Adiwijaya Adiwijaya

With the rapid growth of data, particularly in the form of data banks, numerous challenges have arisen, among which the issue of imbalanced data has become increasingly prominent. Generally, three main approaches address imbalanced data: data-level, algorithm-level, and hybrid approaches. The data-level approach, also known as sampling techniques, is widely adopted because it does not depend on a specific classifier. Evolutionary computation has become a popular sampling method, referred to as evolutionary sampling techniques, and has proven effective in various optimization tasks. Imbalanced data issues are also often related to data quality problems, such as noise and class overlap. However, to the best of our knowledge, no review has focused on evolutionary sampling techniques, particularly for handling noise and class overlap. This paper reviews evolutionary sampling techniques, emphasizing how they address noise and class overlap. This paper proposes a taxonomy encompassing five key aspects in developing evolutionary sampling techniques: data quality problems, individual representations, fitness functions, the role of evolutionary algorithms, and the utilized evolutionary algorithms. Our review identifies three roles of evolutionary algorithms in the sampling process. i.e., training set selection, synthetic sample generation, and non-evolutionary parameter optimization. Furthermore, the Genetic Algorithm is the most commonly implemented. This paper also identifies key challenges and opportunities, guiding future advancements in handling imbalanced data classification with evolutionary sampling techniques.

Sharia-compliant stocks have expanded beyond Muslim-majority markets and are increasingly sought by global investors who prioritize investment in ethical and faith-based financial instruments. Despite their similarity with conventional stocks, empirical and conceptual discussions on the determinants of Sharia stock performance, particularly in sector-specific contexts, remain limited. The current study proposes a conceptual framework for assessing Sharia-compliant stock investment decisions, specifically in Indonesia’s telecommunications industry. Using a literature-based approach, our framework integrates macroeconomic indicators, information and communication technologies (ICT) development, and firm-specific financial variables to identify relevant factors for Sharia stock return analysis. The targeted telecommunication sector was selected due to its close relationship with digital infrastructure and ICT development and is included in the permissible investment sector by Sharia law. Our study presents a preliminary conceptual model that can guide future empirical testing. At the same time presenting different perspective regarding Sharia-compliant stock studies such as Zuliansyah et al. (2023) and Handyansyah and Sukarno (2023). Furthermore, the proposed framework contributes to the literature by organizing potential determinants of Sharia stock performance within Indonesia’s telecommunication sector. Future studies can refer to our framework to validate it and assess its predictive capacity, model reliability, and practical applicability.

Polycystic Ovary Syndrome (PCOS) is commonly assessed with ovarian ultrasonography, but speckle can conceal follicular margins and reduce the robustness of automated interpretation. Although automated PCOS studies increasingly employ machine learning, the contribution of conventional despeckling to subsequent segmentation and classification has not been examined consistently. This study compares five classical filters - Mean, Median, Lee, Frost, and Kuan - within an interpretable machine-learning pipeline for ovarian ultrasound analysis. From a public collection of 12,680 images, a balanced sample of 300 scans (150 PCOS and 150 non-PCOS) was selected. Two radiologists produced follicle annotations, and disagreements were resolved with a third expert to obtain consensus masks. Each filtered image was segmented by adaptive thresholding with morphological refinement, after which geometric and intensity descriptors were extracted. Support Vector Machine (SVM), Random Forest (RF), k-Nearest Neighbors (k-NN), and Logistic Regression (LR) were trained using a stratified 70/30 train-test split with cross-validated hyperparameter tuning. The Kuan-LR configuration yielded the strongest result, reaching 94.44% accuracy and an AUC of 0.98, together with the best edge-preservation score and segmentation agreement. The results indicate that preprocessing materially affects the reliability of an interpretable PCOS detection pipeline and provide quantitative guidance for selecting a speckle-reduction strategy before segmentation and classification.

During the pandemic crisis that hit after 2020, Indonesia, like many other countries, faced tremendous challenges in areas such as health, economy, and mobility. An in-depth understanding of the dynamics and changes in these areas is essential to address the impacts of the pandemic. This research is an attempt to deeply analyze the impact of the pandemic and the most effective forecasting methods based on data and phenomena. Indonesia, with its growing economy and constantly adapting health system, faces conventional economic impacts, while its health system response tries to keep up with urgent needs driven by the spread of the virus. In the context of mobility, changes in how people move and interact significantly affect virus transmission. Modeling a pandemic event with all its complexities is not an easy task. Even more so, in finding the right method for prediction, ensemble techniques such as stacking and regression voting are emerging as promising approaches. However, deep learning and particle swarm optimization (PSO) techniques offer new innovations. The results of this study show that the ensemble vote provides the best performance in predicting confirmed positive cases and mortality based on factors of health, economic and population mobility in Indonesia. Through feature importance analysis using MDI and Tree SHAP, we conclude that factors such as active cases, the number of vaccinations, and economic indicators, such as close IDR and close IHSG, have a significant influence on the growth of confirmed positive cases. Meanwhile, recovery factors and vaccination number play an important role in the growth of the number of death cases. This study confirms that a multivariate approach that considers health, economy and mobility is the key to understanding and responding more effectively to the pandemic in Indonesia.

Hybrid Multi-Objective Metaheuristic Machine Learning for Optimizing Pandemic Growth Prediction

Presents corrections to the paper, (Corrections to “Chronic Diseases Prediction Using Machine Learning With Data Preprocessing Handling: A Critical Review”).