Publication Search

Development of digital technology has brought very big change in the world of education especially in the teaching and learning process which is then expected to become more flexible, interactive and easy to access. but in reality digitalization progress also creates challenges in the form of the influence of algorithms low digital literacy and use Artificial Intelligence (AI) which is excessive in the learning process. Community Service Activities (PKM) carried out in order celebration National Education Day (Hardiknas) with a theme Digital Education; Key Opens the Gate Future Unlocked Algorithm. Activities are carried out and implemented via a webinar held and broadcast live via the Islamic Center of East Kalimantan YouTube channel on May 5, 2026. Methods of implementing activities using guided interactive discussions by a moderator and presenting competent speakers in their fields. Results of the discussion shows that technology is increasingly developing able to provide convenience in the process learning and increasing understanding participant regarding the importance of digital education, digital literacy influence of algorithms and usage Artificial Intelligence (AI) wiser in teaching and learning activities.

The increasing use of mobile applications in the retail industry has generated a large volume of user reviews that contain valuable insights regarding customer experience and service quality. However, the unstructured nature of these reviews requires an automated approach to extract meaningful patterns efficiently. This study aims to perform sentiment analysis on user reviews of the Indomaret Poinku application by integrating lexicon-based labeling with machine learning classification. A total of 10,000 reviews were collected from Google Play Store and processed through a series of text preprocessing steps, including cleaning, case folding, normalization, tokenization, stopword removal, and stemming. Sentiment labeling was performed using the Indonesian Sentiment Lexicon (InSet), producing three sentiment classes: positive, negative, and neutral. The labeled data were vectorized using CountVectorizer and classified using two algorithms: K-Nearest Neighbors (KNN) and Random Forest (RF). Evaluation results show that Random Forest outperforms KNN, achieving an accuracy of 82.5%, compared to 69% for KNN. Random Forest demonstrates superior performance in handling high-dimensional sparse text features and yields more stable predictions across sentiment classes. This study contributes to the growing body of research on Indonesian sentiment analysis by demonstrating the effectiveness of combining lexicon-based labeling with ensemble learning methods, offering practical implications for developers seeking to improve the quality and user satisfaction of digital retail applications.

This study presents a comprehensive comparative analysis of four traditional machine learning algorithms Decision Tree, Random Forest, K-Nearest Neighbors, and Support Vector Machine for Android malware detection using the preprocessed TUANDROMD dataset comprising 4,465 instances and 241 features representing both static and dynamic application characteristics. Motivated by the limitations of conventional signature-based and hybrid detection methods, especially in managing imbalanced datasets and detecting emerging malware variants, the study employed SMOTE to ensure balanced training data and fair model evaluation. The dataset was divided into 80% training and 20% testing subsets, and models were assessed using key performance metrics including accuracy, precision, recall, F1-score, and ROC AUC. The findings revealed that the proposed Random Forest model outperformed the other classifiers, achieving an accuracy of 0.993, precision of 0.992, recall of 1.000, F1-score of 0.996, and a near-perfect ROC AUC of 0.9998 surpassing state-of-the-art approaches. These results affirm the superior predictive capability, consistency, and robustness of the Random Forest algorithm in Android malware detection. The study concludes that base models, when integrated with class-balancing techniques, provide reliable and efficient malware detection across imbalanced datasets. For future research, the study recommends exploring advanced hybrid or ensemble frameworks that integrate Random Forest with deep learning architectures or other meta-heuristic optimization techniques to further enhance detection accuracy, adaptability, and resilience against rapidly evolving Android malware threats.

Financial distress is a condition of declining financial health of a company that can develop gradually and lead to business failure if not detected early. With the increasing complexity of the business environment and the limitations of conventional statistical methods, Artificial Intelligence/AI is increasingly being adopted in the development of early warning systems (EWS) to predict financial distress. This study aims to examine the development of AI-based EWS research, identify the most widely used algorithms, and evaluate the effectiveness of AI models compared to conventional methods in predicting financial distress. The method used is a comprehensive systematic literature review of 15 relevant scientific articles. The results show that the paradigm has shifted from statistical models to machine learning and deep learning. Random Forest and Artificial Neural Network are the most widely used algorithms and have better predictive performance. This study offers a conceptual synthesis of the progress, effectiveness, and challenges of applying AI in predicting financial distress and opens opportunities for further research on the development of contextual and interpretative EWS.

Because it directly impacts revenue, customer loyalty, and long-term business sustainability, customer churn is a critical issue for the e-commerce industry. High churn rates indicate that a business is unable to retain existing customers, which means it is more expensive to acquire new customers. Therefore, a precise analytical approach is needed to identify customer behavior patterns that are likely to churn. Using machine learning methods, this study analyzes and predicts customer churn. For this study, the E-Commerce Customer Churn 2025 dataset, obtained from Kaggle, was used. This dataset consists of 10,000 customer data and contains fifteen variables covering transaction behavior, customer characteristics, and churn status. Data preprocessing, descriptive analysis, exploratory data analysis (EDA), and classification model development using Logistic Regression and Random Forest algorithms were part of the research project. Model evaluation was conducted using a Confusion Matrix and Receiver Operating Characteristic (ROC) Curve to evaluate the model's accuracy and ability to distinguish between churned and non-churned customers. The results showed that the Random Forest model performed better than Logistic Regression, with an ROC-AUC of 1.00. Furthermore, feature importance analysis revealed that the days_since_last_purchase variable was the most dominant factor in predicting customer churn. These findings are expected to help e-commerce companies design more effective, data-driven customer retention strategies.  

 Autonomous robot navigation in dynamic and unstructured environments remains a critical challenge due to unpredictable obstacles, sensor uncertainty, and limited adaptability of traditional planning algorithms. Although conventional navigation methods such as graph-based, potential field–based, and sampling-based approaches have been widely adopted, their performance under real-time dynamic conditions is still constrained. This study aims to design and implement a comprehensive experimental framework to evaluate the effectiveness and limitations of conventional navigation algorithms for autonomous mobile robots operating in dynamic unstructured environments. The research adopts an experimental and comparative methodology by implementing A*, Dijkstra, Artificial Potential Field (APF), and Rapidly-Exploring Random Tree (RRT) algorithms in simulated static and dynamic scenarios. Performance is assessed using quantitative metrics including path length, computation time, success rate, collision rate, and path smoothness. The experimental results demonstrate that graph-based algorithms achieve high success rates and optimal path efficiency in static environments but exhibit limited adaptability to dynamic changes. APF offers fast computation but suffers from high collision rates due to local minima, while RRT shows better adaptability in dynamic environments at the cost of longer and less smooth paths. These findings confirm that conventional navigation methods are insufficient for robust autonomous navigation in highly dynamic and unstructured environments. The study highlights the necessity of adaptive and learning-based navigation frameworks, such as deep reinforcement learning, to enhance real-time decision-making, robustness, and autonomy in future robotic systems.

This study investigates the integration of computational thinking (CT) principles with adaptive curricula to enhance problem-solving skills in undergraduate programming education. Traditional programming curricula often emphasize syntax and basic concepts, neglecting critical problem-solving strategies. The adaptive curriculum framework used in this study combines CT skills such as decomposition, pattern recognition, abstraction, and algorithmic thinking with personalized learning experiences. A mixed-method approach, combining qualitative and quantitative research, was employed to assess the effectiveness of this integrated approach. The results show significant improvements in students' problem-solving abilities, conceptual understanding, and engagement compared to a control group following a traditional curriculum. Students in the experimental group, which received the adaptive curriculum, demonstrated better performance in applying algorithms and debugging code. Additionally, students expressed higher levels of engagement and motivation, suggesting that the personalized learning environment fostered greater academic involvement. The study highlights the importance of integrating CT principles with adaptive learning frameworks to create a more inclusive and effective learning environment that accommodates diverse learning needs. The findings suggest that adaptive curricula can bridge gaps in traditional education by providing personalized support and ensuring that students progress at their own pace. This approach is especially beneficial for programming education, where both conceptual understanding and practical problem-solving skills are critical for success. Future research should explore the long-term impact of adaptive learning frameworks and investigate how these technologies can be integrated with traditional teaching methods to maximize their effectiveness.

Detection and identification of plant diseases is critical to the success and efficiency of agricultural production. Plant disease outbreaks are becoming more frequent throughout the world, and the presence of these diseases in cultivated plants has a significant impact on productivity. Therefore, researchers are focusing on developing effective and reliable plant disease detection methods. Thus, farmers can take advantage of early detection of this disease to minimize future losses. This article discusses machine learning approaches as well as decision trees, K-nearest neighbors, naive Bayes, support vector machines (SVM), and random forests for detecting coffee leaf diseases using leaf images. The above-mentioned classifications were researched and compared to determine the most suitable plant disease prediction model with the highest accuracy. Compared with other classification algorithms, the SVM algorithm achieves the highest accuracy of 99.75%. All the models trained above will be used by farmers to quickly identify and classify new diseases in images as a prevention strategy. As a preventive measure, farmers can detect and classify new diseases in images early.

The development of Artificial Intelligence (AI) technology has brought significant changes in the digital learning system, especially in higher education. One of the promising applications of AI is a web-based adaptive learning system that is able to adjust the material, methods, and level of learning difficulty according to the characteristics and needs of each student. This research aims to implement Artificial Intelligence in web-based adaptive learning systems and analyze its impact on the effectiveness of student learning. The research method used is a system development method with a user-centered design approach, which includes the stages of needs analysis, system design, implementation of AI algorithms, and system evaluation. The system was developed by utilizing machine learning algorithms to model student learning profiles based on user interaction data. The results of the study show that AI-based adaptive learning systems are able to increase user engagement, learning effectiveness, and student satisfaction with the online learning process. This research is expected to be a reference for the development of a more personalized and data-based digital learning system in the higher education environment.

Credit scoring is an important element in decision-making for providing financing, especially for microfinance institutions. Several methods for predicting credit scoring include Decession Tree, Gradient Boosted, Neural Network, K-NN, and Rule Induction. This study aims to improve the accuracy of financing risk prediction by efficiently integrating historical data. The Neural Network (NN) algorithm is a machine learning algorithm consisting of neurons (nodes) connected to each other in several layers (input, hidden, and output). NN is used for pattern recognition, classification, regression, and complex non-linear modeling. The NN algorithm has the advantage of working well on large and diverse data and unstructured data. However, the NN algorithm has weaknesses such as overfitting and data dependence. In this study, the integration of the Sample Bootstrapping and Weighted Principal Component Analysis (PCA) methods is proposed to improve optimal accuracy in the NN algorithm. The Sample Bootstrapping method is used to reduce the amount of training data to be processed. The Weighted PCA method is used to reduce attributes. This study uses a financing customer dataset. The results of the study show that the integration of the NN algorithm with Sample Bootstrapping and Weighted PCA resulted in an accuracy increase of 1-3% (97%-99%) compared to other algorithms. Therefore, it can be concluded that the integration of the NN algorithm with Sample Bootstrapping and Weighted PCA produces better accuracy than other algorithms

Background: The development of modern manufacturing systems requires production scheduling strategies that not only improve productivity but also optimize energy utilization. Multi-machine production systems with job-shop configurations exhibit high complexity due to dynamic interactions between machines, job queues, and varying processing times, making conventional scheduling methods less effective in handling changing operational conditions. Objective: This study aims to develop and evaluate a reinforcement learning based production scheduling approach to improve production efficiency while reducing energy consumption in multi-machine manufacturing systems. Methods: This research employs a job-shop based multi-machine production simulation model as the experimental environment. The scheduling problem is formulated as a Markov Decision Process, enabling the implementation of reinforcement learning algorithms, namely Q-learning and Deep Q-Network, to learn optimal scheduling policies through interaction with the simulation environment. Energy consumption parameters are incorporated into the reward function so that the learning agent can consider energy efficiency in the scheduling decision-making process. System performance is evaluated using three main metrics, namely energy consumption, throughput, and makespan. Results: The experimental results show that the reinforcement learning based scheduling approach achieves better performance compared to conventional scheduling methods, resulting in lower energy consumption, higher job completion rates, and shorter production completion times within the multi-machine manufacturing system.

This study aims to classify customer payment methods at 17 Coffee & Eatery using machine learning algorithms, namely Naïve Bayes and Support Vector Machine (SVM). The increasing use of digital and non-cash payments has generated large volumes of transaction data that are rarely analyzed optimally, even though such data contain valuable information for business decision making. This research used secondary transaction data collected from January to March 2025, consisting of 10,147 transaction records. The dataset included several attributes such as order time, payment time, transaction type, total sales, number of items, and payment method. Data preprocessing was performed through data cleaning, feature engineering, normalization, and label encoding before being divided into training and testing sets with an 80:20 ratio. The Naïve Bayes and SVM models were then trained and evaluated using accuracy, precision, recall, F1-score, and ROC–AUC metrics. The results show that both algorithms were able to classify payment methods effectively, but SVM achieved higher accuracy and more stable performance than Naïve Bayes. These findings indicate that SVM is more suitable for handling complex and heterogeneous transaction patterns. The implementation of machine learning for transaction classification can support more efficient financial management and data-driven decision making for small and medium enterprises in the culinary sector.

AImbalanced data remains a significant issue in heart disease classification using machine learning, as it tends to cause models to overestimate the majority class while ignoring minority classes with high clinical value. This can lead to a decrease in accuracy and the model's ability to accurately detect disease cases. Therefore, this study aims to assess the effectiveness of oversampling techniques, namely Random Oversampling and Synthetic Minority Oversampling Technique (SMOTE), in improving the performance of the K-Nearest Neighbors (KNN), Naive Bayes (NB), and Random Forest (RF) algorithms. The dataset used comes from Kaggle and consists of 918 data sets with 12 attributes representing patient information related to heart disease prediction. The research stages include data preprocessing, baseline model testing, and re-evaluation using the two oversampling methods. Experimental results show that oversampling can improve the performance of all algorithms. KNN achieved the best results with SMOTE, with an accuracy of 72.98% and an F1-score of 75.39%. In the Naive Bayes algorithm, both oversampling techniques produced relatively stable performance, with the highest F1-score of 73.56% using SMOTE. Meanwhile, Random Forest showed the most optimal performance when combined with Random Oversampling, with an accuracy of 79.19% and an F1-score of 81.51%. These findings confirm that the success of data balancing techniques is strongly influenced by the characteristics of the classification algorithm used, and provide a practical contribution in determining strategies for handling imbalanced data in health research.

Jambi Province is one of the largest natural rubber producing regions in Indonesia; however, rubber factories under GAPKINDO Jambi still face productivity issues, particularly the gap between production capacity and actual output, and productivity assessment that is still conducted manually by GAPKINDO Jambi. This study employs Decision Tree, Random Forest, KNN, and SVM algorithms within a structured pipeline involving preprocessing, feature selection, standardization, data balancing using SMOTE, and hyperparameter tuning. The proposed solution applies productivity level classification both individually and through paired combinations (ensemble voting). The results show that the Decision Tree + Random Forest model achieves the best performance with an accuracy of 0.84 and an F1-score of 0.83, confirming the effectiveness of ensemble methods in supporting productivity improvement decisions.

In recent years, with the rapid development of artificial intelligence, many innovative changes have been made in the field of intelligent mobile robot development. In the field of control and navigation of mobile robots, learning-based methods have many advantages over traditional ones. The study of mobile robot control methods using deep reinforcement learning is a remarkable area in the development of mobile robots that must operate in dynamic environments. In the previous studies, the proposed robot control algorithms using deep reinforcement learning are mostly based on the given target point and obstacle information, the robot path planning is performed, and the corresponding control is based on the obtained path. The DDPG-based method is a typical example. However, in dynamic environments, DRL based robot path planning requires a state of target point and obstacles information, which leads to a large amount of computation, resulting in extremely long convergence time and even non-convergent cases. In this paper, we propose a new method for mobile robot control in dynamic environment that solves the dimensional problem by extracting the features of the configuration of obstacles using autoencoder and learning the DDPG algorithm based on the obtained features. Simulation results show that the proposed algorithm can effectively solve the mobile robot control problem in dynamic environment.

The growing demand for energy-efficient and intelligent thermal systems has driven significant advancements in adaptive compressor design. This paper presents a comprehensive literature review on the development of AI-based compressor systems, with a specific focus on enhancing efficiency under partial-load conditions and optimizing the utilization of residual energy. Through the synthesis of five recent high-impact studies (2020–2025), we examine the application of deep reinforcement learning (DRL), hybrid evolutionary algorithms, and neural network surrogate modeling in compressor optimization. Key findings indicate that model-based DRL combined with surrogate CFD can achieve up to 8% efficiency gains at off-design conditions. Hybrid approaches integrating Genetic Algorithms (GA) with DRL reduce optimization time by 30% while improving pressure ratios. Neural network surrogates provide high-speed, real-time performance predictions with less than 1% error, enabling mass iterative design. Furthermore, intelligent load classification using radial basis function networks (RBFN) allows adaptive response to varying operating conditions with over 95% accuracy. Collectively, these methods form a framework for intelligent, self-optimizing compressor systems capable of real-time adaptation and energy recovery. The results suggest that AI-enhanced adaptive compressors represent a transformative direction for energy-sensitive sectors, including HVAC, power generation, and sustainable industry.

The rapid growth of open-source software (OSS) in machine learning (ML) has intensified the need for reliable, automated methods to assess project quality, particularly as OSS increasingly underpins critical applications in science, industry, and public infrastructure. This study evaluates the effectiveness of a diverse set of machine learning and deep learning (ML/DL) algorithms for classifying GitHub OSS ML projects as engineered or non-engineered using a SMOTE-enhanced and explainable modeling pipeline. The dataset used in this research includes both numerical and categorical attributes representing documentation, testing, architecture, community engagement, popularity, and repository activity. After handling missing values, standardizing numerical features, encoding categorical variables, and addressing the inherent class imbalance using the Synthetic Minority Oversampling Technique (SMOTE), seven different classifiers—K-Nearest Neighbors (KNN), Decision Tree (DT), Random Forest (RF), XGBoost (XGB), Logistic Regression (LR), Support Vector Machine (SVM), and a Deep Neural Network (DNN)—were trained and evaluated. Results show that LR (84%) and DNN (85%) outperform all other models, indicating that both linear and moderately deep non-linear architectures can effectively capture key quality indicators in OSS ML projects. Additional explainability analysis using SHAP reveals consistent feature importance across models, with documentation quality, unit testing practices, architectural clarity, and repository dynamics emerging as the strongest predictors. These findings demonstrate that automated, explainable ML/DL-based quality assessment is both feasible and effective, offering a practical pathway for improving OSS sustainability, guiding contributor decisions, and enhancing trust in ML-based systems that depend on open-source components.

The rapid growth of web technologies and online services has increased the exposure of web applications to cyber threats such as Cross-Site Scripting (XSS) and SQL Injection (SQLi). Conventional rule-based mechanisms, such as Web Application Firewalls (WAFs), often fail to detect emerging attack patterns. To address this, Machine Learning (ML) and Deep Learning (DL) have emerged as adaptive approaches for enhancing web attack detection. This study performs a Systematic Literature Review (SLR) following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines to analyze recent ML/DL-based detection methods. Of the 263 retrieved studies, 15 met the inclusion criteria for detailed review. The findings reveal that Random Forest (RF), Support Vector Machine (SVM), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM) are the most applied algorithms. At the same time, recent works emphasize Transformer-based and hybrid ML–DL models. These approaches achieved robust performance (accuracy 85–97%, F1-score >90%) but still face challenges in dataset representativeness, class imbalance, and computational cost. This review highlights future research directions in Explainable Artificial Intelligence (XAI), Federated Learning (FL), and adversarial robustness to develop more efficient and trustworthy web attack detection systems.

Millions of people suffer from malaria, one of the most serious parasitic diseases that threatens human life and causes high rates of morbidity and mortality, particularly in tropical and subtropical regions. Traditional diagnostic methods, such as blood smear examination, which can be performed using a microscope, face many challenges due to the inaccuracy of manual analysis and the reliance on individual skills. Therefore, the use of machine learning or deep learning algorithms to automate malaria detection offers promising solutions to improve accuracy, reduce diagnosis time, and enhance scalability. In this paper, a multi-class convolutional neural network (CNN)-based model is designed to classify cells infected with Plasmodium falciparum (P. falciparum) and Plasmodium vivax (P. vivax) and uninfected cells from blood smears, as most severe cases and deaths are caused by P. falciparum and P. vivax. This is achieved by building and training a CNN from scratch, rather than using transfer learning from pre-trained models. The proposed network was trained and tested on the Kaggle dataset, which consists of 27,558 images of infected and uninfected individuals. These images were divided into 13,779 images of uninfected individuals, 6,890 images of individuals with P. falciparum malaria, and 6,889 images of individuals with P. vivax malaria. The images were preprocessed using several operations, including blurring, denoising, and morphological processing. The proposed model achieved the best evaluation accuracy when compared with other deep learning algorithms, with an accuracy rate of 96.5%, a sensitivity rate of 95%, a specificity rate of 97.6%, and an F1-score rate of 96.5%. These results demonstrate the effectiveness of the proposed model as a tool to assist clinicians in malaria diagnosis, reducing reliance on manual analysis.

Typhoid fever is an infectious disease caused by the bacterium Salmonella typhi, commonly found in developing countries, including Indonesia. Prompt and accurate treatment is crucial to prevent serious complications in patients. One way to assist in diagnosing typhoid fever is by applying machine learning methods to classify patient data. The Naive Bayes method is one of the machine learning algorithms frequently used in medical data classification due to its strong ability to handle large and complex datasets. This article discusses the application of the Naive Bayes method for classifying typhoid patient data at Rantauprapat General Hospital (RSUD Rantauprapat). By utilizing medical data that includes clinical symptoms, laboratory test results, and patients’ medical histories, the Naive Bayes model can provide fairly accurate predictions regarding the likelihood of a person having typhoid fever. The research findings indicate that Naive Bayes is reliable in predicting typhoid diagnoses with adequate accuracy, thereby supporting healthcare professionals in making faster and more precise decisions. It is expected that the implementation of this method can accelerate the diagnostic process and improve the quality of healthcare services at RSUD Rantauprapat, as well as in other regions.