Mohammad Mahdi Ershadi

Background: Accurate electroencephalogram (EEG) classification is hindered by the nonlinear, nonstationary nature of brain activity and high inter-subject variability. Conventional clustering often fails to capture the temporal and complex EEG patterns, limiting cross-dataset performance. Method: This study introduces a hybrid framework combining the Whale Optimization Algorithm (WOA) with Dynamic Time Warping (DTW) to optimize cluster centroids using temporal similarity, enhancing EEG dynamic representation. The method was validated on four real-world EEG datasets covering binary and multi-class tasks. Preprocessing and dimensionality reduction preceded clustering, followed by evaluation using five different classifiers. Results: WOA-DTW consistently outperformed baseline and traditional clustering methods, achieving accuracy gains up to 13% and F1-score improvements of 15%. The highest accuracy, 94.98%, was obtained on dataset 2 (EEG SSVEP) using CNN. Paired t-tests confirmed statistical significance (p < 0.05). Compared with K-means, DBSCAN, FCM, SOM, and standalone DTW, the proposed method better captured nonlinear and temporal EEG characteristics, improving classifier discriminability. Conclusions: The WOA-DTW framework effectively models EEG temporal dynamics, significantly enhancing classification performance and showing strong potential for brain–computer interfaces and neurological diagnostic applications.

This study proposes an integrated fuzzy multi-objective decision-support framework for the simultaneous optimization of procurement allocation and logistics network design in multi-echelon supply chains. The framework explicitly captures the interdependence between sourcing and transportation decisions while balancing four strategic objectives: minimization of total operational cost, minimization of supplier-related quality defects, maximization of supplier sustainability performance, and minimization of supply chain disruption risk. To address uncertainty in production capacities and operational conditions, the model incorporates fuzzy parameters and is solved using an Augmented Max–Min Fuzzy Multi-Objective Linear Programming (AMM-FMOLP) approach that generates balanced compromise solutions across conflicting objectives. The applicability of the proposed framework is demonstrated through a real-world case study involving a computer numerical control (CNC) machine-tool assembly supply chain consisting of 15 suppliers, 2 assembly facilities, 3 distribution centers, and 6 customer zones. The obtained compromise solution achieved utility values of 0.6667, 0.6820, 0.6747, and 0.6667 for cost, defect rate, sustainability performance, and disruption risk, respectively, resulting in a total operational cost of 26.586 million monetary units, a defect-rate index of 209.57, a sustainability score of 1,546.148, and a disruption-risk index of 214.223. Comparative scenario analyses revealed that single- and partial-objective optimization approaches yielded marginal improvements in individual objectives but produced less balanced overall performance. Sensitivity analyses further confirmed robustness of proposed framework under different conditions. Results demonstrate that proposed framework provides an effective mechanism for enhancing supply chain efficiency, sustainability, and resilience, making it a valuable decision-support tool for intelligent supply chain management in uncertain operating environments.

This study focused on predicting chronic disease treatment default and evaluating the effectiveness of random sampling optimization techniques in addressing dataset class imbalance. Class imbalance, a common issue in real-world applications like frau...

The rapid identification of respiratory ailments, such as lung cancer and COVID-19, is critical for timely intervention. Chest X-rays (CXR) serve as an accessible diagnostic tool; however, existing machine learning models often struggle with limited accuracy and sensitivity. This study proposes an ensemble learning-based approach for classifying respiratory ailments using both biomedical and image-based data. Three biomedical datasets and one CXR dataset are utilized as case studies. Histogram of Oriented Gradients (HOG) and Radiomics techniques are applied to extract features from CXR images, which are then processed using Principal Component Analysis (PCA) for dimensionality reduction. To enhance model performance, the Taguchi method is used to tune the parameters of multiple classifiers, including Convolutional Neural Networks (CNN), Support Vector Machine (SVM), Decision Tree (DT), Naïve Bayes (NB), K-Nearest Neighbors (KNN), and Tree Bagger (TB). The proposed ensemble learning approach outperforms individual classifiers by at least 10%, demonstrating significant improvements in accuracy, sensitivity, specificity, precision, recall, F-measure, and G-mean. Statistical tests, including the Wilcoxon Signed-Rank Test and ANOVA, are employed to determine the optimal train-test split and validate the efficiency of the applied methods. The results highlight the potential of ensemble learning in improving diagnostic accuracy for respiratory ailments.

This study focused on the methodology of information mining, which involves extracting significant patterns from historical data. This technique is commonly applied in various real-world applications such as web records, fraud detection, speech recog...

This study focuses on the application of Bayes' theorem in psychology, particularly for non-experts. It proposes a simplified version of Bayes' theorem, utilizing common statistical values, to calculate the probability of a null hypothesis being fals...

This study focused on enhancing enterprise financial risk management through the utilization of data mining technology, specifically the application of the K-means clustering algorithm in risk audit processes. The paper investigates the integration o...

This study focused on the underemphasized aspect of optimization within widespread digital teaching tools, despite its fundamental role in mathematics. The relevance of optimality was explored, and the paper highlights its support in the FeliX dynami...