Digital Library[ Search Result ]
Integrating Domain Knowledge with Graph Convolution based on a Semantic Network for Elderly Depression Prediction
Seok-Jun Bu, Kyoung-Won Park, Sung-Bae Cho
http://doi.org/10.5626/JOK.2023.50.3.243
Depression in the elderly is a global problem that causes 300 million patients and 800,000 suicides every year, so it is critical to detect early daily activity patterns closely related to mobility. Although a graph-convolution neural network based on sensing logs has been promising, it is required to represent high-level behaviors extracted from complex sensing information sequences. In this paper, a semantic network that structuralizes the daily activity patterns of the elderly was constructed using additional domain knowledge, and a graph convolution model was proposed for complementary uses of low-level sensing log graphs. Cross-validation with 800 hours of data from 69 senior citizens provided by DNX, Inc. revealed improved prediction performance for the suggested strategy compared to the most recent deep learning model. In particular, the inference of a semantic network was justified by a graph convolution model by showing a performance improvement of 28.86% compared with the conventional model.
An Autism Spectrum Disorder Detection System Based on Learning Dynamic Connectivity of the Superior Temporal Sulcus
Kyoung-Won Park, Seok-Jun Bu, Sung-Bae Cho
http://doi.org/10.5626/JOK.2022.49.5.354
Considering a hypothesis that abnormalities in the superior temporal sulcus (STS) connected with visual cortex regions can be a critical sign of ASD, autism spectrum disorder, a model is required to exploit the brain functional connectivity between the STS and visual cortex to reinforce the neurobiological evidence. This paper proposes a deep learning model comprising attention and convolutional recurrent neural networks that can select and extract the time-series pattern of dynamic connectivity between the two regions within the brain based on observations. By integration of the extracted autism disorder features from dynamic connectivity through attention with the structure containing interlayer connections to preserve the functional connectivity loss within a neural network, the model extracts the connectivity between the STS and visual cortex, leading to an increase in generalization performance. A 10-fold cross-validation to compare the performance shows that the proposed model outperforms the state-of-the-art models by achieving an improvement of 4.90% in the ASD classification. Additionally, we use the proposed method to diagnose ASD by visualizing dynamic brain connectivity of the neural network layers.
Search
Journal of KIISE
- ISSN : 2383-630X(Print)
- ISSN : 2383-6296(Electronic)
- KCI Accredited Journal
Editorial Office
- Tel. +82-2-588-9240
- Fax. +82-2-521-1352
- E-mail. chwoo@kiise.or.kr