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
 96   97   98   99   100 
Analysis of User Sentiment Toward Mountain Climbing Content Based on YouTube Comments Using the K-Nearest Neighbors Algorithm Ghiffari Arrozaq; Sri Mujiono
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.v10i4.13518

Abstract

The growth of social media has made YouTube one of the primary sources of information regarding mountain climbing activities. YouTube’s comment feature contains a variety of user opinions that can be used to gauge public perception of climbing content. However, the sheer volume of comments makes manual analysis less effective. This study aims to analyze user sentiment toward mountain climbing content based on YouTube comments using the K-Nearest Neighbor (KNN) algorithm. The research method used is a quantitative approach involving data collection through YouTube comment crawling, manual sentiment abelling, and data preprocessing which includes cleaning, case folding, normalization, tokenization, stopword removal, and stemming followed by feature weighting using Term Frequency–Inverse Document Frequency (TF-IDF) and classification using the K -Nearest Neighbor (KNN) algorithm. The model was evaluated using a confusion matrix with the metrics of accuracy, precision, recall, and F1-score. The results of the study show that the K-Nearest Neighbor (KNN) algorithm is capable of classifying the sentiment of YouTube comments with a maximum accuracy of 79.35% at K = 5. These results indicate that the K-Nearest Neighbor (KNN) algorithm is quite effective in analyzing the sentiment of comments related to mountain climbing content, although it still has limitations in understanding semantic context, such as the use of informal language, irony, and sarcasm. Therefore, future research is recommended to use more complex feature representation methods, such as Word2Vec, FastText, or BERT-based models, to improve classification capabilities and sentiment analysis accuracy.
Comparative Analysis of Machine Learning Algorithms for Lung Cancer Classification: A Progressive Evaluation from Preprocessing to Hyperparameter Tuning Laurentius Joandanu; Usman Sudibyo
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.v10i4.13523

Abstract

Lung cancer is one of the leading causes of cancer-related deaths worldwide, with the main challenge being the difficulty of diagnosis at an early stage. Machine learning-based approaches have been proven to provide efficient solutions in supporting the classification process of this disease. This study proposes a comparative study of five machine learning algorithms, namely K-Nearest Neighbors (KNN), Logistic Regression, Random Forest, CatBoost and LightBGM, for lung cancer classification using the survey_lung_cancer.csv dataset consisting of 309 instances and 16 clinical features. All models were trained using a comprehensive preprocessing pipeline including duplicate data removal, missing values handling, outlier handling using the Interquartile Range (IQR) method, and categorical feature encoding using One-Hot Encoding. Hyperparameter optimization was performed uniformly using RandomizedSearchCV with Stratified K-Fold (k=10) and 50 iterations to ensure a fair comparison between algorithms. Each algorithm was evaluated under three progressive modelling conditions: baseline, after preprocessing, and after hyperparameter tuning, to quantify the individual contribution of each stage to model performance. The results show that Random Forest consistently recorded the best performance across all modelling conditions with an accuracy of 0.9464 and F1-Score of 0.9684 after applying preprocessing and hyperparameter tuning, demonstrating the effectiveness of the proposed progressive preprocessing and hyperparameter tuning pipeline. Learning curve analysis proves that none of the models experienced significant overfitting on the dataset used, indicating stable performance that has yet to be validated on independent clinical data.
Digital Gold Price Prediction on Indogold Platform Using Generalized Autoregressive Conditional Heteroskedasticity Model Devni Prima Sari; Siti Syadza Najiba
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.v10i4.13524

Abstract

The digital gold market in Indonesia has experienced significant growth, with transaction values reaching IDR 53.3 trillion during January–November 2024, representing a 556 percent increase compared to the previous year. Despite this rapid growth, digital gold prices exhibit high volatility characterized by volatility clustering and conditional heteroskedasticity that conventional time series models cannot adequately capture. Although the GARCH model has been widely applied to predict physical gold prices, no prior study has specifically examined digital gold price volatility on Indonesian fintech-based trading platforms. This study aims to construct a univariate Generalized Autoregressive Conditional Heteroskedasticity (GARCH) model based solely on historical price movements to predict digital gold prices on the Indogold platform and evaluate its predictive accuracy. Accordingly, the proposed model relies exclusively on historical price data and does not incorporate external macroeconomic variables, such as exchange rates, inflation, interest rates, or international gold prices. The data used consisted of weekly closing prices of digital gold on the Indogold platform from January 5, 2020, to December 29, 2024, totaling 261 observations. Analysis was conducted using RStudio software through logarithmic return calculation, data splitting via trial and error (selected proportion 80%:20%), Augmented Dickey-Fuller stationarity testing, ARMA order identification through ACF and PACF plots followed by AIC-based model selection, ARCH-LM effect testing, GARCH model estimation, and Ljung-Box and ARCH-LM diagnostic testing. The best model identified was ARMA(2,2)-GARCH(1,1) with the conditional variance equation σₜ² = 0.000073 + 0.405334εₜ₋₁² + 0.476482σₜ₋₁². The model passed all diagnostic tests with Ljung-Box p-value = 0.3362 and ARCH-LM p-value = 0.9999. Prediction accuracy evaluation on the test data yielded MAPE = 1.8141%, which is categorized as highly accurate according to Lewis (1982), indicating strong price forecasting performance; however, its suitability as an investment decision-making tool requires further evaluation of return, risk, and trading strategy performance beyond price accuracy alone.
Artificial Intelligence and the Future of Digital Banking in Nigeria: A Systematic Review of Emerging Opportunities and Associated Risks Omojokun Gabriel Aju
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.v10i4.13550

Abstract

Artificial intelligence (AI) is increasingly embedded in digital banking, yet evidence concerning its actual adoption, operational value, and governance implications in Nigeria remains fragmented. This study provides a PRISMA 2020-guided systematic literature review to examine the emerging opportunities and associated risks of AI-enabled digital banking in Nigeria. Scopus, Web of Science, IEEE Xplore, and Google Scholar were searched for English-language publications issued between 2018 and 2026, supplemented by selected policy and organisational documents. From 3,583 identified records, 1,258 were screened, 236 full texts were assessed, and 89 records were retained. Evidence was appraised using source-sensitive criteria derived from the Mixed Methods Appraisal Tool, AMSTAR 2, and AACODS, and was synthesised through thematic, temporal, technology-use-case, and adoption-maturity analyses. The evidence indicates that AI adoption in Nigerian banking is accelerating but remains uneven and predominantly function-specific. Fraud detection, cybersecurity, customer-service automation, and predictive analytics show the clearest operational uptake, whereas explainable credit scoring, generative AI, and enterprise-wide integration remain emergent. Benefits relating to efficiency, financial inclusion, personalisation, and risk detection are inseparable from data-protection, bias, cybersecurity, model-risk, skills, and infrastructure constraints. The review contributes a Nigeria-specific socio-technical synthesis that links AI capabilities, institutional readiness, adoption maturity, and regulatory safeguards. Sustainable deployment requires privacy-by-design, model validation, human oversight, interoperable digital infrastructure, and coordinated supervision by banking, data-protection, and technology regulators.
Accuracy Analysis of the Capsule Network Method in Cataract Fundus Image Classification Salshabila Putri; Arnawan Hasibuan; 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.v10i4.13557

Abstract

Cataract is one of the leading causes of blindness worldwide and requires early detection to prevent vision deterioration. Advances in artificial intelligence, particularly deep learning, have enabled the development of automated systems for medical image classification. However, conventional Convolutional Neural Networks (CNNs) tend to lose important spatial information due to pooling operations, which may affect classification performance. This study aims to analyze the accuracy of the Capsule Network (CapsNet) method for cataract classification using fundus images. The proposed method employs image preprocessing techniques, including resizing, data augmentation, and normalization, before training the CapsNet model. The model was developed using Python and the PyTorch framework. Performance evaluation was conducted using a Confusion Matrix and several metrics, namely Accuracy, Precision, Recall, Specificity, F1-score, and Area Under the Curve (AUC). Experimental results showed that the model achieved a training accuracy of 86.29% and a best validation accuracy of 81.34%. Furthermore, testing on 1,813 fundus images resulted in an accuracy of 89.85%, precision of 94.56%, recall of 84.53%, specificity of 95.15%, F1-score of 89.26%, AUC-ROC of 95.27%, and Average Precision (AP) of 94.71%. These findings indicate that CapsNet is capable of effectively classifying cataract fundus images. Although the obtained performance is consistent with the theoretical capability of CapsNet to preserve spatial relationships among image features, this capability was not directly evaluated in the present study.
Retrieval-Augmented Local Llama 3.2 for Dynamic Quest Generation and Consistent NPC Personalities in Role-Playing Games Benaya Friyandi Siahaan; Hanny Haryanto
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.v10i4.13560

Abstract

The integration of Large Language Models into game engines is hindered by cloud dependency and high latency. This study proposes a fully localized Retrieval-Augmented Generation (RAG) framework using the Llama 3.2 Small Language Model to generate role-playing game quests and maintain character personalities without parameter fine-tuning. Operating within a C++ environment under strict hardware constraints (primarily CPU-bound), the methodology evaluates three retrieval methods (MiniLM, FastText, and BPE Tokenizer) combined with a memory-efficient JSON Vector Database. System effectiveness was measured using BLEU, ROUGE, and user evaluations. Results show the initial BPE Tokenizer achieved the lowest quest generation time of 152.01 seconds, the fastest average response time of 23.53 seconds, the highest BLEU score of 0.0118, and a peak persona consistency score of 3.70. However, the relatively long response times remain a primary weakness hindering real-time immersion. Furthermore, a critical "Stopping Condition Dilemma" emerged; lacking engine awareness, the model failed to detect narrative conclusions. This caused generation loops that spiked processing times up to 220.59 seconds. Future research must integrate strict, state-based logic triggers from the game engine to prevent context collapse and optimize inference to reduce latency.
Benchmarking Pseudo-Mask Generation Methods for ResNet34-U-Net Acne Segmentation Nikita Amelia Valencia; Puguh Hiskiawan
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.v10i4.13568

Abstract

Acne lesion segmentation is essential for automated dermatological image analysis. However, developing accurate deep learning segmentation models requires pixel-level annotations, which are costly and time-consuming to obtain. To address this limitation, pseudo-mask generation methods can be utilized to produce surrogate labels for training segmentation networks without manual annotation. This study presents a comparative evaluation of five pseudo-mask generation methods for acne lesion segmentation, namely Contour-Based, Superpixel (SLIC), K-Means, Weakly Supervised Semantic Segmentation (WSSS) based on Otsu Thresholding and Morphological Operations, and Pseudo-Mask-Based Generation. The generated pseudo masks were employed as supervisory labels to train a ResNet34-U-Net segmentation model under identical experimental settings. To improve the robustness of the training process, data augmentation was applied exclusively to the training dataset. Segmentation performance was quantitatively evaluated using Dice Score, Intersection over Union (IoU), Precision, Recall and Validation Loss, and qualitatively assessed through visual comparisons of the generated pseudo masks and predicted segmentation results. The experimental results demonstrate that pseudo-mask quality has a substantial impact on segmentation performance. Among the evaluated methods, Superpixel (SLIC) achieved the highest performance with a Dice Score of 0.898, an IoU of 0.815, a Precision of 0.889, a Recall of 0.908, and the lowest validation loss of 0.268 indicating superior lesion boundary preservation and region consistency. WSSS (Otsu + Morphology) also produced competitive results, whereas Pseudo-Mask-Based and Contour-Based methods yielded comparatively lower performance. These findings demonstrate that high-quality pseudo masks can provide effective supervision for ResNet34-U-Net training, offering an annotation-efficient approach for acne lesion segmentation and providing practical insights into selecting suitable pseudo-mask generation methods for dermatological image analysis.
Human Body Posture Classification from Digital Images Using the InceptionV3 Architecture Munandar Rahmat Prayogi; Christy Atika Sari; Eko Hari Rachmawanto
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.v10i4.13571

Abstract

This study aims to develop a human body posture classification model based on digital images using the InceptionV3 architecture. The dataset used in this study is the MPII Human Pose Dataset, which contains a wide variety of human activities and body postures. The research began with label extraction from a metadata file in .mat format, followed by the selection of the 20 activity classes with the largest number of samples. Subsequently, the dataset was balanced using an undersampling technique, resulting in 140 images for each class. The images were then resized to 224×224 pixels, normalized using the preprocess_input function, and enhanced through data augmentation applied to the training set. The model was developed using a transfer learning approach with InceptionV3 as the base model. Additional layers, including Global Average Pooling, Dropout, and Dense layers, were added to perform multi-class classification. The experimental results showed that the proposed model achieved a test accuracy of 0.8893 with a test loss of 0.5587. Furthermore, the macro-average metrics obtained from the classification report were 0.9018 for precision, 0.8893 for recall, and 0.8877 for F1-score. These results indicate that the model was able to classify most activity classes effectively. However, several classes with similar visual characteristics still caused misclassification, indicating opportunities for further improvement in human posture recognition performance.
Performance Analysis of YOLO26 in Pothole Detection on an Indonesian Road Dataset Mohammad Alwi Nanda Saputra; Farrikh Alzami; Christy Atika Sari
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.v10i4.13585

Abstract

Road damage is one of the infrastructure problems that can compromise safety, comfort, and the smooth flow of traffic. The road inspection process, which is still carried out manually, requires a relatively large amount of time, labor, and cost, making a more efficient method necessary. Advances in computer vision and deep learning technologies enable the automatic detection of road damage through an object detection approach. This study aims to analyze the performance of the YOLO26l model as a baseline model in detecting four categories of road damage such as potholes, alligator cracking, lateral cracking, and longitudinal cracking using the Road Damage Indonesia Dataset. The dataset was divided into 70% training data, 15% validation data, and 15% testing data. The training process was conducted using the pre-trained weights from yolo26l.pt via the Ultralytics framework without any architectural modifications or the application of image enhancement methods. Performance evaluation was conducted using the Precision, Recall, mAP@0.50 (mAP@0.50), and mAP@0.50:0.95 (mAP@0.50:0.95) metrics. The results of the study show that the YOLO26l model achieved a Precision of 0.7028, a Recall of 0.6492, a mAP@0.50 of 0.6890, and a mAP@0.50:0.95 of 0.3391. Analysis using a confusion matrix, precision–recall curve, and visualization of the detection results showed that the model was able to identify all four categories of road damage well, although there were still some objects that went undetected under poor lighting conditions, due to small object sizes, or complex road surface textures. Based on these results, it can be concluded that YOLO26l performs well as a baseline model for road damage detection on the Indonesian road dataset
Image Classification using DenseNet-121 Based on MediaPipe Face Mesh for Real-Time Drowsiness Detection Raihan Ramadhan Hamzah; Christy Atika Sari; Eko Hari Rachmawanto; Rabei Raad Ali
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.v10i4.13586

Abstract

The high rate of traffic accidents caused by driver drowsiness and microsleep highlights the urgent need for reliable driver monitoring systems. However, conventional Eye Aspect Ratio (EAR) methods often fail due to their high sensitivity to changes in head poses and ambient lighting conditions, while standard Convolutional Neural Network (CNN) models impose heavy computational loads on hardware. This study aims to implement and evaluate a real-time drowsiness detection system by integrating the DenseNet-121 architecture with MediaPipe Face Mesh. The proposed method utilizes MediaPipe Face Mesh to isolate the left and right eye Regions of Interest (ROI) independently, using a proportional padding of 35%, which are then classified using a DenseNet-121 transfer learning model fine-tuned in two stages across its last 30 layers. Evaluation was conducted using a custom dataset of 2,000 source images from five subjects, yielding 3,926 eye-region samples after extraction and quality filtering, assessed using a Subject-Independent Leave-One-Subject-Out (LOSO) cross-validation protocol. Across five folds, the model achieved a mean accuracy of 83.22% (standard deviation 13.22 percentage points) and a mean AUC of 0.879 (standard deviation 0.131), with performance variation across subjects found to correlate with inter-subject differences in eye-closure expressiveness, where the two lowest performing subjects also exhibited the lowest AUC values (0.707 and 0.769). The system achieved an average total latency of 198.00 ms per frame, equivalent to 5.1 FPS. These findings indicate that the integration of MediaPipe Face Mesh and DenseNet-121 shows meaningful potential for real-time drowsiness monitoring, while also highlighting the importance of subject-independent evaluation and cross-domain generalization for reliable real-world deployment.

Page 98 of 101 | Total Record : 1006

 96   97   98   99   100 

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