Reconstruction of the External Stimuli from Brain Signals

TL;DR

This paper explores reconstructing external stimuli from brain signals by regressing stimuli spectrograms from neuroimaging data, demonstrating the feasibility of such methods for real-world applications.

Contribution

It introduces a regression-based approach to reconstruct stimuli spectrograms from brain signals, advancing brain decoding capabilities beyond classification.

Findings

Feasibility of reconstructing stimuli spectrograms from brain signals.

Applicable to out-of-lab neuroimaging scenarios.

Supports naturalistic stimulus reconstruction.

Abstract

Despite the rapid advances in Brain-computer Interfacing (BCI) and continuous effort to improve the accuracy of brain decoding systems, the urge for the systems to reconstruct the experiences of the users has been widely acknowledged. This urge has been investigated by some researchers during the past years in terms of reconstruction of the naturalistic images, abstract images, video and audio. In this study, we try to tackle this issue by regressing the stimuli spectrogram using the spectrogram analysis of the brain signals. The results of our regression-based method suggest the feasibility of such reconstructions using the neuroimaging techniques that are appropriate for out-of-lab scenarios.