Product Design Time Forecasting by Kernel-Based Regression with Gaussian Distribution Weights
There exist problems of small samples and heteroscedastic noise in design time forecasts. To solve them, a kernel-based regression with Gaussian distribution weights (GDW-KR) is proposed here. GDW-KR maintains a Gaussian distribution over weight vectors for the regression. It is applied to seek the...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2016-06-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1099-4300/18/6/231 |
| _version_ | 1798034808079646720 |
|---|---|
| author | Zhi-Gen Shang Hong-Sen Yan |
| author_facet | Zhi-Gen Shang Hong-Sen Yan |
| author_sort | Zhi-Gen Shang |
| collection | DOAJ |
| description | There exist problems of small samples and heteroscedastic noise in design time forecasts. To solve them, a kernel-based regression with Gaussian distribution weights (GDW-KR) is proposed here. GDW-KR maintains a Gaussian distribution over weight vectors for the regression. It is applied to seek the least informative distribution from those that keep the target value within the confidence interval of the forecast value. GDW-KR inherits the benefits of Gaussian margin machines. By assuming a Gaussian distribution over weight vectors, it could simultaneously offer a point forecast and its confidence interval, thus providing more information about product design time. Our experiments with real examples verify the effectiveness and flexibility of GDW-KR. |
| first_indexed | 2024-04-11T20:49:31Z |
| format | Article |
| id | doaj.art-d536cb9dda3b4d288da8143195808d1c |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-04-11T20:49:31Z |
| publishDate | 2016-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-d536cb9dda3b4d288da8143195808d1c2022-12-22T04:03:53ZengMDPI AGEntropy1099-43002016-06-0118623110.3390/e18060231e18060231Product Design Time Forecasting by Kernel-Based Regression with Gaussian Distribution WeightsZhi-Gen Shang0Hong-Sen Yan1MOE Key Laboratory of Measurement and Control of Complex Systems of Engineering, School of Automation, Southeast University, Nanjing 210096, ChinaMOE Key Laboratory of Measurement and Control of Complex Systems of Engineering, School of Automation, Southeast University, Nanjing 210096, ChinaThere exist problems of small samples and heteroscedastic noise in design time forecasts. To solve them, a kernel-based regression with Gaussian distribution weights (GDW-KR) is proposed here. GDW-KR maintains a Gaussian distribution over weight vectors for the regression. It is applied to seek the least informative distribution from those that keep the target value within the confidence interval of the forecast value. GDW-KR inherits the benefits of Gaussian margin machines. By assuming a Gaussian distribution over weight vectors, it could simultaneously offer a point forecast and its confidence interval, thus providing more information about product design time. Our experiments with real examples verify the effectiveness and flexibility of GDW-KR.http://www.mdpi.com/1099-4300/18/6/231design time forecastkernel-based regressionKullback-Leibler divergenceheteroscedasticity |
| spellingShingle | Zhi-Gen Shang Hong-Sen Yan Product Design Time Forecasting by Kernel-Based Regression with Gaussian Distribution Weights Entropy design time forecast kernel-based regression Kullback-Leibler divergence heteroscedasticity |
| title | Product Design Time Forecasting by Kernel-Based Regression with Gaussian Distribution Weights |
| title_full | Product Design Time Forecasting by Kernel-Based Regression with Gaussian Distribution Weights |
| title_fullStr | Product Design Time Forecasting by Kernel-Based Regression with Gaussian Distribution Weights |
| title_full_unstemmed | Product Design Time Forecasting by Kernel-Based Regression with Gaussian Distribution Weights |
| title_short | Product Design Time Forecasting by Kernel-Based Regression with Gaussian Distribution Weights |
| title_sort | product design time forecasting by kernel based regression with gaussian distribution weights |
| topic | design time forecast kernel-based regression Kullback-Leibler divergence heteroscedasticity |
| url | http://www.mdpi.com/1099-4300/18/6/231 |
| work_keys_str_mv | AT zhigenshang productdesigntimeforecastingbykernelbasedregressionwithgaussiandistributionweights AT hongsenyan productdesigntimeforecastingbykernelbasedregressionwithgaussiandistributionweights |