Efficiently Improving the Wi-Fi-Based Human Activity Recognition, Using Auditory Features, Autoencoders, and Fine-Tuning

Article


Rahdar, A., Chahoushi, M. and Ghorashi, S. 2024. Efficiently Improving the Wi-Fi-Based Human Activity Recognition, Using Auditory Features, Autoencoders, and Fine-Tuning. Computers in Biology and Medicine. 172 (Art. 108232). https://doi.org/10.1016/j.compbiomed.2024.108232
AuthorsRahdar, A., Chahoushi, M. and Ghorashi, S.
Abstract

Human activity recognition (HAR) based on Wi-Fi signals has attracted significant attention due to its convenience and the availability of infrastructures and sensors. Channel State Information (CSI) measures how Wi-Fi signals propagate through the environment. However, many scenarios and applications have insufficient training data due to constraints such as cost, time, or resources. This poses a challenge for achieving high accuracy levels with machine learning techniques. In this study, multiple deep learning models for HAR were employed to achieve acceptable accuracy levels with much less training data than other methods. A pre-trained encoder trained from a Multi-Input Multi-Output Autoencoder (MIMO AE) on Mel Frequency Cepstral Coefficients (MFCC) from a small subset of data samples was used for feature extraction. Then, fine-tuning was applied by adding the encoder as a fixed layer in the classifier, which was trained on a small fraction of the remaining data. The evaluation results (K-fold cross-validation and K=5) showed that using only 30% of the training and validation data (equivalent to 24% of the total data), the accuracy was improved by 17.7% compared to the case where the encoder was not used (with an accuracy of 79.3% for the designed classifier, and an accuracy of 90.3% for the classifier with the fixed encoder). While by considering more calculational cost, achieving higher accuracy using the pre-trained encoder as a trainable layer is possible (up to 2.4% improvement), this small gap demonstrated the effectiveness and efficiency of the proposed method for HAR using Wi-Fi signals.

KeywordsAutoencoder; Channel State Information; Deep Learning; Fine-Tuning; Human Activity Recognition; Machine Learning; Mel Frequency Cepstral Coefficient
JournalComputers in Biology and Medicine
Journal citation172 (Art. 108232)
ISSN0010-4825
1879-0534
Year2024
PublisherElsevier
Publisher's version
License
File Access Level
Anyone
Digital Object Identifier (DOI)https://doi.org/10.1016/j.compbiomed.2024.108232
Publication dates
Online27 Feb 2024
PrintApr 2024
Publication process dates
Accepted25 Feb 2024
Deposited26 Feb 2024
Copyright holder© 2024, The Author
Permalink -

https://repository.uel.ac.uk/item/8x595

Download files


Publisher's version
Efficiently improving the Wi-Fi-based h...pdf
License: CC BY 4.0
File access level: Anyone

  • 67
    total views
  • 113
    total downloads
  • 3
    views this month
  • 3
    downloads this month

Export as

Related outputs

A CSI-based Human Activity Recognition using Canny Edge Detector
Shahverdi, H., Moshiri, P. F., Nabati, M., Asvadi, R. and Ghorashi, S. 2024. A CSI-based Human Activity Recognition using Canny Edge Detector. in: Ahad, M., Inoue, S., Lopez, G. and Hossain, T. (ed.) Human Activity and Behavior Analysis: Advances in Computer Vision and Sensors: Volume 2 CRC Press: Taylor & Francis Group. pp. 67-82
Complexity Reduction in Beamforming of Uniform Array Antennas for MIMO Radars
Faghand, E., Mehrshahi, E. and Ghorashi, S. A. 2023. Complexity Reduction in Beamforming of Uniform Array Antennas for MIMO Radars. IEEE Transactions on Radar Systems. 1, pp. 413-422. https://doi.org/10.1109/TRS.2023.3309579
Enhancing CSI-Based Human Activity Recognition by Edge Detection Techniques
Shahverdi, H., Nabati, M., Fard Moshiri, P., Asvadi, R. and Ghorashi, S. 2023. Enhancing CSI-Based Human Activity Recognition by Edge Detection Techniques. Information. 14 (7), p. 404. https://doi.org/https://doi.org/10.3390/info14070404
MIMO Virtual Array Design for mmWave 4D-Imaging Radar Sensors
Sichani, N. K., Ahmadi, M., Raei, E., Alaee-Kerahroodi, M., Shankar, M. R. B., Mehrshahi, E. and Ghorashi, S. 2023. MIMO Virtual Array Design for mmWave 4D-Imaging Radar Sensors. EUSIPCO 2023: 31st European Signal Processing Conference . Helsinki, Finland 04 - 08 Sep 2023 IEEE. https://doi.org/10.23919/EUSIPCO58844.2023.10290050
Waveform Design for 4D-Imaging mmWave PMCW MIMO Radars with Spectrum Compatibility
Sichani, N. K., Alaee-Kerahroodi, M., Shankar, M. R. B., Mehrshahi, E. and Ghorashi, S. 2023. Waveform Design for 4D-Imaging mmWave PMCW MIMO Radars with Spectrum Compatibility. European Radar Conference 2023. Berlin, Germany. 20 - 22 Sep 2023 IEEE. https://doi.org/10.23919/EuRAD58043.2023.10289319
CSI-Based Human Activity Recognition Using Multi-Input Multi-Output Autoencoder and Fine-Tuning
Chahoushi, M., Nabati, M., Asvadi, R. and Ghorashi, S. 2023. CSI-Based Human Activity Recognition Using Multi-Input Multi-Output Autoencoder and Fine-Tuning. Sensors. 23 (7), p. 3591. https://doi.org/10.3390/s23073591
A real-time fingerprint-based indoor positioning using deep learning and preceding states
Nabati, M. and Ghorashi, S. 2023. A real-time fingerprint-based indoor positioning using deep learning and preceding states. Expert Systems with Applications. 213 (Art. 118889). https://doi.org/10.1016/j.eswa.2022.118889
Time-series clustering for sensor fault detection in large-scale Cyber-Physical Systems
Alwan, A., Brimicombe, A., Ciupala, A., Ghorashi, S., Baravalle, A. and Falcarin, P. 2022. Time-series clustering for sensor fault detection in large-scale Cyber-Physical Systems. Computer Networks. 218 (Art. 109384). https://doi.org/10.1016/j.comnet.2022.109384
Confidence interval estimation for fingerprint-based indoor localization
Nabati, M., Ghorashi, S. and Shahbazian, R. 2022. Confidence interval estimation for fingerprint-based indoor localization. Ad Hoc Networks. 134 (Art. 102877). https://doi.org/10.1016/j.adhoc.2022.102877
JGPR: a computationally efficient multi-target Gaussian process regression algorithm
Nabati, M., Ghorashi, S. A. and Shahbazian, R. 2022. JGPR: a computationally efficient multi-target Gaussian process regression algorithm. Machine Learning. 111, pp. 1987-2010. https://doi.org/10.1007/s10994-022-06170-3
The Impact of CISO Appointment Announcements on the Market Value of Firms
Ford, A., Al-Nemrat, A., Ghorashi, S. and Davidson, J. 2022. The Impact of CISO Appointment Announcements on the Market Value of Firms. 17th International Conference on Cyber Warfare and Security (ICCWS 2022). Albany, New York, USA 17 - 18 Mar 2022 Academic Conferences International (ACI).
A Machine Learning Framework for House Price Estimation
Awonaike, A., Ghorashi, S. and Hammad, R. 2022. A Machine Learning Framework for House Price Estimation. 21st International Conference on Intelligent Systems Design and Applications (ISDA 2021). Online 13 - 15 Dec 2021 Springer. https://doi.org/10.1007/978-3-030-96308-8_90
CSI-Based Human Activity Recognition using Convolutional Neural Networks
Fard Moshiri, P., Nabati, M., Shahbazian, R. and Ghorashi, S. 2021. CSI-Based Human Activity Recognition using Convolutional Neural Networks. 11th International Conference on Computer and Knowledge Engineering (ICCKE 2021). Ferdowsi University of Mashhad, Mashhad, Iran 28 - 29 Oct 2021 IEEE. https://doi.org/10.1109/ICCKE54056.2021.9721516
Data quality challenges in large-scale cyber-physical systems: A systematic review
Alwan, A., Ciupala, A., Brimicombe, A., Ghorashi, S., Baravalle, A. and Falcarin, P. 2021. Data quality challenges in large-scale cyber-physical systems: A systematic review. Information Systems. 105 (Art. 101951). https://doi.org/10.1016/j.is.2021.101951
The Impact of Data Breach Announcements on Company Value in European Markets
Ford, A., Al-Nemrat, A., Ghorashi, S. and Davidson, J. 2021. The Impact of Data Breach Announcements on Company Value in European Markets. WEIS 2021: The 20th Annual Workshop on the Economics of Information Security. 28 - 29 Jun 2021
The Impact of GDPR Infringement Fines on the Market Value of Firms
Ford, A., Al-Nemrat, A., Ghorashi, S. and Davidson, J. 2021. The Impact of GDPR Infringement Fines on the Market Value of Firms. ECCWS 2021- Proceeding of the 20th European Conference on Cyber Warfare and Security. 24 - 25 Jun 2021 Academic Conferences International (ACI). https://doi.org/10.34190/EWS.21.088
A CSI-Based Human Activity Recognition Using Deep Learning
Fard Moshiri, P., Shahbazian, R., Nabati, M. and Ghorashi, S. A. 2021. A CSI-Based Human Activity Recognition Using Deep Learning. Sensors. https://doi.org/10.3390/s21217225
Reconfigurable Linear Antenna Arrays for Beam-Pattern Matching in Collocated MIMO Radars
Kavousi Ghafi, E., Ghorashi, S. and Mehrshahi, E. 2021. Reconfigurable Linear Antenna Arrays for Beam-Pattern Matching in Collocated MIMO Radars. IEEE Transactions on Aerospace and Electronic Systems. 57 (5), pp. 2715-2724. https://doi.org/10.1109/TAES.2021.3062173
Generative Adversarial Networks (GANs) in Networking: A Comprehensive Survey & Evaluation
Navidan, H., Fard Moshiri, P., Nabati, M., Shahbazian, R., Ghorashi, S., Shah-Mansouri, V. and Windridge, D. 2021. Generative Adversarial Networks (GANs) in Networking: A Comprehensive Survey & Evaluation. Computer Networks. 194 (Art. 108149). https://doi.org/10.1016/j.comnet.2021.108149
Joint Coordinate Optimization in Fingerprint-Based Indoor Positioning
Nabati, M., Ghorashi, S. and Shahbazian, R. 2021. Joint Coordinate Optimization in Fingerprint-Based Indoor Positioning. IEEE Communications Letters. 25 (4), pp. 1192-1195. https://doi.org/10.1109/LCOMM.2020.3047352
A fingerprint technique for indoor localization using autoencoder based semi-supervised deep extreme learning machine
Ezzati Khatab, Z., Hajihoseini Gazestani, A., Ghorashi, S. and Ghavami, M. 2020. A fingerprint technique for indoor localization using autoencoder based semi-supervised deep extreme learning machine. Signal Processing. 181 (Art. 107915). https://doi.org/10.1016/j.sigpro.2020.107915
Joint Optimization of Power and Location in Full-Duplex UAV Enabled Systems
Gazestani A. H., Ghorashi, S. A., Yang, Z. and Shikh-Bahaei, M. 2020. Joint Optimization of Power and Location in Full-Duplex UAV Enabled Systems. IEEE Systems Journal. 16 (1), pp. 914-921. https://doi.org/10.1109/JSYST.2020.3036275
Fingerprinting Based Indoor Localization Considering the Dynamic Nature of Wi-Fi Signals
Alikhani, N., Moghtadaiee, V. and Ghorashi, S. 2020. Fingerprinting Based Indoor Localization Considering the Dynamic Nature of Wi-Fi Signals. Wireless Personal Communications. 115 (2), pp. 1445-1464. https://doi.org/10.1007/s11277-020-07636-0
Resource Allocation in Full-Duplex UAV Enabled Multi Small Cell Networks
Hajihoseini Gazestani, A., Ghorashi, S. A., Yang, Z. and Shikh-Bahaei, M 2020. Resource Allocation in Full-Duplex UAV Enabled Multi Small Cell Networks. IEEE Transactions on Mobile Computing. 21 (3), pp. 1049-1060. https://doi.org/10.1109/TMC.2020.3017137
Privacy preserving in indoor fingerprint localization and radio map expansion
Ghorashi, S. A., Sazdar, A. M., Alikhani, N. and Khonsari, A. 2020. Privacy preserving in indoor fingerprint localization and radio map expansion. Peer-to-Peer Networking and Applications. 14, p. 121–134. https://doi.org/10.1007/s12083-020-00950-1
A Low-complexity trajectory privacy preservation approach for indoor fingerprinting positioning systems
Sazdar, A. M., Ghorashi, S. A., Moghtadaiee, V., Khonsari, A. and Windridge, D. 2020. A Low-complexity trajectory privacy preservation approach for indoor fingerprinting positioning systems. Journal of Information Security and Applications. 53 (Art. 102515). https://doi.org/10.1016/j.jisa.2020.102515
Using Synthetic Data to Enhance the Accuracy of Fingerprint-Based Localization: A Deep Learning Approach
Nabati, M., Navidan, H., Shahbazian, R., Ghorashi, S. A. and Windridge, D. 2020. Using Synthetic Data to Enhance the Accuracy of Fingerprint-Based Localization: A Deep Learning Approach. IEEE Sensors Letters. 4 (Art. 6000204). https://doi.org/10.1109/LSENS.2020.2971555
Power Allocation for D2D Communications Using Max-Min Message-Passing Algorithm
Kazemi Rashed, S, Asvadi, R., Rajabi, S., Ghorashi, S. A. and Martini, M. G. 2020. Power Allocation for D2D Communications Using Max-Min Message-Passing Algorithm. IEEE Transactions on Vehicular Technology. 69 (8), pp. 8443-8458. https://doi.org/10.1109/TVT.2020.2995534
Throughput Improvement by Mode Selection in Hybrid Duplex Wireless Networks
Mousavinasab, B., Gazestani, A. H., Ghorashi, S. A. and Shikh-Bahaei, M. 2020. Throughput Improvement by Mode Selection in Hybrid Duplex Wireless Networks. Wireless Networks. 26, p. 3687–3699. https://doi.org/10.1007/s11276-020-02286-3
New Reconstructed Database for Cost Reduction in Indoor Fingerprinting Localization
Moghatdaiee, V., Ghorashi, S. and Ghavami, G. 2019. New Reconstructed Database for Cost Reduction in Indoor Fingerprinting Localization. IEEE Access. 7, pp. 104462-104477. https://doi.org/10.1109/ACCESS.2019.2932024