DMPat-based SOXFE: investigations of the violence detection using EEG signals

Abstract

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.

Keywords: Cortical connectome diagram; Distance matrix pattern; EEG signal analysis; SOXFE; Violence detection.

Fig. 1

Visuıal overview of the proposed DMPat-based SOXFE approach. Herein, f: feature vector, s: chosen feature vector t: tkNN-based outcome and v: voted outcome

Fig. 2

Graphical explanation of the proposed DMPat FEX function

Fig. 3

Graphical depiction of the tkNN classifier

Fig. 4

Confusion matrices of the final outcomes. Herein, 1: violence, 2: control

Fig. 5

Frequencies of the used DLob symbols according to the DLob string

Fig. 6

Classification accuracies of the feature vectors. Herein, the first feature vector was generated by deploying the minimum distance, the second feature vector was created using the maximum distance, and the third feature vector was the merged version of the first and second feature vectors