{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T01:50:10Z","timestamp":1760233810841,"version":"build-2065373602"},"reference-count":51,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2021,2,12]],"date-time":"2021-02-12T00:00:00Z","timestamp":1613088000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Key R&amp;D Program of China","award":["2019YFC1520500","2020YFC1523004"],"award-info":[{"award-number":["2019YFC1520500","2020YFC1523004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.3390\/s21041318","type":"journal-article","created":{"date-parts":[[2021,2,12]],"date-time":"2021-02-12T18:45:00Z","timestamp":1613155500000},"page":"1318","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Dropout Deep Belief Network Based Chinese Ancient Ceramic Non-Destructive Identification"],"prefix":"10.3390","volume":"21","author":[{"given":"Jizhong","family":"Huang","sequence":"first","affiliation":[{"name":"Institute for the Conservation of Cultural Heritage, Shanghai University, Shanghai 200444, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yepeng","family":"Guan","sequence":"additional","affiliation":[{"name":"School of Communication and Information Engineering, Shanghai University, Shanghai 200444, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,2,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1007\/s10973-018-7244-5","article-title":"Thermoanalytical investigations of ancient ceramics: Review on theory and practice","volume":"133","author":"Drebushchak","year":"2018","journal-title":"J. Therm. Anal. Calorim."},{"key":"ref_2","first-page":"182","article-title":"A multi-technique study for the spectroscopic characterization of the ceramics from Santa Maria do Castelo church (Torres Novas, Portugal)","volume":"6","author":"Ferreira","year":"2016","journal-title":"J. Archaeol. Sci. Rep."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1016\/j.microc.2015.12.009","article-title":"A multi-spectroscopic study for the characterization and definition of production techniques of German ceramic sherds","volume":"126","author":"Ricci","year":"2016","journal-title":"Microchem. J."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.sab.2018.07.012","article-title":"Applications of laser-induced breakdown spectroscopy for cultural heritage: A comparison with x-ray fluorescence and particle induced x-ray emission techniques","volume":"149","author":"Lazic","year":"2018","journal-title":"Spectrochim. Acta B"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1201","DOI":"10.1177\/0003702819861576","article-title":"Identifying ancient ceramics using laser-induced breakdown spectroscopy combined with a back propagation neural network","volume":"73","author":"He","year":"2019","journal-title":"Appl. Spectrosc."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"8495","DOI":"10.1016\/j.ceramint.2016.02.072","article-title":"Colour-generating mechanism of copper-red porcelain from Changsha kiln (AD 7th\u201310th century), China","volume":"42","author":"Li","year":"2016","journal-title":"Ceram. Int."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"11616","DOI":"10.1016\/j.ceramint.2017.05.334","article-title":"Coloring and translucency mechanisms of Five dynasty celadon body from Yaozhou kiln","volume":"43","author":"Shi","year":"2017","journal-title":"Ceram. Int."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"10589","DOI":"10.1016\/j.ceramint.2019.02.125","article-title":"The colouring mechanism of the Brown glaze porcelain of the Yaozhou kiln in the Northern Song dynasty","volume":"45","author":"Wen","year":"2019","journal-title":"Ceram. Int."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1007\/s10973-009-0226-x","article-title":"Thermal analysis of Romanian ancient ceramics","volume":"102","author":"Ion","year":"2010","journal-title":"J. Therm. Anal. Calorim."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"18128","DOI":"10.1016\/j.ceramint.2016.08.126","article-title":"Study on preparation of thermal storage ceramic by using clay shale","volume":"42","author":"Deng","year":"2016","journal-title":"Ceram. Int."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1371","DOI":"10.1016\/j.ceramint.2016.10.095","article-title":"Prototype Doucai porcelain\u2014A special form of ancient Honglvcai in Cizhou kiln, Jin dynasty (1115-1234 AD), China","volume":"43","author":"Jiang","year":"2017","journal-title":"Ceram. Int."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"13362","DOI":"10.1016\/j.ceramint.2019.04.031","article-title":"Multi-micro analytical studies of blue-and-white porcelain (Ming dynasty) excavated from Shuangchuan island","volume":"45","author":"Wen","year":"2019","journal-title":"Ceram. Int."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2145","DOI":"10.1007\/s10973-019-08767-8","article-title":"Thermoanalytical investigations of some ceramics dated from the Neolithic period, discovered at Oxenbrickel, S\u00e2nandrei, Romania","volume":"138","author":"Vlase","year":"2019","journal-title":"J. Therm. Anal. Calorim."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"966","DOI":"10.1111\/arcm.12149","article-title":"Elemental characterization by EDXRF of imperial Longquan Celadon Porcelain excavated from Fengdongyan Kiln, Dayao County","volume":"57","author":"Li","year":"2016","journal-title":"Archaeometry"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1111\/arcm.12355","article-title":"A study on the elemental composition of Chinese mise type wares from different periods and kilns","volume":"60","author":"Sun","year":"2018","journal-title":"Archaeometry"},{"key":"ref_16","unstructured":"Qi, L.Y., and Wang, K.G. (2010, January 16\u201318). Kernel fuzzy clustering based classification of ancient ceramic fragments. Proceedings of the 2nd IEEE International Conference on Information Management and Engineering, Chengdu, China."},{"key":"ref_17","unstructured":"Zhang, B., Wang, G., Guilin, X., and Xue, L. (2018, January 14\u201316). An improving data stream classification algorithm based on BP neural network. Proceedings of the International Conference CSPS, Dalian, China."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"18140","DOI":"10.1016\/j.ceramint.2019.06.003","article-title":"Research on ancient ceramic identification by artificial intelligence","volume":"45","author":"Mu","year":"2019","journal-title":"Ceram. Int"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"8104","DOI":"10.1016\/j.ceramint.2019.12.037","article-title":"A new classification method of ancient Chinese ceramics based on machine learning and component analysis","volume":"46","author":"Sun","year":"2020","journal-title":"Ceram. Int."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"22253","DOI":"10.1016\/j.ceramint.2020.05.303","article-title":"Regional microstructural characteristics between the body and glaze of ancient Chinese ceramics","volume":"46","author":"Wang","year":"2020","journal-title":"Ceram. Int."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1016\/j.jmsy.2018.06.004","article-title":"Smart optimization of a friction-drilling process based on boosting ensembles","volume":"48","author":"Bustillo","year":"2018","journal-title":"J. Manuf. Syst."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"358","DOI":"10.1016\/j.ejor.2020.07.058","article-title":"Predicting mortgage early delinquency with machine learning methods","volume":"290","author":"Chen","year":"2021","journal-title":"Eur. J. Oper. Res."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"8214","DOI":"10.1016\/j.petrol.2020.108214","article-title":"A new machine learning ensemble model for class imbalance problem of screening enhanced oil recovery methods","volume":"198","author":"Pirizadeh","year":"2021","journal-title":"J. Pet. Sci. Eng."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1016\/j.eswa.2018.07.024","article-title":"Feature ranking for enhancing boosting-based multi-label text categorization","volume":"113","author":"Salemi","year":"2018","journal-title":"Expert Syst. Appl."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Lu, J., Huang, J., and Lu, F. (2019). Distributed kernel extreme learning machines for aircraft engine failure diagnostics. Appl. Sci., 9.","DOI":"10.3390\/app9081707"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Gao, F., Huang, T., and Wang, J. (2017). Dual-branch deep convolution neural network for Polarimetric SAR image classification. Appl. Sci., 7.","DOI":"10.3390\/app7050447"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"4504","DOI":"10.1109\/TNNLS.2017.2746107","article-title":"Extensions to online feature selection using bagging and boosting","volume":"29","author":"Ditzler","year":"2018","journal-title":"IEEE Trans. Neural Netw. Learn."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1021","DOI":"10.1016\/j.measurement.2010.02.006","article-title":"Advanced technique for non-destructive testing of friction stir welding of metals","volume":"43","author":"Rosado","year":"2010","journal-title":"Measurement"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Cunha, R., Maciel, R., Nandi, G.S., Daros, M.R., Cardoso, J.P., Francis, L.T., Ramos, V.F.C., Marcelino, R., Frohlich, A.A., and Araujo, G.M.D. (2018, January 5\u20138). Applying non-destructive testing and machine learning to ceramic tile quality control. Proceedings of the VIII Brazilian Symposium on Computing Systems Engineering (SBESC), Salvador, Brazil.","DOI":"10.1109\/SBESC.2018.00017"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Czimmermann, T., Ciuti, G., Milazzo, M., Chiurazzi, M., Roccella, S., Oddo, C.M., and Dario, P. (2020). Visual-based defect detection and classification approaches for industrial applications\u2014A survey. Sensors, 20.","DOI":"10.3390\/s20051459"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Wei, Y., Li, X., Pan, X., and Li, L. (2020). Nondestructive classification of soybean seed varieties by hyperspectral imaging and ensemble machine learning algorithms. Sensors, 20.","DOI":"10.3390\/s20236980"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1016\/j.culher.2017.11.010","article-title":"First spectroscopic analysis of lead glazes of Belgian tile panels","volume":"41","author":"Pevenage","year":"2020","journal-title":"J. Cult. Herit."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Patchava, K.C., Alrezj, O., Benaissa, M., and Behairy, H. (2016, January 16\u201320). Savitzky-Golay coupled with digital bandpass filtering as a pre-processing technique in the quantitative analysis of glucose from near infrared spectra. Proceedings of the 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Orlando, FL, USA.","DOI":"10.1109\/EMBC.2016.7592147"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/j.vibspec.2018.05.002","article-title":"Robust generalized multiplicative scatter correction algorithm on pretreatment of near infrared spectral data","volume":"97","author":"Jayanthi","year":"2018","journal-title":"Vib. Spectrosc."},{"key":"ref_35","first-page":"491","article-title":"Fractional differential mask: A fractional differential-based approach for multiscale texture enhancement","volume":"19","author":"Pu","year":"2010","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1016\/S0378-4371(98)00550-0","article-title":"Fractional calculus and the evolution of fractal phenomena","volume":"265","author":"Rocco","year":"1999","journal-title":"Phys. A"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"3084","DOI":"10.1109\/78.330368","article-title":"The fractional Fourier transform and time-frequency representations","volume":"42","author":"Almeida","year":"1994","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1137\/S0036144598349435","article-title":"Fractional splines and wavelets","volume":"42","author":"Unser","year":"2000","journal-title":"SIAM Rev."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Ozaktas, H.M., Zalevsky, Z., and Kutay, M.A. (2001). The Fractional Fourier Transform: With Applications in Optics and Signal Processing, Wiley.","DOI":"10.23919\/ECC.2001.7076127"},{"key":"ref_40","first-page":"286","article-title":"Encryption with fractional wavelet packet method","volume":"119","author":"Linfei","year":"2006","journal-title":"Int. J. Light Electron. Opt."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.chaos.2017.05.026","article-title":"Restricted fractional differential transform for solving irrational order fractional differential equations","volume":"101","author":"Khudair","year":"2017","journal-title":"Chaos Solitons Fractals"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s00466-016-1320-0","article-title":"Differential operator multiplication method for fractional differential equations","volume":"58","author":"Tang","year":"2016","journal-title":"Comput. Mech."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"9028","DOI":"10.1142\/S0218001419590286","article-title":"A fault diagnosis intelligent algorithm based on improved BP neural network","volume":"33","author":"Liu","year":"2019","journal-title":"Int. J. Pattern Recogn."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"6471","DOI":"10.1007\/s00500-016-2205-z","article-title":"Finding a good initial configuration of parameters for restricted Boltzmann machine pre-training","volume":"21","author":"Xie","year":"2016","journal-title":"Soft. Comput."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"751","DOI":"10.1007\/s11426-008-0080-x","article-title":"Outlier detection in near-infrared spectroscopic analysis by using Monte Carlo cross-validation","volume":"51","author":"Liu","year":"2008","journal-title":"SCI China Ser. B"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/j.chemolab.2013.07.009","article-title":"Key wavelengths selection from near infrared spectra using Monte Carlo sampling-recursive partial least squares","volume":"28","author":"Zhang","year":"2013","journal-title":"Chemometr. Intell. Lab."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1016\/j.biombioe.2012.06.007","article-title":"Prediction of biomass gross calorific values using visible and near infrared spectroscopy","volume":"45","author":"Everard","year":"2012","journal-title":"Biomass Bioenerg."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Fu, X. (2016, January 17\u201319). Unsupervised Pre-training classifier based on restricted Boltzmann machine with imbalanced data. Proceedings of the International Conference on Smart Computing and Communication, Shenzhen, China.","DOI":"10.1007\/978-3-319-52015-5_11"},{"key":"ref_49","unstructured":"Lee, T., and Yoon, S. (2015, January 7\u20139). Boosted categorical restricted Boltzmann machine for computational prediction of splice junctions. Proceedings of the 32nd International Conference on Machine Learning, Lille, France."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Zhelezniak, V., Savkov, A., Shen, A., and Hammerla, N.Y. (2019). Correlation coefficients and semantic textual similarity. arXiv.","DOI":"10.18653\/v1\/N19-1100"},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"26","DOI":"10.5539\/mas.v13n10p26","article-title":"Scaled Pearson\u2019s correlation coefficient for evaluating text similarity measures","volume":"13","author":"Atoum","year":"2019","journal-title":"Mod. Appl. Sci."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/4\/1318\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:23:27Z","timestamp":1760160207000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/4\/1318"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,12]]},"references-count":51,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2021,2]]}},"alternative-id":["s21041318"],"URL":"https:\/\/doi.org\/10.3390\/s21041318","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2021,2,12]]}}}