cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Jay Idoan Sihotang
Contact Email
jay.sihotang@unai.edu
Phone
+62222700161
Journal Mail Official
jurnal.teika@unai.edu
Editorial Address
Universitas Advent Indonesia, Jalan Kolonel Masturi 288, Kec. Parongpong, Kab. Bandung Barat
Location
Kab. bandung barat,
Jawa barat
INDONESIA
Teika
Published by Universitas Advent Indonesia
ISSN : 19796439     EISSN : 23385979     DOI : https://doi.org/10.36342/teika
Core Subject : Science, Education, Engineering,
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Languange, Linguistic, Communication & Media
TeIKa (Teknologi Informasi dan Komunikasi) Journal invites scholars, researchers, and students to contribute the result of their studies and researches in the areas related to Information and Communication Technology work which covers Information System, Computer Networks, Computer Security, Database, Programming, Artificial Inteligence, Datamining, Multimedia Technology. It also seeks to provide a forum for an open exchange of ideas, based on research and serious professional reflection on both the theoretical underpinning of practice and practical applications of theory. TeIKa welcomes contributions from all Information Technology Lectures nationwide as well as fresh voices with something new to contribute to the community. Scope - Information System - Computer Networks - Computer Security - Database - Programming - Artificial Inteligence - Operating System - Multimedia - Data Mining
Arjuna Subject : Ilmu Komputer (semua kategori) - Kecerdasan Buatan
Articles 225 Documents
 19   20   21   22   23 
Design and Development of an Educational Children’s Product E-Commerce Website Using a Hybrid Payment Method Based on Laravel Intan Maiyuni; Rizky Parlika
TeIKa Vol 16 No 2 (2026): Jurnal TeIKa Volume 16, Nomor 2, Oktober 2026
Publisher : Fakultas Teknologi Informasi - Universitas Advent Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36342/ds1chf39

Abstract

The purpose of this research is to design and build a Laravel-based e-commerce website for children's educational products with a hybrid payment system to support a more effective and flexible digital transaction process. The problem raised is that the sale of children's educational products is still carried out conventionally, causing limited promotions, manual transaction management, and difficulties in recording sales data. The system development uses the Waterfall method with data collection through semi-structured interviews and direct observation. The system design uses UML and the database uses CDM and PDM with MySQL, and is integrated with Midtrans as an automatic payment gateway and a manual payment channel as a complement. Testing uses Blackbox Testing with Equivalence Partitioning and Boundary Value Analysis techniques, while validation uses Pearson correlation and Kappa Cohen. The test results show that 10 test scenarios in 5 main modules are valid, with calculated r values ​​ranging from 0.647-0.851 above r table = 0.334, and a κ value = 0.714 in the Substantial Agreement category. The system has proven to be able to digitize the sales process of children's educational products in a more structured, flexible, and user-friendly manner.
Implementation of the Frontend Website Admin of the Communication and Information Service of East Java Province Using the Svelte and Shadcn Maulidya Khairina Balqis; Defina Aulia Salsabila; Firza Prima Aditiawan
TeIKa Vol 16 No 2 (2026): Jurnal TeIKa Volume 16, Nomor 2, Oktober 2026
Publisher : Fakultas Teknologi Informasi - Universitas Advent Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36342/qf1ext31

Abstract

This research aims to implement the frontend of the admin website at the Communication and Information Office of East Java Province using the Svelte and Shadcn-Svelte frameworks. The development was carried out to support the needs of an administrative system that is able to effectively manage user data and access rights through a responsive and easy-to-use interface. The frontend of a website is implemented using Svelte as the primary framework for building user interfaces, while Shadcn-Svelte is used as a component library to maintain design consistency by speeding up the application implementation process. The features implemented include authentication pages, dashboards, user management, access rights management, and several other supporting pages needed in the system administration process. Implementation is carried out through the stages of needs analysis, interface design, implementation, and functional testing of each developed feature. The results of the implementation show that the admin website is able to display data in a structured manner, support user and access rights management more efficiently, and provide a good user experience. Functional testing shows that all key features can run according to predefined requirements. In addition, Svelte and Shadcn-Svelte users help improve development efficiency, simplifying the system maintenance process. Thus, the management of information systems at the East Java Provincial Communication and Information Service becomes more effective and efficient.
Comparative Performance of Naïve Bayes and Support Vector Machine Algorithms for Machine Learning-Based Spam Email Detection Lidia Apriyanti; Tirta Anhari
TeIKa Vol 16 No 2 (2026): Jurnal TeIKa Volume 16, Nomor 2, Oktober 2026
Publisher : Fakultas Teknologi Informasi - Universitas Advent Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36342/tt4ych50

Abstract

Email spam is one of the primary threats in digital communication with a continuously growing volume. Based on the Spam and Phishing in 2024 report released by Kaspersky, email spam accounted for approximately 47.27% of total global email traffic in 2024. This study aims to implement and compare the performance of the Naïve Bayes and Support Vector Machine (SVM) algorithms in detecting email spam using the Enron Spam Subset dataset from Kaggle, consisting of 10.000 emails with a balanced distribution (5.000 spam, 5.000 ham). The research stages include preprocessing text (case folding, cleaning, tokenizing, stopword removal, stemming), TF-IDF feature extraction with N-grams (unigram and bigram), and evaluation using 5-fold stratified cross-validation and a paired-sample t-test (α = 0.05). The results show that both NB+Unigram and SVM+Unigram configurations achieved the highest accuracy (98.80%) on the test set, with NB+Unigram achieving an F1-score of 0.9880, while SVM+Unigram achieved an F1-score of 0.9881. In the cross-validation evaluation, SVM+Unigram obtained the highest mean F1-score of 0.9827. Statistical testing confirmed a significant difference between NB and SVM in the unigram configuration (p = 0.023). The TF-IDF unigram combination outperformed bigrams for both algorithms on this dataset.
Enhancing Academic System Usability: A Design Thinking Approach to Redesigning the Simakip Uhamka Website Interface Amarta Syahputra Nepa Nepa; Tirta Anhari
TeIKa Vol 16 No 2 (2026): Jurnal TeIKa Volume 16, Nomor 2, Oktober 2026
Publisher : Fakultas Teknologi Informasi - Universitas Advent Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36342/rgj9c935

Abstract

There have been reports of usability and navigation problems with the SIMAKIP UHAMKA internet interface, a critical system for academic personnel that impedes operating efficiency. The primary objectives were to develop a high-fidelity prototype and design system using the Design Thinking framework and to evaluate how effectively the new design enhanced user satisfaction and usability for lecturers and academic staff. The five steps of the Design Thinking process—Empathize, Define, Ideate, Prototype, and Test—were rigorously followed in this study. The evaluation used both qualitative and quantitative approaches, such as the System Usability Scale (SUS) and Usability Testing with the Think-Aloud procedure to obtain detailed user insights. Survey to quantify user pleasure. The outcomes demonstrated a significant improvement. Data on user performance showed reduced time on task, a high task success rate, and a low error rate. The new interface prototype received a qualitative grade of "Excellent" and was placed in the "Acceptable" category after the average SUS score from the quantitative evaluation surpassed the global benchmark of 68. These results show that the user-centered redesign significantly enhanced the system's usability, efficacy, and user happiness, providing a validated model for improving similar academic information systems.
Lean Diagnostics: Optimizing Clinical Decision Boundaries in Deep Learning: Application of Youden’s J Statistic for Skin Tumor Triage Argha Orion Silitonga
TeIKa Vol 16 No 2 (2026): Jurnal TeIKa Volume 16, Nomor 2, Oktober 2026
Publisher : Fakultas Teknologi Informasi - Universitas Advent Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36342/5033vq53

Abstract

Deep learning models for dermoscopic skin tumor classification typically default to a static 0.5 probability threshold. In highly imbalanced clinical datasets, this rigid boundary yields unacceptable false-negative rates for critical malignancies. This study proposes a lean diagnostic framework designed to maximize clinical triage safety and computational efficiency for edge-based environments. An EfficientNet-B3 architecture was trained on ISIC imagery using an Alpha-Weighted Binary Focal Loss. To minimize computational overhead, we applied true structural channel pruning via L2-norm magnitude at 0%, 30%, and 60% sparsity. Rather than relying on default cutoffs, we dynamically calibrated the decision boundary by applying Youden’s J statistic to the Receiver Operating Characteristic (ROC) validation curve to maximize discriminative sensitivity. Network surgery at 60% sparsity reduced parameters from 10.70M to 1.81M and FLOPs from 1.93G to 0.37G. By recalculating predictions with the Youden-derived optimal threshold (0.4110), the lightweight model sustained a high malignant recall (sensitivity) of 82.54% and an Area Under the Curve (AUC) of 0.8457, closely rivaling the unpruned baseline recall of 84.72%. Grad-CAM evaluations confirmed that despite the physical severing of 60% of network channels, the model preserved high spatial fidelity in localizing relevant morphological features. Shifting from static probability thresholds to statistically optimized boundaries allows highly pruned, computationally efficient networks to maintain safe triage recall rates, providing a robust framework for automated, resource-constrained skin cancer screening.
Development of a Web-Based Basketball Statistical Tracking and Analytics System using Linear Regression and XGBoost Algorithms to Predict Player Efficiency Rating: A Case Study of Universitas Advent Indonesia Maharayatara Pakpahan; Andrew Fernando Pakpahan
TeIKa Vol 16 No 2 (2026): Jurnal TeIKa Volume 16, Nomor 2, Oktober 2026
Publisher : Fakultas Teknologi Informasi - Universitas Advent Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36342/j8cthe62

Abstract

The development of sports analytics has transformed basketball into a data-driven discipline. While professional leagues fully utilize advanced metrics like the Player Efficiency Rating (PER), collegiate sports environments in Indonesia, including Universitas Advent Indonesia (UNAI), still rely on manual data tracking, leading to information loss and a lack of predictive foresight. This research bridges this gap by developing a web-based basketball statistical tracking and analytics system tailored for the UNAI Varsity Team. The platform integrates a comparative machine learning engine evaluating traditional Linear Regression against XGBoost (Extreme Gradient Boosting) to forecast future player efficiency based on box-score metrics. Developed using a Svelte frontend and FastAPI backend, the system incorporates automated median and sequential imputation to resolve collegiate "cold-start" data sparsity. Empirical evaluation demonstrates that XGBoost significantly outperforms the linear baseline, achieving a Residual Sum of Squares (RSS) of 0.0847 and an R² score of 96.42%, representing a 44.4% error reduction over Linear Regression (0.1523 RSS, 88.10% R²). The resulting web application equips UNAI athletic decision-makers with data-supported tactical insights and prospective roster optimizations.
Dominant Factors of Lecturer Competence Influencing Information Technology Students' Satisfaction with Mathematics Learning Albinur Limbong
TeIKa Vol 16 No 2 (2026): Jurnal TeIKa Volume 16, Nomor 2, Oktober 2026
Publisher : Fakultas Teknologi Informasi - Universitas Advent Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36342/3pww6970

Abstract

Increasing student satisfaction is one of the main priorities for lecturers so that students' abilities can develop. This article aims to look at the dominant factors of lecturer competence that influence student satisfaction in learning mathematics. The population in the study consists of all information technology students taking mathematics courses from 2020/2021 to 2025/2026. The sample includes students who voluntarily agreed to fill out lecturer evaluations, totaling 82.9% of the population. Lecturer evaluation data was obtained from a questionnaire containing 12 questions covering 5 dimensions: Pedagogical, Social-Religious, Professional, Personality, and Satisfaction. The data was processed and analyzed using ANOVA to see differences in average lecturer evaluations, and then regression tests were conducted to examine the effect of lecturer competence on student satisfaction. The research results show that there is a significant difference in the average lecturer evaluations based on time and lecturer competence. Student satisfaction is higher with in-person learning (after the COVID-19 pandemic) compared to online learning (during the COVID-19 pandemic). From the multiple regression test simultaneously, it was found that the Pedagogic (x1), Social-religious (x2), Professional (x3), and Personality (x4) aspects simultaneously affect Satisfaction (y). However, partial regression tests show that only professional competence significantly affects student satisfaction, with the regression equation y = -0.127x1 - 0.107x2 + 1.453x3 - 0.116x4 - 0.444. The results suggest that lecturers need to improve their professional aspects to enhance the quality of learning and student satisfaction.
Perancangan Sistem Konversi Mata Kuliah Berbasis Web Menggunakan OCR dan Gemini AI Andrew Jonathan Jordy Simbolon; Jay Idoan Sihotang
TeIKa Vol 16 No 2 (2026): Jurnal TeIKa Volume 16, Nomor 2, Oktober 2026
Publisher : Fakultas Teknologi Informasi - Universitas Advent Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36342/r0yr4s37

Abstract

In the era of digital transformation, academic services are required to be managed quickly, accurately, and in an integrated manner. However, the process of submitting course conversion requests may still be conducted manually, potentially causing recording errors, processing delays, and limited transparency of request status. This research aims to design and develop a web-based course conversion system utilizing Optical Character Recognition (OCR) and Gemini AI to automatically extract data from academic transcript documents. The development method used is Rapid Application Development (RAD), consisting of the Requirements Planning, User Design, Construction, and Cutover phases. The system was developed using React, TypeScript, Supabase, and PostgreSQL, with features including online submission, transcript upload, automatic data extraction, multi-level verification, and digital report generation. Black Box Testing showed that the main system functions operated according to the defined test scenarios. OCR testing on one academic transcript containing seven courses resulted in 20 of 21 data items being extracted correctly, with an overall accuracy of 95.24%. An error was found in the extraction of one course name, while the remaining data in the tested document were extracted correctly. These results indicate that the developed system can support the digital submission and verification of course conversion requests, while the extracted data should still be reviewed by users.
Design and Development of a Mathematics Educational Game As A Learning Tool For Slow-Learning and Reguler Students at SMP IT Yabunaya Giovani Siburian; Yang Agita Rindri; Riki Afriansyah
TeIKa Vol 16 No 2 (2026): Jurnal TeIKa Volume 16, Nomor 2, Oktober 2026
Publisher : Fakultas Teknologi Informasi - Universitas Advent Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36342/7rgk8121

Abstract

Mathematics instruction in inclusive schools requires teaching materials that are appropriate for both regular students and students with learning difficulties. Differences in learning abilities cause some students to struggle with understanding mathematics concepts, making it necessary to use teaching materials that are more engaging and interactive. This study aims to design and develop a web-based educational math game as a learning tool for students with learning difficulties and regular students at SMP IT Yabunaya, as well as to describe the responses of teachers and students to the use of the game. This study employed the Research and Development (R&D) method using the ADDIE model, which consists of the Analysis, Design, Development, Implementation, and Evaluation stages. The educational game was developed using the Laravel 11 framework with a MySQL database. System testing was conducted using Black Box Testing, subject matter expert validation, and the distribution of questionnaires to teachers and students. The results showed that all system functions operated as intended. Content expert validation yielded a percentage of 81.6%, while the questionnaire results showed a percentage of 92% from teachers and 94.2% from students. Based on these results, the “Friendly Math” educational game is deemed suitable for use as a learning medium for both slow learners and regular students at SMP IT Yabunaya.
Hoax Detection in Informal Indonesian Language through a Hybrid Approach: Integrating Lexicon and Deep Learning Rabiatul Adwiya; Achmad Arif Munaji; Airways Parlindungan Siahaan; Nor Alya; Nor Aisyah
TeIKa Vol 16 No 2 (2026): Jurnal TeIKa Volume 16, Nomor 2, Oktober 2026
Publisher : Fakultas Teknologi Informasi - Universitas Advent Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36342/mfw5kg39

Abstract

Informal Indonesian is highly variable: slang, abbreviations, misspellings, and other nonstandard forms often express the same meaning in different surface forms. This variability can complicate automatic hoax detection because the classifier must interpret both the underlying message and its unconventional wording. This study examines a hybrid pipeline in which lexicon-based normalization is applied before IndoBERT fine-tuning. Here, hybrid refers to a sequential combination of lexical preprocessing and deep learning classification; it does not imply a new neural architecture or training algorithm. The dataset initially contained 3,628 labeled Indonesian texts collected in 2026. Nine records with invalid split information were removed, leaving 3,258 samples for development and 361 samples for a fixed hold-out test. Two otherwise identical configurations were evaluated: one used the original text, while the other used lexicon-normalized text. Using 10-fold StratifiedGroupKFold grouped by topic, the original-text configuration obtained a Macro-F1 of 75.29 +/- 3.10%, compared with 75.21 +/- 3.66% for the normalized-text configuration. Neither the Wilcoxon signed-rank test (W = 24.0; p = 0.7695) nor the exact McNemar test (41 versus 40 discordant cases; p = 1.00) indicated a significant difference. On the fixed hold-out set, the normalized-text configuration achieved 80.89% accuracy and 71.39% Macro-F1 (95% bootstrap CI: 65.4-76.9). Because a majority-class predictor already reaches 80.61% accuracy, the accuracy figure should be read cautiously. Overall, explicit normalization did not improve global performance, although exploratory subset results indicate that its influence may depend on how many tokens are actually normalized.

Page 22 of 23 | Total Record : 225

 19   20   21   22   23 

Filter by Year

2008 2026


Reset
Filter By Issues
All Issue Vol 16 No 2 (2026): Jurnal TeIKa Volume 16, Nomor 2, Oktober 2026 Vol 16 No 1 (2026): Jurnal TeIKa Vol 15 No 1 (2025): TEIKA - April 2025 Vol 15 No 2 (2025): Jurnal Vol 14 No 2 (2024): TeIKa: Oktober 2024 Vol 14 No 1 (2024): TeIKa: April 2024 Vol 13 No 02 (2023): TeIKa: Oktober 2023 Vol 13 No 01 (2023): TeIKa: April 2023 Vol 12 No 02 (2022): TeIKa: Oktober 2022 Vol 12 No 01 (2022): TeIKa: April 2022 Vol 11 No 2 (2021): TeIKa: Oktober 2021 Vol 11 No 1 (2021): TeIKa: April 2021 Vol 10 No 2 (2020): TeIKa: Oktober 2020 Vol 10 No 1 (2020): TeIKa: April 2020 Vol 9 No 2 (2019): TeIKa: Oktober 2019 Vol 9 No 1 (2019): TeIKa: April 2019 Vol 8 No 2 (2018): TeIKa : Oktober 2018 Vol 8 No 1 (2018): TeIKa : April 2018 Vol 7 No 2 (2017): Teika : Oktober 2017 Vol 7 No 1 (2017): TeIKa : April 2017 Vol 6 No 1 (2016): TeIKa : Desember 2016 Vol 5 No 2 (2013): TeIka Oktober 2013 Vol 5 No 1 (2013): Teika April 2013 Vol 4 No 1 (2011): TeIka Juni 2011 Vol 3 No 2 (2010): TeIka Desember 2010 Vol 3 No 1 (2010): TeIka Juni 2010 Vol 2 No 2 (2009): TeIka Desember 2009 Vol 2 No 1 (2009): TeIka Juni 2009 Vol 1 No 2 (2008): TeIka Desember 2008 Vol 1 No 1 (2008): TeIka Juni 2008 More Issue