Quantitative Analysis of Structural Parameters Importance of Helical Temperature Microfiber Sensor by Artificial Neural Network
With the assistance of the evaluation algorithms based on the well-performed backpropagation neural network (BPNN), we quantitatively analyze the importance of the structural parameters of the supported helical microfiber (HMF) temperature sensor. The relative output intensities of HMF sensor at dif...
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
IEEE
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/8c7793bcc0a54932b21f588ace0db1f6 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:8c7793bcc0a54932b21f588ace0db1f6 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:8c7793bcc0a54932b21f588ace0db1f62021-11-18T00:10:24ZQuantitative Analysis of Structural Parameters Importance of Helical Temperature Microfiber Sensor by Artificial Neural Network2169-353610.1109/ACCESS.2021.3124665https://doaj.org/article/8c7793bcc0a54932b21f588ace0db1f62021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9597537/https://doaj.org/toc/2169-3536With the assistance of the evaluation algorithms based on the well-performed backpropagation neural network (BPNN), we quantitatively analyze the importance of the structural parameters of the supported helical microfiber (HMF) temperature sensor. The relative output intensities of HMF sensor at different temperatures are predicted by the BPNN with the HMF’s structural parameters as the input variables. The best-forecasted performance is obtained by the BPNN with one hidden layer of ten neurons. Compared with the actual values, the root-mean-square error (RMSE) and the correlation coefficient of the predicted values are 9.7 <inline-formula> <tex-math notation="LaTeX">$\times \,\,10^{-3}$ </tex-math></inline-formula> dB and 99.84%, respectively. Based on the BPNN with precise prediction, the backward stepwise elimination and the holdback input randomization methods are used to quantitatively discuss the influence of the structural parameters on the output intensity of the HMF. The relative importance from high to low is the helical length (~38%), microfiber diameter (~27%), helical angle (~25%), and cone angle (~10%). The importance of four geometric parameters obtained by the two methods is ranked the same. Quantitative analysis of structural parameters relying on the well-predicted BPNN can give basic information on the structural characteristics of the HMF sensor, which helps to optimize the structure design of the optical sensors based on micro/nanofiber and provides a powerful guarantee for its practical application.Juan LiuMinghui ChenHang YuJinjin HanHongyi JiaZhili LinZhijun WuJixiong PuXining ZhangHao DaiIEEEarticleHelical microfibertemperature sensorquantitative contribution of structural parametersbackpropagation neural networkElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 148156-148163 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Helical microfiber temperature sensor quantitative contribution of structural parameters backpropagation neural network Electrical engineering. Electronics. Nuclear engineering TK1-9971 |
| spellingShingle |
Helical microfiber temperature sensor quantitative contribution of structural parameters backpropagation neural network Electrical engineering. Electronics. Nuclear engineering TK1-9971 Juan Liu Minghui Chen Hang Yu Jinjin Han Hongyi Jia Zhili Lin Zhijun Wu Jixiong Pu Xining Zhang Hao Dai Quantitative Analysis of Structural Parameters Importance of Helical Temperature Microfiber Sensor by Artificial Neural Network |
| description |
With the assistance of the evaluation algorithms based on the well-performed backpropagation neural network (BPNN), we quantitatively analyze the importance of the structural parameters of the supported helical microfiber (HMF) temperature sensor. The relative output intensities of HMF sensor at different temperatures are predicted by the BPNN with the HMF’s structural parameters as the input variables. The best-forecasted performance is obtained by the BPNN with one hidden layer of ten neurons. Compared with the actual values, the root-mean-square error (RMSE) and the correlation coefficient of the predicted values are 9.7 <inline-formula> <tex-math notation="LaTeX">$\times \,\,10^{-3}$ </tex-math></inline-formula> dB and 99.84%, respectively. Based on the BPNN with precise prediction, the backward stepwise elimination and the holdback input randomization methods are used to quantitatively discuss the influence of the structural parameters on the output intensity of the HMF. The relative importance from high to low is the helical length (~38%), microfiber diameter (~27%), helical angle (~25%), and cone angle (~10%). The importance of four geometric parameters obtained by the two methods is ranked the same. Quantitative analysis of structural parameters relying on the well-predicted BPNN can give basic information on the structural characteristics of the HMF sensor, which helps to optimize the structure design of the optical sensors based on micro/nanofiber and provides a powerful guarantee for its practical application. |
| format |
article |
| author |
Juan Liu Minghui Chen Hang Yu Jinjin Han Hongyi Jia Zhili Lin Zhijun Wu Jixiong Pu Xining Zhang Hao Dai |
| author_facet |
Juan Liu Minghui Chen Hang Yu Jinjin Han Hongyi Jia Zhili Lin Zhijun Wu Jixiong Pu Xining Zhang Hao Dai |
| author_sort |
Juan Liu |
| title |
Quantitative Analysis of Structural Parameters Importance of Helical Temperature Microfiber Sensor by Artificial Neural Network |
| title_short |
Quantitative Analysis of Structural Parameters Importance of Helical Temperature Microfiber Sensor by Artificial Neural Network |
| title_full |
Quantitative Analysis of Structural Parameters Importance of Helical Temperature Microfiber Sensor by Artificial Neural Network |
| title_fullStr |
Quantitative Analysis of Structural Parameters Importance of Helical Temperature Microfiber Sensor by Artificial Neural Network |
| title_full_unstemmed |
Quantitative Analysis of Structural Parameters Importance of Helical Temperature Microfiber Sensor by Artificial Neural Network |
| title_sort |
quantitative analysis of structural parameters importance of helical temperature microfiber sensor by artificial neural network |
| publisher |
IEEE |
| publishDate |
2021 |
| url |
https://doaj.org/article/8c7793bcc0a54932b21f588ace0db1f6 |
| work_keys_str_mv |
AT juanliu quantitativeanalysisofstructuralparametersimportanceofhelicaltemperaturemicrofibersensorbyartificialneuralnetwork AT minghuichen quantitativeanalysisofstructuralparametersimportanceofhelicaltemperaturemicrofibersensorbyartificialneuralnetwork AT hangyu quantitativeanalysisofstructuralparametersimportanceofhelicaltemperaturemicrofibersensorbyartificialneuralnetwork AT jinjinhan quantitativeanalysisofstructuralparametersimportanceofhelicaltemperaturemicrofibersensorbyartificialneuralnetwork AT hongyijia quantitativeanalysisofstructuralparametersimportanceofhelicaltemperaturemicrofibersensorbyartificialneuralnetwork AT zhililin quantitativeanalysisofstructuralparametersimportanceofhelicaltemperaturemicrofibersensorbyartificialneuralnetwork AT zhijunwu quantitativeanalysisofstructuralparametersimportanceofhelicaltemperaturemicrofibersensorbyartificialneuralnetwork AT jixiongpu quantitativeanalysisofstructuralparametersimportanceofhelicaltemperaturemicrofibersensorbyartificialneuralnetwork AT xiningzhang quantitativeanalysisofstructuralparametersimportanceofhelicaltemperaturemicrofibersensorbyartificialneuralnetwork AT haodai quantitativeanalysisofstructuralparametersimportanceofhelicaltemperaturemicrofibersensorbyartificialneuralnetwork |
| _version_ |
1718425176814649344 |