Abstract
Face recognition and related psychological phenomenon have been the subject of neurocognitive studies during last decades. More recently the problem of face identification is also addressed to test the possibility of finding markers on the electroencephalogram signals. To this end, this work presents an experimental study where Brain Computer Interface strategies were implemented to find features on the signals that could discriminate between culprit and innocent. The feature extraction block comprises time domain and frequency domain characteristics of single-trial signals. The classification block is based on a support vector machine and its performance for the best ranked features. The data analysis comprises the signals of a cohort of 28 participants.
Highlights
1.1 MotivationBefore the DNA analysis entered the court houses, around seventy one percent of the innocent convicted criminals had been condemned by eye witnesses [1]
The nature of the predominant features, both the spatial and temporal characteristics, were studied but only the ones provided by the ANalysis Of VAriance (ANOVA) method since the number of selected features by the Support Vector Machine (SVM)-RFE was highly different among all the participants
Frequency domain data consisted in information from theta, alpha and beta band during the entire epoch and time domain information consisted in the power and latency values of the following Event-Related Potential (ERP) components: P100, N170, P200 and P300
Summary
1.1 MotivationBefore the DNA analysis entered the court houses, around seventy one percent of the innocent convicted criminals had been condemned by eye witnesses [1]. In most cases, the crime itself is something that takes a few seconds and the witness might not had the time to process what was even happening, or maybe he/she only took a glimpse of the situation and consciously is unable to provide viable information to some investigation that is taking place. This may just be the detail missing in order to get a criminal in jail or stop an innocent from being wrongly accused. The application of such devices to vital witnesses could be a key feature to the justice system because it would, in theory, allow a detective to know if the information he/she is being provided with is reliable or if it is just outside noise like fear or anxiety clouding the witness’ judgement
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
