Tensor-Train-Based Multiuser Multivariate Multiorder Physical Markov Process Informed Multimodal Prediction for Industrial Trajectory Applications

• Published in: IEEE transactions on industrial informatics Vol. 19; no. 8; pp. 8900 - 8909
• Main Authors: Liu, Huazhong, Wang, Jiawei, Yin, Xiaoxue, Ding, Jihong, Yang, Laurence T., Yao, Tong, Yang, Jing, Gao, Yuan
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.08.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Algorithms; Big Data; Computational efficiency; Computational modeling; Computing time; Data mining; Data models; Efficiency; Industrial applications; Industrial big data; Markov analysis; Markov processes; Mathematical analysis; multimodal trajectory prediction; multiuser multivariate multiorder physical Markov model; Multivariate analysis; Pattern analysis; Predictive models; Route selection; stationary joint eigentensor; tensor and tensor-train; Tensors; Trajectories; Trajectory; Transportation systems; unified product
• ISSN: 1551-3203; 1941-0050
• DOI: 10.1109/TII.2022.3222366

Combining data-driven approaches and physical laws for industrial trajectory prediction can improve the performance of industrial applications such as path planning of robots and route selection of vehicles in transportation systems. In the era of industrial Big Data, the application of industrial trajectory prediction based on the physical Markov process and tensor model has attracted much attention. To synchronously improve the prediction accuracy and computational efficiency, this article proposes a tensor-train (TT)-based multiuser multivariate multiorder (3M) physical Markov prediction approach for multimodal industrial trajectory pattern mining. First, we propose a TT-based unified product calculation rule with its scalable computation approach based on decomposed TT cores to speed up the execution efficiency. Then, a TT-based 3M (TT-3M) Markov transition approach is presented. Furthermore, we put forward a TT-based power method to calculate the stationary joint eigentensor (SJE) and an SJE-based multimodal prediction algorithm to mine concealed trajectory patterns. Experimental results based on real GPS trajectory dataset show that compared with the original tensor-based 3M approach, the TT-3M approach can improve the computational efficiency up to three times and reduce the storage space proportion to a minimum of 1‰ while ensuring basically consistent prediction accuracy.