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.
Highlights
Human activity recognition (HAR) presents significant opportunities for various domains, from healthcare applications such as patient monitoring to fitness tracking and productivity assessment, where a system can efficiently detect a specific subject movement, such as standing up or sitting down, while ignoring other activities
Evaluation of Performance With Only Accelerometer Inputs we investigate the impact of the removal of gyroscope inputs on the accuracy of Long Short-Term Memory (LSTM) and Continuous Time Recurrent Neural Network (CTRNN) models
This finding may have a substantial impact on reducing the complexity of implementing the microelectromechanical systems (MEMS) CTRNN hardware as there is no need to fabricate and integrate gyroscopes in the computing hardware
Summary
Human activity recognition (HAR) presents significant opportunities for various domains, from healthcare applications such as patient monitoring to fitness tracking and productivity assessment, where a system can efficiently detect a specific subject movement, such as standing up or sitting down, while ignoring other activities. Wrist-wearable devices embedded with many highly sensitive and fast-response Microelectromechanical Systems (MEMS) Inertial Measurement Units (IMUs), such as accelerometers and gyroscopes, are among the best candidates for performing this kind of detection. They can ensure a high degree of adoption because they are perceived as non-intrusive pieces of jewelry. The high energy cost of wirelessly transmitting data, limits the amount of raw sensor data that can be sent and processed externally [1, 2] These limitations reduce the accuracy and applicability of machine learning models, especially when data are sampled at very high rates, which leads to latencies [3]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.