Temperature Field Reconstruction Method for Acoustic Tomography Based on Multi-Dictionary Learning
A reconstruction algorithm is proposed, based on multi-dictionary learning (MDL), to improve the reconstruction quality of acoustic tomography for complex temperature fields. Its aim is to improve the under-determination of the inverse problem by the sparse representation of the sound slowness signa...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/1/208 |
| _version_ | 1797431236688347136 |
|---|---|
| author | Yuankun Wei Hua Yan Yinggang Zhou |
| author_facet | Yuankun Wei Hua Yan Yinggang Zhou |
| author_sort | Yuankun Wei |
| collection | DOAJ |
| description | A reconstruction algorithm is proposed, based on multi-dictionary learning (MDL), to improve the reconstruction quality of acoustic tomography for complex temperature fields. Its aim is to improve the under-determination of the inverse problem by the sparse representation of the sound slowness signal (i.e., reciprocal of sound velocity). In the MDL algorithm, the K-SVD dictionary learning algorithm is used to construct corresponding sparse dictionaries for sound slowness signals of different types of temperature fields; the KNN peak-type classifier is employed for the joint use of multiple dictionaries; the orthogonal matching pursuit (OMP) algorithm is used to obtain the sparse representation of sound slowness signal in the sparse domain; then, the temperature distribution is obtained by using the relationship between sound slowness and temperature. Simulation and actual temperature distribution reconstruction experiments show that the MDL algorithm has smaller reconstruction errors and provides more accurate information about the temperature field, compared with the compressed sensing and improved orthogonal matching pursuit (CS-IMOMP) algorithm, which is an algorithm based on compressed sensing and improved orthogonal matching pursuit (in the CS-IMOMP, DFT dictionary is used), the least square algorithm (LSA) and the simultaneous iterative reconstruction technique (SIRT). |
| first_indexed | 2024-03-09T09:41:59Z |
| format | Article |
| id | doaj.art-b8e19327388a474793a8228768ea64b7 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T09:41:59Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-b8e19327388a474793a8228768ea64b72023-12-02T00:54:15ZengMDPI AGSensors1424-82202022-12-0123120810.3390/s23010208Temperature Field Reconstruction Method for Acoustic Tomography Based on Multi-Dictionary LearningYuankun Wei0Hua Yan1Yinggang Zhou2School of Information Science and Engineering, Shenyang University of Technology, Shenyang 110870, ChinaSchool of Information Science and Engineering, Shenyang University of Technology, Shenyang 110870, ChinaSchool of Information Science and Engineering, Shenyang University of Technology, Shenyang 110870, ChinaA reconstruction algorithm is proposed, based on multi-dictionary learning (MDL), to improve the reconstruction quality of acoustic tomography for complex temperature fields. Its aim is to improve the under-determination of the inverse problem by the sparse representation of the sound slowness signal (i.e., reciprocal of sound velocity). In the MDL algorithm, the K-SVD dictionary learning algorithm is used to construct corresponding sparse dictionaries for sound slowness signals of different types of temperature fields; the KNN peak-type classifier is employed for the joint use of multiple dictionaries; the orthogonal matching pursuit (OMP) algorithm is used to obtain the sparse representation of sound slowness signal in the sparse domain; then, the temperature distribution is obtained by using the relationship between sound slowness and temperature. Simulation and actual temperature distribution reconstruction experiments show that the MDL algorithm has smaller reconstruction errors and provides more accurate information about the temperature field, compared with the compressed sensing and improved orthogonal matching pursuit (CS-IMOMP) algorithm, which is an algorithm based on compressed sensing and improved orthogonal matching pursuit (in the CS-IMOMP, DFT dictionary is used), the least square algorithm (LSA) and the simultaneous iterative reconstruction technique (SIRT).https://www.mdpi.com/1424-8220/23/1/208acoustic tomographytemperature field reconstructionmulti-dictionary learningpeak-type classifiersparse representationOMP |
| spellingShingle | Yuankun Wei Hua Yan Yinggang Zhou Temperature Field Reconstruction Method for Acoustic Tomography Based on Multi-Dictionary Learning Sensors acoustic tomography temperature field reconstruction multi-dictionary learning peak-type classifier sparse representation OMP |
| title | Temperature Field Reconstruction Method for Acoustic Tomography Based on Multi-Dictionary Learning |
| title_full | Temperature Field Reconstruction Method for Acoustic Tomography Based on Multi-Dictionary Learning |
| title_fullStr | Temperature Field Reconstruction Method for Acoustic Tomography Based on Multi-Dictionary Learning |
| title_full_unstemmed | Temperature Field Reconstruction Method for Acoustic Tomography Based on Multi-Dictionary Learning |
| title_short | Temperature Field Reconstruction Method for Acoustic Tomography Based on Multi-Dictionary Learning |
| title_sort | temperature field reconstruction method for acoustic tomography based on multi dictionary learning |
| topic | acoustic tomography temperature field reconstruction multi-dictionary learning peak-type classifier sparse representation OMP |
| url | https://www.mdpi.com/1424-8220/23/1/208 |
| work_keys_str_mv | AT yuankunwei temperaturefieldreconstructionmethodforacoustictomographybasedonmultidictionarylearning AT huayan temperaturefieldreconstructionmethodforacoustictomographybasedonmultidictionarylearning AT yinggangzhou temperaturefieldreconstructionmethodforacoustictomographybasedonmultidictionarylearning |