Objective. The main objective of this work is to present a hand-modelled one-dimensional signal classification system to detect Attention-Deficit Hyperactivity Disorder (ADHD) disorder using electroencephalography (EEG) signals. Approach. A novel handcrafted feature extraction method is presented in this research. Our proposed method uses a directed graph and an eight-pointed star pattern (EPSPat). Also, tunable q wavelet transforms (TQWT), wavelet packet decomposition (WPD), statistical extractor, iterative Chi2 (IChi2) selector, and the k-nearest neighbors (kNN) classifier have been utilized to develop the EPSPat based learning model. This network uses two wavelet decomposition methods (TQWT and WPD), and 85 wavelet coefficient bands are extracted. The proposed EPSPat and statistical feature creator generate features from the 85 wavelet coefficient bands and the original EEG signal. The learning network is termed EPSPatNet86. The main purpose of the presented EPSPatNet86 is to detect abnormalities of the EEG signals. Therefore, 85 wavelet subbands have been generated to extract features. The created 86 feature vectors have been evaluated using the Chi2 selector and the kNN classifier in the loss value calculation phase. The final features vector is created by employing a minimum loss-valued eight feature vectors. The IChi2 selector selects the best feature vector, which is fed to the kNN classifier. An EEG signal dataset has been used to demonstrate the presented model’s EEG signal classification ability. We have used an ADHD EEG dataset since ADHD is a commonly seen brain-related ailment. Main results. Our developed EPSPatNet86 model can detect the ADHD EEG signals with 97.19% and 87.60% accuracy using 10-fold cross and subject-wise validations, respectively. Significance. The calculated results demonstrate that the presented EPSPatNet86 attained satisfactory EEG classification ability. Results show that we can apply our developed EPSPatNet86 model to other EEG signal datasets to detect abnormalities.

Background\Objectives: Solving the secrets of the brain is a significant challenge for researchers. This work aims to contribute to this area by presenting a new explainable feature engineering (XFE) architecture designed to obtain explainable results related to stress and mental performance using electroencephalography (EEG) signals. Materials and Methods: Two EEG datasets were collected to detect mental performance and stress. To achieve classification and explainable results, a new XFE model was developed, incorporating a novel feature extraction function called Cubic Pattern (CubicPat), which generates a three-dimensional feature vector by coding channels. Classification results were obtained using the cumulative weighted iterative neighborhood component analysis (CWINCA) feature selector and the t-algorithm-based k-nearest neighbors (tkNN) classifier. Additionally, explainable results were generated using the CWINCA selector and Directed Lobish (DLob). Results: The CubicPat-based model demonstrated both classification and interpretability. Using 10-fold cross-validation (CV) and leave-one-subject-out (LOSO) CV, the introduced CubicPat-driven model achieved over 95% and 75% classification accuracies, respectively, for both datasets. Conclusions: The interpretable results were obtained by deploying DLob and statistical analysis.

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.

In the early 2000s, the more traditional modes of communication via mobile devices were voice calls, emails, and short message services (SMS). Nowadays, communication through mobile applications such as WhatsApp, Facebook, Twitter, Instagram, etc. About Facebook the leading social network with monthly active users of about 2.85 billion people. With this number of users, a large amount of data is generated. Exploring this data provides an insight into the users’ activities which can aid in tackling security challenges and business planning, among other benefits. This study presents a neighborhood component analysis (NCA) and relief-based weight generation methods for a regression task on Facebook data. The features are calculated using the weight generated and four widely used activation functions. The features are then fed to four regression models for prediction. The proposed model is used to predict nine different attributes of the FB dataset whose values are continuous. RMSE, R-squared, MSE, MAE, and training time were calculated and used as evaluation metrics for all nine cases. The average R-square value of the Relief and NCA-based methods were calculated as 0.9689 and 0.9667, respectively. The results indicated that our proposed methods are very efficient and successful for regression tasks on Facebook data.