{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T05:48:40Z","timestamp":1772862520625,"version":"3.50.1"},"reference-count":45,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2020,2,6]],"date-time":"2020-02-06T00:00:00Z","timestamp":1580947200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"China Scholarship Council (CSC)","award":["1"],"award-info":[{"award-number":["1"]}]},{"name":"Natural Sciences and Engineering Research Council (NSERC) of Canada","award":["1"],"award-info":[{"award-number":["1"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Near-infrared (NIR) spectral sensors can deliver the spectral response of light absorbed by materials. Data analysis technology based on NIR sensors has been a useful tool for quality identification. In this paper, an improved deep convolutional neural network (CNN) with batch normalization and MSRA (Microsoft Research Asia) initialization is proposed to discriminate the tobacco cultivation regions using data collected from NIR sensors. The network structure is created with six convolutional layers and three full connection layers, and the learning rate is controlled by exponential attenuation method. One-dimensional kernel is applied as the convolution kernel to extract features. Meanwhile, the methods of L2 regularization and dropout are used to avoid the overfitting problem, which improve the generalization ability of the network. Experimental results show that the proposed deep network structure can effectively extract the complex characteristics inside the spectrum, which proves that it has excellent recognition performance on tobacco cultivation region discrimination, and it also demonstrates that the deep CNN is more suitable for information mining and analysis of big data.<\/jats:p>","DOI":"10.3390\/s20030874","type":"journal-article","created":{"date-parts":[[2020,2,7]],"date-time":"2020-02-07T03:13:27Z","timestamp":1581045207000},"page":"874","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":37,"title":["Improved Deep CNN with Parameter Initialization for Data Analysis of Near-Infrared Spectroscopy Sensors"],"prefix":"10.3390","volume":"20","author":[{"given":"Di","family":"Wang","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering, Chongqing Jiaotong University, Chongqing 400074, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fengchun","family":"Tian","sequence":"additional","affiliation":[{"name":"School of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6888-7993","authenticated-orcid":false,"given":"Simon X.","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Engineering, University of Guelph, Guelph, ON N1G 2W1, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiqin","family":"Zhu","sequence":"additional","affiliation":[{"name":"College of Automation, Chongqing University of Posts and Telecommunications, Chongqing 400065, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daiyu","family":"Jiang","sequence":"additional","affiliation":[{"name":"College of Automation, Chongqing University of Posts and Telecommunications, Chongqing 400065, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Cai","sequence":"additional","affiliation":[{"name":"Guizhou Tobacco Rebaking Co. LTD, Guizhou 550025, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2020,2,6]]},"reference":[{"key":"ref_1","first-page":"1078","article-title":"The contents of some major and trace elements for quality groups of Aegean Region tobaccos","volume":"9","author":"Ekren","year":"2011","journal-title":"J. Food Agric. Environ."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Yasmin, J., Ahmed, M.R., Lohumi, S., Wakholi, C., Kim, M.S., and Cho, B.K. (2019). Classification Method for Viability Screening of Naturally Aged Watermelon Seeds Using FT-NIR Spectroscopy. Sensors, 19.","DOI":"10.3390\/s19051190"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Kim, W., Song, J.M., and Park, K.R. (2018). Multimodal Biometric Recognition Based on Convolutional Neural Network by the Fusion of Finger-Vein and Finger Shape Using Near-Infrared (NIR) Camera Sensor. Sensors, 18.","DOI":"10.3390\/s18072296"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Manattayil, J.K., Ravichandran, N.K., Wijesinghe, R.E., Shirazi, M.F., Lee, S.Y., Kim, P., Jung, H.Y., Jeon, M., and Kim, J. (2018). Non-Destructive Classification of Diversely Stained Capsicum annuum Seed Specimens of Different Cultivars Using Near-Infrared Imaging Based Optical Intensity Detection. Sensors, 18.","DOI":"10.3390\/s18082500"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Nguyen, D.T., Yoon, H.S., Pham, T.D., and Park, K.R. (2017). Spoof Detection for Finger-Vein Recognition System Using NIR Camera. Sensors, 17.","DOI":"10.3390\/s17102261"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Lee, K.W., Yoon, H.S., Song, J.M., and Park, K.R. (2018). Convolutional Neural Network-Based Classification of Driver\u2019s Emotion during Aggressive and Smooth Driving Using Multi-Modal Camera Sensors. Sensors, 18.","DOI":"10.3390\/s18040957"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Xiao, S.P., He, Y., Dong, T., and Nie, P.C. (2018). Spectral Analysis and Sensitive Waveband Determination Based on Nitrogen Detection of Different Soil Types Using Near Infrared Sensors. Sensors, 18.","DOI":"10.3390\/s18020523"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"6884","DOI":"10.1109\/TGRS.2018.2845450","article-title":"Tensor-Based Classification Models for Hyperspectral Data Analysis","volume":"56","author":"Makantasis","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1966","DOI":"10.1039\/C9AY00413K","article-title":"Fast inline tobacco classification by near-infrared hyperspectral imaging and support vector machine-discriminant analysis","volume":"11","author":"Marcelo","year":"2019","journal-title":"Anal. Methods"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Makantasis, K., Karantzalos, K., Doulamis, A., and Doulamis, N. (2015, January 26\u201331). Deep Supervised Learning for Hyperspectral Data Classification through Convolutional Neural Networks. Proceedings of the IEEE International Geoscience and Remote Sensing Symposium (Igarss), Milan, Italy.","DOI":"10.1109\/IGARSS.2015.7326945"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1016\/j.infrared.2016.06.005","article-title":"NIR models for predicting total sugar in tobacco for samples with different physical states","volume":"77","author":"Qin","year":"2016","journal-title":"Infrared Phys. Technol."},{"key":"ref_12","first-page":"78","article-title":"Tobacco Quality Analysis of Producing Areas of Yunnan Tobacco Using Near-Infrared (NIR) Spectrum","volume":"33","author":"Wang","year":"2013","journal-title":"Spectrosc. Spect. Anal."},{"key":"ref_13","first-page":"3014","article-title":"Tobacco Quality Analysis of Industrial Classification of Different Years Using Near-Infrared (NIR) Spectrum","volume":"32","author":"Wang","year":"2012","journal-title":"Spectrosc. Spect. Anal."},{"key":"ref_14","first-page":"391","article-title":"Automatic Prediction of Leave Chemical Compositions Based on Nir Spectroscopy with Machine Learning","volume":"34","author":"Wang","year":"2019","journal-title":"Int. J. Rob. Autom."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Wang, D., Xie, L., Yang, S.X., and Tian, F.C. (2018). Support Vector Machine Optimized by Genetic Algorithm for Data Analysis of Near-Infrared Spectroscopy Sensors. Sensors, 18.","DOI":"10.3390\/s18103222"},{"key":"ref_16","first-page":"1620","article-title":"Using EN-NIR with Support Vector Machine for Classification of Producing Year of Tobacco","volume":"38","author":"Zhang","year":"2018","journal-title":"Spectrosc. Spect. Anal."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/j.indcrop.2012.02.040","article-title":"Determination of 27 chemical constituents in Chinese southwest tobacco by FT-NIR spectroscopy","volume":"40","author":"Duan","year":"2012","journal-title":"Ind. Crops Prod."},{"key":"ref_18","first-page":"672","article-title":"Research on the nonlinear model of near infrared spectroscopy and the total sugar of tobacco samples","volume":"24","author":"Da","year":"2004","journal-title":"Spectrosc. Spect. Anal."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"30353","DOI":"10.1039\/C5RA25052H","article-title":"A modified random forest approach to improve multi-class classification performance of tobacco leaf grades coupled with NIR spectroscopy","volume":"6","author":"Bin","year":"2016","journal-title":"RSC Adv."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Aqib, M., Mehmood, R., Alzahrani, A., Katib, I., Albeshri, A., and Altowaijri, S.M. (2019). Smarter Traffic Prediction Using Big Data, In-Memory Computing, Deep Learning and GPUs. Sensors, 19.","DOI":"10.3390\/s19092206"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Wang, L., Zang, J.L., Zhang, Q.L., Niu, Z.X., Hua, G., and Zheng, N.N. (2018). Action Recognition by an Attention-Aware Temporal Weighted Convolutional Neural Network. Sensors, 18.","DOI":"10.3390\/s18071979"},{"key":"ref_22","first-page":"1","article-title":"Deep Learning for Computer Vision: A Brief Review","volume":"2018","author":"Voulodimos","year":"2018","journal-title":"Comput. Intell. Neurosci."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1016\/j.neucom.2015.09.116","article-title":"Deep learning for visual understanding: A review","volume":"187","author":"Guo","year":"2016","journal-title":"Neurocomputing"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.patrec.2014.01.008","article-title":"A review of unsupervised feature learning and deep learning for time-series modeling","volume":"42","author":"Langkvist","year":"2014","journal-title":"Pattern Recognit. Lett."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1016\/j.chemolab.2019.06.004","article-title":"Feature selection based convolutional neural network pruning and its application in calibration modeling for NIR spectroscopy","volume":"191","author":"Chen","year":"2019","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.aca.2016.12.010","article-title":"Convolutional neural networks for vibrational spectroscopic data analysis","volume":"954","author":"Acquarelli","year":"2017","journal-title":"Anal. Chim. Acta"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/j.chemolab.2018.07.008","article-title":"Modern practical convolutional neural networks for multivariate regression: Applications to NIR calibration","volume":"182","author":"Cui","year":"2018","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Lee, Y.W., Kim, K.W., Hoang, T.M., Arsalan, M., and Park, K.R. (2019). Deep Residual CNN-Based Ocular Recognition Based on Rough Pupil Detection in the Images by NIR Camera Sensor. Sensors, 19.","DOI":"10.3390\/s19040842"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Tazim, R.J., Miah, M.M.M., Surma, S.S., Islam, M.T., Shahnaz, C., and Fattah, S.A. (2018, January 28\u201331). Biometric Authentication Using CNN Features of Dorsal Vein Pattern Extracted from NIR Image. Proceedings of the 2018 IEEE Region 10 Conference, Jeju Island, Korea.","DOI":"10.1109\/TENCON.2018.8650439"},{"key":"ref_30","first-page":"3724","article-title":"The Study of Classification Modeling Method for Near Infrared Spectroscopy of Tobacco Leaves Based on Convolution Neural Network","volume":"38","author":"Lu","year":"2018","journal-title":"Spectrosc. Spect. Anal."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Chen, Y.T., Tao, J.J., Wang, J., Chen, X., Xie, J.B., Xiong, J., and Yang, K. (2019). The Novel Sensor Network Structure for Classification Processing Based on the Machine Learning Method of the ACGAN. Sensors, 19.","DOI":"10.3390\/s19143145"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2029","DOI":"10.1007\/s00521-018-3441-1","article-title":"Convolutional neural network-based multimodal image fusion via similarity learning in the shearlet domain","volume":"30","author":"Hermessi","year":"2018","journal-title":"Neural Comput. Appl."},{"key":"ref_33","unstructured":"Ioffe, S., and Szegedy, C. (2015, January 6\u201311). Batch Normalization Accelerating Deep Network Training by Reducing Internal Covariate Shift. Proceedings of the 32nd International Conference on Machine Learning (ICML), Lille, France."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Wei, X., Liu, W.C., Chen, L., Ma, L., Chen, H., and Zhuang, Y. (2019). FPGA-Based Hybrid-Type Implementation of Quantized Neural Networks for Remote Sensing Applications. Sensors, 19.","DOI":"10.3390\/s19040924"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Sun, C.W., Yang, Y.X., Wen, C., Xie, K., and Wen, F.Q. (2018). Voiceprint Identification for Limited Dataset Using the Deep Migration Hybrid Model Based on Transfer Learning. Sensors, 18.","DOI":"10.3390\/s18072399"},{"key":"ref_36","unstructured":"Glorot, X., Bordes, A., and Bengio, Y. (2011, January 11\u201313). Deep Sparse Rectifier Neural Networks. Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS), Fort Lauderdale, FL, USA."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Zeiler, M.D., Ranzato, M., Monga, R., Mao, M., Yang, K., Le, Q.V., Nguyen, P., Senior, A., Vanhoucke, V., and Dean, J. (2013, January 26\u201331). On Rectified Linear Units for Speech Processing. Proceedings of the (IEEE) International Conference on Acoustics, Speech and Signal Processing (ICASSP), Vancouver, BC, Canada.","DOI":"10.1109\/ICASSP.2013.6638312"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Dahl, G.E., Sainath, T.N., and Hinton, G.E. (2013, January 26\u201331). Improving Deep Neural Networks for Lvcsr Using Rectified Linear Units and Dropout. Proceedings of the 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (Icassp), Vancouver, BC, Canada.","DOI":"10.1109\/ICASSP.2013.6639346"},{"key":"ref_39","first-page":"1929","article-title":"Dropout: A Simple Way to Prevent Neural Networks from Overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1007\/s10822-016-9895-2","article-title":"Improving quantitative structure-activity relationship models using Artificial Neural Networks trained with dropout","volume":"30","author":"Mendenhall","year":"2016","journal-title":"J. Comput.-Aided Mol. Des."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"He, K.M., Zhang, X.Y., Ren, S.Q., and Sun, J. (2005, January 21). Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), Beijing, China.","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Wu, J., and Yang, S.X. (2019). Intelligent control of bulk tobacco curing schedule using LS-SVM- and ANFIS-based multi-sensor data fusion approaches. Sensors, 19.","DOI":"10.3390\/s19081778"},{"key":"ref_43","first-page":"545","article-title":"Application of X-ray fluorescence in tobacco origin identification based on discriminant analysis","volume":"36","author":"Chen","year":"2015","journal-title":"J. Jiangsu Univ."},{"key":"ref_44","first-page":"34","article-title":"Application of SVM near infrared spectroscopy in the identification of flue-cured tobacco producing areas","volume":"18","author":"Qiu","year":"2012","journal-title":"Mod. Instrum."},{"key":"ref_45","first-page":"77","article-title":"Application of near infrared spectroscopy in tobacco origin identification","volume":"33","author":"Duan","year":"2011","journal-title":"J. Yunnan Univ."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/3\/874\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T08:55:29Z","timestamp":1760172929000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/3\/874"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2,6]]},"references-count":45,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2020,2]]}},"alternative-id":["s20030874"],"URL":"https:\/\/doi.org\/10.3390\/s20030874","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,2,6]]}}}