{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T03:57:15Z","timestamp":1760241435639,"version":"build-2065373602"},"reference-count":37,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2018,2,16]],"date-time":"2018-02-16T00:00:00Z","timestamp":1518739200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"JSPS KAKENHI","award":["JP16J08577"],"award-info":[{"award-number":["JP16J08577"]}]},{"name":"Grant-in-Aid for Scientific Research on Innovative Areas","award":["16H06569"],"award-info":[{"award-number":["16H06569"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Data representing driving behavior, as measured by various sensors installed in a vehicle, are collected as multi-dimensional sensor time-series data. These data often include redundant information, e.g., both the speed of wheels and the engine speed represent the velocity of the vehicle. Redundant information can be expected to complicate the data analysis, e.g., more factors need to be analyzed; even varying the levels of redundancy can influence the results of the analysis. We assume that the measured multi-dimensional sensor time-series data of driving behavior are generated from low-dimensional data shared by the many types of one-dimensional data of which multi-dimensional time-series data are composed. Meanwhile, sensor time-series data may be defective because of sensor failure. Therefore, another important function is to reduce the negative effect of defective data when extracting low-dimensional time-series data. This study proposes a defect-repairable feature extraction method based on a deep sparse autoencoder (DSAE) to extract low-dimensional time-series data. In the experiments, we show that DSAE provides high-performance latent feature extraction for driving behavior, even for defective sensor time-series data. In addition, we show that the negative effect of defects on the driving behavior segmentation task could be reduced using the latent features extracted by DSAE.<\/jats:p>","DOI":"10.3390\/s18020608","type":"journal-article","created":{"date-parts":[[2018,2,20]],"date-time":"2018-02-20T03:54:22Z","timestamp":1519098862000},"page":"608","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Defect-Repairable Latent Feature Extraction of Driving Behavior via a Deep Sparse Autoencoder"],"prefix":"10.3390","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2195-3380","authenticated-orcid":false,"given":"HaiLong","family":"Liu","sequence":"first","affiliation":[{"name":"The Graduate School of Information Science and Engineering, Ritsumeikan University, Kusatsu, Shiga 525-8577, Japan"},{"name":"Research Fellow (DC) with the Japan Society for the Promotion of Science, Tokyo 102-0083, Japan"}]},{"given":"Tadahiro","family":"Taniguchi","sequence":"additional","affiliation":[{"name":"The College of Information Science and Engineering, Ritsumeikan University, Kusatsu, Shiga 525-8577, Japan"}]},{"given":"Kazuhito","family":"Takenaka","sequence":"additional","affiliation":[{"name":"The Corporate R&D Div.1, Sensing System R&D Dept., DENSO CORPORATION, Aichi 448-8661, Japan"}]},{"given":"Takashi","family":"Bando","sequence":"additional","affiliation":[{"name":"The DENSO International America, Inc., San Jose, CA 95110, USA"}]}],"member":"1968","published-online":{"date-parts":[[2018,2,16]]},"reference":[{"key":"ref_1","unstructured":"Tagawa, T., Tadokoro, Y., and Yairi, T. (2015, January 20\u201322). Structured denoising autoencoder for fault detection and analysis. Proceedings of the Asian Conference on Machine Learning, Hong Kong, China."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1385","DOI":"10.1016\/0967-0661(95)00141-G","article-title":"Nonlinear parity equation based residual generation for diagnosis of automotive engine faults","volume":"3","author":"Krishnaswami","year":"1995","journal-title":"Control Eng. Pract."},{"key":"ref_3","unstructured":"Malhotra, P., Vig, L., Shroff, G., and Agarwal, P. (2015, January 22\u201324). Long Short Term Memory Networks for Anomaly Detection in Time Series. Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges, Belgium."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1016\/j.neucom.2015.08.104","article-title":"Auto-encoder based dimensionality reduction","volume":"184","author":"Wang","year":"2016","journal-title":"Neurocomputing"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Liu, H., Taniguchi, T., Tanaka, Y., Takenaka, K., and Bando, T. (July, January 28). Essential Feature Extraction of Driving Behavior Using a Deep Learning Method. Proceedings of the IEEE Intelligent Vehicles Symposium 2015, Seoul, Korea.","DOI":"10.1109\/IVS.2015.7225824"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Liu, H., Taniguchi, T., Takenaka, K., Tanaka, Y., and Bando, T. (2016, January 11\u201314). Reducing the Negative Effect of Defective Data on Driving Behavior Segmentation via a Deep Sparse Autoencoder. Proceedings of the 5th IEEE Global Conference on Consumer Electronics, Kyoto, Japan.","DOI":"10.1109\/GCCE.2016.7800355"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Takano, W., Matsushita, A., Iwao, K., and Nakamura, Y. (2008, January 22\u201326). Recognition of human driving behaviors based on stochastic symbolization of time series signal. Proceedings of the IROS 2008 IEEE\/RSJ International Conference on Intelligent Robots and Systems, Nice, France.","DOI":"10.1109\/IROS.2008.4650671"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Taniguchi, T., Nagasaka, S., Hitomi, K., Chandrasiri, N.P., and Bando, T. (2012, January 3\u20137). Semiotic prediction of driving behavior using unsupervised double articulation analyzer. Proceedings of the IEEE Intelligent Vehicles Symposium 2012, Madrid, Spain.","DOI":"10.1109\/IVS.2012.6232243"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Bando, T., Takenaka, K., Nagasaka, S., and Taniguchi, T. (2014, January 8\u201311). Generating contextual description from driving behavioral data. Proceedings of the 2014 IEEE Intelligent Vehicles Symposium, Dearborn, MI, USA.","DOI":"10.1109\/IVS.2014.6856476"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.jsr.2015.06.007","article-title":"Drunk driving detection based on classification of multivariate time series","volume":"54","author":"Li","year":"2015","journal-title":"J. Saf. Res."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/0169-7439(87)80084-9","article-title":"Principal component analysis","volume":"2","author":"Wold","year":"1987","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"3256","DOI":"10.1109\/TVT.2007.906410","article-title":"Extending driver\u2019s horizon through comprehensive incident detection in vehicular networks","volume":"56","author":"Chatzigiannakis","year":"2007","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Calder\u00f3-Bardaj\u00ed, P., Longfei, X., Jaschke, S., Reermann, J., Mideska, K., Schmidt, G., Deuschl, G., and Muthuraman, M. (2016, January 16\u201320). Detection of steering direction using EEG recordings based on sample entropy and time-frequency analysis. Proceedings of the 2016 IEEE 38th Annual International Conference of the Engineering in Medicine and Biology Society (EMBC), Orlando, FL, USA.","DOI":"10.1109\/EMBC.2016.7590830"},{"key":"ref_14","unstructured":"Lin, C.T., Liang, S.F., Chen, Y.C., Hsu, Y.C., and Ko, L.W. (2006, January 21\u201324). Driver\u2019s drowsiness estimation by combining EEG signal analysis and ICA-based fuzzy neural networks. Proceedings of the 2006 IEEE International Symposium on Circuits and Systems, Kos, Greece."},{"key":"ref_15","unstructured":"Hyv\u00e4rinen, A., Karhunen, J., and Oja, E. (2004). Independent Component Analysis, John Wiley & Sons."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1016\/S0893-6080(00)00026-5","article-title":"Independent component analysis: Algorithms and applications","volume":"13","author":"Oja","year":"2000","journal-title":"Neural Netw."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Sch\u00f6lkopf, B., Smola, A., and M\u00fcller, K.R. (1997, January 8\u201310). Kernel principal component analysis. Proceedings of the International Conference on Artificial Neural Networks, Lausanne, Switzerland.","DOI":"10.1007\/BFb0020217"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Zhao, C., Zheng, C., and Zhao, M. (2010, January 16\u201318). Classifying driving mental fatigue based on multivariate autoregressive models and kernel learning algorithms. Proceedings of the 2010 3rd International Conference on Biomedical Engineering and Informatics, Yantai, China.","DOI":"10.1109\/BMEI.2010.5639579"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Dong, W., Yuan, T., Yang, K., Li, C., and Zhang, S. (arXiv, 2017). Autoencoder Regularized Network For Driving Style Representation Learning, arXiv.","DOI":"10.24963\/ijcai.2017\/222"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Hori, C., Watanabe, S., Hori, T., Harsham, B.A., Hershey, J., Koji, Y., Fujii, Y., and Furumoto, Y. (2016, January 11\u201315). Driver confusion status detection using recurrent neural networks. Proceedings of the 2016 IEEE International Conference on Multimedia and Expo (ICME), Seattle, WA, USA.","DOI":"10.1109\/ICME.2016.7552966"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"770","DOI":"10.1080\/01691864.2016.1159981","article-title":"Double articulation analyzer with deep sparse autoencoder for unsupervised word discovery from speech signals","volume":"30","author":"Taniguchi","year":"2016","journal-title":"Adv. Robot."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2477","DOI":"10.1109\/TITS.2017.2649541","article-title":"Visualization of driving behavior based on hidden feature extraction by using deep learning","volume":"18","author":"Liu","year":"2017","journal-title":"IEEE Trans. Intell. Transport. Syst."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Kaneda, Y., Irizuki, Y., and Yamakita, M. (2012, January 25\u201328). Design method of robust Kalman filter via L1 regression and its application for vehicle control with outliers. Proceedings of the 38th Annual Conference on IEEE Industrial Electronics Society 2012, Montreal, QC, Canada.","DOI":"10.1109\/IECON.2012.6388678"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"453","DOI":"10.1049\/iet-its.2015.0103","article-title":"Outlier filtering algorithm for travel time estimation using dedicated short-range communications probes on rural highways","volume":"10","author":"Jang","year":"2016","journal-title":"IET Intell. Transp. Syst."},{"key":"ref_25","unstructured":"Duan, Y., Lv, Y., Kang, W., and Zhao, Y. (2014, January 8\u201311). A deep learning based approach for traffic data imputation. Proceedings of the 17th International IEEE Conference on Intelligent Transportation Systems, Qingdao, China."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Ku, W.C., Jagadeesh, G.R., Prakash, A., and Srikanthan, T. (2016, January 10\u201312). A clustering-based approach for data-driven imputation of missing traffic data. Proceedings of the IEEE Forum on Integrated and Sustainable Transportation Systems 2016, Beijing, China.","DOI":"10.1109\/FISTS.2016.7552320"},{"key":"ref_27","first-page":"111","article-title":"Performance analysis of various activation functions in generalized MLP architectures of neural networks","volume":"1","author":"Karlik","year":"2011","journal-title":"Int. J. Artif. Intell. Expert Syst."},{"key":"ref_28","unstructured":"Ng, A. (2011). Sparse Autoencoder, Stanford University. CS294A Lecture Notes."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"Rumelhart","year":"1986","journal-title":"Nature"},{"key":"ref_30","unstructured":"Magdon-Ismail, M., and Boutsidis, C. (arXiv, 2015). Optimal sparse linear auto-encoders and sparse pca, arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"2639","DOI":"10.1162\/0899766042321814","article-title":"Canonical correlation analysis: An overview with application to learning methods","volume":"16","author":"Hardoon","year":"2004","journal-title":"Neural Comput."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"284","DOI":"10.1134\/S1995080212030158","article-title":"Few remarks on the geometry of the uncentered coefficient of determination","volume":"33","author":"Triacca","year":"2012","journal-title":"Lobachevskii J. Math."},{"key":"ref_33","first-page":"1020","article-title":"A sticky HDP-HMM with application to speaker diarization","volume":"5","author":"Fox","year":"2009","journal-title":"Ann. Appl. Stat."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Nagasaka, S., Taniguchi, T., Hitomi, K., Takenaka, K., and Bando, T. (2014, January 8\u201311). Prediction of Next Contextual Changing Point of Driving Behavior Using Unsupervised Bayesian Double Articulation Analyzer. Proceedings of the 2014 IEEE Intelligent Vehicles Symposium 2014, Dearborn, MI, USA.","DOI":"10.1109\/IVS.2014.6856468"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Mori, M., Takenaka, K., Bando, T., Taniguchi, T., Miyajima, C., and Takeda, K. (July, January 28). Automatic lane change extraction based on temporal patterns of symbolized driving behavioral data. Proceedings of the 2015 IEEE Intelligent Vehicles Symposium (IV), Seoul, Korea.","DOI":"10.1109\/IVS.2015.7225811"},{"key":"ref_36","unstructured":"Kingma, D.P., and Welling, M. (arXiv, 2013). Auto-encoding variational bayes, arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Sak, H., Senior, A., and Beaufays, F. (2014, January 14\u201318). Long short-term memory recurrent neural network architectures for large scale acoustic modeling. Proceedings of the Fifteenth Annual Conference of the International Speech Communication Association, Singapore.","DOI":"10.21437\/Interspeech.2014-80"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/2\/608\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T14:55:24Z","timestamp":1760194524000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/2\/608"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,2,16]]},"references-count":37,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2018,2]]}},"alternative-id":["s18020608"],"URL":"https:\/\/doi.org\/10.3390\/s18020608","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2018,2,16]]}}}