cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Rizal Furqan Ramadhan
Contact Email
admin@rizaniamedia.com
Phone
+6285257563813
Journal Mail Official
admin@rizaniamedia.com
Editorial Address
RT 10 RW 04 Desa Pucanganak Kec.Tugu Kab. Trenggalek
Location
Kab. trenggalek,
Jawa timur
INDONESIA
Jurnal Ilmiah Informatika dan Komputer
Published by CV.RIZANIA MEDIA PRATAMA
ISSN : -     EISSN : 30474752     DOI : https://doi.crossref.org/10.69533
Core Subject : Science,
Computer Science & IT
INFORMATECH : Jurnal Ilmiah Informatika dan Komputer (E-ISSN : 3047-4752) merupakan Jurnal nasional dengan akses terbuka yang menerbitkan artikel hasil penelitian di bidang Teknik Informatika dan Ilmu Komputer. Ruang Lingkup Jurnal meliputi Kecerdasan Buatan (Artificial Intellegence), Sistem Informasi, Robotika, Jaringan Komputer, Pengolahan Citra (Image Processing), Aplikasi Mobile, Data Mining dan bidang ilmu informatika lainnya. Jurnal INFORMATECH dikelola dan dipublikasikan oleh Rumah Jurnal RIZANIA MEDIA PRATAMA. Jurnal ini diterbitkan sebagai sarana dan wadah para dosen, ilmuan, peneliti maupun pakar bidang Teknik Informatika dan Ilmu Komputer mempublikasikan hasil-hasil penelitiannya untuk menunjang Tugas dan Program Tri Dharma Perguruan Tinggi secara Umum. Jurnal INFORMATECH terbit dua kali dalam setahun pada bulan Juni dan Desember.
Arjuna Subject : Ilmu Komputer (semua kategori) - Kecerdasan Buatan
Articles 69 Documents
 3   4   5   6   7 
Implementation of Edge Detection Using the Sobel Operator on Papaya Leaf Images Yuda Apriansyah; Khairi, Nouval; Haikal Habibi Siregar; Supiyandi; Aidil Halim Lubis
Jurnal Ilmiah Informatika dan Komputer Vol. 2 No. 2 (2025): Desember 2025
Publisher : CV.RIZANIA MEDIA PRATAMA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69533/ma9w7b36

Abstract

Recent advances in digital image processing and computer vision have enhanced feature extraction techniques for plant identification based on leaf morphology. Edge detection is a fundamental operation that highlights intensity discontinuities corresponding to object boundaries. This study implements the Sobel operator to perform edge detection on tropical leaf images using an experimental–computational approach. The workflow involves grayscale conversion, horizontal and vertical Sobel filtering, and gradient magnitude computation implemented in Python using the OpenCV library. Experimental evaluation demonstrates that the Sobel operator effectively delineates primary leaf contours and preserves morphological consistency, despite reduced performance under non-uniform illumination and noisy conditions. These results confirm that the Sobel operator remains a reliable preprocessing technique for leaf-based feature extraction and classification, offering a computationally efficient baseline for future integration with machine learning-based plant recognition systems.
Design and Development of a WhatsApp Chatbot-Based Expert System Using the Depth-First Search Algorithm for Thesis Topic Recommendation Zatadini, Galuh Indah
Jurnal Ilmiah Informatika dan Komputer Vol. 2 No. 2 (2025): Desember 2025
Publisher : CV.RIZANIA MEDIA PRATAMA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69533/6c7k7s60

Abstract

The rapid development of digital technology has encouraged the creation of various intelligent systems that can support decision-making processes, one of which is an expert system. In the academic environment, students often encounter difficulties in determining appropriate thesis topics that align with their areas of interest. Therefore, this study aims to develop an expert system integrated with a WhatsApp chatbot to assist students in identifying suitable thesis themes based on their academic interests. The system employs the Depth-First Search (DFS) algorithm as a problem-solving approach due to its flexibility in exploring decision paths within the knowledge base. The expert system is implemented through a WhatsApp chatbot interface to ensure ease of use, as the messaging interface is already widely familiar among university students. This approach allows users to interact with the system naturally without the need to learn a new interface. The results of system testing indicate that the developed expert system effectively assists students in determining thesis topics. Evaluation results show an accuracy level of 95.4%, demonstrating that the proposed system provides reliable recommendations. Furthermore, the use of a chatbot-based interface enhances user accessibility and usability. In conclusion, the integration of an expert system with the DFS algorithm and a WhatsApp chatbot interface provides an effective and user-friendly solution for supporting students in selecting appropriate thesis topics based on their interests.
Smart Trafo: A Random Forest and LLM-Based Decision Support System for Power Transformer Fault Diagnosis via Dissolved Gas Analysis Jeremia David Anthony Paduli; Jonathan Gabrillio Kaligis; Ade Yusupa; Yaulie Rindengan
Jurnal Ilmiah Informatika dan Komputer Vol. 3 No. 1 (2026): Juni 2026 (In Progress)
Publisher : CV.RIZANIA MEDIA PRATAMA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69533/informatech.volume3number1.511

Abstract

Manual management of Dissolved Gas Analysis (DGA) data for power transformers at PT. PLN (Persero) UPT Manado has been identified as a critical operational bottleneck, with existing spreadsheet-based workflows susceptible to human error, poor historical traceability, and limited scalability. Prior studies on DGA-based transformer diagnosis have been predominantly confined to standalone classification models without integration into operational management systems, leaving a significant gap in practical field deployment. This research contributes a novel integrated Decision Support System named Smart Trafo, which is the first to combine a Random Forest classification model, Duval Pentagon visualization, historical trending analysis, and an LLM-based conversational assistant (Volty AI) within a unified full-stack web platform. The Random Forest model was trained on 375 DGA samples across six fault classes using five gas parameters conforming to IEEE C57.104, achieving an overall accuracy of 84% and a macro-average F1-score of 0.83. Feature importance analysis revealed Hydrogen (H₂) as the dominant diagnostic indicator at 26.2%. The system successfully automates DGA fault classification, eliminates manual calculation errors, and provides real-time technical recommendations, thereby enabling more efficient and data-driven preventive maintenance decisions at PT. PLN (Persero) UPT Manado.
Queue-Based Batch Processing Architecture for Scalable Educational Assessment Systems Using MERN Stack April Firman Daru; Aria Hendrawan; Toti Kresna Wardana
Jurnal Ilmiah Informatika dan Komputer Vol. 3 No. 1 (2026): Juni 2026 (In Progress)
Publisher : CV.RIZANIA MEDIA PRATAMA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69533/informatech.volume3number1.492

Abstract

The increasing volume of student assessment data requires educational information systems that remain responsive during concurrent access and large-scale data import. This study proposes and evaluates a queue-based batch processing architecture for a web-based educational assessment system developed using the MERN stack. The main contribution is the integration of a RESTful API layer, FIFO-oriented asynchronous job queue, and batch segmentation strategy to decouple bulk Excel import from foreground user requests. The system was developed using Extreme Programming to support iterative requirement refinement and continuous testing. Evaluation was designed through functional testing using Cypress, API testing using HTTPie/Thunder Client, load testing using Apache JMeter, and frontend quality assessment using Google PageSpeed Insights. The scalability benchmark compares direct synchronous insertion as a baseline against the proposed asynchronous queue-based batch architecture under multiple concurrency levels, dataset sizes, and batch configurations. The verified PageSpeed results indicate excellent web quality scores, namely Performance 93, Accessibility 96, Best Practices 96, and SEO 100. The JMeter-based metrics, including average response time, 95th percentile response time, throughput, error rate, CPU usage, memory usage, queue waiting time, and job completion time, should be inserted from the exported test logs before final submission. The proposed architecture is expected to improve responsiveness, prevent server overload during bulk import, and provide a more reliable foundation for scalable educational assessment management.
Comparative Analysis of Naive Bayes and Support Vector Machine for Sentiment Classification of Indonesian-Language Mobile Application Reviews on Google Play Store Norris Elden Salassa; Arpen Patanduk; Ade Yusupa; Yaulie Deo Y. Rindengan
Jurnal Ilmiah Informatika dan Komputer Vol. 3 No. 1 (2026): Juni 2026 (In Progress)
Publisher : CV.RIZANIA MEDIA PRATAMA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69533/informatech.volume3number1.515

Abstract

This study conducted a comparative performance evaluation of Multinomial Naive Bayes and Support Vector Machine (SVM) with a linear kernel in classifying the sentiment of Indonesian-language mobile application reviews collected from the Google Play Store. A total of 2,847 reviews targeting the GoPay digital wallet application were gathered via web scraping using the google-play-scraper library. After preprocessing, including case folding, cleansing, tokenization, stopword removal, and stemming using the Sastrawi library, the final dataset comprised 2,634 usable reviews. Sentiment labeling was conducted automatically based on star ratings: ratings of 4 and 5 were assigned as positive (1,841 reviews, 69.9%), while ratings of 1 and 2 were assigned as negative (793 reviews, 30.1%). Feature extraction used TF-IDF with a vocabulary size of 8,432 unique terms. Model training used an 80:20 train-test split with stratified sampling. SVM parameters were set to kernel=linear and C=1.0; Naive Bayes used alpha=1.0 (Laplace smoothing). Experimental results show that SVM achieved an accuracy of 88.3%, precision of 0.89, recall of 0.88, and F1-score of 0.88, while Naive Bayes obtained an accuracy of 82.1%, precision of 0.84, recall of 0.82, and F1-score of 0.83. SVM demonstrated superior performance across all four evaluation metrics, with the largest gap observed in the F1-score for the negative class (SVM: 0.71 vs. Naive Bayes: 0.56). These findings confirm that SVM is more robust against class imbalance in informal Indonesian-language review data.
AI-Driven Learning Personalization in LMS Platforms:A Systematic Review Of Mechanisms, Effectiveness, And Computational Challenges Jacob Alfanicolls Rahayaan; Andre Immanuel Porayou; Arpen Patanduk; Ade Yusupa
Jurnal Ilmiah Informatika dan Komputer Vol. 3 No. 1 (2026): Juni 2026 (In Progress)
Publisher : CV.RIZANIA MEDIA PRATAMA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69533/informatech.volume3number1.517

Abstract

Background: The widespread adoption of Learning Management System (LMS) platforms in higher education has yet to overcome the fundamental limitation of uniform content delivery, which fails to accommodate individual differences in prior knowledge, learning pace, and cognitive style. Artificial Intelligence (AI) offers a transformative pathway to address this gap through data-driven personalization. Objective: This Systematic Literature Review (SLR) synthesises empirical evidence on the computational mechanisms, implementations, effectiveness outcomes, and technical-ethical challenges of AI-driven learning personalization in LMS environments within higher education, with an explicit focus on informatics and computational perspectives. Method: Adhering to PRISMA 2020 guidelines, 38 articles were selected from 312 candidates retrieved from Google Scholar, ScienceDirect, IEEE Xplore, and DOAJ (2021–2026), following three-stage screening and quality appraisal using the Mixed Methods Appraisal Tool (MMAT; minimum score 3/5). Results: Five dominant computational mechanism clusters were identified: (1) behavioral log analytics using sequence mining, clustering, and NLP; (2) academic failure prediction with Random Forest and Gradient Boosting (AUC up to 0.91, accuracy 78–89%); (3) hybrid recommender systems combining collaborative filtering, content-based filtering, and Knowledge Graph-GNN approaches (Precision@K gains of 14.3%); (4) adaptive assessment via Bayesian Knowledge Tracing combined with Item Response Theory; and (5) emerging applications of Large Language Models, Retrieval-Augmented Generation (RAG), Federated Learning, and Explainable AI (XAI/SHAP). A meta-analytic synthesis across 47 experimental studies yields a pooled effect size of d = 0.52 (medium-to-large) on academic performance. Significant challenges persist in data privacy compliance (UU PDP No. 27/2022), algorithmic fairness for 3T-region students, instructor AI literacy, and infrastructure disparity. Novelty: This review introduces a computational taxonomy of AI mechanisms in LMS, differentiating it from prior SLRs that focus predominantly on pedagogical or descriptive dimensions. Six priority research gaps are identified, including XAI adoption, culturally-fair algorithm design, and federated architectures for decentralised Indonesian institutions.
Apriori and FP-Growth Comparative Analysis of MPL Indonesia Season 13 Hero Drafts Andre Immanuel Porayou; Jacob Alfanicolls Rahayaan; Ade Yusupa; Yaulie Deo Y. Rindengan
Jurnal Ilmiah Informatika dan Komputer Vol. 3 No. 1 (2026): Juni 2026 (In Progress)
Publisher : CV.RIZANIA MEDIA PRATAMA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69533/informatech.volume3number1.524

Abstract

Hero combination selection or drafting is a crucial factor in determining victory in Mobile Legends: Bang Bang (MLBB) games at the professional level such as MPL Indonesia Season 13. However, counter-pick strategies are often based solely on the subjective intuition of players or coaches. This study aims to provide an objective basis for determining winning hero combination patterns by applying the Association Rule Mining (ARM) technique. Two main algorithms, namely Apriori and Frequent Pattern Growth (FP-Growth), are compared to evaluate the performance efficiency and accuracy of the resulting rules. The research data includes 183 winning transactions during the regular season of MPL ID Season 13, with parameters of minimum support 0.05 (5%), minimum confidence 0.40 (40%), and minimum lift 1.2. The results show that the strongest association rules are found in the combinations {Lapu-lapu} → {Fredrinn} (confidence 0.71) and {Cici} → {Fredrinn} (confidence 0.59). In terms of technical performance, the Apriori algorithm recorded a faster execution time than FP-Growth on this dataset. This study concluded that both algorithms produce identical association rule outputs, while Apriori demonstrated faster execution on this small-scale dataset, a finding attributed to the limited transaction volume rather than a universal superiority of Apriori over FP-Growth. The resulting rules can serve as a data-driven strategic recommendation system for professional esports teams in the pick and ban phase.
Developing a Content-Based Book Recommendation System for School E-Libraries Using TF-IDF and Cosine Similarity Muhammad Fatkul Roziq; Riska Nurtantyo Sarbini; Halimahtus Mukminna Halimahtus; Moh. Syaiful Anam
Jurnal Ilmiah Informatika dan Komputer Vol. 3 No. 1 (2026): Juni 2026 (In Progress)
Publisher : CV.RIZANIA MEDIA PRATAMA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69533/informatech.volume3number1.543

Abstract

The rapid growth of e-libraries has increased the availability of digital book collections, making it difficult for users to identify relevant reading materials. This study develops an automated book recommendation system for the SMKN 1 Semen e-library using Content-Based Filtering with TF-IDF for term weighting and Cosine Similarity for similarity measurement. The dataset consisted of 35 book records containing metadata and book descriptions collected from the SMKN 1 Semen e-library. Text data were processed through case folding, tokenization, stopword removal, and stemming before recommendation generation. The system was developed using the Laravel framework and a MySQL database following the Research and Development (R&D) method with the Waterfall model. Recommendation performance was evaluated using a Top-5 recommendation scenario, where the recommended books were compared with manually identified relevant books based on content similarity using Precision and Recall metrics, while system functionality was verified through Black Box Testing. The experimental results achieved a Precision of 80% and a Recall of 57.14%, indicating that the proposed approach effectively generates relevant book recommendations. This study contributes by demonstrating that the integration of Content-Based Filtering, TF-IDF, and Cosine Similarity provides an effective recommendation approach for school e-libraries with limited user interaction data, enabling personalized book recommendations and improving the efficiency of book discovery in small-scale digital library environments.
Optimizing iPhone Spare Parts Inventory Using K-Medoid Clustering Naurah Atikah Nurpadhilah; Aliya Dwi Ardiyanti; M. Aufa Rafiqi; Nur Ayu Siti Hardianti; Yusa Virginiawan Guntara
Jurnal Ilmiah Informatika dan Komputer Vol. 3 No. 1 (2026): Juni 2026 (In Progress)
Publisher : CV.RIZANIA MEDIA PRATAMA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69533/informatech.volume3number1.555

Abstract

MR. GADGET store in Bengkulu faces significant challenges in managing iPhone spare parts inventory due to a manual recording system. This study proposes a data science-based solution using the K-Medoid Clustering algorithm to group data based on characteristic similarity. Utilizing a dataset of 471 products, this study compares K-Medoid with conventional partitioning methods (like K-Means), demonstrating its superior robustness against outliers by using actual data points as cluster centers. The clustering quality is evaluated using the Silhouette Score and Davies-Bouldin Index (DBI), yielding best-performing results with a Silhouette Score of 0.681 and a DBI of 0.798. The algorithm generates three main clusters: Fast-Moving, Medium-Moving, and Slow-Moving. The system's functionality is validated through Black Box Testing. The results indicate that this approach provides more accurate procurement recommendations, optimizes inventory turnover, and reduces the risk of inventory imbalance, offering a practical data-driven framework for local retail businesses.

Page 7 of 7 | Total Record : 69

 3   4   5   6   7 

Filter by Year

2024 2026


Reset
Filter By Issues
All Issue Vol. 3 No. 1 (2026): Juni 2026 (In Progress) Vol. 2 No. 2 (2025): Desember 2025 Vol. 2 No. 1 (2025): June 2025 Vol. 1 No. 2 (2024): Desember 2024 Vol. 1 No. 1 (2024): Juni 2024