Home // HEALTHINFO 2018, The Third International Conference on Informatics and Assistive Technologies for Health-Care, Medical Support and Wellbeing // View article

Depression Severity Prediction by Multi-model Fusion

Authors:
Bin Li
Jie Zhu
Chunpeng Wang

Keywords: Depress detection; multi-model; fusion; machine learning.

Abstract:
Depression is a common mental disorder and over 300 million people are estimated to suffer from it,which makes the diagnosis of it, especially for the severity, a signifcant but challenge problem. In this paper,we propose a multi-model fusion framework to detect the depression severity based on the random forest machine learning algorithms, and using features selected from different mediums. We frst selected features of audio, video, and text contents of each patient with a fusion strategy using the decision-level fusion. The multimodel fusion regressors were trained with the extracted features to obtain the depression severity. To handle the imbalanced dataset problem, a sampling strategy was also conducted. Experiments were demonstrated on the Distress Analysis Interview Corpus-Wizard of Oz (DAIC-WOZ) database. The proposed framework achieved a Root Mean Square Error (RMSE) of 5.98, which is less than the baseline of 6.62 and suggest that our approach is efcient and suitable for the depression severity detection.

Pages: 19 to 24

Copyright: Copyright (c) IARIA, 2018

Publication date: October 14, 2018

Published in: conference

ISSN: 2519-8491

ISBN: 978-1-61208-675-0

Location: Nice, France

Dates: from October 14, 2018 to October 18, 2018