Graph Representation Learning-Based Early Depression Detection Framework in Smart Home Environments.

Jongmo Kim,Mye Sohn

doi:10.3390/s22041545

Abstract

Although the diagnosis and treatment of depression is a medical field, ICTs and AI technologies are used widely to detect depression earlier in the elderly. These technologies are used to identify behavioral changes in the physical world or sentiment changes in cyberspace, known as symptoms of depression. However, although sentiment and physical changes, which are signs of depression in the elderly, are usually revealed simultaneously, there is no research on them at the same time. To solve the problem, this paper proposes knowledge graph-based cyber–physical view (CPV)-based activity pattern recognition for the early detection of depression, also known as KARE. In the KARE framework, the knowledge graph (KG) plays key roles in providing cross-domain knowledge as well as resolving issues of grammatical and semantic heterogeneity required in order to integrate cyberspace and the physical world. In addition, it can flexibly express the patterns of different activities for each elderly. To achieve this, the KARE framework implements a set of new machine learning techniques. The first is 1D-CNN for attribute representation in relation to learning to connect the attributes of physical and cyber worlds and the KG. The second is the entity alignment with embedding vectors extracted by the CNN and GNN. The third is a graph extraction method to construct the CPV from KG with the graph representation learning and wrapper-based feature selection in the unsupervised manner. The last one is a method of activity-pattern graph representation based on a Gaussian Mixture Model and KL divergence for training the GAT model to detect depression early. To demonstrate the superiority of the KARE framework, we performed the experiments using real-world datasets with five state-of-the-art models in knowledge graph entity alignment.

Highlights

Since the KG is huge, we propose an intermediary knowledge graph called the cyber–physical view entire KG is huge, we propose an intermediary knowledge graph called the cyber–physical (CPV) that extracts and represents the core elements of the KG required for view (CPV) that extracts and represents the core elements of the KG required the early detection of depression (Figure 1 right pane)
Experimental graph datasets collected from multiple domains such as the KG were required, and information such as the label text needed to be attached to the components of the graph
We proposed the use of the KARE framework, which enables the early detection of the depression in the elderly by integrating data from the physical world and the cyber world

Summary

Introduction

Detection of Depression (EDD) research using ICTs and AI technology is divided into two aspects. The first one detects depression early by capturing behavioral changes while continuously monitoring the behavior of the elderly in a smart home environment in which various sensors and their network are installed. Researchers in this field detect depression by recognizing changes in body shape such as a patient’s gait [13,14], head position [15], and thoracic kyphosis [16]. Unlike the young, the elderly in cyberspace are mostly passive users who enjoy surfing, watching, and enjoying, rather than active users who actively express their opinions and participate [19]

Methods

Results

Conclusion