Violence Detection From ECG Signals: A Preliminary Study 

Abstract

This research studied violence detection from less than 6-second ECG signals. Features were calculated based on the Bivariate Empirical Mode Decomposition (BEMD) and the Recurrence Quantification Analysis (RQA) applied to ECG signals from violence simulation in a primary school, involving 12 pupils from two grades. The feature sets were fed to a kNN classifier and tested using 10-fold cross validation and leave-one-subject-out (LOSO) validation in subject-dependent and subject-independent training models respectively. Features from BEMD outperformed the ones from RQA in both 10-fold cross validation, i.e. 88% vs. 73% (2nd grade pupils) and 87% vs. 81% (5th grade pupils), and LOSO validation, i.e. 77% vs. 75% (2nd grade pupils) and 80% vs. 76% (5th grade pupils), but have larger variation than the ones from RQA in both validations. Average performances for subject-specific system in 10-fold cross validation were 100% vs. 93% (2nd grade pupils) and 100% vs. 97% (5th grade pupils) for features from the BEMD and the RQA respectively. The results indicate that ECG signals as short as 6 seconds can be used successfully to detect violent events using subject-specific classifiers.

VITEC: A Violence Detection Framework

“…Once a suspicious event is identified, the primary agent sends signals carrying that suspicious event along with the primary agent's ID and geographical location acquired from GPS to the cloud for further processing. The contribution of detecting violence using human body movements [21,30] and physiological signal [22] fit for this role. Fig.…”

“…EDA [19], EEG [20]. Secondly, the systems use signals measured from the victims directly, for example, their human body movement [21] and ECG signal [22]. Nam, Alghoniemy, and Tewfik pioneered a study on violent scene characterization based on flame and blood detection [16].…”

“…Using single channel ECG (electrical activity of the heart) signals measured in pupils involved in violence simulation, violent events could also be identified [22]. This work also emphasized on the violence detection from the victim's point of view.…”

“…Both physiological signals are sensitive enough to affect stimulation, such that it may indicate that the subject is not in danger but having fun. Ferdinando et al (2017) showed that it is possible, although not always, to separate some fun activities denoted as non-violence, e.g. playing, from simulated violence, e.g.…”

Towards a Holistic ICT Platform for Protecting Intimate Partner Violence Survivors Based on the IoT Paradigm

“…Heart rate is one of the commonly measured features in most of the models, and Ferdinando et al [26] found that it could be an indicator of emotional state. Other complex systems involve the use of the electrocardiogram (ECG) to detect an abuse situation [27].…”