the assessment involves multiple criteria, including students' academic abilities and participation in school activities. To address this challenge, a Decision Support System (DSS) employing the Weighted Aggregated Sum Product Assessment (WASPAS) method was developed to assist decision-makers in the scholarship selection process. The WASPAS method minimizes assessment errors and optimizes the ranking process by accurately determining the highest- and lowest-scoring candidates. The system was implemented using the PHP programming language and a MySQL database, while the software development process followed the Waterfall methodology. The results of system testing indicate that the WASPAS-based Decision Support System effectively performs the ranking process and supports the selection of merit scholarship recipients accurately and efficiently.

Sistem Pendukung Keputusan Penerimaan Beasiswa Dengan Metode SAW (Simple Additive Weighting) Dan Electre (Elimination Et Choix Traduisant La Réalité) Pada Pondok Pesantren Darul Amal

Candra Handika — 2026-10-23

Scholarship awards are one of the efforts to support academically outstanding students who face financial constraints. At Darul Amal Islamic Boarding School, the scholarship selection process is still conducted manually, making it susceptible to subjectivity, limited transparency, and relatively lengthy processing times. Therefore, a Decision Support System (DSS) is needed to facilitate the selection of scholarship recipients in an objective, efficient, and accurate manner. This study aims to design and develop a Decision Support System for scholarship selection by implementing the Simple Additive Weighting (SAW) and Elimination Et Choix Traduisant La Realité (ELECTRE) methods at Darul Amal Islamic Boarding School. The evaluation criteria include students' average academic report scores, number of parental dependents, and parents' income. The SAW method is employed to calculate preference values through normalization and weighting processes, while the ELECTRE method is used to select alternatives based on the concepts of concordance and discordance. The system was developed using the PHP programming language with a MySQL database and followed the System Development Life Cycle (SDLC) methodology. The results demonstrate that the developed system effectively supports the scholarship selection process by making it more efficient, transparent, and objective. Based on the SAW calculation results, a ranking of scholarship candidates was generated, providing recommendations to assist the boarding school in identifying the most eligible scholarship recipients. The implementation of the SAW and ELECTRE methods produces more objective decisions because the evaluation is based on predetermined criteria and weights. In conclusion, the developed system provides reliable decision support for the scholarship selection process, ensuring that scholarship awards are determined in a fair, accurate, transparent, and accountable manner.

Sistem Pakar Untuk Diagnosa Penyakit Kardiovaskular (Jantung Dan Pembuluh Darah) Menggunakan Metode Dempster Shafer

Bima Defriansyah — 2026-10-23

Cardiovascular system plays a vital role in the human body, as no cells or tissues can function properly without an adequate supply of oxygen and blood. When the cardiovascular system is impaired, the entire body is affected. Cardiovascular diseases, particularly heart and blood vessel disorders, are among the most common health problems experienced by the general population. To assist the public and healthcare professionals in providing education, consultation, and awareness regarding cardiovascular diseases, this study designed and developed an expert system application by implementing the Dempster–Shafer method. The Dempster–Shafer method determines the degree of belief based on the symptoms experienced by the user and combines evidence from multiple symptoms to calculate the probability of the cardiovascular disease being diagnosed. The final outcome of this research is an expert system capable of diagnosing cardiovascular diseases using the Dempster–Shafer method and providing the probability value for each diagnosis, representing the system's level of confidence in the identified disease. The developed system is expected to support preliminary diagnosis and improve public awareness of cardiovascular diseases while serving as a decision-support tool for healthcare professionals

Analisis Kesenjangan (Gap Analysis) Keamanan Informasi pada Instansi Pemerintah Indonesia Berdasarkan Indeks KAMI 5.0 dan Standar Internasional

Dimas Ahsanul Habibi — 2026-10-24

Penelitian ini bertujuan menganalisis kesenjangan (gap analysis) keamanan informasi pada instansi pemerintah di Indonesia menggunakan Indeks Keamanan Informasi (KAMI) versi 5.0 yang dikembangkan oleh Badan Siber dan Sandi Negara (BSSN). Evaluasi difokuskan pada tiga aspek utama, yaitu tata kelola keamanan informasi, pengelolaan risiko, dan kerangka kerja keamanan informasi, kemudian dibandingkan dengan persyaratan ISO/IEC 27001:2022 serta NIST Cybersecurity Framework (CSF). Hasil analisis menunjukkan bahwa sebagian besar instansi pemerintah masih berada pada tingkat kematangan dasar dengan nilai rata-rata 450 dari total 645 poin. Kesenjangan yang paling signifikan ditemukan pada aspek pengelolaan risiko, implementasi pengendalian keamanan, serta mekanisme pemantauan dan evaluasi yang belum sepenuhnya memenuhi standar internasional. Kondisi tersebut menunjukkan bahwa penerapan keamanan informasi masih memerlukan penguatan, baik dari sisi kebijakan, tata kelola, maupun pengendalian teknis untuk meningkatkan efektivitas perlindungan aset informasi. Berdasarkan temuan tersebut, penelitian ini merekomendasikan penguatan manajemen risiko, peningkatan kepatuhan terhadap ISO/IEC 27001:2022, optimalisasi penerapan NIST CSF, serta pengembangan kompetensi sumber daya manusia sebagai langkah strategis dalam meningkatkan tingkat kematangan keamanan informasi di lingkungan instansi pemerintah Indonesia.