Fusion_dataset

Facial expression: 1152 x 2048 pixels and RGB tones were lost in the preprocessing of the collected facial expression images. "facial_expression.csv.zip" contains gray scale 48 x 48 pixel data. Audio Signals.zip file: raw audio data Physiological Signal: The physiological signals of participants were sampled at varying frequencies using the wrist-worn Empatica E4 sensor device. To resolve this issue, a downsampling technique was used to make the frequencies of the signals more uniform. Downsampling was chosen to achieve a balance between computing efficiency and accuracy. By downsampling all physiological inputs to 4 Hz, consistency and effective fusion were attained.