{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T10:42:35Z","timestamp":1776681755815,"version":"3.51.2"},"reference-count":41,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T00:00:00Z","timestamp":1776038400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>In the realm of intelligent transportation systems (ITS), achieving optimal system performance relies heavily on the acquisition of comprehensive and high-quality spatio-temporal traffic data. In practical data-gathering processes, factors such as sensor malfunctions or communication interruptions often lead to incomplete or missing data records, which in turn substantially hinder the advancement of ITS applications. To address missing spatio-temporal data, a widely adopted paradigm involves the Latent Factorization of Tensors (LFT) model. Traditional LFT frameworks often employ the standard L2 metric in their learning objective, making them easily affected by abnormal data points. Moreover, impulse noise frequently arises in sensors and communication scenarios. To address these limitations, this paper develops an Adaptive Lp,\u03f5-norm-incorporated Latent Factorization of Tensors (Lp,\u03f5LFT) model founded on two-fold concepts: (a) constructing a generalized objective function grounded in the Lp,\u03f5-norm distance to enhance robustness against outliers; (b) realizing the self-adaptation of model hyper-parameters through a fuzzy controller to enhance model practicality. Experimental evaluations on six traffic speed datasets derived from multiple metropolitan traffic networks demonstrate that the proposed Lp,\u03f5LFT model yields significantly higher imputation accuracy and superior computational efficiency compared with seven state-of-the-art approaches.<\/jats:p>","DOI":"10.3390\/e28040435","type":"journal-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T10:19:14Z","timestamp":1776075554000},"page":"435","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["High-Quality Representation Learning Approach to Spatio-Temporal Traffic Speed Data with Lp,\u03f5-Norm"],"prefix":"10.3390","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6466-5755","authenticated-orcid":false,"given":"Lei","family":"Yang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziwen","family":"Ma","sequence":"additional","affiliation":[{"name":"College of Computer and Information Science, Southwest University, Chongqing 400715, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yikai","family":"Hou","sequence":"additional","affiliation":[{"name":"College of Computer and Information Science, Southwest University, Chongqing 400715, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Wang, J., Liu, X., Xu, L., Li, M., Li, L., and Shen, S. (2023). Local unitary equivalence of quantum states based on the tensor decompositions of unitary matrices. Entropy, 25.","DOI":"10.3390\/e25081139"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"3685","DOI":"10.1109\/TSP.2021.3085116","article-title":"Robust Low-Rank Tensor Completion Based on Tensor Ring Rank via \u2113p,\u03f5-Norm","volume":"69","author":"Li","year":"2021","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"14393","DOI":"10.1109\/TITS.2025.3564318","article-title":"Collaborative Bayesian Tensor Factorization-Based Reliable Traffic Speed Data Prediction in T-CPS","volume":"26","author":"Yang","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"8524","DOI":"10.1109\/TPAMI.2025.3576719","article-title":"Dynamic Autoregressive Tensor Factorization for Pattern Discovery of Spatiotemporal Systems","volume":"47","author":"Chen","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"24550","DOI":"10.1109\/TITS.2022.3205917","article-title":"Multitask neural tensor factorization for road traffic speed-volume correlation pattern learning and joint imputation","volume":"23","author":"Zhu","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"12107","DOI":"10.1109\/TITS.2023.3289193","article-title":"A customized data fusion tensor approach for interval-wise missing network volume imputation","volume":"24","author":"Xing","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"119797","DOI":"10.1016\/j.ins.2023.119797","article-title":"NT-DPTC: A non-negative temporal dimension preserved tensor completion model for missing traffic data imputation","volume":"653","author":"Chen","year":"2024","journal-title":"Inf. Sci."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"4296","DOI":"10.1109\/TSP.2013.2263502","article-title":"lp-MUSIC: Robust Direction-of-Arrival Estimator for Impulsive Noise Environments","volume":"61","author":"Zeng","year":"2013","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"802","DOI":"10.1109\/TSC.2022.3178543","article-title":"A double-space and double-norm ensembled latent factor model for highly accurate web service QoS prediction","volume":"16","author":"Wu","year":"2022","journal-title":"IEEE Trans. Serv. Comput."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2937","DOI":"10.1109\/TSMC.2025.3535783","article-title":"An Adaptive p-Norms-Based Kinematic Calibration Model for Industrial Robot Positioning Accuracy Promotion","volume":"55","author":"Chen","year":"2025","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1125","DOI":"10.1109\/TSP.2017.2784361","article-title":"Outlier-Robust Matrix Completion via lp-Minimization","volume":"66","author":"Zeng","year":"2017","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Nie, F., Wang, H., Cai, X., Huang, H., and Ding, C. (2012, January 10\u201313). Robust matrix completion via joint schatten p-norm and lp-norm minimization. Proceedings of the 2012 IEEE 12th International Conference on Data Mining, Brussels, Belgium.","DOI":"10.1109\/ICDM.2012.160"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"724","DOI":"10.1109\/TITS.2024.3486529","article-title":"Latent factor analysis model with temporal regularized constraint for road traffic data imputation","volume":"26","author":"Yang","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"11001","DOI":"10.1109\/TITS.2023.3279321","article-title":"HRST-LR: A hessian regularization spatio-temporal low rank algorithm for traffic data imputation","volume":"24","author":"Xu","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"13452","DOI":"10.1109\/TITS.2021.3124613","article-title":"Spatio-temporal constraint-based low rank matrix completion approaches for road traffic networks","volume":"23","author":"Sure","year":"2021","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"6734","DOI":"10.1109\/TITS.2025.3531221","article-title":"Fourth-order dimension preserved tensor completion with temporal constraint for missing traffic data imputation","volume":"26","author":"Chen","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2690","DOI":"10.1109\/TITS.2024.3493864","article-title":"Low-Rank and Deep Plug-and-Play Priors for Missing Traffic Data Imputation","volume":"26","author":"Chen","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2573","DOI":"10.1109\/TKDE.2019.2954868","article-title":"Learning spatiotemporal latent factors of traffic via regularized tensor factorization: Imputing missing values and forecasting","volume":"33","author":"Baggag","year":"2019","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"18673","DOI":"10.1109\/TITS.2024.3422214","article-title":"Low-rank tensor completion with 3-D spatiotemporal transform for traffic data imputation","volume":"25","author":"Shu","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"19549","DOI":"10.1109\/TITS.2024.3461735","article-title":"Self-attention graph convolution imputation network for spatio-temporal traffic data","volume":"25","author":"Wei","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"102038","DOI":"10.1016\/j.inffus.2023.102038","article-title":"Semantic understanding and prompt engineering for large-scale traffic data imputation","volume":"102","author":"Zhang","year":"2024","journal-title":"Inf. Fusion"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Wang, S., Li, J., Miao, H., Zhang, J., Zhu, J., and Wang, J. (2022, January 17\u201321). Generative-free urban flow imputation. Proceedings of the 31st ACM International Conference on Information & Knowledge Management, Atlanta, GA, USA.","DOI":"10.1145\/3511808.3557334"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"528","DOI":"10.1109\/TBDATA.2022.3181068","article-title":"Self-attention graph convolution residual network for traffic data completion","volume":"9","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Big Data"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"102292","DOI":"10.1016\/j.inffus.2024.102292","article-title":"Hierarchical spatio-temporal graph convolutional neural networks for traffic data imputation","volume":"106","author":"Xu","year":"2024","journal-title":"Inf. Fusion"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"2829","DOI":"10.1109\/TNNLS.2023.3339786","article-title":"Robust low-rank latent feature analysis for spatiotemporal signal recovery","volume":"36","author":"Wu","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"796","DOI":"10.1109\/JAS.2020.1003533","article-title":"Robust latent factor analysis for precise representation of high-dimensional and sparse data","volume":"8","author":"Wu","year":"2020","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Liu, S., Shi, X., and Liao, Q. (2023). Rank-adaptive tensor completion based on Tucker decomposition. Entropy, 25.","DOI":"10.3390\/e25020225"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Favier, G., and Rocha, D.S. (2024). Overview of Tensor-Based Cooperative MIMO Communication Systems\u2014Part 2: Semi-Blind Receivers. Entropy, 26.","DOI":"10.3390\/e26110937"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"J\u00f8rgensen, P.J., Nielsen, S.F., Hinrich, J.L., Schmidt, M.N., Madsen, K.H., and M\u00f8rup, M. (2024). Probabilistic parafac2. Entropy, 26.","DOI":"10.3390\/e26080697"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Huang, X., Chen, D., Wang, D., and Ren, T. (2020). Identifying influencers in social networks. Entropy, 22.","DOI":"10.3390\/e22040450"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Zeng, J., Qiu, Y., Ma, Y., Wang, A., and Zhao, Q. (2024). A novel tensor ring sparsity measurement for image completion. Entropy, 26.","DOI":"10.3390\/e26020105"},{"key":"ref_32","first-page":"1379","article-title":"An Outlier-Resilient Autoencoder for Representing High-Dimensional and Incomplete Data","volume":"9","author":"Wu","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_33","first-page":"4659","article-title":"Bayesian temporal factorization for multidimensional time series prediction","volume":"44","author":"Chen","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Liu, M., Huang, H., Feng, H., Sun, L., Du, B., and Fu, Y. (2023, January 3\u20137). Pristi: A conditional diffusion framework for spatiotemporal imputation. Proceedings of the 2023 IEEE 39th International Conference on Data Engineering, Anaheim, CA, USA.","DOI":"10.1109\/ICDE55515.2023.00150"},{"key":"ref_35","first-page":"6148","article-title":"NeuLFT: A novel approach to nonlinear canonical polyadic decomposition on high-dimensional incomplete tensors","volume":"35","author":"Luo","year":"2022","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"4888","DOI":"10.1109\/TCSS.2023.3296479","article-title":"Tensor factorization with sparse and graph regularization for fake news detection on social networks","volume":"11","author":"Che","year":"2023","journal-title":"IEEE Trans. Comput. Social Syst."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"110678","DOI":"10.1016\/j.patcog.2024.110678","article-title":"A generalizable framework for low-rank tensor completion with numerical priors","volume":"155","author":"Yuan","year":"2024","journal-title":"Pattern Recognit."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"15319","DOI":"10.1609\/aaai.v38i14.29456","article-title":"Efficient nonparametric tensor decomposition for binary and count data","volume":"Volume 38","author":"Tao","year":"2024","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1798","DOI":"10.1109\/TCYB.2019.2903736","article-title":"Temporal pattern-aware QoS prediction via biased non-negative latent factorization of tensors","volume":"50","author":"Luo","year":"2019","journal-title":"IEEE Trans. Cybern."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Ye, F., Lin, Z., Chen, C., Zheng, Z., and Huang, H. (2021, January 19\u201323). Outlier-resilient web service QoS prediction. Proceedings of the Web Conference 2021, Ljubljana, Slovenia.","DOI":"10.1145\/3442381.3449938"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"3843","DOI":"10.1109\/TNSM.2021.3074547","article-title":"A tensor-based approach for the QoS evaluation in service-oriented environments","volume":"18","author":"Su","year":"2021","journal-title":"IEEE Trans. Netw. Serv. Manag."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/4\/435\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T09:41:54Z","timestamp":1776678114000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/4\/435"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":41,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["e28040435"],"URL":"https:\/\/doi.org\/10.3390\/e28040435","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,13]]}}}