Dropout Deep Belief Network Based Chinese Ancient Ceramic Non-Destructive Identification
A non-destructive identification method was developed here based on dropout deep belief network in multi-spectral data of ancient ceramic. A fractional differential algorithm was proposed to enhance the spectral details by making use of the difference between the first and second-order differential...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/4/1318 |
| _version_ | 1797396777862692864 |
|---|---|
| author | Jizhong Huang Yepeng Guan |
| author_facet | Jizhong Huang Yepeng Guan |
| author_sort | Jizhong Huang |
| collection | DOAJ |
| description | A non-destructive identification method was developed here based on dropout deep belief network in multi-spectral data of ancient ceramic. A fractional differential algorithm was proposed to enhance the spectral details by making use of the difference between the first and second-order differential pre-process spectral data. An unsupervised multi-layer restricted Boltzmann machine (RBM) was employed to extract some high-level features during pre-training. Some weight and bias values trained by RBM were used to initialize a back propagation (BP) neural network. The RBM deep belief network was fine-tuned by the BP neural network to promote the initiative performance of network training, which helped to overcome local optimal limitation of the network due to the random initializing weight parameter. The dropout strategy has been put forward into the RBM network to solve the over-fitting of small sample spectral data. The experimental results show that the proposed method has excellent recognition performance of the ceramics by comparisons with some other ones. |
| first_indexed | 2024-03-09T00:56:25Z |
| format | Article |
| id | doaj.art-45c5e488dae9497ca26b82e10504f8b9 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T00:56:25Z |
| publishDate | 2021-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-45c5e488dae9497ca26b82e10504f8b92023-12-11T16:53:30ZengMDPI AGSensors1424-82202021-02-01214131810.3390/s21041318Dropout Deep Belief Network Based Chinese Ancient Ceramic Non-Destructive IdentificationJizhong Huang0Yepeng Guan1Institute for the Conservation of Cultural Heritage, Shanghai University, Shanghai 200444, ChinaSchool of Communication and Information Engineering, Shanghai University, Shanghai 200444, ChinaA non-destructive identification method was developed here based on dropout deep belief network in multi-spectral data of ancient ceramic. A fractional differential algorithm was proposed to enhance the spectral details by making use of the difference between the first and second-order differential pre-process spectral data. An unsupervised multi-layer restricted Boltzmann machine (RBM) was employed to extract some high-level features during pre-training. Some weight and bias values trained by RBM were used to initialize a back propagation (BP) neural network. The RBM deep belief network was fine-tuned by the BP neural network to promote the initiative performance of network training, which helped to overcome local optimal limitation of the network due to the random initializing weight parameter. The dropout strategy has been put forward into the RBM network to solve the over-fitting of small sample spectral data. The experimental results show that the proposed method has excellent recognition performance of the ceramics by comparisons with some other ones.https://www.mdpi.com/1424-8220/21/4/1318dropout deep belief networkancient ceramicmulti-spectral datafractional order differentialnon-destructive identification |
| spellingShingle | Jizhong Huang Yepeng Guan Dropout Deep Belief Network Based Chinese Ancient Ceramic Non-Destructive Identification Sensors dropout deep belief network ancient ceramic multi-spectral data fractional order differential non-destructive identification |
| title | Dropout Deep Belief Network Based Chinese Ancient Ceramic Non-Destructive Identification |
| title_full | Dropout Deep Belief Network Based Chinese Ancient Ceramic Non-Destructive Identification |
| title_fullStr | Dropout Deep Belief Network Based Chinese Ancient Ceramic Non-Destructive Identification |
| title_full_unstemmed | Dropout Deep Belief Network Based Chinese Ancient Ceramic Non-Destructive Identification |
| title_short | Dropout Deep Belief Network Based Chinese Ancient Ceramic Non-Destructive Identification |
| title_sort | dropout deep belief network based chinese ancient ceramic non destructive identification |
| topic | dropout deep belief network ancient ceramic multi-spectral data fractional order differential non-destructive identification |
| url | https://www.mdpi.com/1424-8220/21/4/1318 |
| work_keys_str_mv | AT jizhonghuang dropoutdeepbeliefnetworkbasedchineseancientceramicnondestructiveidentification AT yepengguan dropoutdeepbeliefnetworkbasedchineseancientceramicnondestructiveidentification |