人工智能
计算机科学
机器学习
多模态
传感器融合
训练集
融合
统计学习
机器人学
计算机视觉
出处
期刊:
[Institute of Electrical and Electronics Engineers]
日期:2026-06-01
卷期号:: 1-4
标识
DOI:10.1109/iehns68708.2026.11606957
摘要
This study aims to explore the application of machine learning technology in art therapy and improve the prediction accuracy of art therapy effects through multimodal data fusion methods. The study integrated visual art works images, audio recordings, and physiological index data, used convolutional neural networks (CNN) and recurrent neural networks (RNN) to extract features of different modalities respectively, and realized feature fusion through multi-layer perceptron (MLP). Experimental results show that the proposed multimodal data fusion method is significantly better than single-modal models and other fusion methods in accuracy and F1 score, with an accuracy of 88% and an F1 score of 0.85, which verifies the effectiveness of multimodal data in capturing complex interactions and emotional changes in the process of art therapy. The research results demonstrate the potential of machine learning technology in improving the evaluation of art therapy effects, indicating that the effective integration of multimodal data can more comprehensively reflect the emotional and physiological changes of subjects, thereby providing a scientific basis for the personalization and precision of art therapy.
科研通智能强力驱动
Strongly Powered by AbleSci AI