Article Per Year (5 Year)
p-Index From 2021 - 2026
2.439
P-Index
This Author published in this journals
All Journal JOIN (Jurnal Online Informatika) Journal of Machine Learning and Soft Computing Jurnal Keuangan dan Akuntansi Terapan (KUAT) Jurnal Dharmabakti Nagri International Journal of Information Technology and Computer Science Applications (IJITCSA) Jurnal Informatika: Jurnal Pengembangan IT Prosiding Seminar Nasional CORISINDO Jurnal Riset Informatika dan Teknologi Informasi (JRITI)
Tb Ai Munandar, Tb Ai
Unknown Affiliation
Humanities Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Engineering Social Sciences Other

Published : 17 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 17 Documents
Search

 1   2 
Agglomerative Spatial Clustering Analysis for Mapping Crime Risk Zone Clusters Munandar, Tb Ai; Ramdhania, Khairunnisa Fadhilla
International Journal of Information Technology and Computer Science Applications Vol. 3 No. 2 (2025): May - August 2025
Publisher : Jejaring Penelitian dan Pengabdian Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58776/ijitcsa.v3i2.197

Abstract

Public safety and order are crucial aspects of social and economic life, especially in densely populated urban areas. High crime rates can undermine the sense of security and quality of life within society. Therefore, a deep understanding of crime distribution patterns is essential for designing effective prevention strategies. This study aims to map crime risk zones in Indonesia using the Agglomerative Clustering method, by integrating socio-economic and demographic variables. This method was chosen for its ability to group data based on similarity of characteristics, making it easier to identify areas with high-risk levels. The results show the formation of four main clusters that reflect crime risk distribution in Indonesia. The first cluster includes several provinces with similar crime patterns, while the other clusters reflect significant differences in crime patterns, particularly in Jakarta, which has very distinct criminal characteristics. This mapping provides valuable insights for the planning of more efficient, data-driven crime prevention policies. The research is expected to provide a strong foundation for policymakers and law enforcement agencies to formulate more targeted strategies to combat crime in Indonesia.
Perangkingan Pegawai Untuk Menentukan Penerima Bonus Akhir Tahun Menggunakan Teknik ELECTRE Pada BPR Rasyid Munandar, Tb Ai
Jurnal Informatika: Jurnal Pengembangan IT Vol 8, No 2 (2023)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v8i2.4882

Abstract

Employee rankings can be done for various needs, one of which relates to year-end bonuses. So far, the awarding of year-end bonuses to research objects has only relied on one criterion, namely targets and achievements. In fact, there are many other indicators that can be assessed, such as attendance, discipline, communication style, cooperation, and initiative. This study aims to provide an alternative computation-based employee ranking method with multi-attribute decision making (MADM). The Elimination and Choice Translation of Reality (ELECTRE) technique is used in research to rank employee data based on their attribute values. The results of the study show that, of the ten employees assessed, four alternatives (employees) are recommended to be selected based on the results of a comparison of the dominant aggregate values. In this study, it can also be seen that alternative 6 (Alt-6) is the strongest alternative to be recommended for selection. Because alternative 6 (Alt-6) is not only better than alternatives 1, 4, 8, 9, and 10, but also better than alternative 3 (Alt-3) and alternative 4 (Alt-4). The order of the second, third, and fourth alternatives, respectively, are alternatives 5, 7, and 8. The recommendations of these four employees can be used as decision-making material for policymakers, given the need to award year-end bonuses.
K-Means-Based Pseudo-Labeling Technique in Supervised Learning Models for Regional Classification Based on Types of Non-Communicable Diseases Surbakti, Herison; Munandar, Tb Ai
JOIN (Jurnal Online Informatika) Vol 10 No 2 (2025)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v10i2.1609

Abstract

Non-Communicable Diseases (NCDs) pose a critical threat to global public health, with Indonesia experiencing significant challenges due to high mortality rates and uneven regional distribution. In Banten Province, limited access to labeled health data hampers effective, data-driven intervention strategies. This study proposes a semi-supervised learning approach to develop a regional classification model for NCDs. The methodology begins with K-Means clustering applied to data from 254 community health centers (Puskesmas) to generate pseudo-labels. Various cluster configurations (k=2 to 8) were evaluated, with the optimal result being two clusters based on a silhouette score of 0.735. These clusters were then used to create a semi-labeled dataset for supervised learning. Eight classification algorithms—CN2 Rule Inducer, k-Nearest Neighbor (kNN), Logistic Regression, Naïve Bayes, Neural Network, Random Forest, Support Vector Machine (SVM), and Decision Tree—were trained and compared. Among them, the Neural Network model achieved the highest performance, with an AUC of 0.999 and an MCC of 0.976, indicating excellent stability and predictive accuracy. The findings validate the effectiveness of semi-supervised learning for health classification tasks when labeled data is scarce. This approach can serve as a valuable decision-support tool for regional health planning and targeted interventions, enhancing the precision and efficiency of public health responses.
Analisa Sentimen terhadap Twitter Pemilu 2024 menggunakan Perbandingan Algoritma Naïve Baiyes rahmaddyan, reyhan tri; Damara, Rian; Pratama Yusuf, Ajif Yunizar; Munandar, Tb Ai
Jurnal Riset Informatika dan Teknologi Informasi Vol 2 No 3 (2025): April - Juli 2025
Publisher : Jejaring Penelitian dan Pengabdian Masyarakat (JPPM)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58776/jriti.v2i3.157

Abstract

In the digital era, sentiment analysis has become essential for understanding public opinion on various issues, including general elections. In the context of the 2024 General Election (Pemilu), this study aims to analyze sentiments expressed on the Twitter platform regarding the event. A primary classification algorithm, Naïve Bayes, was used to classify sentiments into positive, negative, and neutral categories and compare its performance. Twitter data was collected using a crawling technique during the 2024 election campaign period and used as the dataset. The data was then processed to remove noise and underwent text preprocessing, including tokenization, stemming, and stop word removal. Subsequently, the Naïve Bayes algorithm was applied to classify the sentiment of the collected tweets. Naïve Bayes, with its probabilistic approach and feature independence assumption, offers a fast and straightforward solution for classification tasks. The analysis results show that the algorithm was able to classify sentiments effectively. In tests using a separate test set, Naïve Bayes achieved an accuracy of approximately 82%. However, this algorithm has strengths and weaknesses that must be considered in the context of sentiment analysis on Twitter related to the 2024 election. For example, Naïve Bayes is more efficient in terms of time and resources. The study concludes that although Naïve Bayes produced accurate results, selecting the best algorithm depends on specific analysis needs, such as processing speed and resource availability. Further research is recommended to explore hybrid methods and deep learning techniques to enhance the accuracy and efficiency of sentiment analysis on social media platforms. The processed data consisted of 1,500 tweets. This study shows that the classification of Twitter data using the Naïve Bayes algorithm achieved an accuracy of 80%.
Clustering Gaya Belajar Mahasiswa dengan Metode K-Means: Analisis VARK untuk Pengembangan Strategi Pembelajaran Adaptif Munandar, Tb Ai
CORISINDO 2025 Vol. 1 (2025): Prosiding Seminar Nasional CORISINDO 2025
Publisher : CORISINDO 2025

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/corisindo.v1.5626

Abstract

This study aims to map students’ learning styles using the VARK (Visual, Auditory, Reading/Writing, Kinesthetic) framework through an unsupervised learning approach. Data were collected from student questionnaires and pre-processed by extracting coded responses, transforming them into numerical variables via one-hot encoding, and applying normalization. The K-Means Clustering algorithm was then employed to group students based on response patterns, with the number of clusters set to four in accordance with the VARK theoretical framework. The results reveal four clusters with distinct characteristics: Visual–Auditory, Auditory–Kinesthetic, Reading/Writing, and Multimodal. Internal validation using the Silhouette Score, Davies–Bouldin Index, Calinski–Harabasz Index, and the Elbow Method confirmed that four clusters represent the optimal configuration. PCA visualization and the distribution of VARK preferences further support the separation among clusters while highlighting the heterogeneity of student learning styles. These findings have practical implications for the design of adaptive learning strategies in higher education. Each cluster requires differentiated approaches, such as the use of visual materials, discussions, hands-on practice, or a variety of methods for multimodal learners. Future studies are recommended to expand the sample size, compare alternative clustering algorithms, and integrate VARK questionnaire data with digital learning behavior to enrich the analysis.
NeoCare: Telehealth System with Intelligent Notification for Neonatal Care Munandar, Tb Ai; Sri Lestari, Tyastuti; Noeman, Achmad
International Journal of Information Technology and Computer Science Applications Vol. 3 No. 3 (2025): September - December 2025
Publisher : Jejaring Penelitian dan Pengabdian Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58776/ijitcsa.v3i3.239

Abstract

Neonatal mortality in low- and middle-income countries remains high, partly because early physiological deterioration is detected late and continuous monitoring is limited outside specialized units. To address this gap, this study presents NeoCare: Telehealth System with Intelligent Notification for Neonatal Care, a multi-actor platform that integrates neonatal data management, vital-sign monitoring, and machine-learning–based alerts. The research followed a software engineering approach comprising stakeholder and context analysis, requirements engineering, clinical data acquisition, system and database design, intelligent notification model design, and prototype implementation. Retrospective neonatal records from two Indonesian referral hospitals were used to characterize heterogeneous and homogeneous clinical populations and to inform the design of classification features for vital-sign–based risk assessment. NeoCare is realized as a layered architecture with sensor, device, communication, processing-intelligence, and application layers. The prototype includes web and mobile interfaces tailored to four actor groups: hospital administrators, doctors, midwives, and parents. Administrators manage users, hospitals, vital-sign data, and machine-learning models while supervising alert output. Doctors and midwives access dashboards that display neonatal lists, detailed histories, trend graphs, and consultation management, supporting triage and longitudinal follow-up. Parents use a simplified mobile interface to view their baby’s status, monitor vital-sign trends, receive alerts, and schedule consultations. The system embeds an intelligent notification mechanism that flags abnormal patterns and presents them through color-coded indicators and concise messages. The results demonstrate the technical feasibility and coherence of a role-based, data-driven telehealth platform for neonatal care, providing a solid foundation for future work on clinical validation, device integration, and large-scale deployment.
Enhancing Association Rule Mining with Metaheuristic Parameter Optimization: A Transactional Data Analysis in Micro-Enterprise Context Primanda, Ferdy Hartanto Primanda; Munandar, Tb Ai; Ramdhania, Khairunnisa Fadhilla
International Journal of Information Technology and Computer Science Applications Vol. 4 No. 1 (2025): January - April 2026
Publisher : Jejaring Penelitian dan Pengabdian Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58776/ijitcsa.v4i1.204

Abstract

Nasi Uduk Mama Ipan is a micro-enterprise that conducts sales through both offline and online platforms. However, only online transaction data is available in analyzable form, while the owner lacks the knowledge to process it. This situation highlights the urgency of leveraging data mining techniques to uncover hidden patterns that can inform effective promotional strategies. This study aims to apply association rule mining using Apriori and FP-Growth algorithms, enhanced through metaheuristic-based hyperparameter tuning, to extract meaningful product bundling insights from transactional data. The research begins with data preprocessing, which involves eliminating irrelevant columns and transforming transactional records into a binary format. Four metaheuristic algorithms—Genetic Algorithm, ACO, PSO, and SA—are employed to determine optimal support and confidence values for both Apriori and FP-Growth. The modeling phase is conducted using Python with the mlxtend.frequent_patterns library, with rules filtered using a lift ratio threshold above 1. Results show that both Apriori and FP-Growth algorithms produce identical bundling recommendations using parameters derived from the Genetic Algorithm. Apriori performs faster, while FP-Growth is more memory-efficient. This study demonstrates that combining association rule mining with metaheuristic optimization can effectively support MSMEs in making data-driven marketing decisions.
Co-Authors Damara, Rian Dwi Budi Srisulistiowati Dwipa Handayani Fathurrazi, Ahmad Kapriadi, Engkap Karyaningsih, Dentik Khairunnisa Fadhilla Ramdhania Kristian Vieri, Jhon Muhammad Fairuzabadi Noeman, Achmad Noe’man,, Achmad No’eman, Achmad Pratama Yusuf, Ajif Yunizar Priatna , Wowon Primanda, Ferdy Hartanto Primanda rahmaddyan, reyhan tri Ramdhania, Khairunnisa Fadhilla Retno Wulandari Rizki Surya Pratama, Daffa Sani, Ardila Sri Lestari, Tyastuti Suhendar, Akip Surbakti, Herison