Neural Networks with Different Initialization Methods for Depression Detection

TL;DR

This paper explores neural network models with different initialization methods to predict depression from physical characteristics, demonstrating that Kaiming initialization improves accuracy to 83%.

Contribution

It introduces the application of neural networks with Kaiming initialization for depression detection based on physical data, which is a novel approach.

Findings

Kaiming initialization yields higher accuracy than Xavier.

A 3-layer neural network achieves 83% accuracy.

Physical characteristics can effectively predict depression.

Abstract

As a common mental disorder, depression is a leading cause of various diseases worldwide. Early detection and treatment of depression can dramatically promote remission and prevent relapse. However, conventional ways of depression diagnosis require considerable human effort and cause economic burden, while still being prone to misdiagnosis. On the other hand, recent studies report that physical characteristics are major contributors to the diagnosis of depression, which inspires us to mine the internal relationship by neural networks instead of relying on clinical experiences. In this paper, neural networks are constructed to predict depression from physical characteristics. Two initialization methods are examined - Xaiver and Kaiming initialization. Experimental results show that a 3-layers neural network with Kaiming initialization achieves $83\%$ accuracy.