Abstract

With the popularity of smart wearable systems, sensor signal processing poses more challenges to machine learning in embedded scenarios. For example, traditional machine-learning methods for data classification, especially in real time, are computationally intensive. The deployment of Artificial Intelligence algorithms on embedded hardware for fast data classification and accurate fall detection poses a huge challenge in achieving power-efficient embedded systems. Therefore, by exploiting the associative memory feature of Hopfield Neural Network, a hardware module has been designed to simulate the Neural Network algorithm which uses sensor data integration and data classification for recognizing the fall. By adopting the Hebbian learning method for training neural networks, weights of human activity features are obtained and implemented/embedded into the hardware design. Here, the neural network weight of fall activity is achieved through data preprocessing, and then the weight is mapped to the amplification factor setting in the hardware. The designs are checked with validation scenarios, and the experiment is completed with a Hopfield neural network in the analog module. Through simulations, the classification accuracy of the fall data reached 88.9% which compares well with some other results achieved by the software-based machine-learning algorithms, which verify the feasibility of our hardware design. The designed system performs the complex signal calculations of the hardware’s feedback signal, replacing the software-based method. A straightforward circuit design is used to meet the weight setting from the Hopfield neural network, which is maximizing the reusability and flexibility of the circuit design.

Highlights

  • With the ever-improving living conditions, sensors-based healthcare has been widely adopted.Embedded systems are used as monitoring tools for well-being or preventive purposes

  • The matrix sample template of human fall activity is achieved by feature extraction computing that is based on data preprocessing for IMU sensor data

  • It shows the output of the human fall signal in the data has a different value with other classes human activities

Read more

Summary

Introduction

With the ever-improving living conditions, sensors-based healthcare has been widely adopted. The instruction set and architecture of a microprocessor constrain these software-based calculations on a general-purpose processor, and it requires many consumption thread resources to complete In this respect, hardware-based neuromorphic computing systems present a more efficient AI technology, that has been proposed by researchers and scientists at various levels. This paper focuses on the use of neuromorphic computing algorithms on hardware circuits, so that low-power and real-time systems for health care applications can be implemented. It uses hardware circuit features for algorithm calculations, to reduce power consumption due to the complexity of the computing architecture.

Neuromorphic Computing Implementation
Hardware Design
Evaluation and Results
Data Preprocessing for Feature Extraction
Comparison with State-of-the-Art Machine-Learning Algorithm and Discussion
Conclusions

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

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.