AI in Emergency Responses: Distress & Lie Detection Using Audio & EEG

The paper contributes findings toward the development of an artificial intelligence system that might be able to, in real-time, detect instances of dishonesty via facial expression analysis and audio spectrograms and EEG data. It uses through the Random Forest classifier applied on the process of processing EEG data analysis a process identifying the brain patterns related to dishonest conduct. The approach used is Faster R-CNN, which is a term for Region-Based Convolutional Neural Network, to detect and classify the micro expressions efficiently and accurately, in facial emotion analysis. These may possibly be the signs of not telling the truth about the person. More so, spectrograms will be utilized by the audio model in finding the stresses, speech, and tone levels in extracting vocal features associated with dishonesty. The same is achieved in making the identification of these features easy. Putting the EEG, facial expressions, and audio modalities together offer a holistic approach to the detection of falsification. This is only possible by this integration of information across the auditory, behavioral, and physiological domains. Although the system is very effective to be used in the critical event management, security, and law enforcement because of its capability to successfully detect dishonesty with data coming from varied sources, for one, it has the capability to effectively detect dishonesty. The system enables automatic report generation as well as the displaying of real-time deception possibilities. It is built to be useful in situations that include different languages and numerous contexts so as to better enhance the processes involved in decision-making.