Background: Electroencephalography (EEG) signal-based machine learning models are among the most cost-effective methods for information retrieval. In this context, we aimed to investigate the cortical activities of psychotic criminal subjects by deploying an explainable feature engineering (XFE) model using an EEG psychotic criminal dataset. Methods: In this study, a new EEG psychotic criminal dataset was curated, containing EEG signals from psychotic criminal and control groups. To extract meaningful findings from this dataset, we presented a new channel-based feature extraction function named Zipper Pattern (ZPat). The proposed ZPat extracts features by analyzing the relationships between channels. In the feature selection phase of the proposed XFE model, an iterative neighborhood component analysis (INCA) feature selector was used to choose the most distinctive features. In the classification phase, we employed an ensemble and iterative distance-based classifier to achieve high classification performance. Therefore, a t-algorithm-based k-nearest neighbors (tkNN) classifier was used to obtain classification results. The Directed Lobish (DLob) symbolic language was used to derive interpretable results from the identities of the selected feature vectors in the final phase of the proposed ZPat-based XFE model. Results: To obtain the classification results from the ZPat-based XFE model, leave-one-record-out (LORO) and 10-fold cross-validation (CV) methods were used. The proposed ZPat-based model achieved over 95% classification accuracy on the curated EEG psychotic criminal dataset. Moreover, a cortical connectome diagram related to psychotic criminal detection was created using a DLob-based explainable artificial intelligence (XAI) method. Conclusions: In this regard, the proposed ZPat-based XFE model achieved both high classification performance and interpretability. Thus, the model contributes to feature engineering, psychiatry, neuroscience, and forensic sciences. Moreover, the presented ZPat-based XFE model is one of the pioneering XAI models for investigating psychotic criminal/criminal individuals.

Automatic violence detection is one of the most important research areas at the intersection of machine learning and information security. Moreover, we aimed to investigate violence detection in the context of neuroscience. Therefore, we have collected a new electroencephalography (EEG) violence detection dataset and presented a self-organized explainable feature engineering (SOXFE) approach. In the first phase of this research, we collected a new EEG violence dataset. This dataset contains two classes: (i) resting, (ii) violence. To detect violence automatically, we proposed a new SOXFE approach, which contains five main phases: (1) feature extraction with the proposed distance matrix pattern (DMPat), which generates three feature vectors, (2) feature selection with iterative neighborhood component analysis (INCA), and three selected feature vectors were created, (3) explainable results generation using Directed Lobish (DLob) and statistical analysis of the generated DLob string, (4) classification deploying t algorithm-based k-nearest neighbors (tkNN), and (5) information fusion employing mode operator and selecting the best outcome via greedy algorithm. By deploying the proposed model, classification and explainable results were generated. To obtain the classification results, tenfold cross-validation (CV), leave-one-record-out (LORO) CV were utilized, and the presented model attained 100% classification accuracy with tenfold CV and reached 98.49% classification accuracy with LORO CV. Moreover, we demonstrated the cortical connectome map related to violence. These results and findings clearly indicated that the proposed model is a good violence detection model. Moreover, this model contributes to feature engineering, neuroscience and social security.

Electroencephalography (EEG) offers a non-invasive and cost-effective means of probing brain activity during language processing; however, prior EEG-based language studies have been limited by small datasets, a predominant focus on native-speaker or speech-unit recognition rather than direct language detection, evaluation on only a small number of experimental settings, and frequent reliance on computationally intensive deep learning models with limited interpretability. The proposed feature engineering models classifies EEG segments by language and task mode. The languages are Arabic and Turkish. The modes are reading and listening. In this study, a signal refers to one fixed-length multi-channel EEG segment (14 channels × 15 s at 128 Hz). A channel refers to one electrode time series within that segment. To address these gaps, we curated a new EEG language detection dataset from 346 participants (98 Arabic and 248 Turkish) recorded in reading and listening modes, yielding 6364 EEG segments. Using this dataset, we proposed DiagPat, an explainable feature engineering (XFE) model that extracts transition table-based features from both EEG channels and signals through diagonal pattern analysis. The model combines DiagPat feature extraction with iterative neighborhood component analysis (INCA) for feature selection, at algorithm-based k-nearest neighbors (tkNN) classifier for prediction, and the Directed Lobish (DLob) symbolic language for explainability. We evaluated the framework across nine classification cases covering language detection, mode detection, and mixed multi-class settings. The proposed DiagPat-driven XFE model achieved more than 90% accuracy in all cases, with accuracies ranging from 92.14% to 99.35%, and generated case-specific cortical connectome diagrams that supported the interpretable characterization of language- and mode-related brain activity. Subject-independent results were also reported using leave-one-subject-out cross-validation (LOSO CV), where LOSO accuracies ranged from 29.75% to 83.50%. Thus, the 10-fold CV results show segment-level performance, whereas the LOSO results show subject-level generalization. Balanced accuracy and macro-F1 are also reported. These findings indicate that DiagPat provides an accurate, lightweight, and explainable framework for EEG-based language detection.

Artificial intelligence is now applied in many fields beyond computer science. In healthcare, it enables early disease detection and improves patient outcomes. This study develops a model that uses AI to find abnormal patterns in cough sounds. A cough is a key symptom of asthma and other respiratory diseases. Previous research has focused on raw audio signals of coughs. In contrast, we analyze spectrogram images derived from these sounds to improve accuracy. We designed a new convolutional neural network (CNN) for this purpose and the recommended CNN is termed as TwoConvNeXt. To showcase the classification performance of the recommended TwoConvNeXt model, a cough sound dataset has been utilized and the recommended TwoConvNeXt achieved 99.66% classification test accuracy. These results illustrate that the presented TwoConvNeXt CNN architecture can be useful in both research and clinical settings. This CNN model can be utilized for other image classification problems. It may aid in the early diagnosis of respiratory conditions. Future work will expand the dataset and test the model on larger, more diverse samples.

Background/Objectives: EEG-based mental performance classification requires participant-separated validation and traceable feature identities. Methods: BioTWavePat-XFE constructs five single-rhythm and 15 signed cross-rhythm channel-rank transition layers, uses four cumulative-weighted selectors and tkNN/IMV classification, and decodes retained identities with Directed Lobish. We compared Protocol A (whole-dataset feature and pooled-test outcome selection), Protocol B (training-fold outcome selection with Protocol A features), and Protocol C (all data-dependent steps restricted to outer training data). STEW and MAT used participant-wise LOSO. TMPD included all 55 participants in 54 identifier groups; two same-class participants sharing an identifier were withheld together. Results: Protocol A segment accuracies were 83.08% (STEW), 93.14% (TMPD), and 91.15% (MAT). Protocol C accuracies were 80.46%, 82.50%, and 74.65%, with balanced accuracies of 80.46%, 75.17%, and 64.15%, respectively. These are the primary estimates without the identified selection leakage under the stated participant-separated validation design. Conclusions: Whole-dataset selection inflated the original estimates, particularly for TMPD and MAT. MAT Protocol C performance was close to majority prediction. Directed Lobish exposes selected feature identities without establishing physiological connectivity, causality or biomarker validity.