Publication Search

 Cryptocurrency price prediction, particularly for highly volatile assets like Solana (SOL), is a crucial challenge in time series data analysis in digital finance. This study aims to compare the performance of the XGBoost machine learning algorithm with the Temporal Fusion Transformer (TFT) deep learning model in predicting Solana's daily closing price. The dataset used consists of historical Solana price data and network fundamentals data in the form of Total Value Locked (TVL). The research process includes data preprocessing, dividing training and test data, model training, and evaluation using the Root Mean Squared Error (RMSE) metric. The results show that using the same-day price feature has the potential to cause target leakage, resulting in invalid prediction accuracy. In testing using pure historical data without data leakage, the XGBoost model performed better than TFT with an RMSE of 4.27, while TFT produced an RMSE of 18.59. Furthermore, the integration of network fundamentals data in the form of TVL did not improve prediction accuracy and even caused a decrease in performance for the XGBoost model with an RMSE of 7.10. The results of this study show that the use of historical price action features is more effective than fundamental network indicators for short-term daily Solana price predictions.

The increasing sedentary lifestyle in the digital era has the potential to cause various health problems due to lack of physical activity. One approach that can be taken to encourage physical activity is through the use of digital games with body movement-based control mechanisms. This study aims to develop a body gesture-based game character control system using a hybrid Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) model. CNN is used to extract spatial features from each video frame, while LSTM serves to model the temporal relationship between frames so that movement patterns can be recognized sequentially. The research method used refers to the Machine Learning Lifecycle stages, starting from data collection, preprocessing, model development, to implementation in the endless runner game genre. Testing results show that the CNN–LSTM model is capable of classifying body gestures and generating outputs that can be used as commands to control game characters. The implementation of this system enables more natural and interactive game interactions without conventional input devices, and has the potential to encourage players to lead a more active lifestyle.

Background: The development of industrial technology in the Industry 4.0 era has encouraged the implementation of intelligent monitoring systems to improve machine reliability and operational efficiency. However, machine fault diagnosis systems based on artificial intelligence often face limitations in terms of interpretability because the models used are complex and difficult to explain. Objective: This study aims to develop a deep learning-based industrial machine fault diagnosis system integrated with an Explainable Artificial Intelligence (XAI) approach to improve diagnostic accuracy while providing interpretable insights for users. Method: The research method involves collecting data from industrial machine sensors consisting of vibration signals, temperature measurements, and acoustic signals, followed by data preprocessing and feature extraction processes. The processed data are then used to train a deep learning-based diagnostic model, after which explainability methods such as SHAP or LIME are applied to analyze the contribution of each feature to the model’s prediction results. Model performance is evaluated using accuracy, precision, recall, and F1-score metrics. Results: The results indicate that the proposed deep learning model achieves better performance compared to conventional machine learning methods such as Support Vector Machine and Random Forest. Furthermore, the explainability analysis reveals that vibration amplitude, increases in machine component temperature, and anomalies in acoustic signals are the main factors influencing machine fault detection. Therefore, the proposed system not only improves the accuracy of machine fault diagnosis but also provides transparency in the decision-making process, thereby supporting the implementation of predictive maintenance in smart manufacturing environments.

Chronic diseases such as chronic kidney disease (CKD), diabetes, and heart disease remain major causes of mortality worldwide, highlighting the need for accurate and interpretable diagnostic models. However, conventional machine learning methods often face challenges of limited generalization, feature redundancy, and class imbalance in medical datasets. This study proposes an integrated classification framework that unifies three complementary feature paradigms: classical tabular attributes, deep latent features extracted through an unsupervised Long Short-Term Memory (LSTM) encoder, and quantum-inspired features derived from a five-qubit circuit implemented in PennyLane. These heterogeneous features are fused using a feature-wise attention mechanism combined with an AdaBoost classifier to dynamically weight feature contributions and enhance decision boundaries. Experiments were conducted on three benchmark medical datasets—CKD, early-stage diabetes, and heart disease—under both balanced and imbalanced configurations using stratified five-fold cross-validation. All preprocessing and feature extraction steps were carefully isolated within each fold to ensure fair evaluation. The proposed hybrid model consistently outperformed conventional and ensemble baselines, achieving peak accuracies of 99.75% (CKD), 96.73% (diabetes), and 91.40% (heart disease) with corresponding ROC AUCs up to 1.00. Ablation analyses confirmed that attention-based fusion substantially improved both accuracy and recall, particularly under imbalanced conditions, while SMOTE contributed minimally once feature-level optimization was applied. Overall, the attention-guided AdaBoost framework provides a robust and interpretable approach for clinical risk prediction, demonstrating that integrating diverse quantum, deep, and classical representations can significantly enhance feature discriminability and model reliability in structured medical data.

This study presents an advanced AI-powered framework to detect and prevent cyberbullying across diverse social media platforms using a multiclass classification approach. Addressing the growing complexity and linguistic diversity of online abuse, the research integrates various machine learning (RF, LR, SVM) and deep learning (Bi-LSTM, BERT) models trained on a balanced dataset covering bullying categories based on religion, age, ethnicity, gender, and neutral content. Data preprocessing, tokenization, feature extraction via TF-IDF and CountVectorizer, and class balancing using SMOTE were applied to enhance model accuracy. The proposed system further supports real-time detection through social media APIs, offering dynamic monitoring and intervention capabilities. Among the tested models, Random Forest and BERT achieved the highest classification performance with 94% accuracy. Despite its robust architecture, limitations include dependence on English-language datasets, exclusion of multimodal data (e.g., memes, audio), and API restrictions that challenge scalability. Future development will focus on incorporating vision-language models and optimizing the system for real-time, multilingual, and multimodal environments. This study contributes to digital safety efforts by proposing a scalable and adaptive detection system suitable for safeguarding users from evolving forms of online harassment.

This study aims to develop an automated pipeline for data cleaning using Pandas and Scikit-learn. The data cleaning process is often performed manually, requiring a long time and prone to errors. This study uses a quantitative experimental method with a dataset of 100,000 rows of e-commerce transaction data. The results show that the automated pipeline reduces missing values by 95.7% and outliers by 91.7%, and accelerates processing time by 35% compared to manual methods. The distribution of data after cleaning becomes more stable, allowing for more accurate analysis. This study contributes to the development of a more efficient and accurate automated data cleaning approach.Keywords: Systematic Literature Review, Artificial Intelligence and Marketing Strategy.

Credit approval prediction is one of the critical challenges in the financial industry, where the accuracy and efficiency of credit decision-making can significantly affect business risk. This study proposes an outlier detection method using the Gaussian Mixture Model (GMM) combined with Extreme Gradient Boosting (XGBoost) to improve prediction accuracy. GMM is used to detect outliers with a probabilistic approach, allowing for finer-grained anomaly identification compared to distance- or density-based methods. Furthermore, the data cleaned through GMM is processed using XGBoost, a decision tree-based boosting algorithm that efficiently handles complex datasets. This study compares the performance of XGBoost with various outlier detection methods, such as LOF, CBLOF, DBSCAN, IF, and K-Means, as well as various other classification algorithms based on machine learning and deep learning. Experimental results show that the combination of GMM and XGBoost provides the best performance with an accuracy of 95.493%, a recall of 91.650%, and an AUC of 95.145%, outperforming other models in the context of credit approval prediction on an imbalanced dataset. The proposed method has been proven to reduce prediction errors and improve the model's reliability in detecting eligible credit applications.

The rapid growth of digital technologies has significantly increased the complexity and frequency of cyber threats, making network security a critical concern in modern information systems. Traditional security approaches, such as rule-based and signature-based systems, are often limited in detecting sophisticated and unknown attacks. Therefore, this study proposes an Anomaly-Based Intrusion Detection System (AbIDS) utilizing machine learning and deep learning techniques to enhance detection capabilities. The research adopts a Design Science Research approach, involving stages of problem identification, data collection, preprocessing, model development, system implementation, and evaluation. Several models, including Decision Tree (DT), Support Vector Machine (SVM), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM), are implemented and compared. The results indicate that deep learning models, particularly LSTM and CNN, outperform traditional machine learning methods in terms of accuracy, precision, recall, and F1-score, while maintaining a lower false positive rate. Additionally, the integration of incremental learning enables the system to adapt to new attack patterns without requiring complete retraining, improving scalability and real-time performance. Despite the promising results, challenges such as computational complexity and false positives remain. Overall, the proposed IDS model demonstrates strong potential as an effective and adaptive solution for enhancing network security in dynamic environments.

The rapid advancement of deep learning technologies has significantly transformed healthcare analytics, particularly in medical data prediction and classification. This study proposes a hybrid Convolutional Neural Network–Long Short-Term Memory (CNN–LSTM) framework for multi-modal healthcare data analysis, integrating medical imaging, structured electronic health records (EHRs), and IoT-generated time-series physiological signals. The proposed architecture combines spatial feature extraction through CNN with temporal dependency modeling via LSTM to enhance predictive accuracy and clinical decision support. A quantitative experimental design was employed, utilizing multi-source healthcare datasets that underwent preprocessing, normalization, and feature engineering prior to model training. The performance of the hybrid model was evaluated using Accuracy, Precision, Recall, F1-Score, AUC-ROC, and Mean Absolute Error (MAE), and compared with conventional machine learning models and standalone deep learning architectures. Experimental results demonstrate that the proposed CNN–LSTM model achieves superior performance, with improved classification accuracy and reduced prediction error, while maintaining strong generalization capability. The findings indicate that integrating spatial and temporal feature learning significantly enhances disease detection, risk stratification, and personalized treatment planning. This approach supports the development of intelligent clinical decision support systems and scalable smart healthcare environments. The proposed framework offers a reliable and efficient solution for advanced healthcare analytics in IoT-enabled systems.

Background: Public opinion analysis has become increasingly important in the digital era, where social media platforms generate large-scale textual data reflecting public perceptions toward environmental policies. Advances in Natural language processing (NLP) and machine learning enable systematic sentiment classification to support data-driven decision-making. Objective: This study aims to evaluate the effectiveness of several sentiment classification models in analyzing Indonesian-language social media data related to environmental policies. Method: The research employed a text mining pipeline including data crawling, preprocessing (case folding, tokenization, stopword removal, and stemming), and vectorization using TF-IDF. Three classification models Logistic Regression, Support Vector Machine (SVM), and Long Short-Term Memory (LSTM) were trained and evaluated using accuracy and F1-score metrics. Results: Experimental findings indicate that LSTM achieved the highest performance with 91.7% accuracy and 91.2% F1-score, outperforming SVM (88.5%) and Logistic Regression (84.2%). Sentiment distribution analysis shows that public opinion is dominated by positive sentiment (47.5%), followed by neutral (32.0%) and negative (20.5%). Overall: The results demonstrate that deep learning-based models provide more robust contextual understanding and more reliable sentiment mapping for environmental policy analysis.