Garuda - Garba Rujukan Digital

Article Per Year (5 Year)

All

Tematik : Jurnal Teknologi Informasi Komunikasi

tematik
Website

Published by POLITEKNIK LP3I BANDUNG

ISSN : 23559055 EISSN : 24433640 DOI : 10.38204

Core Subject : Science,

Computer Science & IT

TEMATIK - Jurnal Teknologi Informasi Dan Komunikasi merupakan jurnal ilmiah sebagai bentuk pengabdian dalam hal pengembangan bidang Teknologi Informasi Dan Komunikasi serta bidang terkait lainnya. TEMATIK - Jurnal Teknologi Informasi Dan Komunikasi diterbitkan oleh LPPM dan Program Studi Manajemen Informatika di Politeknik LP3I Bandung. Redaksi mengundang para dosen, peneliti dan professional dari dunia industri dan kerja untuk menulis karya ilmiah dan pengalaman praktis di lapangan terkait implementasi Informatika dan Komputer.

Arjuna Subject : Ilmu Komputer (semua kategori) - Sistem Informasi

Articles 252 Documents

22 23 24 25 26

Drivers and Inhibitors Determining Government-Enabled Digital Platform Adoption for MSMEs in West Papua Province: PLS-SEM and IPMA Analysis Husna, Asmaul; Dedi I. Inan; Ratna Juita; Muhamad Indra
TEMATIK Vol. 12 No. 1 (2025): Tematik : Jurnal Teknologi Informasi Komunikasi (e-Journal) - Juni 2025
Publisher : LPPM POLITEKNIK LP3I BANDUNG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38204/tematik.v12i1.2291

Digital transformation plays a vital role in enhancing the competitiveness of Micro, Small, and Medium Enterprises (MSMEs) in developing regions. A case in point is Rumahekraf in West Papua Province, which faces infrastructure challenges such as limited internet access, inadequate technological devices, and insufficient digital training for MSME actors. In addition to infrastructure challenges, external factors such as economic conditions, local culture, and the digital divide also influence the adoption rate of this platform. This study aims to investigate the factors that drive and hinder its adoption. By combining the Technology Acceptance Model (TAM), Technology Readiness Index (TRI), and Performance Importance Map Analysis (IPMA). Particularly, this study examines the role of optimism, innovativeness, discomfort, and insecurity in shaping behavioral intention (BI) that might lead to usage behavior (UB). With a total of 157 respondents, and analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM), the results showed that perceived ease of use (PEOU) and perceived usefulness (PU) have a significant effect on BI (R2=56.3%), while BI influenced UB (R2=58%). Optimism affects PEOU but not PU, this can be explained by the nature of optimism, which tends to reinforce confidence in one's ability to master technology rather than directly evaluating the platform's perceived benefits. While Innovativeness positively affects both. The findings emphasize that in areas with limited infrastructure, such as West Papua, prioritizing easy-to-use design and useful features is key to effective platform adoption. This research provides insights for policymakers and developers to improve strategies in promoting digital platform adoption among MSMEs.

Pengamanan Dokumen Digital Menggunakan Kombinasi Algoritma Enkripsi Blowfish dan Encoding Base64 Ziayuddin, Muhammad Ziad; Imelda, Imelda
TEMATIK Vol. 12 No. 1 (2025): Tematik : Jurnal Teknologi Informasi Komunikasi (e-Journal) - Juni 2025
Publisher : LPPM POLITEKNIK LP3I BANDUNG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38204/tematik.v12i1.2316

In the digital era, document protection is crucial to safeguard the confidentiality and integrity of organizational information against various security threats. Numerous data breach incidents occur due to weak protection of internal documents that are not properly encrypted. This study aims to develop and evaluate a multi-format digital document security system by combining the Blowfish encryption algorithm with Base64 encoding. Blowfish serves as the main encryption algorithm to convert plaintext into binary ciphertext, while Base64 is used to convert the encrypted output into ASCII text format to facilitate storage and transmission, but not as a primary security mechanism. The system is implemented as a web-based application to enable convenient access and operation through a browser interface. The research methodology includes problem identification, data collection using Excel documents, system design, algorithm implementation, and testing. Functional validation and brute-force resistance tests were conducted. The results show that the system successfully performed encryption and decryption with 100% accuracy on five test files without data loss. The encrypted file size increased by approximately 0.3% due to the encoding process, which remains within acceptable limits. Security testing using CrypTool indicated that the ciphertext could not be deciphered without a valid key, even under systematic key search attempts. The primary contribution of this study is the integration of Blowfish encryption and Base64 encoding into an efficient web-based digital document security system, validated for brute-force resistance, which has not been widely explored in previous research.

Klasifikasi Aktivitas Pengguna yang Berpotensi Menyebabkan Kebocoran Informasi Sensitif Menggunakan Algoritma Random Forest Alda Amorita Azza; Asep Id Hadiana; Agus Komarudin
TEMATIK Vol. 12 No. 1 (2025): Tematik : Jurnal Teknologi Informasi Komunikasi (e-Journal) - Juni 2025
Publisher : LPPM POLITEKNIK LP3I BANDUNG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38204/tematik.v12i1.2325

Sensitive information leaks are a growing concern in cybersecurity, often caused by insider threats. To address this, a Random Forest classification model was developed to detect user activities that may lead to data leaks. By applying SMOTE-ENN for class balancing and optimizing model parameters, the study achieved remarkable accuracy. The model demonstrated a strong performance with an average F1-Score of 0.9167 in cross-validation and 0.9231 on the test data, reflecting its ability to identify abnormal activities with a balanced approach to precision and recall. Specifically, the model detected abnormal activities with Recall of 94.28%, meaning it effectively identified most of the risky activities while minimizing false positives. The AUC-ROC score of 0.9721 highlights the model's ability to distinguish between normal and abnormal behaviors. The results indicate that Random Forest, paired with SMOTE-ENN and parameter optimization, is an effective tool for detecting data leakage risks and insider threats, with potential for use in information security systems to monitor suspicious activities.

Klasifikasi Multi-Label Jenis dan Warna Buah Menggunakan Convolutional Neural Network (CNN) dengan Encoder Fitur Nida Ulhasanah; Yulison Herry Chrisnanto; Melina; Julian Evan Chrisnanto
TEMATIK Vol. 12 No. 1 (2025): Tematik : Jurnal Teknologi Informasi Komunikasi (e-Journal) - Juni 2025
Publisher : LPPM POLITEKNIK LP3I BANDUNG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38204/tematik.v12i1.2328

Indonesia merupakan negara tropis dengan keanekaragaman buah yang sangat tinggi, baik dari segi jenis maupun warna. Tantangan utama dalam klasifikasi buah secara otomatis terletak pada kompleksitas pengenalan atribut ganda, seperti jenis dan warna, secara simultan di tengah variasi kondisi nyata seperti pencahayaan, latar belakang, dan sudut pandang gambar. Penelitian ini bertujuan untuk mengembangkan model klasifikasi multi-label buah menggunakan arsitektur Convolutional Neural Network (CNN) yang dilengkapi encoder ResNet-50 guna mengenali jenis dan warna buah secara bersamaan dengan tingkat akurasi dan generalisasi yang tinggi. Metode yang digunakan melibatkan pelatihan model pada dataset Fruit-360 yang berskala besar dan memiliki keragaman tinggi, serta penerapan teknik n-fold cross-validation untuk meningkatkan validitas hasil dan mengurangi risiko overfitting. Hasil penelitian menunjukkan bahwa model dengan augmentasi data mencapai akurasi validasi hingga 97%, dengan precision sebesar 98,20% dan recall 97,61%, yang membuktikan efektivitas pendekatan multi-label dalam klasifikasi atribut visual buah secara simultan.

Ekstraksi Informasi dari Artikel Berita Agromaritim di Indonesia Menggunakan Teknik Named Entity Recognition (NER) Adam Firmansyah Suhendar; Wina Witanti; Melina
TEMATIK Vol. 12 No. 1 (2025): Tematik : Jurnal Teknologi Informasi Komunikasi (e-Journal) - Juni 2025
Publisher : LPPM POLITEKNIK LP3I BANDUNG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38204/tematik.v12i1.2329

Indonesia sebagai negara kepulauan memiliki potensi besar dalam sektor agromaritim, khususnya perikanan, namun pemanfaatan informasi geografis dari artikel berita masih menghadapi kendala akibat struktur teks yang tidak terstruktur dan variasi bahasa. Penelitian ini bertujuan untuk mengembangkan sistem ekstraksi informasi geografis dari berita agromaritim menggunakan teknik Named Entity Recognition (NER) berbasis model Bidirectional Encoder Representations from Transformers (BERT). Model BERT digunakan karena kemampuannya dalam memahami konteks kata secara mendalam, sehingga mampu mengenali entitas geografis seperti nama wilayah perairan meskipun terdapat variasi struktur kalimat. Penelitian ini juga menghasilkan dataset beranotasi khusus agromaritim yang digunakan dalam proses pelatihan model. Proses evaluasi dilakukan menggunakan metrik precision, recall, dan F1-score untuk mengukur performa sistem. Hasil penelitian menunjukkan bahwa model memperoleh precision 0.9768, recall 0.9762, dan F1-score 0.9712, yang mengindikasikan bahwa model tersebut berperforma sangat baik. Sistem yang dikembangkan ini diharapkan dapat mendukung pemanfaatan informasi geografis dari berita secara lebih efektif, serta menjadi fondasi bagi pengembangan teknologi berbasis data dalam pengelolaan sumber daya agromaritim di Indonesia.

Penerapan Convolutional Neural Network (CNN) untuk Klasifikasi Kualitas Beras sebagai Strategi Peningkatan Keamanan Pangan di Indonesia Ade Bastian; Priyadi, Deni; Zaliluddin, Dadan; Mardiana, Ardi; Wahid, Abrar; Rifki, Muhamamad; Fahmi Aziz, Muhamamad
TEMATIK Vol. 12 No. 1 (2025): Tematik : Jurnal Teknologi Informasi Komunikasi (e-Journal) - Juni 2025
Publisher : LPPM POLITEKNIK LP3I BANDUNG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38204/tematik.v12i1.2332

Food fraud has emerged as a significant global issue, threatening public health, economic stability, and consumer trust across the food supply chain. In the context of rice—a staple consumed by more than half of the world’s population—the proliferation of counterfeit products poses a critical risk. This study aims to develop a deep learning-based classification model using Convolutional Neural Networks (CNN) to accurately distinguish between medium-grade, premium, and counterfeit rice. The research involved the systematic collection of 100 grain images per rice category, followed by preprocessing, data augmentation, and model training using an optimized CNN architecture for image-based classification. The dataset was split into training, validation, and testing subsets with a 60:20:20 ratio. The model was trained over 12 epochs, achieving a training accuracy of 95%. Evaluation using the test set yielded identical accuracy, with the confusion matrix confirming perfect classification across categories. External validation further demonstrated the model’s robustness and generalizability. The findings highlight CNN’s potential as an effective tool for enhancing food safety monitoring systems and combating rice fraud. This AI-driven approach contributes to agricultural quality control and emphasizes the role of machine learning in promoting food security and authenticity assurance. However, CNN models face limitations, including susceptibility to overfitting when trained on insufficiently diverse data and high computational demands during training. These challenges underscore the need for diversified datasets and the exploration of alternative architectures offering comparable performance with greater computational efficiency.

Perbandingan Klasifikasi Tipe Kesuksesan Generasi Z Menggunakan Algoritma Naïve Bayes dan Decision Tree Novara Aulist Zakia; Ryando, M. Bucci; Agung, Halim
TEMATIK Vol. 12 No. 1 (2025): Tematik : Jurnal Teknologi Informasi Komunikasi (e-Journal) - Juni 2025
Publisher : LPPM POLITEKNIK LP3I BANDUNG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38204/tematik.v12i1.2334

This study aims to classify the types of success of Generation Z using the CRISP-DM method approach and using the Naïve Bayes and Decision Tree algorithms. Generation Z who grew up in a digital environment has a unique view of the meaning of success, which is no longer limited to income or position, but also includes life balance and self-development. This study identifies several important factors such as educational background, technological skills, work experience, personal branding, and use of social media as determining variables in the classification of types of success. The classification model produces four main categories of success, namely financial, career, self-development, and life balance. The results showed that life balance was the most dominant category of success among respondents. The use of the Naïve Bayes and Decision Tree algorithms showed that Decision Tree with balancing techniques (random oversampling) provided the highest classification accuracy, which was 94%, compared to Naïve Bayes which only reached 37%. This study makes an important contribution to the development of human resource strategies, education, and policies that are relevant to the characteristics and aspirations of Generation Z in the digital era.

Analisis Klaster Daerah Rawan Gempa di Indonesia Menggunakan K-Means dan DBSCAN Berbasis Data Historis BMKG Iqbal Prayoga Willyana; Asep Id Hadiana; Ridwan Ilyas
TEMATIK Vol. 12 No. 1 (2025): Tematik : Jurnal Teknologi Informasi Komunikasi (e-Journal) - Juni 2025
Publisher : LPPM POLITEKNIK LP3I BANDUNG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38204/tematik.v12i1.2369

Indonesia is one of the countries with the highest levels of seismic activity in the world because it is located at the meeting point of three major plates. The high potential for earthquakes requires a data-based approach to map vulnerable areas more accurately. This study aims to group earthquake-prone areas in Indonesia using the K-Means and DBSCAN clustering algorithms. The dataset used includes spatial data (latitude, longitude) and seismic data (magnitude, depth, phasecount, azimuth_gap) obtained from the BMKG earthquake catalog for the period 2008–2025. The study begins with the data preprocessing stage, which includes data cleaning, type conversion, feature selection, missing value imputation, outlier detection and removal, and normalization. Furthermore, the clustering algorithm is applied in three main scenarios, namely spatial data, seismic data, and a combination of spatial and seismic data. Evaluation using Silhouette Score and Davies-Bouldin Index (DBI) metrics shows that the K-Means algorithm provides better cluster separation, with a DBI value of 1.2551 in the combined scenario, while the DBSCAN algorithm tends to form only one dominant cluster and is sensitive to the presence of outliers. The final result of this study produces a map of earthquake-prone areas in Indonesia, which are divided into several clusters with different risk characteristics. The cluster with the highest concentration includes areas such as western Sumatra, the southern coast of Java, and parts of Maluku and Papua, which have historically been recorded as having higher earthquake frequency and magnitude. Meanwhile, other clusters covering areas such as Kalimantan and parts of Sulawesi show lower seismic activity intensity.

Identifikasi Hotspot Kebakaran Hutan Kalimatan Timur Tahun 2023 Menggunakan Teknik Spasial-Temporal Clustering ST-DBSCAN Salsabila, Mira; Hadiana, Asep Id; Melina
TEMATIK Vol. 12 No. 1 (2025): Tematik : Jurnal Teknologi Informasi Komunikasi (e-Journal) - Juni 2025
Publisher : LPPM POLITEKNIK LP3I BANDUNG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38204/tematik.v12i1.2377

Kebakaran hutan merupakan masalah serius yang berdampak pada lingkungan dan kesehatan masyarakat. Kebakaran hutan dapat dideteksi dari jumlah hotspot. Jika jumlah hotspot kebakaran hutan besar, maka semakin tinggi dan besar pula potensi kebakaran. Identifikasi hotspot kebakaran hutan yang akurat dan efesien sangat penting untuk pencegahan terjadinya kebakaran hutan. Penelitian ini bertujuan untuk mengidentifikasi hotspot kebakaran hutan menggunakan teknik spasial clustering Spatio Temporal – Density Based Spatial Clustering Application with Noise (ST-DBSCAN) yang mempertimbangkan aspek spasial dan temporal dalam menganalisis data titik api. Dataset yang digunakan sejumlah 1761 records dengan 12 atribut dari citra satelit MODIS (Moderate-Resolution Imaging Spectroradiometer) diproses menggunakan algoritma ST-DBSCAN untuk mengelompokan titik-titik api yang berdekatan secara spasial dan temporal. Dari eksperimen yang dilakukan dengan eps 1 = 0.05, eps 2 =1.0 dan MinPts = 4 menghasilkan 85 cluster dengan total titik data 1760, dan 162 titik merupakan outlier dengan sillhoutte score 0.134.

Arsitektur Keamanan Komputasi Awan Di Internet Nirkabel Zen Munawar; Sri Sutjiningtyas; Novianti Indah Putri; Milla Marlina Assegaf; Rita Komalasari; Herru Soerjono
TEMATIK Vol. 12 No. 1 (2025): Tematik : Jurnal Teknologi Informasi Komunikasi (e-Journal) - Juni 2025
Publisher : LPPM POLITEKNIK LP3I BANDUNG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38204/tematik.v12i1.2409

Penelitian ini bertujuan untuk mengusulkan arsitektur keamanan komputasi awan yang efektif dalam konteks internet nirkabel. Dengan meningkatnya penggunaan layanan komputasi awan, tantangan keamanan yang dihadapi menjadi semakin kompleks, terutama terkait dengan privasi data dan ancaman siber. Untuk mengatasi masalah ini, kami menerapkan pendekatan multi-layer dan Security as a Service (SeaaS) dalam merancang arsitektur yang adaptif dan aman. Metode yang digunakan melibatkan simulasi dan pengujian sistem pada arsitektur yang diusulkan. Kami mengimplementasikan arsitektur di lingkungan yang terkendali untuk mengamati performa dan respons keamanan, serta melakukan pengujian terhadap berbagai skenario serangan untuk mengevaluasi efektivitasnya. Hasil penelitian menunjukkan bahwa arsitektur ini mampu mengatasi berbagai risiko keamanan yang dihadapi oleh pengguna layanan komputasi awan di lingkungan nirkabel. Pembahasan menganalisis hasil yang diperoleh dari pengujian arsitektur. Kelebihan dari arsitektur ini adalah kemampuannya untuk menyesuaikan diri dengan berbagai jenis serangan melalui pendekatan multi-layer, yang meningkatkan tingkat keamanan secara keseluruhan. Namun, terdapat juga kekurangan dalam hal kompleksitas implementasi yang mungkin memerlukan sumber daya lebih untuk pengelolaannya. Kesimpulan penelitian ini menegaskan bahwa arsitektur keamanan komputasi awan yang diusulkan memberikan kontribusi signifikan terhadap peningkatan keamanan layanan di internet nirkabel, serta menawarkan fleksibilitas dan adaptabilitas yang diperlukan untuk memenuhi kebutuhan pengguna yang beragam.

Page 25 of 26 | Total Record : 252

22 23 24 25 26

Filter by Year

2014 2025

Filter By Issues

Home Page

OAI Link

Editorial Team

Contact

Reviewer

Google Scholar

Contact Name
Hadiansyah

Contact Email
kanghadiansyah@plb.ac.id

Phone
+6285220199772

Journal Mail Official
tematik@plb.ac.id

Editorial Address
Program Studi Manajemen Informatika Politeknik LP3I Bandung Jl. Pahlawan No. 59 Bandung 40123 Telp. (022) 2506500, Fax. (022) 2512564 Email : tematik@plb.ac.id

Location
Kota bandung,

Jawa barat

INDONESIA

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Home Page

OAI Link

Editorial Team

Contact

Reviewer

Google Scholar

Contact Name Hadiansyah

Contact Email kanghadiansyah@plb.ac.id

Phone +6285220199772

Journal Mail Official tematik@plb.ac.id

Editorial Address Program Studi Manajemen Informatika Politeknik LP3I Bandung Jl. Pahlawan No. 59 Bandung 40123 Telp. (022) 2506500, Fax. (022) 2512564 Email : tematik@plb.ac.id

Location Kota bandung, Jawa barat INDONESIA

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Contact Name
Hadiansyah

Contact Email
kanghadiansyah@plb.ac.id

Phone
+6285220199772

Journal Mail Official
tematik@plb.ac.id

Editorial Address
Program Studi Manajemen Informatika Politeknik LP3I Bandung Jl. Pahlawan No. 59 Bandung 40123 Telp. (022) 2506500, Fax. (022) 2512564 Email : tematik@plb.ac.id

Location
Kota bandung,

Jawa barat

INDONESIA