Plantar Pressure Based Personality Type Classification Using Gait Cycle Features.

Area of Science:

• Biomechanics
• Psychology
• Machine Learning

Background:

• Gait provides rich individual information, yet studies linking gait and personality are limited.
• Existing research lacks comprehensive analysis of diverse gait data and personality traits.

Purpose of the Study:

• To investigate the potential of classifying personality traits using gait cycle features from plantar pressure data.
• To analyze the correlation between specific gait cycle features and personality dimensions.

Main Methods:

• Collected gait plantar pressure data and personality type information from 24 healthy subjects.
• Extracted gait cycle features and employed Support Vector Machine (SVM) for classification.
• Utilized Pearson correlation analysis to examine feature importance and gait-personality relationships.

Main Results:

• SVM achieved classification accuracies of 0.775 for E-I, 0.741 for S-N, 0.63 for T-F, and 0.65 for J-P.
• Significant correlations were found between E-I and 2nd Double Support Time (-0.45), and S-N and Mid Stance Time (-0.418).
• No significant correlations were observed for T-F and J-P personality dimensions.

Conclusions:

• Gait cycle features from plantar pressure data show potential for classifying certain personality traits (E-I, S-N).
• This study offers foundational insights into the relationship between gait biomechanics and personality.
• Further research is needed to explore T-F and J-P trait classification and refine gait-based personality analysis.