Automatic Bi-LSTM Architecture Search Using Bayesian Optimisation for Vehicle Activity Recognition

Book chapter


AlZoubi, A. and Radhakrishnan , R. 2023. Automatic Bi-LSTM Architecture Search Using Bayesian Optimisation for Vehicle Activity Recognition. in: A. Augusto de Sousa, Kurt Debattista, Alexis Paljic, Mounia Ziat, Christophe Hurter, Helen Purchase, Giovanni Maria Farinella, Petia Radeva and Kadi Bouatouch (ed.) Computer Vision, Imaging and Computer Graphics Theory and Applications New York Springer. pp. 108–134
AuthorsAlZoubi, A. and Radhakrishnan , R.
EditorsA. Augusto de Sousa, Kurt Debattista, Alexis Paljic, Mounia Ziat, Christophe Hurter, Helen Purchase, Giovanni Maria Farinella, Petia Radeva and Kadi Bouatouch
Abstract

This paper presents a novel method to find optimal Bidirectional Long-Short Term Memory Neural Network (Bi-LSTM) using Bayesian Optimisation method for vehicle trajectory classification. We extend our previous approach to be able to classify a larger number of vehicle trajectories collected from different sources in a single Bi-LSTM network. We also explored the use of deep learning visual explainability by highlighting the parts of the activity (or trajectory) contribute to the classification decision of the network. In particular, Qualitative Trajectory Calculus (QTC), spatio-temporal calculus, method is used to encode the relative movement between vehicles as a trajectory of QTC states. We then develop a Bi-LSTM network (called VNet) to classify QTC trajectories that represent vehicle pairwise activities. Existing Bi-LSTM networks for vehicle activity analysis are manually designed without considering the optimisation of the whole architecture nor its trainable hyperparameters. Therefore, we adapt Bayesian Optimisation method to search for an optimal Bi-LSTM architecture for classifying QTC trajectories of vehicle interaction. To test the validity of the proposed VNet, four datasets of 8237 trajectories of 9 unique vehicle activities in different traffic scenarios are used. We further compare our VNet model’s performance with the state-of-the-art methods. The results on the combined dataset (accuracy of 98.21%) showed that the proposed method generates light and most robust Bi-LSTM model. We also demonstrate that Activation Map is a promising approach for visualising the Bi-LSTM model decisions for vehicle activity recognition.

KeywordsVehicle Activity Classification; Qualitative Trajectory Calculus; Long-Short Term Memory Neural Network; Automatic LSTM Architecture Design; Bayesian Optimisation; Activation Map
Page range108–134
Year2023
Book titleComputer Vision, Imaging and Computer Graphics Theory and Applications
17th International Joint Conference, VISIGRAPP 2022, Virtual Event, February 6–8, 2022, Revised Selected Papers
PublisherSpringer
Place of publicationNew York
SeriesCommunications in Computer and Information Science
ISBN9783031457241
ISSN1865-0929
Digital Object Identifier (DOI)https://doi.org/10.1007/978-3-031-45725-8_6
https://doi.org/10.1007/978-3-031-45725-8
Web address (URL)https://link.springer.com/chapter/10.1007/978-3-031-45725-8_6
File
License
All rights reserved
File Access Level
Open
Output statusPublished
Publication dates
Online18 Oct 2023
Publication process dates
Deposited06 Dec 2023
Permalink -

https://repository.derby.ac.uk/item/q2xw5/automatic-bi-lstm-architecture-search-using-bayesian-optimisation-for-vehicle-activity-recognition

Restricted files

File

  • 34
    total views
  • 1
    total downloads
  • 3
    views this month
  • 0
    downloads this month

Export as

Related outputs

Explainable DCNN Decision Framework for Breast Lesion Classification from Ultrasound Images Based on Cancer Characteristics
AlZoubi, A., Eskandari, A., Yu, H. and Du, H. 2024. Explainable DCNN Decision Framework for Breast Lesion Classification from Ultrasound Images Based on Cancer Characteristics . Bioengineering. 11 (5), pp. 1-23. https://doi.org/10.3390/bioengineering11050453
ENAS-B: Combining ENAS with Bayesian Optimisation for Automatic Design of Optimal CNN Architectures for Breast Lesion Classification from Ultrasound Images
Ahmed, M., Du, H. and AlZoubi, A. 2023. ENAS-B: Combining ENAS with Bayesian Optimisation for Automatic Design of Optimal CNN Architectures for Breast Lesion Classification from Ultrasound Images. Ultrasonic Imaging. https://doi.org/10.1177/01617346231208709
Automatic Detection of Thyroid Nodule Characteristics From 2D Ultrasound Images
Han, D., Ibrahim, N., Lu, F., Zhu, Y., Du, H. and AlZoubi, A. 2023. Automatic Detection of Thyroid Nodule Characteristics From 2D Ultrasound Images. Ultrasonic Imaging. pp. 1-18. https://doi.org/10.1177/01617346231200804
Classification of breast lesions in ultrasound images using deep convolutional neural networks: transfer learning versus automatic architecture design
AlZoubi, A., Lu, F., Zhu, Y., Ying, T., Ahmed, M. and Du, H. 2023. Classification of breast lesions in ultrasound images using deep convolutional neural networks: transfer learning versus automatic architecture design. Medical & Biological Engineering & Computing. pp. 1-15. https://doi.org/10.1007/s11517-023-02922-y
A generic deep learning framework to classify thyroid and breast lesions in ultrasound images
Zhu, Y.C., AlZoubi, A., Jassim, S., Jiang, Q., Zhang, Y., Wang, Y.B., Ye, X.D. and Hongbo, D.U. 2021. A generic deep learning framework to classify thyroid and breast lesions in ultrasound images. Ultrasonics. 110, pp. 1-8. https://doi.org/10.1016/j.ultras.2020.106300
Machine Learning Assisted Doppler Features for Enhancing Thyroid Cancer Diagnosis
Zhu, Y., Du, H., Jiang, Q., Zhang, T., Huang, X., Zhang, Y., Shi, X., Shan, J. and AlZoubi, A. 2021. Machine Learning Assisted Doppler Features for Enhancing Thyroid Cancer Diagnosis. Journal of Ultrasound in Medicine. 41 (8), pp. 1961-1974. https://doi.org/10.1002/jum.15873