Intensity and Wavelength-Division Multiplexing Fiber Sensor Interrogation Using a Combination of Autoencoder Pre-Trained Convolution Neural Network and Differential Evolution Algorithm
This paper proposes a new fiber Bragg grating central wavelength interrogation system by combining evolutionary algorithm and machine learning techniques integrated with an unsupervised autoencoder (AE) pre-training strategy. The proposed unsupervised AE pre-training convolution neural network (CNN)...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Photonics Journal |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9319234/ |
| _version_ | 1819291225323208704 |
|---|---|
| author | Po-Han Chiu Yu-Shen Lin Yibeltal Chanie Manie Jyun-Wei Li Ja-Hon Lin Peng-Chun Peng |
| author_facet | Po-Han Chiu Yu-Shen Lin Yibeltal Chanie Manie Jyun-Wei Li Ja-Hon Lin Peng-Chun Peng |
| author_sort | Po-Han Chiu |
| collection | DOAJ |
| description | This paper proposes a new fiber Bragg grating central wavelength interrogation system by combining evolutionary algorithm and machine learning techniques integrated with an unsupervised autoencoder (AE) pre-training strategy. The proposed unsupervised AE pre-training convolution neural network (CNN) allows training of the convolutional layers independently from a regression task in order to learn a new data representation and give better generalization. It is also used to improve the system accuracy by four times without extra-labeled data. Moreover, AE is combined with a differential evolutionary (DE) algorithm to automate the human labeling task. The proposed autoencoder pre-training convolution neural network and differential evolutionary (AECNNDE) interrogation system achieve good accuracy and can speed-up the computational time by a maximum of 30 times than DE algorithm. |
| first_indexed | 2024-12-24T03:35:15Z |
| format | Article |
| id | doaj.art-053a24d947ec4fdebd423d30a94299b9 |
| institution | Directory Open Access Journal |
| issn | 1943-0655 |
| language | English |
| last_indexed | 2024-12-24T03:35:15Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Photonics Journal |
| spelling | doaj.art-053a24d947ec4fdebd423d30a94299b92022-12-21T17:17:04ZengIEEEIEEE Photonics Journal1943-06552021-01-011311910.1109/JPHOT.2021.30502989319234Intensity and Wavelength-Division Multiplexing Fiber Sensor Interrogation Using a Combination of Autoencoder Pre-Trained Convolution Neural Network and Differential Evolution AlgorithmPo-Han Chiu0Yu-Shen Lin1Yibeltal Chanie Manie2https://orcid.org/0000-0002-9584-661XJyun-Wei Li3Ja-Hon Lin4https://orcid.org/0000-0003-3271-7033Peng-Chun Peng5https://orcid.org/0000-0003-2663-0919Department of Electro-Optical Engineering, National Taipei University of Technology, Taipei, TaiwanDepartment of Electro-Optical Engineering, National Taipei University of Technology, Taipei, TaiwanDepartment of Electro-Optical Engineering, National Taipei University of Technology, Taipei, TaiwanDepartment of Electro-Optical Engineering, National Taipei University of Technology, Taipei, TaiwanDepartment of Electro-Optical Engineering, National Taipei University of Technology, Taipei, TaiwanDepartment of Electro-Optical Engineering, National Taipei University of Technology, Taipei, TaiwanThis paper proposes a new fiber Bragg grating central wavelength interrogation system by combining evolutionary algorithm and machine learning techniques integrated with an unsupervised autoencoder (AE) pre-training strategy. The proposed unsupervised AE pre-training convolution neural network (CNN) allows training of the convolutional layers independently from a regression task in order to learn a new data representation and give better generalization. It is also used to improve the system accuracy by four times without extra-labeled data. Moreover, AE is combined with a differential evolutionary (DE) algorithm to automate the human labeling task. The proposed autoencoder pre-training convolution neural network and differential evolutionary (AECNNDE) interrogation system achieve good accuracy and can speed-up the computational time by a maximum of 30 times than DE algorithm.https://ieeexplore.ieee.org/document/9319234/Intensity and wavelength division multiplexing (IWDM)Fiber Bragg gratings (FBG)Machine learning |
| spellingShingle | Po-Han Chiu Yu-Shen Lin Yibeltal Chanie Manie Jyun-Wei Li Ja-Hon Lin Peng-Chun Peng Intensity and Wavelength-Division Multiplexing Fiber Sensor Interrogation Using a Combination of Autoencoder Pre-Trained Convolution Neural Network and Differential Evolution Algorithm IEEE Photonics Journal Intensity and wavelength division multiplexing (IWDM) Fiber Bragg gratings (FBG) Machine learning |
| title | Intensity and Wavelength-Division Multiplexing Fiber Sensor Interrogation Using a Combination of Autoencoder Pre-Trained Convolution Neural Network and Differential Evolution Algorithm |
| title_full | Intensity and Wavelength-Division Multiplexing Fiber Sensor Interrogation Using a Combination of Autoencoder Pre-Trained Convolution Neural Network and Differential Evolution Algorithm |
| title_fullStr | Intensity and Wavelength-Division Multiplexing Fiber Sensor Interrogation Using a Combination of Autoencoder Pre-Trained Convolution Neural Network and Differential Evolution Algorithm |
| title_full_unstemmed | Intensity and Wavelength-Division Multiplexing Fiber Sensor Interrogation Using a Combination of Autoencoder Pre-Trained Convolution Neural Network and Differential Evolution Algorithm |
| title_short | Intensity and Wavelength-Division Multiplexing Fiber Sensor Interrogation Using a Combination of Autoencoder Pre-Trained Convolution Neural Network and Differential Evolution Algorithm |
| title_sort | intensity and wavelength division multiplexing fiber sensor interrogation using a combination of autoencoder pre trained convolution neural network and differential evolution algorithm |
| topic | Intensity and wavelength division multiplexing (IWDM) Fiber Bragg gratings (FBG) Machine learning |
| url | https://ieeexplore.ieee.org/document/9319234/ |
| work_keys_str_mv | AT pohanchiu intensityandwavelengthdivisionmultiplexingfibersensorinterrogationusingacombinationofautoencoderpretrainedconvolutionneuralnetworkanddifferentialevolutionalgorithm AT yushenlin intensityandwavelengthdivisionmultiplexingfibersensorinterrogationusingacombinationofautoencoderpretrainedconvolutionneuralnetworkanddifferentialevolutionalgorithm AT yibeltalchaniemanie intensityandwavelengthdivisionmultiplexingfibersensorinterrogationusingacombinationofautoencoderpretrainedconvolutionneuralnetworkanddifferentialevolutionalgorithm AT jyunweili intensityandwavelengthdivisionmultiplexingfibersensorinterrogationusingacombinationofautoencoderpretrainedconvolutionneuralnetworkanddifferentialevolutionalgorithm AT jahonlin intensityandwavelengthdivisionmultiplexingfibersensorinterrogationusingacombinationofautoencoderpretrainedconvolutionneuralnetworkanddifferentialevolutionalgorithm AT pengchunpeng intensityandwavelengthdivisionmultiplexingfibersensorinterrogationusingacombinationofautoencoderpretrainedconvolutionneuralnetworkanddifferentialevolutionalgorithm |