Loading...
Please wait, while we are loading the content...
Similar Documents
Low-Power FPGA Implementation of Convolution Neural Network Accelerator for Pulse Waveform Classification
| Content Provider | MDPI |
|---|---|
| Author | Chen, Chuanglu Li, Zhiqiang Zhang, Yitao Zhang, Shaolong Hou, Jiena Zhang, Haiying |
| Copyright Year | 2020 |
| Description | In pulse waveform classification, the convolution neural network (CNN) shows excellent performance. However, due to its numerous parameters and intensive computation, it is challenging to deploy a CNN model to low-power devices. To solve this problem, we implement a CNN accelerator based on a field-programmable gate array (FPGA), which can accurately and quickly infer the waveform category. By designing the structure of CNN, we significantly reduce its parameters on the premise of high accuracy. Then the CNN is realized on FPGA and optimized by a variety of memory access optimization methods. Experimental results show that our customized CNN has high accuracy and fewer parameters, and the accelerator costs only 0.714 W under a working frequency of 100MHz, which proves that our proposed solution is feasible. Furthermore, the accelerator classifies the pulse waveform in real time, which could help doctors make the diagnosis. |
| Starting Page | 213 |
| e-ISSN | 19994893 |
| DOI | 10.3390/a13090213 |
| Journal | Algorithms |
| Issue Number | 9 |
| Volume Number | 13 |
| Language | English |
| Publisher | MDPI |
| Publisher Date | 2020-08-31 |
| Access Restriction | Open |
| Subject Keyword | Algorithms Nuclear Energy and Engineering Convolution Neural Network (cnn) Traditional Chinese Medicine (tcm) Pulse Waveform Classification Field-programmable Gate Array (fpga) |
| Content Type | Text |
| Resource Type | Article |
