Predicting an EEG-Based hypnotic time estimation with non-linear kernels of support vector machine algorithm.

Our ability to measure time is vital for daily life, technology use, and even mental health; however, separating pure time perception from other mental processes (like emotions) is a research challenge requiring precise tests to isolate and understand brain activity solely related to time estimation. To address this challenge, we designed an experiment utilizing hypnosis alongside electroencephalography (EEG) to assess differences in time estimation, namely underestimation and overestimation. Hypnotic induction is designed to reduce awareness and meta-awareness, facilitating a detachment from the immediate environment. This reduced information processing load minimizes the need for elaborate internal thought during hypnosis, further simplifying the cognitive landscape. To predict time perception based on brain activity during extended durations (5 min), we employed artificial intelligence techniques. Utilizing Support Vector Machines (SVMs) with both radial basis function (RBF) and polynomial kernels, we assessed their effectiveness in classifying time perception-related brain patterns. We evaluated various feature combinations and different algorithms to identify the most accurate configuration. Our analysis revealed an impressive 80.9% classification accuracy for time perception detection using the RBF kernel, demonstrating the potential of AI in decoding this complex cognitive function.