cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
-
Editorial Address
-
Location
,
INDONESIA
JOURNAL OF APPLIED INFORMATICS AND COMPUTING
Published by Politeknik Negeri Batam
ISSN : -     EISSN : 25486861     DOI : 10.3087
Core Subject : Science,
Computer Science & IT
Journal of Applied Informatics and Computing (JAIC) Volume 2, Nomor 1, Juli 2018. Berisi tulisan yang diangkat dari hasil penelitian di bidang Teknologi Informatika dan Komputer Terapan dengan e-ISSN: 2548-9828. Terdapat 3 artikel yang telah ditelaah secara substansial oleh tim editorial dan reviewer.
Arjuna Subject : -
Articles 1,006 Documents
 91   92   93   94   95 
Comparative Analysis Of Automatic Labeling With Cohen's Kappa Validation For Cyberbullying On Tiktok Using Pre-Trained Transformers David Rian Prabowo; Khoiriya Latifah; Nugroho Dwi Saputro
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13108

Abstract

The rapid growth of TikTok users in Indonesia increases the risk of cyberbullying, making manual content moderation inefficient. This study compares two automatic labeling methods, InSet Lexicon and Zero-Shot Classification, to address the problem of limited labeled data in cyberbullying detection. A total of 5,864 comment data were collected through scraping techniques and processed through comprehensive text preprocessing stages, including slang normalization. To evaluate labeling reliability, a validation test using Cohen's Kappa Score metric was conducted against a human annotated Gold Standard of 1,141 comments. The results show that Zero-Shot Classification achieves high reliability with a Kappa score of 0.9132 (almost perfect agreement), outperforming InSet Lexicon which drops to 0.2585 (fair agreement) due to lexical rigidity and high false positives on casual slang. The automatically labeled datasets were balanced using Random Oversampling (for the Zero-Shot Classification labeling scenario) and split via a stratified 80:10:10 ratio to fine-tune IndoBERT and RoBERTa. On independent test data, IndoBERT trained on Zero-Shot labels delivers the best performance, reaching an Accuracy and F1-Score of 91.10%, outperforming RoBERTa under the same scenario (85.83%). Conversely, training on InSet Lexicon labels reduces performance, limiting IndoBERT to an 86.94% F1-Score and RoBERTa to 80.21%. This study concludes that using Zero-Shot Classification and fine-tuning IndoBERT is more optimal for application to informal social media comment moderation systems.
Adoption of Sustainable and Human-Centered Explainable AI in Higher Education. An Extended UTAUT Perspective Fine Masimba; Bester Chimbo; Kudakwashe Maguraushe
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13124

Abstract

As Artificial Intelligence permeates higher education, concerns regarding its "black-box" nature, ethical implications and environmental sustainability have intensified. This study develops and empirically validates an Extended Unified Theory of Acceptance and Use of Technology (UTAUT) framework to investigate the factors influencing AI adoption among students in Zimbabwean universities. The model integrates five contemporary AI constructs which are perceived explainability, trust in AI, perceived human-centeredness, perceived sustainability and perceived fairness into the traditional UTAUT1 framework. Data were collected through a structured Likert-scale questionnaire from a sample of 352 students across major Zimbabwean HEIs. Regression analysis was employed to examine the relationships among constructs. The extended model explains 68.4% of the variance in behavioural intention (R² = 0.684). Results indicate that while performance expectancy and trust in AI are the strongest predictors, perceived explainability and human-centeredness significantly enhance adoption intentions. Surprisingly, perceived sustainability emerged as a nascent but significant driver, reflecting a growing awareness of "Green AI." The findings provide critical theoretical contributions by bridging the gap between instrumental adoption drivers and human-centric design. Practically, the study offers a roadmap for university administrators and AI developers in developing countries to foster transparent, fair and sustainable AI ecosystems.
Real-Time Heart Rate Pattern Analysis During Computer-Based Work Activities Muhammad Fatiha Assyfa; Muhammad Fikry; Zara Yunizar
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13148

Abstract

The development of Internet of Things (IoT) technology provides opportunities for real-time health monitoring systems, including stress detection based on users’ physiological conditions. This study aims to develop an IoT-based heart rate monitoring and stress detection system using a Pulse Sensor and ESP8266 microcontroller. The system is designed to read heart rate signals in real-time and transmit the data to a computer through serial USB communication for further processing using the Python programming language. The data processing stages include signal preprocessing, Beats Per Minute (BPM) calculation, sliding window processing, and kurtosis analysis as an indicator of user stress levels. The processed data are visualized through a Streamlit-based monitoring dashboard in the form of time-series graphs, gauge meters, and real-time user condition status. The study involved 20 Informatics Engineering students performing computer-based work activities within a certain duration. The results show that the system is capable of performing real-time heart rate monitoring and stress analysis effectively. The kurtosis values indicate changes in heart rate signal distribution patterns that can be used as indicators of normal and stress conditions. The developed system is expected to provide a simple, affordable, and extensible health monitoring solution.
Implementation of a Hybrid Model Using Principal Component Analysis, K-Means, and Naïve Bayes for Tuition Fee Category Prediction Nurdin Nurdin; Jessika Jessika; Munirul Ula
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13184

Abstract

The determination of Tuition Fee Categories in higher education institutions is commonly conducted through manual verification of students’ socioeconomic documents, which may lead to subjectivity and inconsistencies in decision-making. This study proposes a hybrid machine learning approach that integrates Principal Component Analysis (PCA), K-Means Clustering, and Naïve Bayes Classifier within a semi-supervised learning framework for student socioeconomic classification based on pseudo-labels generated from clustering results. The dataset used in this study consists of 452 student records with 12 socioeconomic attributes obtained from the New Student Admission system of STAIN Teungku Dirundeng Meulaboh in 2025. Data preprocessing includes attribute selection, categorical transformation using One Hot Encoding, and feature standardization. PCA is applied to reduce dimensionality from 18 features to 12 principal components while retaining 95% of the total variance. The processed data are clustered using K-Means with the optimal number of clusters determined as 8 based on Elbow and Silhouette Score analysis. These clusters are used as pseudo-labels for training the Naïve Bayes classifier. Experimental results show that the proposed model achieves 98.89% training accuracy and 97.80% testing accuracy, with a weighted average F1-score of 0.98. The results indicate that the proposed hybrid approach is effective in capturing underlying socioeconomic patterns and provides a stable classification performance. However, the model is based on pseudo-labels rather than official tuition fee categories. Therefore, further validation using real labeled data is recommended to enhance generalizability and practical applicability.
Security and Performance Analysis of PRESENT, SPECK, and ASCON Lightweight Cryptographic Algorithms in MQTT-Based IoT Environments I Wayan Rangga Pinastawa; Susanto Susanto; Khoironi Khoironi
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13189

Abstract

The rapid growth of the Internet of Things (IoT) has increased the demand for lightweight cryptographic algorithms capable of providing adequate security while maintaining low computational overhead on resource-constrained devices. This study aims to analyze and compare the ASCON, PRESENT, and SPECK algorithms in MQTT-based IoT environments using the MQTT-IoT-IDS2020 dataset as a source of communication payloads. The evaluation was conducted using a Python-based framework with security and randomness metrics, including Avalanche Effect, Strict Avalanche Criterion (SAC), Bit Independence Criterion (BIC), Shannon Entropy, Approximate Entropy, Hamming Distance, Monobit Test, and Runs Test. Performance was evaluated using execution time, throughput, memory usage, and CPU usage. The validity of the results was strengthened through statistical analysis using 95% confidence intervals, One-Way ANOVA, and Tukey HSD. The results indicate that all three algorithms exhibit strong diffusion and randomness characteristics, with Avalanche Effect values close to the ideal value of 50% and ciphertext randomness metrics that satisfy the applied statistical tests. SPECK achieved the best performance with an execution time of 0.000238 seconds and a throughput of 2,199,891 bits/s, while PRESENT demonstrated the lowest memory consumption at 2.85 KB. Based on the calculated Security Score and Efficiency Score, PRESENT achieved the highest Security Score of 0.692, while SPECK achieved the highest Efficiency Score of 0.993, respectively. Statistical analysis revealed that significant differences among the algorithms primarily occurred in diffusion-related and computational performance metrics. Therefore, within the scope of the evaluated diffusion, randomness, and performance metrics, SPECK provides the most favorable balance between security-related characteristics and computational efficiency among the evaluated algorithms for MQTT-based IoT environments.
Comparative Evaluation of Ensemble Learning Models for Prenatal Stunting Risk Assessment Based on Maternal Health Data Nur Inaya Bahar; Eka Qadri Nuranti; Intan Sari Areni
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13208

Abstract

Stunting remains a significant public health challenge, where interventions are often delayed as they occur postnatally. This research aims to shift the detection focus to the prenatal phase by comparing the performance of four Ensemble Learning algorithms: Random Forest, XGBoost, CatBoost, and Light Gradient Boosting Machine (LGBM). Using a maternal dataset from DPPKB Parepare City consisting of 871 respondents, the models were developed through a Stratified 5-Fold Group Cross Validation scheme to predict stunting risk based on clinical features of pregnant women. Experimental results show that LGBM is the most optimal algorithm, where the hyperparameter tuning process increased model performance to an F1-Score of 94.34% and an accuracy of 94.50%. Ablation analysis identified maternal age, height, and the age of the last child as the most dominant predictors. The best model was integrated into a web-based decision support system using cloud-based microservices architecture, featuring geospatial mapping. This study proves that the application of LGBM on prenatal maternal data can provide accurate early detection to support targeted nutritional interventions for Family Assistance Teams (TPK) in Parepare City, although its generalizability remains limited to local administrative characteristics and warrants further prospective external validation before broader deployment.
Decision Tree-Based Web Expert System for Preliminary Screening of Refractive Eye Disorders Dini Fariha; Rizal Tjut Adek; Rizki Suwanda
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13213

Abstract

Refractive eye disorders remain one of the leading causes of visual impairment worldwide, while limited access to ophthalmology services often delays early diagnosis. This study investigates the effectiveness of the Decision Tree algorithm for symptom-based classification of refractive eye disorders and its implementation within a web-based expert system for preliminary eye health screening. Data were collected from 505 respondents using a structured Google Forms questionnaire. After preprocessing and labeling, the dataset was divided into 80% training data and 20% testing data. Model performance was evaluated using a confusion matrix together with accuracy, precision, recall, and F1-score metrics to provide a comprehensive assessment under an imbalanced class distribution. Experimental results showed that the proposed Decision Tree model achieved an overall accuracy of 89.11% and demonstrated satisfactory performance in identifying dominant diagnostic classes while maintaining transparent and interpretable decision rules. The developed web-based system provides symptom-based diagnosis, examination history management, and PDF report generation to support preliminary eye health assessment. These findings indicate that the proposed approach is suitable as an accessible decision-support tool for preliminary refractive eye disorder screening, particularly in areas with limited access to ophthalmology services.
Implementation of Isolation Forest and Rule-Based Prioritization in the Automation of Warehouse Inventory Monitoring Using a Near Real-Time Dashboard Muhammad Windri; Ida Nurhaida
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13218

Abstract

This research implements an automated warehouse inventory monitoring system using a hybrid approach that combines Isolation Forest and rule-based prioritization for anomaly detection, while Long Short-Term Memory (LSTM) is used for demand forecasting. The system automatically detects three types of anomalies: spike (quantity surge), drop (quantity decline), and pattern shift (changes in transaction patterns). The method utilizes 341,879 inventory records over two and a half years, combining Isolation Forest for outlier detection, rule-based prioritization for spike and drop detection, and LSTM for time series forecasting. The system is equipped with a near real-time dashboard (periodic auto-refresh), API service, and a business validation mechanism involving warehouse users. The system generated 211,450 detection candidates, consisting of 187,537 operational anomaly alerts and 23,913 INFO-level records, with accuracy of 93.0%, precision of 88.7%, recall of 100%, and F1-score of 94.0%. The INFO category is not displayed on the dashboard due to low confidence scores. The near real-time dashboard displays HIGH, MEDIUM, and LOW priority alerts with auto-refresh. Business validation achieved an 84% confirmation rate. The system also provides LSTM forecast features for predicting inventory needs for 7, 14, and 30 days ahead. This research shows that AI implementation for warehouse inventory monitoring can automate anomaly detection and improve inventory issue identification. The system shows potential for medium to large-scale warehouses requiring near real-time monitoring.
Comparative Analysis of K-Nearest Neighbors and Support Vector Machine for Student Stress Prediction Lutfi Khoirul Umam; Setyoningsih Wibowo; Agung Handayanto
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13224

Abstract

Student stress has emerged as an important issue because it can negatively affect both academic achievement and mental well-being. The growing development of machine learning techniques has enabled the creation of predictive models that can classify stress levels using various student-related factors. This research evaluates and compares the effectiveness of the K-Nearest Neighbors (KNN) and Support Vector Machine (SVM) algorithms in predicting student stress categories. The dataset was sourced from Kaggle and contains questionnaire-based data, including variables such as sleep quality, frequency of headaches, academic achievement, study workload, participation in extracurricular activities, and stress level classifications. The study followed several stages, including data preprocessing, feature normalization, model development, and performance assessment. Model evaluation was conducted using accuracy, precision, recall, F1-score, and confusion matrix metrics. To validate the practical implementation of the models, both algorithms were incorporated into a web-based application built with the Flask framework and supported by a MySQL database. The experimental results revealed that the KNN algorithm delivered superior classification performance compared to SVM. KNN obtained an accuracy score of 88.46% and a weighted F1-score of 0.89, whereas SVM achieved 46.15% accuracy with a weighted F1-score of 0.41. These findings suggest that KNN is more effective in identifying patterns within the student survey data. In addition, the successful deployment of the prediction system demonstrates that conventional machine learning methods can be utilized to provide real-time assessments of student stress levels and support mental health monitoring efforts.
Sentiment Analysis of Skincare Product Reviews: A Comparison of Naïve Bayes and Support Vector Machine Algorithms Refida Septiana Putri; Reykha Putri Randika; Febi Dwi Sasmita; Pungkas Subarkah
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13227

Abstract

The rapid growth of the skincare industry has generated a massive volume of consumer reviews on e-commerce platforms, making manual sentiment analysis increasingly impractical. This study compares the performance of Multinomial Naïve Bayes and Support Vector Machine (SVM) for sentiment classification of skincare product reviews using the Sephora Products and Skincare Reviews dataset from Kaggle, consisting of 602,130 reviews. Unlike previous studies that often employ different datasets and experimental settings, this research evaluates both algorithms using a uniform pipeline, including automatic sentiment labeling based on rating values, text preprocessing, Bag of Words feature representation, and identical evaluation procedures. Model performance was assessed using Area Under Curve (AUC), Accuracy, Precision, Recall, F1-Score, and Matthews Correlation Coefficient (MCC). The results indicate that positive sentiment dominates the dataset (82.37%), resulting in a highly imbalanced class distribution. Multinomial Naïve Bayes achieved better performance than SVM on most evaluation metrics, with an AUC of 0.784, F1-Score of 0.764, Precision of 0.749, and MCC of 0.153, whereas SVM obtained an AUC of 0.497, F1-Score of 0.743, Precision of 0.695, and MCC of 0.000. The near-zero MCC and low AUC of SVM suggest that the model struggled to distinguish minority classes under extreme class imbalance despite achieving high accuracy. These findings highlight the importance of employing multiple evaluation metrics beyond accuracy when assessing classification performance on imbalanced datasets. Furthermore, the results indicate that Multinomial Naïve Bayes provided better performance than SVM under the dataset characteristics and experimental configuration used in this study.

Page 93 of 101 | Total Record : 1006

 91   92   93   94   95 

Filter by Year

2017 2026


Reset
Filter By Issues
All Issue Vol. 10 No. 4 (2026): August 2026 Vol. 10 No. 3 (2026): June 2026 Vol. 10 No. 2 (2026): April 2026 Vol. 10 No. 1 (2026): February 2026 Vol. 9 No. 6 (2025): December 2025 Vol. 9 No. 5 (2025): October 2025 Vol. 9 No. 4 (2025): August 2025 Vol. 9 No. 3 (2025): June 2025 Vol. 9 No. 2 (2025): April 2025 Vol. 9 No. 1 (2025): February 2025 Vol. 8 No. 2 (2024): December 2024 Vol. 8 No. 1 (2024): July 2024 Vol. 7 No. 2 (2023): December 2023 Vol. 7 No. 1 (2023): July 2023 Vol. 6 No. 2 (2022): December 2022 Vol 6 No 1 (2022): July 2022 Vol 5 No 2 (2021): December 2021 Vol. 5 No. 2 (2021): December 2021 Vol 5 No 1 (2021): July 2021 Vol. 5 No. 1 (2021): July 2021 Vol 4 No 2 (2020): Desember 2020 Vol. 4 No. 2 (2020): Desember 2020 Vol 4 No 1 (2020): Juli 2020 Vol 3 No 2 (2019): Desember 2019 Vol 3 No 1 (2019): Juli 2019 Vol 2 No 2 (2018): Desember 2018 Vol 2 No 1 (2018): Juli 2018 Vol. 2 No. 1 (2018): Juli 2018 Vol 1 No 2 (2017): Desember 2017 Vol 1 No 1 (2017): Juli 2017 More Issue