FPGA-Based Implementation of Stochastic Configuration Networks for Regression Prediction
The implementation of neural network regression prediction based on digital circuits is one of the challenging problems in the field of machine learning and cognitive recognition, and it is also an effective way to relieve the pressure of the Internet in the era of intelligence. As a nonlinear netwo...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/15/4191 |
| _version_ | 1797561083381153792 |
|---|---|
| author | Yunqi Gao Feng Luan Jiaqi Pan Xu Li Yaodong He |
| author_facet | Yunqi Gao Feng Luan Jiaqi Pan Xu Li Yaodong He |
| author_sort | Yunqi Gao |
| collection | DOAJ |
| description | The implementation of neural network regression prediction based on digital circuits is one of the challenging problems in the field of machine learning and cognitive recognition, and it is also an effective way to relieve the pressure of the Internet in the era of intelligence. As a nonlinear network, the stochastic configuration network (SCN) is considered to be an effective method for regression prediction due to its good performance in learning and generalization. Therefore, in this paper, we adapt the SCN to regression analysis, and design and verify the field programmable gate array (FPGA) framework to implement SCN model for the first time. In addition, in order to improve the performance of the SCN model based on the FPGA, the implementation of the nonlinear activation function on the FPGA is optimized, which effectively improves the prediction accuracy while considering the utilization rate of hardware resources. Experimental results based on the simulation data set and the real data set prove that the proposed FPGA framework successfully implements the SCN regression prediction model, and the improved SCN model has higher accuracy and a more stable performance. Compared with the extreme learning machine (ELM), the prediction performance of the proposed SCN implementation model based on the FPGA for the simulation data set and the real data set is improved by 56.37% and 17.35%, respectively. |
| first_indexed | 2024-03-10T18:10:14Z |
| format | Article |
| id | doaj.art-9279da4460224f3e9318cc6febbb42b6 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T18:10:14Z |
| publishDate | 2020-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-9279da4460224f3e9318cc6febbb42b62023-11-20T08:12:50ZengMDPI AGSensors1424-82202020-07-012015419110.3390/s20154191FPGA-Based Implementation of Stochastic Configuration Networks for Regression PredictionYunqi Gao0Feng Luan1Jiaqi Pan2Xu Li3Yaodong He4School of Computer Science and Engineering, Northeastern University, Shenyang 110819, ChinaSchool of Computer Science and Engineering, Northeastern University, Shenyang 110819, ChinaSchool of Computer Science and Engineering, Northeastern University, Shenyang 110819, ChinaThe State Key Laboratory of Rolling and Automation, Northeastern University, Shenyang 110819, ChinaThe State Key Laboratory of Rolling and Automation, Northeastern University, Shenyang 110819, ChinaThe implementation of neural network regression prediction based on digital circuits is one of the challenging problems in the field of machine learning and cognitive recognition, and it is also an effective way to relieve the pressure of the Internet in the era of intelligence. As a nonlinear network, the stochastic configuration network (SCN) is considered to be an effective method for regression prediction due to its good performance in learning and generalization. Therefore, in this paper, we adapt the SCN to regression analysis, and design and verify the field programmable gate array (FPGA) framework to implement SCN model for the first time. In addition, in order to improve the performance of the SCN model based on the FPGA, the implementation of the nonlinear activation function on the FPGA is optimized, which effectively improves the prediction accuracy while considering the utilization rate of hardware resources. Experimental results based on the simulation data set and the real data set prove that the proposed FPGA framework successfully implements the SCN regression prediction model, and the improved SCN model has higher accuracy and a more stable performance. Compared with the extreme learning machine (ELM), the prediction performance of the proposed SCN implementation model based on the FPGA for the simulation data set and the real data set is improved by 56.37% and 17.35%, respectively.https://www.mdpi.com/1424-8220/20/15/4191field programmable gate arrayhardware neural networksregression predictionstochastic configuration networks |
| spellingShingle | Yunqi Gao Feng Luan Jiaqi Pan Xu Li Yaodong He FPGA-Based Implementation of Stochastic Configuration Networks for Regression Prediction Sensors field programmable gate array hardware neural networks regression prediction stochastic configuration networks |
| title | FPGA-Based Implementation of Stochastic Configuration Networks for Regression Prediction |
| title_full | FPGA-Based Implementation of Stochastic Configuration Networks for Regression Prediction |
| title_fullStr | FPGA-Based Implementation of Stochastic Configuration Networks for Regression Prediction |
| title_full_unstemmed | FPGA-Based Implementation of Stochastic Configuration Networks for Regression Prediction |
| title_short | FPGA-Based Implementation of Stochastic Configuration Networks for Regression Prediction |
| title_sort | fpga based implementation of stochastic configuration networks for regression prediction |
| topic | field programmable gate array hardware neural networks regression prediction stochastic configuration networks |
| url | https://www.mdpi.com/1424-8220/20/15/4191 |
| work_keys_str_mv | AT yunqigao fpgabasedimplementationofstochasticconfigurationnetworksforregressionprediction AT fengluan fpgabasedimplementationofstochasticconfigurationnetworksforregressionprediction AT jiaqipan fpgabasedimplementationofstochasticconfigurationnetworksforregressionprediction AT xuli fpgabasedimplementationofstochasticconfigurationnetworksforregressionprediction AT yaodonghe fpgabasedimplementationofstochasticconfigurationnetworksforregressionprediction |