Memristive Circuit Design of Sequencer Network for Human Emotion Classification

Abstract

Mental health problem is an increasingly common social issue leading to diseases such as depression, addiction, and heart attack. Facial expression is one of the most natural and universal signals for human beings to convey their emotional states and behavior intentions. Numerous studies have been conducted on automatic human emotion classification that can effectively establish the relationship between facial expression and mental health, while still suffer from intensive computation and low efficiency. Here, we present a memristive circuit design of Sequencer network for human emotion classification, which offers an environmentally friendly approach with low cost and easily deployable hardware. Specifically, a kind of eco-friendly memristor is fabricated using two-dimensional (2D) materials, and the corresponding testing performance is conducted to make sure its efficiency and stability. Then, the memristor-based Sequencer block, as a core component of Sequencer network, consisting of bidirectional long short-term memory (BiLSTM) circuit and some necessary function circuit modules is proposed. Based on this, the memristive Sequencer network can be achieved. Furthermore, the proposed memristive Sequencer network is applied for human emotion classification. The experimental results demonstrate that the proposed circuit has advantages in computational efficiency and cost, comparable to the main existing software-based methods.