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
Penerapan PAM Clustering untuk Analisis Pola dan Optimasi Pemesanan Tiket Angkutan Umum syaffina Amalia Ash'ari; Liza Fitria; Rizalul Akram
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.v11i2.10031

Abstract

This study aims to analyze bus and minibus (Hiace) ticket booking patterns using the Partitioning Around Medoids (PAM) clustering method to support the optimization of public transportation operations. Managing fleet allocation and departure schedules is crucial for maintaining operational efficiency due to varying passenger mobility. This research applies the Knowledge Discovery in Databases (KDD) framework to analyze historical booking data obtained from the Transportation Agency of Aceh Tamiang Regency. The systematic stages include data selection, preprocessing, data transformation, application of the PAM algorithm, and comprehensive evaluation of the clustering results. A total of 76 transaction data records covering 15 main travel routes were analyzed and grouped into three distinct clusters based on booking frequency: stable-demand, high-demand, and very high-demand clusters. The evaluation results demonstrate that the PAM algorithm successfully identifies specific demand patterns across different routes with a Total Cost value of 2.0, indicating a highly stable and well-structured clustering outcome. Furthermore, this model is integrated into a desktop-based system to facilitate efficient data processing. Ultimately, the findings provide valuable insights into passenger demand characteristics for each route, which can actively support strategic decision-making in scheduling, effective fleet allocation, and overall service management improvement.
Model Hybrid Particle Swarm Optimization, Correlation Feature Selection dan Naive Bayes untuk Deteksi Penyakit Jantung Renaldi Yoga Rendy Menono; Taghfirul Azhima Yoga Siswa; Wawan Joko Pranoto
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.v11i2.10240

Abstract

Heart disease is a leading cause of mortality in Indonesia, with the number of cases reaching 15.5 million in 2022. This study aims to classify heart disease using the Naïve Bayes algorithm optimized with Particle Swarm Optimization (PSO) to improve classification performance. The dataset used in this study was obtained from the Zenodo repository, consisting of 1,025 heart disease records with 14 features. The data were processed through preprocessing stages and divided into training and testing sets using the 10-Fold Cross Validation method. PSO optimization was applied to the var_smoothing parameter of the Naïve Bayes algorithm. Model performance was evaluated using a confusion matrix to obtain accuracy, precision, recall, and F1-score values. The results indicate that Particle Swarm Optimization (PSO) improves the performance of the Naïve Bayes algorithm. On the correlation-based feature selection dataset, accuracy increased from 81.49% to 84.48%, precision slightly decreased from 82.57% to 82.37%, recall increased from 84.38% to 91.62%, and F1-score increased from 83.00% to 86.33%. These findings demonstrate that the combination of Naïve Bayes and Particle Swarm Optimization (PSO) is effective in enhancing heart disease classification performance.
FRAMEWORK MODULAR BERBASIS BLE untuk KONFIGURASI DINAMIS PERANGKAT EMBEDDED HEADLESS dengan APLIKASI MOBILE Eka Stephani Sinambela; Marojahan Mula Timbul Sigiro; Rivaldo Butar-butar; Ezra Pasaribu; Rika Simatupang; Frengki Simatupang; istas Pratomo Manalu; Gerry Italiano Wowiling; Sari Muthia Silalahi; Pandapotan Siagian
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.v11i2.10271

Abstract

– This study presents the development of a modular Bluetooth Low Energy (BLE)-based framework designed to enable dynamic configuration of headless embedded devices using an ESP32 microcontroller through a mobile application. Manual configuration processes that require physical device access and firmware reprogramming are often prone to human error and inefficiency, particularly for Internet of Things (IoT) devices deployed at the production stage. The proposed system aims to address these challenges by facilitating real-time, energy-efficient configuration management via wireless communication. The BLE-based mobile application serves as a user interface that allows secure bidirectional data exchange with the embedded device, enabling the modification of configuration parameters such as PIN, IP address, and SSID. The framework also ensures that all configuration updates are stored permanently within the device’s non-volatile memory, thereby eliminating the need for repeated reprogramming. Experimental evaluations were conducted to validate the system’s functionality and reliability. The results indicate that the application successfully scans, connects to, and updates individual ESP32-based headless devices. Configuration changes were applied accurately and persistently, confirming the stability and robustness of the proposed framework. The findings demonstrate that this approach significantly improves efficiency in IoT device management by reducing configuration time, minimizing potential errors, and simplifying maintenance workflows. Overall, the study contributes to advancing the development of intelligent, modular, and energy-efficient solutions for managing distributed embedded systems in modern IoT environments.
Model Hybrid PSO-SMOTE, Correlation Feature Selection dan Random Forest untuk Deteksi Penyakit Jantung Nur Dila Yuanti; Taghfirul Azhima Yoga Siswa; Wawan Joko Pranoto
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.v11i2.10241

Abstract

Heart disease is one of the leading causes of death worldwide, with approximately 17.8 million deaths reported in 2021. In Indonesia, the number of cases reached an estimated 15.5 million in 2022, highlighting the need for accurate early detection. This study aims to improve heart disease classification by integrating Correlation Feature Selection (CFS), Synthetic Minority Oversampling Technique (SMOTE), Particle Swarm Optimization (PSO), and Random Forest. CFS was applied to remove less relevant features before classification, SMOTE addressed class imbalance, and PSO optimized the Random Forest hyperparameters. The dataset consisted of 1,025 records from four heart disease datasets, which were cleaned into 302 unique instances. CFS eliminated the fasting blood sugar (fbs) attribute due to its very weak correlation with the target variable. Evaluation using 10-fold cross-validation showed that the baseline Random Forest achieved an accuracy of 82.80%, precision of 83.62%, recall of 86.07%, and f1-score of 84.46%, while Random Forest–PSO with SMOTE produced the best performance, achieving 85.11% accuracy, 84.62% precision, 89.74% recall, and 86.77% f1-score. These findings indicate that PSO provides the greatest performance improvement, while CFS simplifies the feature set before classification. The proposed hybrid model contributes by integrating feature selection, data balancing, and hyperparameter optimization into a single classification framework for more effective heart disease prediction.
Analisis Perbandingan Kinerja Metode GFPGAN dan RestoreFormer dalam Restorasi Foto Lama Hariman Bahtiar; Amri Muliawan Nur; Almi Yulistia Alwanda; Zulkipli Zulkipli
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.v11i2.10291

Abstract

A This study aims to analyze and compare the performance of two artificial intelligence–based image restoration methods, namely GFPGAN (Generative Facial Prior GAN) and RestoreFormer, in enhancing the quality of old photographs of TGKH. Muhammad Zainuddin Abdul Madjid. Both methods were tested on images that had undergone visual degradation, with OpenCV used as a conventional baseline. The evaluation was conducted using two main parameters: processing time and result quality, measured through the Peak Signal-to-Noise Ratio (PSNR) metric. The results show that GFPGAN produced the best outcome, achieving the highest PSNR value (32.8 dB) and the fastest processing time (9 seconds), generating sharp and realistic facial details. RestoreFormer yielded nearly comparable quality with a PSNR of approximately 30 dB and a slightly longer processing time (10 seconds), but it demonstrated greater consistency in preserving the authenticity of textures and structural details. Meanwhile, the manual OpenCV-based method achieved only moderate improvement (25.2 dB) with the longest processing time (12.5 seconds). These findings indicate that AI-based technologies, particularly GFPGAN and RestoreFormer, hold great potential for the preservation of historical visual archives, as they can significantly enhance the quality of old photographs while maintaining their original visual character. The combination of both methods is recommended for digital restoration efforts that balance technical efficiency and cultural authenticity.
Analisis Sentimen Berbasis Aspek dalam Ulasan Merek Fashion di Marketplace Menggunakan Support Vector Machine M. Ihsan Yusuf Lubis; Ilka Zufria; Ari Usman
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.v11i2.10159

Abstract

Kementerian Pariwisata dan Ekonomi Kreatif Indonesia menyoroti peran penting ekspor produk fashion, yang mencakup lebih dari separuh total ekspor subsektor ekonomi kreatif nasional. Hal ini menggarisbawahi minat global terhadap merek fesyen Indonesia. Oleh karena itu, para peneliti bertujuan untuk menyelidiki sentimen publik Indonesia terhadap merek fesyen, dengan fokus pada Erigo, yang menarik perhatian setelah sukses memamerkan produknya di New York Fashion Week 2022. Dengan menggunakan analisis sentimen berbasis aspek menggunakan metode Support Vector Machine, 1000 ulasan dari marketplace Shopee dan Tokopedia dianalisis. Hasilnya mengungkapkan kualitas sebagai aspek yang paling banyak diulas, dengan layanan mengumpulkan sentimen negatif tertinggi. Hal ini menunjukkan adanya kekhawatiran yang terus-menerus terkait layanan merek fesyen. Metode Support Vector Machine mencapai akurasi tinggi sebesar 89,5% dalam klasifikasi sentimen. Secara keseluruhan, studi ini menyoroti persepsi konsumen Indonesia terhadap merek fesyen, menekankan area yang perlu ditingkatkan dalam kualitas layanan.
Perbandingan Kinerja Skema Pengamanan Data AES‑256+X25519 dengan AES‑256+RSA‑OAEP pada Blockchain PoA Irza Nur Fauzi; Aghus Sofwan; Maman Somantri
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.v11i2.10279

Abstract

Keamanan data dalam sistem blockchain Proof of Authority yang menggunakan pendekatan terpusat menuntut mekanisme enkripsi dan pengelolaan kunci yang tidak hanya kuat tetapi juga efisien, sehingga penelitian ini memfokuskan pada evaluasi kinerja dua skema pembungkus kunci, yaitu X25519 dan RSA OAEP, yang dipadukan dengan AES 256 GCM sebagai algoritma enkripsi utama. Tujuan penelitian adalah membandingkan performa kedua skema dari sisi waktu enkripsi, waktu dekripsi, ukuran artefak kriptografis, serta dampaknya terhadap integritas blok dalam struktur rantai yang diperkuat blockchain Proof of Authority. Metode yang digunakan merupakan pendekatan Design and Development Research melalui perancangan dan implementasi prototipe blockchain berisi sepuluh blok yang diuji secara berurutan, termasuk skenario sabotase pada Blok 3 untuk mengamati ketahanan struktur integritas. Hasil penelitian menunjukkan bahwa RSA OAEP memiliki waktu enkripsi rata-rata lebih cepat yaitu 0.166 ms, sedangkan X25519 lebih unggul pada proses dekripsi dengan rata-rata 0.182 ms dan menghasilkan wrapped key yang lebih ringkas. Uji integritas menunjukkan bahwa modifikasi tunggal pada satu blok menyebabkan kegagalan blockchain Proof of Authority pada blok yang diserang dan ketidaksesuaian tautan hash pada blok-blok berikutnya sehingga seluruh rantai dinyatakan tidak valid. Simpulan penelitian menegaskan bahwa X25519 lebih cocok untuk lingkungan PoA yang menuntut efisiensi verifikasi, sementara RSA OAEP tetap relevan untuk sistem yang memprioritaskan kecepatan enkripsi pada sisi pengirim.
Optimasi Metode Ensemble Stacking Dalam Klasifikasi Kualitas Air Berbasis Algoritma XGBoost, LightGBM, dan CatBoost Raihan Aly Zaky; Windha Mega Pradnya Dhuhita
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.v11i2.10090

Abstract

Kualitas air merupakan isu lingkungan yang berdampak langsung terhadap kesehatan manusia dan keberlanjutan ekosistem, sehingga diperlukan sistem deteksi kualitas air yang akurat, cepat, dan andal untuk mendukung pengambilan keputusan. Penelitian ini bertujuan mengoptimalkan kinerja klasifikasi kualitas air dengan menerapkan metode Ensemble Stacking berbasis algoritma XGBoost, LightGBM, dan CatBoost, dengan Random Forest sebagai meta-learner. Proses penelitian meliputi pemuatan dataset kualitas air, eksplorasi data, tahap preprocessing, pelatihan model dasar, serta pembentukan skema stacking. Untuk meningkatkan performa model, diterapkan mekanisme passthrough atau penambahan fitur asli yang dikombinasikan dengan optimasi hyperparameter menggunakan RandomizedSearchCV guna memperoleh konfigurasi model terbaik. Hasil pengujian menunjukkan bahwa metode Ensemble Stacking mampu mencapai akurasi sebesar 97,06%. Setelah dilakukan optimasi melalui passthrough dan tuning hyperparameter, performa model meningkat dengan akurasi tertinggi sebesar 97,12% dan nilai precision mencapai 90,48%. Model yang diusulkan terbukti mampu menurunkan kesalahan prediksi, khususnya False Positive, sehingga lebih aman dalam penentuan status kualitas air. Dengan demikian, penelitian ini menghasilkan model prediksi yang andal dan berpotensi diterapkan pada instansi lingkungan, fasilitas pengolahan air, serta sistem pemantauan kualitas air berbasis data.
Pengaruh Feature Engineering terhadap Kualitas Clustering pada Segmentasi Pelanggan Ritel Daring Amril Mutoi Siregar
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.v11i2.10267

Abstract

Segmentasi pelanggan yang didasarkan pada data transaksi merupakan tantangan signifikan dalam ranah pemasaran digital, karena kemanjuran hasil pengelompokan sangat bergantung pada fitur yang digunakan. Ketergantungan pada fitur transaksi yang belum sempurna sering menghasilkan metrik evaluasi numerik yang meningkat; Namun, itu tidak cukup menangkap seluk-beluk perilaku pelanggan yang sebenarnya. Upaya penelitian ini berusaha untuk menyelidiki dampak rekayasa fitur pada kualitas segmentasi yang berkaitan dengan pelanggan ritel online. Metodologi yang digunakan adalah kerangka kerja kuantitatif eksperimental yang menyandingkan dua model fitur, khususnya Model 1 yang didasarkan pada fitur fundamental dan Model 2 yang berlabuh dalam fitur rekayasa perilaku pelanggan, mencakup RFM, Nilai Pesanan Rata-Rata, dan keragaman produk. Untuk tujuan ini, tiga algoritma pengelompokan tanpa pengawasan digunakan, yaitu K-Means, Model Campuran Gaussian, dan DBSCAN, dengan evaluasi dilakukan menggunakan Skor Silhouette dan Indeks Davies-Bouldin. Temuan menunjukkan bahwa sementara Model 1 menghasilkan nilai metrik yang unggul, ia menunjukkan relevansi yang berkurang dengan konteks bisnis. Sebaliknya, Model 2 menghasilkan cluster yang ditandai dengan peningkatan stabilitas, konsistensi, dan interpretabilitas untuk aplikasi pemasaran. Studi ini akhirnya menyimpulkan bahwa keberhasilan segmentasi pelanggan sebagian besar dipengaruhi oleh kaliber rekayasa fitur daripada hanya nilai yang meningkat dari metrik evaluasi internal
Analisis Proses Bisnis Surat Keterangan Pendamping Ijazah Menggunakan Metode Fishbone sumarsono sumarsono; Naufal Mahardhiko Yazidu Rozak
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.v11i2.9118

Abstract

 The digitalization of the Diploma Supplement (Surat Keterangan Pendamping Ijazah/SKPI) registration service through the Academic Information System has improved the efficiency of academic administration but has not fully resolved challenges affecting the effectiveness of its business process. This study aims to identify the root causes of problems in the SKPI registration business process at UIN Sunan Kalijaga using the Fishbone Diagram. A descriptive case study approach was employed. Data were collected through direct observation of the SKPI registration process based on the SKPI Manual Book for Students and documentation of the implemented service mechanism. The data were analyzed by classifying the root causes into four categories: people, technology, process, and documentation. The results indicate that the effectiveness of the SKPI registration process is influenced by these four factors. The people factor relates to students' understanding, accuracy in data entry, and ability to use digital services. The technology factor concerns limitations in system feedback and notification mechanisms. The process factor reflects a linear verification procedure that limits data correction, while the documentation factor refers to service guidelines that do not fully support users' understanding. The findings suggest that improving SKPI services requires not only information system enhancement but also integrated business process improvement involving users, technology, processes, and documentation to achieve more effective, transparent, adaptive, and user-oriented academic services.