Food Recognition System: A New Approach Based on Wavelet-LSTM
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,...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sukkur IBA University
2023-07-01
|
| Series: | Sukkur IBA Journal of Emerging Technologies |
| Subjects: | |
| Online Access: | http://sjcmss.iba-suk.edu.pk:8089/SIBAJournals/index.php/sjet/article/view/1258 |
| _version_ | 1797783946102046720 |
|---|---|
| author | Ghulam Hussain |
| author_facet | Ghulam Hussain |
| author_sort | Ghulam Hussain |
| collection | DOAJ |
| description |
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%
|
| first_indexed | 2024-03-13T00:33:06Z |
| format | Article |
| id | doaj.art-96341e41c0a8486ebc786a3fd9283a9b |
| institution | Directory Open Access Journal |
| issn | 2616-7069 2617-3115 |
| language | English |
| last_indexed | 2024-03-13T00:33:06Z |
| publishDate | 2023-07-01 |
| publisher | Sukkur IBA University |
| record_format | Article |
| series | Sukkur IBA Journal of Emerging Technologies |
| spelling | doaj.art-96341e41c0a8486ebc786a3fd9283a9b2023-07-10T09:15:03ZengSukkur IBA UniversitySukkur IBA Journal of Emerging Technologies2616-70692617-31152023-07-016110.30537/sjet.v6i1.1258Food Recognition System: A New Approach Based on Wavelet-LSTM Ghulam Hussain0Electronic Engneering, Quaid-e-Awam University, Larkana 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% http://sjcmss.iba-suk.edu.pk:8089/SIBAJournals/index.php/sjet/article/view/1258Food recognition, Signal segmentation, Wearable sensors, Signal processing |
| spellingShingle | Ghulam Hussain Food Recognition System: A New Approach Based on Wavelet-LSTM Sukkur IBA Journal of Emerging Technologies Food recognition, Signal segmentation, Wearable sensors, Signal processing |
| title | Food Recognition System: A New Approach Based on Wavelet-LSTM |
| title_full | Food Recognition System: A New Approach Based on Wavelet-LSTM |
| title_fullStr | Food Recognition System: A New Approach Based on Wavelet-LSTM |
| title_full_unstemmed | Food Recognition System: A New Approach Based on Wavelet-LSTM |
| title_short | Food Recognition System: A New Approach Based on Wavelet-LSTM |
| title_sort | food recognition system a new approach based on wavelet lstm |
| topic | Food recognition, Signal segmentation, Wearable sensors, Signal processing |
| url | http://sjcmss.iba-suk.edu.pk:8089/SIBAJournals/index.php/sjet/article/view/1258 |
| work_keys_str_mv | AT ghulamhussain foodrecognitionsystemanewapproachbasedonwaveletlstm |