Analyzing The Effect of Coffee Consumption On Visual Pathway Using Visual Evoked Potential (VEP) Signals and Machine Learning Algorithms

Abstract

In contemporary society, where coffee has assumed a fundamental role in daily routines, comprehending its influence on crucial neurological processes has paramount importance. Known for its significant caffeine content, it has garnered extensive recognition due to its ability to stimulate the central nervous system (CNS), resulting in various positive benefits such as mood enhancement, increased attention, and improved cognitive function. The effects of caffeine on the complex visual processing pathway have attracted attention due to studies indicating its influence on multiple aspects of visual processing. Although there is considerable interest in the cognitive effects of caffeine, there is a lack of research specifically examining its impact on the visual pathway using VEP signals and machine learning algorithms. In this study, a total of seven machine learning techniques will be employed for the purpose of data analysis. In addition, the performance of the models will be assessed using evaluation measures such as the precision-recall curve and confusion matrix. Therefore, the primary objective of this study is to address the existing information gap by examining changes in the visual pathway by analyzing the characteristics of the visual evoked potential (VEP) signals following the consumption of coffee using machine learning algorithms.