cover
Contact Name
Ardi Susanto
Contact Email
ardisusanto@poltektegal.ac.id
Phone
-
Journal Mail Official
informatika.ejournal@poltektegal.ac.id
Editorial Address
Gedung B, Politeknik Harapan Bersama, Jl Mataram No 9 Pesurungan Lor Kota Tegal
Location
Kota tegal,
Jawa tengah
INDONESIA
Jurnal Informatika: Jurnal Pengembangan IT
ISSN : 24775126     EISSN : 25489356     DOI : https://doi.org/10.30591
Core Subject : Science,
The scope encompasses the Informatics Engineering, Computer Engineering and information Systems., but not limited to, the following scope: 1. Information Systems Information management e-Government E-business and e-Commerce Spatial Information Systems Geographical Information Systems IT Governance and Audits IT Service Management IT Project Management Information System Development Research Methods of Information Systems Software Quality Assurance 2. Computer Engineering Intelligent Systems Network Protocol and Management Robotic Computer Security Information Security and Privacy Information Forensics Network Security Protection Systems 3. Informatics Engineering Software Engineering Soft Computing Data Mining Information Retrieval Multimedia Technology Mobile Computing Artificial Intelligence Games Programming Computer Vision Image Processing, Embedded System Augmented/ Virtual Reality Image Processing Speech Recognition
Articles 487 Documents
Sistem Informasi Identifikasi Faktor Yang Mempengaruhi Prestasi Siswa Man Karo Menggunakan Pendekatan Data Mining Ai Siti Mariam
Jurnal Informatika: Jurnal Pengembangan IT Vol 11, No 1 (2026)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v11i1.10035

Abstract

Prestasi akademik siswa merupakan indikator utama keberhasilan proses pembelajaran. Pencapaian prestasi ini dipengaruhi oleh beragam faktor internal (seperti motivasi, gaya belajar, dan kehadiran) dan faktor eksternal (seperti dukungan orang tua dan fasilitas belajar). Penelitian ini bertujuan untuk mengidentifikasi faktor-faktor penentu prestasi akademik siswa dengan menerapkan sistem informasi berbasis web menggunakan algoritma Apriori. Penelitian ini menggunakan pendekatan deskriptif kuantitatif dengan data dari 300 siswa MAN Karo, yang dikumpulkan melalui kuesioner dan catatan akademik. Algoritma Apriori diterapkan dengan parameter dukungan minimum 0,05 dan kepercayaan minimum 0,6, menghasilkan total 1.621 aturan asosiasi. Hasil menunjukkan bahwa kombinasi faktor eksternal dan internal berkorelasi kuat dengan prestasi tinggi. Aturan asosiasi terkuat mengindikasikan bahwa siswa yang mengikuti bimbingan belajar (Les=Ya) mencapai nilai rapor tinggi (≥85) dan memiliki fasilitas lengkap dengan tingkat kepercayaan 67,6% dan rasio lift 3,12. Secara keseluruhan, baik faktor internal (seperti motivasi 77,33% dan kehadiran tinggi 63,67%) maupun faktor eksternal berkontribusi signifikan terhadap peningkatan prestasi akademik siswa.
Optimalisasi Rute Distribusi di Kantor Pos Berbasis Capacitated Vehicle Routing Problem Menggunakan Algoritma Genetika Ismawati Ainol Robbi; Achmad Mufliq; Syahri Mu'min
Jurnal Informatika: Jurnal Pengembangan IT Vol 11, No 2 (2026)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v11i2.10274

Abstract

In the logistics sector, distribution plays a crucial role as it directly affects operational costs and delivery time efficiency. The Sidoarjo Branch Post Office is one of the logistics service providers with a wide delivery coverage area. However, it still faces several issues, particularly suboptimal delivery routes and an imbalance in workload distribution among couriers. Therefore, this study aims to optimize delivery routes by considering vehicle capacity and workload balancing using the Capacitated Vehicle Routing Problem (CVRP) approach combined with a Genetic Algorithm. The Genetic Algorithm was selected due to its ability to explore a wide solution space and avoid being trapped in local optima. The process includes population initialization, fitness evaluation, selection, crossover, mutation, and the generation of new populations. The CVRP model is applied to minimize total travel distance while considering constraints such as vehicle capacity, customer visits, and workload distribution among couriers. The results show that the proposed approach produces shorter delivery routes compared to the manual method, achieving a distance reduction of 19.9%. In addition, the number of required couriers is reduced from 13 to 10 without exceeding capacity constraints. The developed web-based decision support system is able to present comparisons before and after optimization, distribute workloads more evenly, reduce the number of active couriers, and provide route recommendations for each courier. Overall, the proposed approach proves to be effective in improving operational efficiency and performance at the Sidoarjo Branch Post Office.
Analisis Sentimen pada Implementasi Pembelajaran Berbasis AI : Studi Kasus Persepsi Mahasiswa dan Dosen di Institusi Swasta Fathoni Mahardika
Jurnal Informatika: Jurnal Pengembangan IT Vol 11, No 1 (2026)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v11i1.9069

Abstract

Penelitian ini mengevaluasi persepsi publik terhadap implementasi Kecerdasan Buatan (Artificial Intelligence/AI) dalam lingkungan pembelajaran di institusi pendidikan swasta. Dengan pendekatan Pemrosesan Bahasa Alami (Natural Language Processing/NLP), penelitian ini melakukan analisis sentimen terhadap tanggapan yang dikumpulkan melalui survei daring dari mahasiswa dan dosen. Tahapan pra-pemrosesan data mencakup case folding, tokenisasi, penghapusan stopword, stemming, dan vektorisasi menggunakan Term Frequency-Inverse Document Frequency (TF-IDF). Model klasifikasi Logistic Regression digunakan untuk mengelompokkan data ke dalam tiga kategori sentimen: positif, netral, dan negatif. Hasil evaluasi menunjukkan bahwa model mencapai akurasi sebesar 88,24% pada data uji. Sebagian besar responden menunjukkan pandangan positif terhadap pembelajaran berbasis AI, meskipun masih terdapat kekhawatiran mengenai kesenjangan akses digital dan efektivitas metode pembelajaran. Temuan ini memberikan masukan strategis bagi institusi pendidikan dalam merancang kebijakan adopsi AI yang inklusif dan efektif di lingkungan akademik.
Automatic Pneumonia Detection Using Deep Convolutional Neural Network on Chest X-Ray Image Rio dhiya udin; Sugiyanto, Sugiyanto,
Jurnal Informatika: Jurnal Pengembangan IT Vol 11, No 2 (2026)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v11i2.10214

Abstract

Pneumonia is an acute respiratory infection that causes approximately 2.5 million deaths annually worldwide, with the highest burden occurring in developing countries. Early and accurate diagnosis using chest X-rays is crucial, but requires radiological expertise that is often scarce in resource-limited settings. This study developed an automated pneumonia detection system based on a Deep Convolutional Neural Network (CNN) with an architecture comprising five progressive convolutional blocks. The model was trained using the Chest X-Ray Pneumonia dataset from Kaggle, which contains 5,863 paediatric chest X-ray images. The implementation includes image pre-processing (conversion to greyscale, resizing to 150×150 pixels, and normalisation), real-time data augmentation (rotation ±30°, zoom ±20%, translation ±10%, and horizontal flipping), as well as regularisation techniques including batch normalisation and a dropout layer to reduce overfitting. The network utilises progressively increasing filter sizes (32-64-64-128-256), optimised via RMSprop with an adaptive learning rate scheduling mechanism. Evaluation results on 624 test images show an accuracy of 90.71% with a sensitivity of 91.54% for pneumonia detection. The model achieves a precision of 93% for the pneumonia class and 86% for the normal class, indicating balanced performance. The confusion matrix shows 357 true positives, 209 true negatives, 25 false positives, and 33 false negatives. This study demonstrates that deep learning approaches can serve as effective diagnostic tools for radiologists, particularly in medical centres with limited radiology expertise. 
Perbandingan Bcrypt, Argon2, dan PBKDF2 pada Keamanan SIMPEG Berbasis Web Muchamad Gilang Dwi Saputra; Denar Regata Akbi
Jurnal Informatika: Jurnal Pengembangan IT Vol 11, No 2 (2026)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v11i2.10280

Abstract

Password security is an important aspect of the web-based Employee Management Information System (SIMPEG) because this system contains user data and sensitive employee information. This study aims to compare the performance and security resilience of the Bcrypt, Argon2, and PBKDF2 algorithms using the SIMPEG authentication module. The method used is applied experimentation where the three algorithms are implemented in the registration and login processes, using a dataset of 200 synthetic passwords divided into four levels of complexity. Performance testing is based on hashing time, verification time, hash length, and resource usage. Security testing has been conducted with a dictionary attack simulation using Hashcat, NVIDIA RTX 3060 6 GB GPU, and a 5000-password wordlist. The test results show that the lowest hashing and verification times are for PBKDF2, which are 226.007 ms and 228.536 ms, followed by Bcrypt with 317.610 ms and 320.693 ms. Argon2 has the highest processing times with 1403.172 ms for hashing and 1198.050 ms for verification. However, Argon2 has the best resistance to dictionary attacks with a cracking time of 6 hours and 35 minutes and a hash rate of 19 H/s, better than Bcrypt and PBKDF2. Thus, Argon2 is recommended for SIMPEG with a higher priority on password security, while Bcrypt can be a more balanced alternative between security and performance.
Deteksi Fertilitas Telur Ayam Menggunakan Metode YOLO untuk Sistem Sortir Otomatis irni ri'khah juliarti; Muhammad Latif; Sri Wahyuni; Achmad Imam Sudianto; Ach. Dafid; Hairil Budiarto
Jurnal Informatika: Jurnal Pengembangan IT Vol 11, No 2 (2026)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v11i2.10166

Abstract

Early detection of egg fertility is crucial for improving incubation efficiency and reducing energy waste in small-scale poultry farms. This study developed an automated sorting system using the YOLOv8n algorithm to detect and classify eggs into two classes: fertile and infertile. The dataset was collected through a candling process using images of 3- to 7-day-old chicken eggs taken under controlled lighting conditions. Data collection included acquiring original images, which were then manually annotated using a bounding box format in the collab platform to train the model to recognize embryo features. The YOLOv8n architecture was chosen for its superiority in fast feature extraction using an efficient backbone structure and neck system for real-time small object detection. Model performance was comprehensively evaluated using confusion matrix and mean average precision (mAP) metrics. The mAP value reached 0.995, precision 0.9, and recall 100% in the training phase. In live system testing using a webcam, the model produced stable confidence values in the range of 85% to 94% with an inference time of only 1.4 ms. The integration of intelligent models and servo actuators in the sorting system has been proven to be able to separate fertile and infertile eggs automatically with a high success rate.
Peramalan Kelembapan Relatif di Kabupaten Bogor Menggunakan Model CNN-LSTM Thariq Abdullah; Achmad Lukman; Dede Rohidin
Jurnal Informatika: Jurnal Pengembangan IT Vol 11, No 2 (2026)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v11i2.10063

Abstract

 Air humidity is a parameter that influences the environment and human activities. Accurate air humidity prediction can be helpful for various purposes, including weather-based decision-making. However, a single model has limitations in capturing non-linear patterns and long-term dependencies in time-series data, making it difficult to predict data well, especially complex and time-series data such as weather. Therefore, a model with a hybrid approach is needed. Hybrid modeling is a combination of two or more learning methods. This study proposes a hybrid approach by combining Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) layers to predict air humidity more accurately and effectively than a single model. CNN is used to extract temporal representations from historical weather data in the form of time sequences, while LSTM is for long-term memory. Prediction is carried out by collecting weather data, data preprocessing, feature transformation (including cyclic feature transformation), designing the CNN-LSTM architecture, model training, and evaluation using evaluation metrics such as mean absolute error (MAE), mean square error (MSE), root mean square error (RMSE), and coefficient of determination (R²). This study uses weather data from Bogor Regency for the period January 1, 2020 to October 31, 2025 obtained from the Citeko Meteorological Station at coordinates Latitude -6.70000, Longitude 106.85000, and an altitude of 920 meters. The results obtained are that the CNN-LSTM model has an average MAE value of 4.3596, MSE 29.9126, RMSE 5.4689, and R² 0.0756 show that the CNN-LSTM hybrid model is able to improve the accuracy of air humidity prediction compared to a single model.
Generative AI vs SMOTE: Studi Kasus Penyeimbangan Data Teks pada Sentimen Analisis Dyah Sulistyowati Rahayu; Iman Paryudi; Erin Divayaning; Afni Puspita Zahra; Arsya Yan Duribta
Jurnal Informatika: Jurnal Pengembangan IT Vol 11, No 2 (2026)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v11i2.10157

Abstract

– Imbalanced data remains a major challenge in sentiment analysis, where the dominance of positive reviews often leads to biased classification results and weak recognition of minority classes. This study aims to address the imbalance problem by applying Large Language Models (LLM) to generate synthetic negative reviews and comparing the results with the traditional SMOTE method. The research process begins with data collection through web scraping, followed by preprocessing using standard text cleaning techniques such as tokenization, stopword removal, and stemming. Augmentation is then performed with LLM to produce additional negative samples, while SMOTE is applied as a baseline method. The classification task is conducted using Support Vector Machine (SVM) with TF-IDF representation, and model performance is evaluated using accuracy, precision, recall, and F1-score. The findings show that LLM augmentation produces synthetic data highly similar to the original distribution, as confirmed by Kolmogorov-Smirnov and Wasserstein Distance tests. Furthermore, the SVM model trained with LLM-augmented data achieved higher accuracy and balanced performance compared to SMOTE, particularly in handling minority classes. In conclusion, the use of LLM provides a more effective and natural approach for text data balancing in sentiment analysis, offering significant improvement in classification quality with accuracy of 99.41%, while using SMOTE get accuracy of 98.12%. 
SentryNap: Sistem Peringatan dan Monitoring Kantuk Operator Industri Menggunakan YOLOv5 dan CCTV M Ilham Yusuf Gumai; Yohana Christy Relyana Sembiring; Sri Lestari
Jurnal Informatika: Jurnal Pengembangan IT Vol 11, No 2 (2026)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v11i2.10111

Abstract

This study aims to develop SentryNap, a real-time drowsiness warning and monitoring system for industrial control-room operators based on YOLOv5s using CCTV/webcam image input. Reduced alertness caused by long shift work and operator drowsiness can increase the risk of operational errors, while many previous approaches still rely on intrusive physiological sensors or visual methods that are sensitive to changes in lighting and head pose. The proposed system uses a YOLOv5s model fine-tuned on a Roboflow dataset with two classes, namely normal and sleeping, and integrates the inference results with a Node.js backend for JSON logging. Model training was conducted for 50 epochs at a resolution of 640 x 640 pixels using the SGD optimizer, while evaluation was carried out through static validation and real-time testing scenarios. The model achieved a precision of 0.986, recall of 1.000, mAP@0.5 of 0.995, and mAP@0.5:0.95 of 0.621. Real-time testing showed that detection results could be recorded by the backend in less than one second. These findings indicate that SentryNap has potential as a non-invasive operator safety monitoring prototype, although larger datasets and broader field validation are still required.
Analisis Pengaruh Kondisi Akuisisi Citra terhadap Kinerja Klasifikasi Butterfly Fish Menggunakan Fitur HSV dan KNN I Putu Arya Putra; Wayan Eka Ariawan
Jurnal Informatika: Jurnal Pengembangan IT Vol 11, No 2 (2026)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v11i2.10022

Abstract

 Image acquisition conditions are a crucial factor in fish image classification; however, they are often overlooked in dataset development. Most previous studies rely on images captured under controlled backgrounds and lighting, resulting in limited evaluation of model performance in more complex real-world environments. This study aims to analyze the effect of image acquisition conditions on the classification performance of butterfly fish using HSV color features and the K-Nearest Neighbor (KNN) algorithm.The dataset is divided into two types: a conditioned dataset captured in a mini-studio with controlled lighting and background, and an unconditioned dataset obtained in an aquarium environment with varying lighting and backgrounds. Feature extraction is performed by computing the average values of Hue, Saturation, and Value, and classification is conducted using KNN with 5-fold and 10-fold cross-validation.The results show that although the conditioned dataset provides more consistent image representations, the unconditioned dataset, which has a larger quantity and higher diversity of data, achieves better classification performance. These findings indicate that while image acquisition conditions remain important for maintaining data quality, in the KNN approach, data quantity and diversity have a more dominant influence on model performance. This study suggests that dataset development for real-world applications should emphasize data diversity and quantity rather than relying solely on controlled acquisition conditions.