ZWZixuan Wu

Zixuan Wu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Zixuan Wu has a total of 4 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Quantifying Emotions via Pupil Diameter and Grip Strength Measurements

    by Zixuan Wu, Yunrui Shang, Yinhua Liu

    Emotions, fundamental to human experiences, pose a persistent challenge in quantification due to their subjective and complex nature. Existing methods usually limit emotional quantification to two dimensions, failing to comprehensively capture the entirety of emotional fluctuations. In this research, a model termed as the "three-dimensional emotion space" (TDES) is introduced to elucidate and quantify emotions via pupil diameter (PD) and grip strength (GS) analysis, while introducing innovative metrics to discern emotional states. Specifically, an emotion induction experiment utilizing auditory and visual stimuli was first conducted to evoke three distinct emotional states (startled, stressed, amused), while collecting pupil diameter and grip strength samples. Kalman filtering and Wavelet denoising were employed to preprocess the raw data. Temporal and frequency domain features were extracted and mapped onto a three-dimensional coordinate system, resulting in a sequence of discrete points that outlined the trajectory curves and classification space of emotions. The results suggest the potential and feasibility of a novel method for quantifying emotions in a three-dimensional manner through the measurement of physiological signals, offering new perspectives in the field of emotion research.


  • Open Access

    EEG-Based Emotion Recognition Using Spatial-Temporal-Connective Features via Multi-Scale CNN

    by Tianyi Li, Baole Fu, Zixuan Wu, Yinhua Liu

    Electroencephalography (EEG) is often used for emotion recognition in brain computer interaction (BCI) research. EEG signals from each channel mainly reflect activities of the brain region close to the channel position, and the activities cooperated by various brain regions are response to the emotion-induced stimuli. In this paper, temporal, spatial and connective features are extracted from EEG signals gotten around the head, and used for emotion recognition via a proposed model, spatial-temporal-connective convolutional neural network (STC-CNN). The channel-to-channel connectivity is gotten to describe brain region-to-region cooperation under emotion stimuli. The STC-CNN achieved an average accuracy of 96.79 percent and 96.89 percent after classifying in two emotion dimensions of arousal and valence. Utilization of the method we proposed not only helped to achieve a higher accuracy of emotion recognition, but also explored a new selection of feature for EEG research.