Affective Brain Computer Interface—Using closed-loop BCI to recognize emotions and solve emotion problems

Abstract

Affective Brain Computer Interface (BCI) is an interdisciplinary system that integrates neuroscience, psychology, and computer science to detect and interpret human emotional states by analyzing brain and physiological signals. This article illustrates how affective BCI using Electroencephalography (EEG) and other physiological signals to recognize different emotions and diagnose mental diseases. With questionaries and interviews, this closed-loop BCI can personalize a specific treatment option. Affective Brain–Computer Interfaces (aBCIs) combine insights from neuroscience, psychology, and computing to better understand and influence human emotions. These systems can interpret signals such as EEG, ECoG, and fNIRS, offering a more objective way to assess conditions like depression or anxiety, which are often measured through self-reports. Unlike traditional open-loop BCIs, a closed-loop aBCI can track emotional states in real time and provide adaptive feedback through methods such as neurofeedback, non-invasive brain stimulation, or even deep brain stimulation. This paper outlines the foundations of emotion modeling, techniques for collecting and classifying signals, and strategies for system design. It also highlights key applications and ongoing challenges. With advances in machine learning and adaptive algorithms, closed-loop aBCIs present a potential pathway toward more personalized and ethically aware approaches to emotional health and treatment.