AUTHOR=Yu Yanhong , Li Wentao , Zhao Yue , Ye Jiayu , Zheng Yunshao , Liu Xinxin , Wang Qingxiang 

TITLE=Depression and Severity Detection Based on Body Kinematic Features: Using Kinect Recorded Skeleton Data of Simple Action

JOURNAL=Frontiers in Neurology

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/neurology/articles/10.3389/fneur.2022.905917

DOI=10.3389/fneur.2022.905917

ISSN=1664-2295

ABSTRACT=Relative limb movement is an important feature in assessing depression. In this paper, we investigated whether a skeleton-mimetic task of natural stimuli can aid depression recognition.
We innovatively used Kinect V2 to collect participant data. Sequential skeletal data was directly extracted from the original Kinect-3D and tetrad coordinates of the participant's 25 body joints. 
After the data preprocessing, two handcrafted skeletal datasets of whole-body joints, which included binary classification and multi classification, were fed into the proposed model for the depression recognition.  We improved the temporal convolution network (TCN),  which built in a hierarchy of temporal convolution groups with different dilated convolution scales to capture important crucial skeletal features for the final result prediction. Experimental results show that our method achieves excellent results, the depression and non-depression groups can be classified automatically with a maximum accuracy of 75.8% in the binary classification task, and 64.3% accuracy in the multi classification dataset to recognize more fine-grained identification of depression severity. Results of automatic depression detection have already achieved a reasonable accuracy, indicating that body postures and movements can effectively contribute to depression recognition.