research-article

An Uncertainty-based Neural Network for Explainable Trajectory Segmentation

Authors:

Guoren WangAuthors Info & Claims

ACM Transactions on Intelligent Systems and Technology (TIST), Volume 13, Issue 1

Article No.: 11, Pages 1 - 18

https://doi.org/10.1145/3467978

Published: 29 November 2021 Publication History

Abstract

As a variant task of time-series segmentation, trajectory segmentation is a key task in the applications of transportation pattern recognition and traffic analysis. However, segmenting trajectory is faced with challenges of implicit patterns and sparse results. Although deep neural networks have tremendous advantages in terms of high-level feature learning performance, deploying as a blackbox seriously limits the real-world applications. Providing explainable segmentations has significance for result evaluation and decision making. Thus, in this article, we address trajectory segmentation by proposing a Bayesian Encoder-Decoder Network (BED-Net) to provide accurate detection with explainability and references for the following active-learning procedures. BED-Net consists of a segmentation module based on Monte Carlo dropout and an explanation module based on uncertainty learning that provides results evaluation and visualization. Experimental results on both benchmark and real-world datasets indicate that BED-Net outperforms the rival methods and offers excellent explainability in the applications of trajectory segmentation.

References

[1]

Charu C. Aggarwal, Xiangnan Kong, Quanquan Gu, Jiawei Han, and Philip S. Yu. 2014. Active learning: A survey. In Data Classification: Algorithms and Applications. CRC Press, 571–606.

Digital Library

[2]

Rex V. Allen. 1978. Automatic earthquake recognition and timing from single traces. Bull. Seismol. Soc. Amer. 68, 5 (Oct. 1978), 1521–1532.

[3]

Md. Zahangir Alom, Mahmudul Hasan, Chris Yakopcic, Tarek M. Taha, and Vijayan K. Asari. 2018. Recurrent residual convolutional neural network based on U-Net (R2U-Net) for medical image segmentation. Retrieved from https://arxiv.org/abs/1802.06955.

[4]

Roy Assaf and Anika Schumann. 2019. Explainable deep neural networks for multivariate time series predictions. In Proceedings of the 28th International Joint Conference on Artificial Intelligence. 6488–6490.

[5]

Catarina Barata, Jacinto C. Nascimento, Joao M. Lemos, and Jorge S. Marques. 2021. Sparse motion fields for trajectory prediction. Pattern Recogn. 110 (2021), 107631.

[6]

Xin Bi, Chao Zhang, Yao He, Xiangguo Zhao, Yongjiao Sun, and Yuliang Ma. 2021. Explainable time-frequency convolutional neural network for microseismic waveform classification. Info. Sci. 546 (2021), 883–896.

[7]

Ángel Bueno, M. Carmen Benítez, Silvio De Angelis, Alejandro Diaz-Moreno, and Jesús M. Ibáñez. 2020. Volcano-Seismic transfer learning and uncertainty quantification with bayesian neural networks. IEEE Trans. Geosci. Remote Sens. 58, 2 (2020), 892–902.

[8]

William N. Caballero, Brian J. Lunday, and Richard P. Uber. 2021. Identifying behaviorally robust strategies for normal form games under varying forms of uncertainty. Eur. J. Operation. Res. 288, 3 (2021), 971–982.

[9]

Jiannan Cai, Yuxi Zhang, Liu Yang, Hubo Cai, and Shuai Li. 2020. A context-augmented deep learning approach for worker trajectory prediction on unstructured and dynamic construction sites. Adv. Eng. Info. 46 (2020), 101173.

[10]

Kai Cheng and Zhenzhou Lu. 2021. Active learning Bayesian support vector regression model for global approximation. Info. Sci. 544 (2021), 549–563.

[11]

Maria Luisa Damiani, Fatima Hachem, Hamza Issa, Nathan Ranc, Paul Moorcroft, and Francesca Cagnacci. 2018. Cluster-based trajectory segmentation with local noise. Data Min. Knowl. Discov. 32, 4 (2018), 1017–1055.

Digital Library

[12]

Antonio Manuel Duran-Rosal, Pedro Antonio Gutierrez, Francisco JoseMartinez-Estudillo, and Cesar Hervas-Martinez. 2018. Simultaneous optimisation of clustering quality and approximation error for time series segmentation. Info. Sci. 442–443 (2018), 186–201.

Digital Library

[13]

Mohammad Etemad, Zahra Etemad, Amílcar Soares, Vania Bogorny, Stan Matwin, and Luis Torgo. 2020. Wise sliding window segmentation: A classification-aided approach for trajectory segmentation. In Advances in Artificial Intelligence. Springer, 208–219.

[14]

Yarin Gal and Zoubin Ghahramani. 2016. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In Proceedings of the 33nd International Conference on Machine Learning. 1050–1059.

Digital Library

[15]

Yuan Gao, Longfei Huang, Jun Feng, and Xin Wang. 2020. Semantic trajectory segmentation based on change-point detection and ontology. Int. J. Geogr. Info. Sci. 34, 12 (2020), 2361–2394.

[16]

A. Gonzlez-Vidal, P. Barnaghi, and A. F. Skarmeta. 2018. BEATS: Blocks of eigenvalues algorithm for time series segmentation. IEEE Trans. Knowl. Data Eng. 30, 11 (2018), 2051–2064.

[17]

Sini Guo, Xiang Li, Wai-Ki Ching, Ralescu Dan, Wai-Keung Li, and Zhiwen Zhang. 2018. GPS trajectory data segmentation based on probabilistic logic. Int. J. Approx. Reason. 103 (2018), 227–247.

[18]

Peilan He, Guiyuan Jiang, Siew-Kei Lam, and Yidan Sun. 2020. Learning heterogeneous traffic patterns for travel time prediction of bus journeys. Info. Sci. 512 (2020), 1394–1406.

[19]

Yuta Hiasa, Yoshito Otake, Masaki Takao, Takeshi Ogawa, Nobuhiko Sugano, and Yoshinobu Sato. 2020. Automated muscle segmentation from clinical CT using bayesian U-Net for personalized musculoskeletal modeling. IEEE Trans. Med. Imag. 39, 4 (2020), 1030–1040.

[20]

Yuta Hiasa, Yoshito Otake, Masaki Takao, Takeshi Ogawa, Nobuhiko Sugano, and Yoshinobu Sato. 2020. Automated muscle segmentation from clinical CT using bayesian U-Net for personalized musculoskeletal modeling. IEEE Trans. Med. Imag. 39, 4 (2020), 1030–1040.

[21]

Sepp Hochreiter and Jügen Schmidhuber. 1997. Long short-term memory. Neural Comput. 9, 8 (1997), 1735–1780.

Digital Library

[22]

C. Huang, J. Chen, Y. Pan, H. Lai, J. Yin, and Q. Huang. 2019. Clothing landmark detection using deep networks with prior of key point associations. IEEE Trans. Cybernet. 49, 10 (2019), 3744–3754.

[23]

Wei Jiang, Jie Zhu, Jiajie Xu, Zhixu Li, Pengpeng Zhao, and Lei Zhao. 2017. A feature based method for trajectory dataset segmentation and profiling. World Wide Web 20, 1 (2017), 5–22.

Digital Library

[24]

Seokjun Kang, Brian Kenji Iwana, and Seiichi Uchida. 2021. Complex image processing with less data—Document image binarization by integrating multiple pre-trained U-Net modules. Pattern Recogn. 109 (2021), 107577.

Digital Library

[25]

Alex Kendall and Yarin Gal. 2017. What uncertainties do we need in bayesian deep learning for computer vision? Retrieved from https://arxiv.org/abs/1703.04977.

Digital Library

[26]

Yongchan Kwon, Joong-Ho Won, Beom Joon Kim, and Myunghee Cho Paik. 2020. Uncertainty quantification using Bayesian neural networks in classification: Application to biomedical image segmentation. Comput. Stat. Data Anal. 142 (2020), 106816.

Digital Library

[27]

Zachary C. Lipton. 2018. The mythos of model interpretability. Commun. ACM 61, 10 (2018), 36–43.

Digital Library

[28]

Wen Liu, Yankui Sun, and Qingge Ji. 2020. MDAN-UNet: Multi-Scale and dual attention enhanced nested U-Net architecture for segmentation of optical coherence tomography images. Algorithms 13, 3 (2020), 60.

[29]

Y. Liu, R. Jia, X. Xie, and Z. Liu. 2019. A two-stage destination prediction framework of shared bicycles based on geographical position recommendation. IEEE Intell. Transport. Syst. Mag. 11, 1 (2019), 42–47.

[30]

V. Nguyen, D. Nguyen, L. N. Van, and K. Than. 2019. Infinite Dropout for training Bayesian models from data streams. In Proceedings of the IEEE International Conference on Big Data (BigData’19). 125–134.

[31]

Ozan Oktay, Jo Schlemper, Loïc Le Folgoc, Matthew C. H. Lee, Mattias P. Heinrich, Kazunari Misawa, Kensaku Mori, Steven G. McDonagh, Nils Y. Hammerla, Bernhard Kainz, Ben Glocker, and Daniel Rueckert. 2018. Attention U-Net: Learning where to look for the pancreas. Retrieved from https://arxiv.org/abs/1804.03999.

[32]

Jose F. Rodrigues-Jr, Marco A. Gutierrez, Gabriel Spadon, Bruno Brandoli, and Sihem Amer-Yahia. 2021. LIG-Doctor: Efficient patient trajectory prediction using bidirectional minimal gated-recurrent networks. Info. Sci. 545 (2021), 813–827.

[33]

Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-Net: Convolutional networks for biomedical image segmentation. In Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI’15), Vol. 9351. 234–241.

[34]

Erin T. Solovey, Kimberly J. Ryan, and M. L. Cummings. 2021. CODA: Mobile interface for enabling safer navigation of unmanned aerial vehicles in real-world settings. Int. J. Hum.-Comput. Studies 145 (2021), 102508.

[35]

H. Su, K. Zheng, K. Zeng, J. Huang, S. Sadiq, N. J. Yuan, and X. Zhou. 2015. Making sense of trajectory data: A partition-and-summarization approach. In Proceedings of the IEEE 31st International Conference on Data Engineering. 963–974.

[36]

Yu-Sen Su, Chuen-Fa Ni, Wei-Ci Li, I-Hsien Lee, and Chi-Ping Lin. 2020. Applying deep learning algorithms to enhance simulations of large-scale groundwater flow in IoTs. Appl. Soft Comput. 92 (2020), 106298.

[37]

Y. Sun, W. Zuo, and M. Liu. 2020. See the future: A semantic segmentation network predicting ego-vehicle trajectory with a single monocular camera. IEEE Robot. Autom. Lett. 5, 2 (2020), 3066–3073.

[38]

S. Thakur, H. van Hoof, J. C. G. Higuera, D. Precup, and D. Meger. 2019. Uncertainty aware learning from demonstrations in multiple contexts using bayesian neural networks. In Proceedings of the International Conference on Robotics and Automation (ICRA’19). 768–774.

[39]

Guotai Wang, Wenqi Li, Maria A. Zuluaga, Rosalind Pratt, Premal A. Patel, Michael Aertsen, Tom Doel, Anna L. David, Jan Deprest, Sébastien Ourselin, and Tom Vercauteren. 2018. Interactive medical image segmentation using deep learning with image-specific fine tuning. IEEE Trans. Med. Imag. 37, 7 (2018), 1562–1573.

[40]

P. Wang, N. C. Bouaynaya, L. Mihaylova, J. Wang, Q. Zhang, and R. He. 2020. Bayesian neural networks uncertainty quantification with cubature rules. In Proceedings of the International Joint Conference on Neural Networks (IJCNN). 1–7.

[41]

Weikun Wu, Yan Zhang, David Wang, and Yunqi Lei. 2020. SK-Net: Deep learning on point cloud via end-to-end discovery of spatial keypoints. In Proceedings of the 34th AAAI Conference on Artificial Intelligence. 6422–6429.

[42]

Yi Xu, Jing Yang, and Shaoyi Du. 2020. CF-LSTM: Cascaded feature-based long short-term networks for predicting pedestrian trajectory. In Proceedings of the 34th AAAI Conference on Artificial Intelligence. 12541–12548.

[43]

Haitao Yuan, Guoliang Li, Zhifeng Bao, and Ling Feng. 2020. Effective travel time estimation: When historical trajectories over road networks matter. In Proceedings of the ACM SIGMOD International Conference on Management of Data. 2135–2149.

Digital Library

[44]

Yue Zhang, Andrea Michi, Johannes Wagner, Elisabeth André, Björn W. Schuller, and Felix Weninger. 2020. A generic human-machine annotation framework based on dynamic cooperative learning. IEEE Trans. Cybernet. 50, 3 (2020), 1230–1239.

[45]

Yu Zheng, Yukun Chen, Quannan Li, Xing Xie, and Wei-Ying Ma. 2010. Understanding transportation modes based on GPS data for web applications. ACM Trans. Web 4, 1 (2010), 1:1–1:36.

Digital Library

[46]

Yu Zheng, Lizhu Zhang, Xing Xie, and Wei-Ying Ma. 2009. Mining interesting locations and travel sequences from GPS trajectories. In Proceedings of the 18th International Conference on World Wide Web. 791–800.

Digital Library

Cited By

Yuan LWang HZhang F(2025)ADMNet: An adaptive downsampling multi-frequency multi-channel network for long-term time series forecastingExpert Systems with Applications10.1016/j.eswa.2024.125588262(125588)Online publication date: Mar-2025
https://doi.org/10.1016/j.eswa.2024.125588
Mihalea ASamoilescu RFlorea A(2023)Self-Supervised Steering and Path Labeling for Autonomous DrivingSensors10.3390/s2320847323:20(8473)Online publication date: 15-Oct-2023
https://doi.org/10.3390/s23208473
Tahir HShahbaz Khan MAhmed FM. Albarrak ANoman Qasem SAhmad J(2023)Prediction of the SARS-CoV-2 Derived T-Cell Epitopes’ Response Against COVID VariantsComputers, Materials & Continua10.32604/cmc.2023.03541075:2(3517-3535)Online publication date: 2023
https://doi.org/10.32604/cmc.2023.035410
Show More Cited By

Index Terms

An Uncertainty-based Neural Network for Explainable Trajectory Segmentation
1. Computing methodologies
  1. Machine learning
    1. Machine learning approaches
      1. Neural networks
2. Mathematics of computing
  1. Probability and statistics
    1. Statistical paradigms
      1. Time series analysis

Recommendations

Vessel Trajectory Segmentation: A Survey
Database Systems for Advanced Applications. DASFAA 2023 International Workshops
Abstract
Vessel trajectory data, usually derived from AIS data, serves as a robust foundation for extensive research on vessel movements and behaviors. The task of vessel trajectory segmentation identifies the typical sub-trajectory segments in the vessel ...
Segmentation and Sampling of Moving Object Trajectories Based on Representativeness

Moving Object Databases (MOD), although ubiquitous, still call for methods that will be able to understand, search, analyze, and browse their spatiotemporal content. In this paper, we propose a method for trajectory segmentation and sampling based on ...
Wise Sliding Window Segmentation: A Classification-Aided Approach for Trajectory Segmentation
Advances in Artificial Intelligence
Abstract
Large amounts of mobility data are being generated from many different sources, and several data mining methods have been proposed for this data. One of the most critical steps for trajectory data mining is segmentation. This task can be seen as ...

Comments

Information & Contributors

Information

Published In

cover image ACM Transactions on Intelligent Systems and Technology

ACM Transactions on Intelligent Systems and Technology Volume 13, Issue 1

February 2022

349 pages

ISSN:2157-6904

EISSN:2157-6912

DOI:10.1145/3502429

Editor:
Huan Liu
Arizona State University, USA

Issue’s Table of Contents

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 29 November 2021

Accepted: 01 May 2021

Revised: 01 March 2021

Received: 01 January 2021

Published in TIST Volume 13, Issue 1

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Refereed

Funding Sources

National Natural Science Foundation of China
Fundamental Research Funds for the Central Universities

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

5
Total Citations
View Citations
657
Total Downloads

Downloads (Last 12 months)74
Downloads (Last 6 weeks)9

Reflects downloads up to 03 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

Yuan LWang HZhang F(2025)ADMNet: An adaptive downsampling multi-frequency multi-channel network for long-term time series forecastingExpert Systems with Applications10.1016/j.eswa.2024.125588262(125588)Online publication date: Mar-2025
https://doi.org/10.1016/j.eswa.2024.125588
Mihalea ASamoilescu RFlorea A(2023)Self-Supervised Steering and Path Labeling for Autonomous DrivingSensors10.3390/s2320847323:20(8473)Online publication date: 15-Oct-2023
https://doi.org/10.3390/s23208473
Tahir HShahbaz Khan MAhmed FM. Albarrak ANoman Qasem SAhmad J(2023)Prediction of the SARS-CoV-2 Derived T-Cell Epitopes’ Response Against COVID VariantsComputers, Materials & Continua10.32604/cmc.2023.03541075:2(3517-3535)Online publication date: 2023
https://doi.org/10.32604/cmc.2023.035410
Ucer SOzyer TAlhajj R(2022)Explainable artificial intelligence through graph theory by generalized social network analysis-based classifierScientific Reports10.1038/s41598-022-19419-712:1Online publication date: 8-Sep-2022
https://doi.org/10.1038/s41598-022-19419-7
Liang MWang XWu S(2022)Improving stock trend prediction through financial time series classification and temporal correlation analysis based on aligning change pointSoft Computing - A Fusion of Foundations, Methodologies and Applications10.1007/s00500-022-07630-727:7(3655-3672)Online publication date: 28-Nov-2022
https://dl.acm.org/doi/10.1007/s00500-022-07630-7

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Article

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Full Text

View this article in Full Text.

HTML Format

View this article in HTML Format.

Figures

Tables

Media

View full text|Download PDF

View Issue’s Table of Contents