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
 81   82   83   84   85 
Benchmarking YOLOv12 Variants for Indonesian Traditional Cuisine Detection Fauzan Firdaus; Lidya Ningsih; Aminah Indahsari Marsuki; Angel Metanosa Afinda
Journal of Applied Informatics and Computing Vol. 10 No. 3 (2026): June 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i3.12625

Abstract

YOLOv12 is one of the latest YOLO versions currently. Several studies have proven that YOLOv12 has better performance compared to previous versions. YOLOv12 itself has five model variants based on its architectural complexity, namely nano, small, medium, large and extra larges. This study tests the performance of YOLOv12 model variants (n, s, m, l, x) for traditional Indonesian culinary detection using a domain-specific object detection dataset. The dataset contains 718 images with 720 bounding-box instances annotated across 20 culinary classes, divided into 418/150/150 images for training/validation/testing. Data processing was performed in Roboflow with automatic orientation and stretching resizing to 640×640, while the training split was enriched using augmentation (horizontal and vertical flips) to increase sample diversity. All YOLOv12 variants were trained with the same configuration and environment, for 50 epochs using the Ultralytics framework with default hyperparameters on an NVIDIA A100-SXM4 80GB GPU. On the validation set, all variants achieved high detection accuracy (mAP@0.5 = 0.985–0.991), while differences emerged under a more stringent localization criterion (mAP@0.5:0.95). The best overall localization performance was achieved by YOLOv12-L (mAP@0.5:0.95 = 0.874), while YOLOv12-N provided the fastest inference (0.8 ms/image) with competitive accuracy (mAP@0.5:0.95 = 0.822). These findings provide preliminary guidance for selecting YOLOv12 variants based on the trade-off between accuracy and speed.
Decision Tree for Sentiment Analysis of Facebook Social Media Posts Related to Traffic Congestion in Palembang City Sukemi Sukemi; Ahmad Fali Oklilas; Hatta Efrizal
Journal of Applied Informatics and Computing Vol. 10 No. 3 (2026): June 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i3.12627

Abstract

This study aims to analyze public perception of traffic congestion in Palembang City through sentiment analysis on Facebook using the Decision Tree algorithm. Data were collected from public comments related to traffic over 32 months using web scraping techniques. Text data were processed through preprocessing stages including case folding, tokenization, stemming, and stopword removal, followed by TF-IDF feature extraction with unigram representation. The model classifies sentiments into positive, negative, and neutral categories. The results show an accuracy of 90.42%. However, the model tends to perform better on the neutral class, influenced by imbalanced data distribution. Therefore, evaluation metrics such as precision and recall are also considered to provide a more comprehensive analysis.
Factor Analysis Influencing Review Scores on E-Commerce Platforms Using Machine Learning Meylani Utari; Kanda Januar Miraswan; Anna Dwi Marjusalinah
Journal of Applied Informatics and Computing Vol. 10 No. 3 (2026): June 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i3.12631

Abstract

In recent years, the rapid growth of e-commerce has made customer reviews an important indicator of product quality, service performance, and customer satisfaction. Review scores play a crucial role in influencing purchasing decisions and evaluating overall shopping experiences on e-commerce platforms. This research aims to analyze the main factors influencing customer review scores by integrating logistics, transaction, and product-related variables using a machine learning approach. The dataset consists of various e-commerce transaction attributes, including delivery information, payment details, and product characteristics. A Random Forest classifier is employed to predict customer review scores and to identify dominant influencing factors through feature importance analysis. The results show that logistics-related factors, particularly delivery time, are the most influential variables affecting review scores, followed by payment value, freight value, and product price. This study also emphasizes the significance of understanding how models work and their real-world applications, offering useful guidance on enhancing logistics efficiency, ensuring clear transaction records, and maintaining high standards of product information. Product attributes such as description length, weight, and physical dimensions also contribute significantly to customer satisfaction. By combining predictive capability and interpretability, this research provides valuable insights for sellers and e-commerce platform managers to improve service quality, optimize logistics performance, and enhance customer satisfaction.
Enhancing Cyberbullying Sentiment Detection: A Comparative Study of IndoBERT and IndoBERTweet over SMOTE and Bernoulli Naive Bayes Approach Eka Mardiana Putri; Mochammad Anshori; M. Syauqi Haris
Journal of Applied Informatics and Computing Vol. 10 No. 3 (2026): June 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i3.12632

Abstract

Cyberbullying has become a critical issue in social media use because it can negatively impact users’ mental health and social interactions. The high volume of aggressive comments and hate speech on digital platforms highlights the need for an automatic detection system that can accurately and reliably identify cyberbullying content. This research compares the performance of Indonesian language transformer models, IndoBERT and IndoBERTweet, in detecting text-based cyberbullying. Before modeling, the dataset undergoes Exploratory Data Analysis to understand its characteristics, class distribution, comment length, and potential data imbalance. Next, text preprocessing and tokenization are performed before dividing the data using stratified holdout splitting to preserve class proportions in training and testing sets. Both models are then trained with the same hyperparameter settings to ensure an objective and fair performance comparison. Results show that IndoBERT achieved an accuracy of 0.8333, while IndoBERTweet performed better with an accuracy of 0.8409. The analysis of the confusion matrix and ROC curve confirms that IndoBERTweet is more effective at detecting cyberbullying across different classes. Compared to previous studies using the SMOTE method and Bernoulli Naïve Bayes algorithm, which achieved 84.00% accuracy, this study's findings are slightly higher at 84.09%. Notably, this was achieved without using synthetic oversampling techniques. This suggests that the approach employed in this research can deliver competitive performance even without data balancing with SMOTE. Overall, these findings indicate that a transformer-based approach, combined with a more representative dataset, can improve cyberbullying detection more efficiently and practically. Therefore, IndoBERTweet is a more suitable model for implementing a cyberbullying content moderation system in Indonesia.
Hybrid Machine Learning for Knowledge Discovery in E-Commerce Reviews Jeremiah Alwin Siahaan; Lailla Syal Syabilla; M. Thoriqul Fadli; Mei Intan Natasyah; Allsela Meiriza; Ken Ditha Tania; Ahmad Rifai
Journal of Applied Informatics and Computing Vol. 10 No. 3 (2026): June 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i3.12635

Abstract

The rapid growth of e-commerce platforms like Tokopedia has triggered a massive accumulation of over 65,000 customer reviews, yet it is often accompanied by information pollution in the form of non-informative reviews that hinder consumer decision-making processes. This research aims to extract new knowledge regarding these review characteristics through the implementation of the Knowledge Discovery in Database (KDD) framework, integrating a hybrid K-Means Clustering and Random Forest algorithm. Diverging from conventional classification approaches, this study utilizes K-Means as an exploratory instrument to naturally map six latent topic patterns of reviews based on their textual structure. Experiments were conducted on 35,000 data samples using TF-IDF features enriched by cluster labels as structural predictors. The results indicate that the hybrid model achieves 94.41% accuracy with an F1-score of 0.90 for the non-informative class, showing high stability via 5-Fold Cross-Validation (94.56% ± 0.19%) . The most crucial knowledge discovery is evidenced through SHAP analysis, where the cluster feature ranks 7th out of 1,001 predictor features, confirming that semantic grouping provides a richer structural context than pure lexical features . Furthermore, error analysis reveals specific linguistic challenges such as sarcasm and semantic ambiguity as constraints in automated review detection . This research provides a managerial contribution to e-commerce platforms in enhancing information quality and mitigating information overload issues.
An Applied Data Science Approach for Detecting Depression Symptoms in Indonesian Social Media Text Using Transformer Models Winson Winson; Puguh Hiskiawan
Journal of Applied Informatics and Computing Vol. 10 No. 3 (2026): June 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i3.12644

Abstract

Depression is a mental health disorder that often remains undetected due to limited access to mental health services and persistent social stigma. Social media platforms provide an alternative source for identifying depressive symptoms through linguistic expressions shared by users in textual posts. This study proposes an applied data science approach for detecting depression symptoms in Indonesian social media text using Transformer-based models. The dataset was constructed by combining the DEPTWEET dataset with social media posts collected through keyword-based scraping guided by PHQ-9 indicators. The proposed framework consists of dataset construction, text preprocessing, Transformer-based modeling, and performance evaluation. Two pre-trained language models, IndoBERT and XLM-RoBERTa, were evaluated under two preprocessing configurations, namely normal preprocessing and light preprocessing. Experimental results show that preprocessing strategies significantly influence classification performance. Light preprocessing consistently improves contextual representation and leads to better results compared with normal preprocessing. XLM-RoBERTa combined with light preprocessing achieves the best overall performance with a test accuracy of 0.77 and an F1-score of 0.77. Additional robustness analysis and pairwise model agreement evaluation further indicate that both models maintain relatively stable predictions when processing noisy social media text. Findings from this study demonstrate the effectiveness of Transformer-based models for multi-class depression detection in Indonesian social media environments. The proposed framework provides insights into how applied data science techniques can support large-scale analysis of mental health signals in online platforms and contribute to the development of data-driven approaches for early detection of depression symptoms.
Comparison of Holt’s Exponential Smoothing and Weighted Moving Average Methods in Predicting the Proportion of Alma Mater Sizes Eko Dwi Nugroho; Miranti Verdiana; Leslie Anggraini; Radhinka Bagaskara
Journal of Applied Informatics and Computing Vol. 10 No. 3 (2026): June 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i3.12645

Abstract

The annual admission of new students requires the early procurement of university jackets to ensure distribution during the inauguration ceremony. However, the lengthy production lead time necessitates ordering months before the actual sizing data is fully collected. This issue is further complicated by low participation rates in size registration and extreme population spikes. This study proposes a time series forecasting approach to predict the proportional distribution of jacket sizes rather than absolute quantities. Specifically, the research compares the performance of Holt’s Exponential Smoothing and the Weighted Moving Average (WMA) method using historical size proportions from 2019 to 2025. Walk-forward validation was employed to evaluate the models based on the Mean Absolute Percentage Error (MAPE). The results demonstrate that WMA outperforms Holt’s Exponential Smoothing by achieving a lower MAPE of 6.56%. By extrapolating the WMA proportions to the 2026 target of 5,250 students and mathematically integrating the 6.56% error rate as a safety stock buffer, the final procurement quantities for sizes S through XXXL were precisely determined. This proportional forecasting framework provides a robust, quantitative foundation for institutional supply chain management, allowing early and accurate ordering despite incomplete preliminary data.
Comparative Analysis of the Performance of Machine Learning Methods and Text Embedding Techniques in Classifying Toxic Conversations in the Roblox Game Octa Dama Yanti; Syifa Alfariani; Syifa Naura Milla Celesta; Ken Dhita Tania; Ahmad Rifai
Journal of Applied Informatics and Computing Vol. 10 No. 3 (2026): June 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i3.12646

Abstract

Online games have evolved into digital social spaces where player interactions often include toxic communication, potentially affecting user experience and psychological well-being, especially among younger players. This research is intended to examine and compare the performance of various machine learning algorithms in classifying toxic chat on the Roblox platform and to identify underlying linguistic patterns. The dataset consists of 7,119 Indonesian-language chat data labeled into six categories: identity_hate, insult, obscene, severe_toxic, threat, and toxic. The methodology includes data preprocessing, text representation using Bag-of-Words (BoW) and TF-IDF, and classification using Naive Bayes, Support Vector Machine (SVM), and Random Forest. To assess how well the model performs, several metrics are used, including accuracy, precision, recall, F1-score, and 3-fold cross-validation. The results show that SVM with TF-IDF achieves the best performance with 84.48% accuracy, followed closely by SVM with BoW. The findings indicate that while classical machine learning models remain effective, challenges persist in distinguishing linguistically similar categories.
Sasirangan Motif Classification Using MobileNetV2 Transfer Learning for Cultural Heritage Preservation Nadia Azaria; Mahdi Mahdi; Muhammad Hanafi; Mambang Mambang; Trifebi Shina Sabrila; Finki Dona Marleny
Journal of Applied Informatics and Computing Vol. 10 No. 3 (2026): June 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i3.12648

Abstract

Sasirangan is a traditional textile from South Kalimantan renowned for its unique motifs and deep cultural significance. However, the preservation of Sasirangan motifs is increasingly challenged by the declining number of skilled craftsmen and inadequate digital documentation. This study presents the development of an automated motif classification system to support the digital preservation of Sasirangan cultural heritage. The system was developed using the MobileNetV2 architecture with transfer learning from ImageNet pre-trained weights, implemented through the TensorFlow framework. A dataset comprising 70 images from 9 different Sasirangan motifs was utilized. To address the limited dataset size, various data augmentation techniques were applied. In the proof-of-concept phase, a binary classification task (Gigi Haruan vs. Unknown) was conducted using an 80:10:10 training-validation-test split. Experimental results demonstrated strong model performance, achieving 96.06% test accuracy for Gigi Haruan motif detection, 96.5% average F1-score, and 98.31% rejection accuracy for non-Sasirangan images. Additionally, a user-friendly web interface based on Gradio was developed, featuring real-time prediction through webcam integration. This study highlights the effectiveness of transfer learning in classifying traditional textile motifs and provides a solid foundation for future advancements, including multi-class classification and cloud-based database integration. The proposed system is expected to contribute significantly to the documentation, education, and preservation of Sasirangan cultural heritage in the digital era.
Temporal Deep Learning for Probabilistic Mutation Forecasting in SARS-CoV-2 Spike Protein Sequences Robert Selemani; Belinda Ndlovu; Amazing Maphosa
Journal of Applied Informatics and Computing Vol. 10 No. 3 (2026): June 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i3.12650

Abstract

Modelling the evolution of biological sequences under temporal and probabilistic constraints remains a complex computational challenge. This study investigates longitudinal deep learning for probabilistic modelling of mutation patterns in the SARS-CoV-2 Spike Protein. A stacked Long Short-Term Memory (LSTM) network is trained on temporally ordered amino acid sequences to estimate residue-level substitution probabilities and rank plausible future mutations. Unlike deterministic classification approaches, the proposed framework treats mutation prediction as a probabilistic ranking task, accounting for the inherent uncertainty of viral evolution. The model is evaluated using metrics suitable for imbalanced sequence data, including Top-K accuracy, precision, recall, F1-score, and ROC-AUC. Results indicate strong ranking performance, with Top-3 accuracy of 94.6% and ROC-AUC of 0.91. In comparison, the overall accuracy (93.1%) is interpreted cautiously, given the dominance of conserved residues. Error analysis shows that difficult predictions are concentrated in low-frequency, rapidly evolving residue positions. A comparison with a frequency-based baseline demonstrates that the LSTM captures temporal dependencies beyond static substitution patterns. Predicted mutation distributions exhibit a structured alignment with known functional regions of the Spike Protein, as supported by the established literature, providing qualitative biological validation. This study contributes a temporally structured and probabilistic framework for mutation modelling, emphasising ranking-based evaluation and biologically contextualised interpretation. The findings demonstrate the feasibility of probabilistic mutation forecasting under controlled experimental conditions and provide a methodological foundation for future research on AI-assisted genomic surveillance.

Page 83 of 101 | Total Record : 1006

 81   82   83   84   85 

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