Food Recognition System: A New Approach Based on Wavelet-LSTM
DOI:
https://doi.org/10.30537/sjet.v6i1.1258Keywords:
Food recognition, Signal segmentation, Wearable sensors, Signal processingAbstract
An automated system for analyzing daily dietary intake is essential for human well-being and healthcare. This work presents a novel wearable necklace embedded with a piezoelectric sensor and a microcontroller to monitor food ingestion of users. To effectively represent the food ingestion patterns, the sensor signal is dynamically segmented using a bidirectional search technique. Each segmented food intake pattern consists of a chewing sequence and a swallow peak. We exploit wavelet transform to decompose the complex food ingestion patterns, collected by the sensor, into frequency sub-bands at discrete scales. The frequency sub-bands are used as sequences to train long short-term memory (LSTM) for the recognition of 5 food categories. Our proposed recognition model based on wavelet-LSTM recognizes 5 food classes with an accuracy of 98.1%
Downloads
References
: Shaikh, Mohsin, et al. "Open-source electronic health record systems: A systematic review of most recent advances." Health Informatics Journal 28.2 (2022): 14604582221099828.
: Hussain, G., et al. ‘Food intake detection and classification using a necklace-type piezoelectric wearable sensor system,’ IEICE TRANS. on Inform. and Syst., 2018, 101, (11), pp. 2795–2807.
: Alshurafa, N., et al. ‘Recognition of nutrition intake using time-frequency decomposition in a wearable necklace using a piezoelectric sensor,’ IEEE Sensors Journal, 2015, 15, (7), pp. 3909–3916.
: Alonso-Arévalo MA, Cruz-Gutiérrez A, Ibarra-Hernández RF, García-Canseco E, Conte-Galván R. Robust heart sound segmentation based on spectral change detection and genetic algorithms. Biomedical Signal Processing and Control. 2021 Jan 1;63:102208.
: Hussain G, Javed K, Cho J, Yi J. Food intake detection and classification using a necklace-type piezoelectric wearable sensor system. IEICE TRANSACTIONS on Information and Systems. 2018 Nov 1;101(11):2795-807.
: Cho HJ, Hussain G, Park JH, Kim JH, Cho JD. Visual fatigue measurement model based on multi-area variance in a stereoscopy. In2016 18th International Conference on Advanced Communication Technology (ICACT) 2016 Jan 31 (pp. 814-817). IEEE.
: West N, Roy T, O'Shea T. Wideband signal localization with spectral segmentation. arXiv preprint arXiv:2110.00583. 2021 Oct 1.
: Al-Rawi M, Materka A. Voiced/Unvoiced Speech Signal Segmentation Using Wavelet Analysis. Computational Intelligence and Applications. 1999;23:85.
: Fearnhead P. Exact Bayesian curve fitting and signal segmentation. IEEE Transactions on Signal Processing. 2005 May 23;53(6):2160-6.
: Saadatnejad, S., et al. ‘LSTM-Based ECG Classification for Continuous Monitoring on Personal Wearable Devices,’ IEEE jour. of bio. and health infor, (2019).
: Hussain, G., et al. ‘Indoor Positioning System: A New Approach Based on LSTM and Two Stage Activity Classification,’ Electronics, 2019, 8, (4), pp. 375.
: Shaikh, Mohsin, Ki-Seong Lee, and Chan-Gun Lee. "Assessing the Bug-Prediction with Re-Usability Based Package Organization for Object Oriented Software Systems." IEICE TRANSACTIONS on Information and Systems 100.1 (2017): 107-117.
: Shaikh, Mohsin, and Chan-Gun Lee. "Aspect Oriented Re-engineering of Legacy Software Using Cross -Cutting Concern Characterization and Significant Code Smells Detection." International Journal of Software Engineering and Knowledge Engineering 26.03 (2016): 513-536.
Downloads
Published
Issue
Section
License
Copyright (c) 2023 Sukkur IBA Journal of Emerging Technologies
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
The SJET holds the rights of all the published papers. Authors are required to transfer copyrights to journal to make sure that the paper is solely published in SJET, however, authors and readers can freely read, download, copy, distribute, print, search, or link to the full texts of its articles and to use them for any other lawful purpose.
The SJET is licensed under Creative Commons Attribution-NonCommercial 4.0 International License.
