Simulation for a Mems-Based CTRNN Ultra-Low Power Implementation of Human Activity Recognition

Muhammad Emad-Ud-Din; Mohammad H Hasan; Roozbeh Jafari; Siavash Pourkamali; Fadi Alsaleem

doi:10.3389/fdgth.2021.731076

Simulation for a Mems-Based CTRNN Ultra-Low Power Implementation of Human Activity Recognition

Front Digit Health. 2021 Sep 22:3:731076. doi: 10.3389/fdgth.2021.731076. eCollection 2021.

Authors

Muhammad Emad-Ud-Din¹, Mohammad H Hasan², Roozbeh Jafari^{1

3

4}, Siavash Pourkamali⁵, Fadi Alsaleem⁶

Affiliations

¹ Department of Computer Science and Engineering, Texas A&M University, College Station, TX, United States.
² Department of Earth and Space Sciences, Columbus State University, Columbus, OH, United States.
³ Department of Electrical and Computer Engineering, University of Texas at Dallas, Dallas, TX, United States.
⁴ Department of Biomedical Engineering, Texas A&M University, College Station, TX, United States.
⁵ Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX, United States.
⁶ Durham School of Architectural Engineering and Construction, University of Nebraska-Lincoln, Omaha, NE, United States.

Abstract

This paper presents an energy-efficient classification framework that performs human activity recognition (HAR). Typically, HAR classification tasks require a computational platform that includes a processor and memory along with sensors and their interfaces, all of which consume significant power. The presented framework employs microelectromechanical systems (MEMS) based Continuous Time Recurrent Neural Network (CTRNN) to perform HAR tasks very efficiently. In a real physical implementation, we show that the MEMS-CTRNN nodes can perform computing while consuming power on a nano-watts scale compared to the micro-watts state-of-the-art hardware. We also confirm that this huge power reduction doesn't come at the expense of reduced performance by evaluating its accuracy to classify the highly cited human activity recognition dataset (HAPT). Our simulation results show that the HAR framework that consists of a training module, and a network of MEMS-based CTRNN nodes, provides HAR classification accuracy for the HAPT that is comparable to traditional CTRNN and other Recurrent Neural Network (RNN) implantations. For example, we show that the MEMS-based CTRNN model average accuracy for the worst-case scenario of not using pre-processing techniques, such as quantization, to classify 5 different activities is 77.94% compared to 78.48% using the traditional CTRNN.

Keywords: LSTM – long short-term memory; MEMS; continuous time recurrent neural network; human activity recognition; recurrent neural networks.