cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Ari Zulsafar
Contact Email
zulsapar@telkomuniversity.ac.id
Phone
+6285280983983
Journal Mail Official
jasminejournal@telkomuniversity.ac.id
Editorial Address
Jl. Telekomunikasi No. 1 Terusan Buahbatu - Bojongsoang. Kabupaten Bandung. Jawa Barat 40257. Indonesia.
Location
Kota bandung,
Jawa barat
INDONESIA
Jasmine : Journal of Intelligent Systems and Machine Learning
Published by Universitas Telkom
ISSN : -     EISSN : 31634788     DOI : https://doi.org/10.25124/jasmine
Core Subject :
JASMINE: Journal of Intelligent Systems and Machine Learning welcomes submissions covering a wide range of topics, including, but not limited to: Deep Learning and Pattern Analysis: Neural networks, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), deep reinforcement learning, data mining, clustering, classification, anomaly detection. Computer Vision: Image processing, object recognition, scene understanding, image captioning. Natural Language Processing (NLP) and Recommender Systems: Text analysis, speech recognition, machine translation, sentiment analysis, personalization algorithms, collaborative filtering, content-based recommendations. Biomedical Engineering and Bioinformatics: AI/ML applications in medical diagnostics, drug discovery, personalized medicine, genomic data analysis, protein structure prediction, computational biology. Optimization Algorithms: Swarm intelligence, evolutionary computation, metaheuristics for complex problem-solving.
Arjuna Subject : -
Articles 13 Documents
 1   2 
CNN-Based Deep Learning Utilization Model for Identification of Crystal Guava Leaf Diseases Ali Mustadji; Arie Qur'ania; Asep Saepulrohman
JASMINE: Journal of Intelligent Systems and Machine Learning Vol. 1 No. 1 (2026)
Publisher : Universitas Telkom

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/jasmine.v1i1.10011

Abstract

Identification of plant diseases is a crucial step in maintaining plant health and preventing economic losses due to decreased productivity. This research aims to develop an intelligent system capable of identifying diseases in Crystal Guava (Psidium guajava L.) plants using a Convolutional Neural Network (CNN) method. The method combines digital image processing techniques with machine learning to classify Crystal Guava leaf images into two categories: healthy and diseased. The implemented CNN architecture is based on the Xception model, known for its superior performance in image classification tasks. The dataset used consisted of 1,500 Crystal Guava leaf images, including both healthy and diseased leaves. Test results showed that the developed system achieved 94% accuracy in identifying diseases in Crystal Guava plants, surpassing the performance of other architectures such as VGG16 and InceptionV3. This high accuracy demonstrates the model's ability to recognize complex features in Crystal Guava leaf images. These findings contribute to the development of artificial intelligence-based diagnostic tools for early detection of plant diseases. The proposed system is expected to assist farmers, agricultural researchers, and policymakers in making informed decisions to improve the productivity and health of Crystal Guava plants.
Deep Learning Model for Identification of Indonesian National Figure Entities on Social Media Using LSTM Architecture Very Setiawan; Dwi Utari Iswavigra; Mutia Ulfa
JASMINE: Journal of Intelligent Systems and Machine Learning Vol. 1 No. 1 (2026)
Publisher : Universitas Telkom

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/jasmine.v1i1.10057

Abstract

In the era of rapid digital communication, social media has become a dominant medium for information exchange and public discourse, particularly in Indonesia. Despite this growth, automatic identification of national figures within social media texts remains a significant challenge due to the informal nature of language, frequent abbreviations, and inconsistent spelling patterns. Addressing this gap, this study aims to develop a Deep Learning model based on Long Short-Term Memory (LSTM) networks to identify Indonesian national figures from social media texts. The research utilizes 1,109 tweets collected from X (formerly Twitter) through the X API, encompassing names of well-known figures from politics, sports, entertainment, and social activism. The research process includes dataset crawling, preprocessing, labeling using the spaCy library, dividing training and test data, and training an LSTM model. The evaluation results show that the proposed model achieves a high level of performance, achieving 97.8% accuracy, 96% precision, 93% recall, and an F1-score of 92% on the validation data, demonstrating the LSTM model's ability to make accurate and reliable predictions. Word cloud analysis shows that the model is able to consistently recognize person entities such as "Prabowo", "Sri Mulyani", and "Agnez Mo". However, the model still experiences limitations in detecting unfamiliar or rarely appearing entities. Overall, this study shows that the combination of spaCy and LSTM is effective for NER tasks on Indonesian social media texts and has the potential for further development with increased data variety and improvements to the labeling process.
Public Sentiment Toward Rupiah Redenomination on Social Media X Agung Febrian; Dody Herdiana; M. Agreindra Helmiawan
JASMINE: Journal of Intelligent Systems and Machine Learning Vol. 1 No. 1 (2026)
Publisher : Universitas Telkom

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/jasmine.v1i1.10121

Abstract

This study examines public sentiment toward the proposed Indonesian Rupiah redenomination policy using data collected from Social Media X. The research applies a structured computational sentiment analysis pipeline, beginning with automatic sentiment labeling using a transformer-based language model, followed by classification using a Support Vector Machine with Term Frequency–Inverse Document Frequency feature representation. The dataset was collected over a one-day period from 7 November 2025 to 8 November 2025 to capture immediate public reactions to the policy discourse. Experimental results show that the classification model achieved an accuracy of 0.68 with balanced classification performance. Rather than aiming to optimize predictive accuracy, this study focuses on identifying general sentiment tendencies and patterns of public opinion regarding currency redenomination. The findings indicate that negative sentiment dominates the discourse, reflecting public concern and hesitation toward the policy, while a substantial proportion of neutral sentiment suggests ongoing evaluation and uncertainty among users. These results highlight the complexity of public responses to monetary policy communication and demonstrate the potential of social media analysis to provide an indicative overview of public sentiment in the digital public sphere. The study also acknowledges limitations related to automatic labeling and the inherent ambiguity of social media language, emphasizing that the findings should be interpreted as exploratory insights rather than definitive conclusions.
Decision Tree-Based Early Warning System for Academic Failure: Comparative Analysis with Random Forest and Logistic Regression Virzan Pasa Nugraha; Fidi Supriadi; David Setiadi
JASMINE: Journal of Intelligent Systems and Machine Learning Vol. 1 No. 1 (2026)
Publisher : Universitas Telkom

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/jasmine.v1i1.10123

Abstract

A Decision Tree–based early warning system for academic failure was evaluated using a dataset of 649 student observations and compared with Random Forest and Logistic Regression models through nested ten-fold cross-validation. The mean accuracy of the Decision Tree model was 0.9169, compared to 0.9260 for the Random Forest model and 0.8922 for the Logistic Regression model. Although the Random Forest model achieved the highest raw accuracy, paired statistical testing indicates that its performance difference with the Decision Tree model is not statistically significant (paired t-test, p = 0.104950). The difference between the Decision Tree model and the Logistic Regression model is statistically significant before Bonferroni correction (p = 0.01734) but becomes non-significant after adjustment (Bonferroni-adjusted p = 0.05201). The Decision Tree model was therefore selected to balance competitive predictive performance with interpretability through explicit and readable decision rules. In out-of-fold evaluation, the Random Forest model achieved the strongest results, with an accuracy of 0.9245, high receiver operating characteristic and precision–recall performance, a balanced accuracy of 0.8409, a minority-class recall of 0.7200, and twenty-eight false-negative predictions. Feature-importance analysis showed that G2 was the most influential variable with a relative importance of 0.2417, followed by G1 with 0.1992. Shapley value analysis and an ablation study further demonstrated that removing G1 and G2 substantially reduced overall accuracy and minority-class recall. These findings support the use of the Decision Tree model in educational contexts, where transparent rule-based decisions can guide early academic interventions while maintaining performance comparable to more complex ensemble methods.
Global Food Waste Prediction (2018-2024): Trend Analysis and Random Forest Regression Model Development kemal pramayuda kemal; Fidi Supriadi; David Setiadi
JASMINE: Journal of Intelligent Systems and Machine Learning 2026: Articles in Press
Publisher : Universitas Telkom

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/jasmine.vi.10124

Abstract

Food waste remains a major global sustainability challenge due to its environmental, economic, and social impacts. Understanding food waste patterns and their contributing factors is essential for supporting effective mitigation strategies. This study aims to (1) investigate food waste trends and patterns through Exploratory Data Analysis (EDA) and (2) develop a predictive model for estimating total food waste using Random Forest Regression. The study utilizes a publicly available dataset containing 5,000 records from 20 countries, covering eight food categories over the period 2018–2024. The dataset includes variables such as food category, economic loss, population, average waste per capita, and household waste percentage. Exploratory analysis reveals variations in waste generation across food categories and countries, with fruits and vegetables contributing a substantial share of total waste. A Random Forest Regression model was developed and evaluated, achieving a coefficient of determination (R²) of 0.9582. In addition to predictive performance, the study highlights the importance of examining key contributing variables to better understand food waste patterns. The findings demonstrate the potential of machine learning techniques as decision-support tools for food waste analysis and management, while also acknowledging the limitations associated with secondary public datasets.
Credit Risk Analysis at Baitul Tanwil Muhammadiyah Cooperative using Supervised Learning Algorithms Luthfi rahmat rahmat; Fathoni M; Dani indra J
JASMINE: Journal of Intelligent Systems and Machine Learning 2026: Articles in Press
Publisher : Universitas Telkom

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/jasmine.vi.10134

Abstract

Credit default is a major challenge faced by microfinance institutions, including Koperasi Baitul Tanwil Muhammadiyah (BTM). The conventional credit scoring process, which relies on manual assessment, often leads to bias and inefficiency. This study aims to develop a credit risk analysis model using supervised learning algorithms to improve the accuracy of credit default prediction among cooperative members. The methodology includes data collection, preprocessing, data splitting into training and testing sets, model training, and performance evaluation using accuracy, precision, recall, F1-score, and AUCROC metrics. Four algorithms are employed: Logistic Regression, Decision Tree, Random Forest, and XGBoost. The expected outcome is a predictive model capable of supporting cooperative decision-making in credit approval through an objective and data-driven approach.
Detection and Classification of Cognitive Distortions in Mental Health Texts Using a Hybrid Natural Language Processing Approach Elizabeth Piscelia Kusuma; Aan Shandy Rahesa; Christin Yulianti; Samuel Ardhian Trisunu
JASMINE: Journal of Intelligent Systems and Machine Learning Vol. 1 No. 1 (2026)
Publisher : Universitas Telkom

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/jasmine.v1i1.10150

Abstract

This study develops a hybrid natural language processing system to detect cognitive distortions in Indonesian text, aiming to support early mental health awareness. The proposed model integrates rule-based keyword matching with a Random Forest classifier, leveraging TF-IDF feature extraction from the preprocessed Indonesian Mental Health Conversation dataset. Evaluation against manually labeled data across eight distortion categories shows the hybrid approach outperforms standalone methods, achieving a classification accuracy of 77.5% and an exact match rate of 76.67%. The system demonstrated robust performance and fairness, maintaining a balanced label distribution across categories and achieving a validation accuracy of 94% on the full dataset. To validate real world applicability, the model was integrated into a reflective chatbot that successfully identifies distorted thinking patterns in user input and retrieves contextually relevant responses. These findings confirm that combining linguistic theory with data driven modeling creates an effective, interpretable, and scalable tool for cognitive distortion detection in informal Indonesian psychological text.
Aspect-Based Sentiment Analysis on Webtoon Reviews Using Ensemble Learning Rival Fakhri Amrullah; Fathoni Mahardika; Dani Indra Junaedi
JASMINE: Journal of Intelligent Systems and Machine Learning Vol. 1 No. 1 (2026)
Publisher : Universitas Telkom

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/jasmine.v1i1.10157

Abstract

The rapid growth of online comic platforms such as LINE Webtoon has produced large volumes of user comments that reflect diverse opinions on storytelling elements. Analyzing these comments provides meaningful insights into reader perceptions of aspects such as plot, characters, and visuals. This study proposes an Aspect-Based Sentiment Analysis (ABSA) framework using ensemble learning to classify sentiment in Indonesian Webtoon reviews. The research follows an experimental quantitative methodology consisting of data collection, text preprocessing, manual annotation of aspects and sentiments, feature extraction using Term Frequency–Inverse Document Frequency (TF-IDF), ensemble model training with Random Forest and XGBoost, and performance evaluation. A total of 1,010 annotated comments were used, covering three aspects—plot, character and visual—and three sentiment categories: negative, neutral, and positive. The results demonstrate that incorporating aspect information enhances sentiment classification performance. While the tuned XGBoost model using TF-IDF features achieved an accuracy of 62.38% in the text-only scenario, the best performance was obtained by the tuned Random Forest ABSA model, which combined TF-IDF and One-Hot Encoded aspect features and achieved an accuracy of 65.84% with a weighted F1-score of 0.65. Class-level analysis shows that neutral comments are the easiest to classify, while negative sentiment remains the most challenging due to informal and context-dependent expressions. A 10-fold cross-validation yielded a mean accuracy of 62.38% with a standard deviation of 0.057, indicating stable generalization. These findings highlight the effectiveness of aspect-enhanced ensemble learning for sentiment analysis in Indonesian Webtoon reviews.
Evaluation of Machine Learning Algorithms for Predicting Phishing Attacks in Higher Education Environments: An Experimental Framework for Enhancing Cybersecurity in Academic Institutions Akmal Muhammad Poetra; Dody Herdiana; Muhammad Agreindra Helmiawan
JASMINE: Journal of Intelligent Systems and Machine Learning 2026: Articles in Press
Publisher : Universitas Telkom

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/jasmine.vi.10178

Abstract

This study evaluates the performance of several machine learning algorithms Logistic Regression, Support Vector Machine, Random Forest, and XGBoost in predicting phishing attacks within higher education environments. Due to the limited availability of anonymized institutional datasets, the research employs a conceptual experiment design and simulation-based approach that mirrors the characteristics of phishing incidents commonly encountered by academic users. The simulated dataset includes URL-based indicators, HTML features, email text elements, and behavioral metadata. The experimental protocol covers synthetic data generation, domain-specific feature engineering, stratified k-fold cross-validation, hyperparameter tuning via grid search, and performance evaluation using accuracy, precision, recall, F1-score, and ROC/AUC. The simulation results indicate that ensemble-based models (Random Forest and XGBoost) outperform linear and kernel-based models, especially in scenarios with class imbalance typical of campus environments. The discussion highlights implications for real-world campus cybersecurity operations, limitations of conceptual simulations, and future research needs such as real-world validation and the integration of user behavior features. The main contribution is a complete experimental framework that can be executed with real institutional datasets, providing guidance for model selection and deployment in higher education cybersecurity systems.
Sentiment Analysis of Instagram Comments on the Ratification of the Criminal Procedure Code Bill using TF-IDF and Multinomial Naive Bayes Dede Yayan Suciyana; Fathoni Mahardika; Dani Indra Junaedi
JASMINE: Journal of Intelligent Systems and Machine Learning 2026: Articles in Press
Publisher : Universitas Telkom

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/jasmine.vi.10188

Abstract

The ratification of the Draft Criminal Procedure Code (RUU KUHAP) has generated a broad and intense public response on social media. This study analyzes public perception of the ratification of the RUU KUHAP through Instagram user comments using Sentiment Analysis techniques based on TF-IDF representation and Multinomial Naive Bayes (MNB) classification. Comments were obtained using the Web Export method based on relevant post links, then preprocessed, converted into TF-IDF features, and classified. The evaluation showed an accuracy of around 66.67%, with the best performance in the negative class, and the positive class was not detected well due to unbalanced data distribution. The findings indicate the dominance of negative and neutral sentiments towards the RUU KUHAP. This study provides an empirical contribution to the understanding of public opinion on national legal issues.

Page 1 of 2 | Total Record : 13

 1   2 

Filter by Year

2026 2026


Reset
Filter By Issues
All Issue Vol. 1 No. 1 (2026) 2026: Articles in Press