Abstract
Having a conversation during a meal, eating slowly, and chewing are some of the passive weight-loss strategies. Furthermore, detecting eating behaviors such as the number of chewing and the duration of the conversation leads to positive dietary behavior. This paper proposes a method that can accurately quantify eating behavior in a natural meal environment. We used a bone conduction microphone and recorded the dietary sounds of 16 subjects. We manually labeled five eating behaviors, namely chewing, swallowing food, swallowing drink, speaking, and other sounds like noise. We then extracted 75 features from the collected dataset and applied appropriate machine learning algorithms and categorized the eating behaviors. The resulting models of discriminating between chewing and speaking were possible with high F1 score. However, they achieved a lower accuracy in classifying swallowing and other sounds, especially swallowing food and swallowing drink. Furthermore, the machine learning models confused swallowing food and swallowing drink as chewing. Therefore, it is necessary to find features that express better the differences between these three behaviors.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Japan Ministry of Health Labor and Welfare. The National Health and Nutrition Survey in Japan, Heisei 29. https://www.mhlw.go.jp/content/10904750/000351576.pdf
Kanazawa Medical Association. About chewing. http://www.kma.jp/ishikai/ishikai_0062.html
Ando, Y., Hanada, N., Yanagisawa, S.: Does “eating slowly” lead to prevent obesity ? Health Sci. Health Care 8(2), 51–63 (2008)
Kishida, N., Kamimura, Y.: Relationship of conversation during meal and health and dietary life of school children. Jpn. J. Nutr. Diet. 51(1), 23–30 (1993)
Mitsui, H., Ohara, J., Yokokubo, A., Lopez, G.: Method to improve real-time chewing and speaking detection accuracy from bone-conduction sound. Multimed. Distrib. Coop. Mobile Symp. 2018(2018), 562–566 (2018)
Zhang, R., Bernhart, S., Amft, O.: Diet eyeglasses: recognising food chewing using emg and smart eyeglasses. In: 2016 IEEE 13th International Conference on Wearable and Implantable Body Sensor Networks (BSN), pp. 7–12 (2016)
Chun, K.S., Bhattacharya, S., Thomaz, E.: Detecting eating episodes by tracking jawbone movements with a non-contact wearable sensor. Proc. ACM Interact. Mobile, Wearable Ubiquitous Technol.2(1), 1–21 (2018)
Wang, S., Zhou, G., Ma, Y., Lisha, H., Chen, Z., Chen, Y., Zhao, H., Jung, W.: Eating detection and chews counting through sensing mastication muscle contraction. Smart Health 9, 179–191 (2018)
Bedri, A., Li, D., Khurana, R., Bhuwalka, K., Goel, M.: FitByte: automatic diet monitoring in unconstrained situations using multimodal sensing on eyeglasses. In: Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems, pp. 1–12 (2020)
Amft, O., Stäger, M., Lukowicz, P., Tröster, G.: Analysis of chewing sounds for dietary monitoring. In: International Conference on Ubiquitous Computing, pp. 56–72 (2005)
Bi, S., Wang, T., Tobias, N., Nordrum, J., Wang, S., Halvorsen, G., Sen, S., Peterson, R., Odame, K., Caine, K., et al.: Auracle: detecting eating episodes with an ear-mounted sensor. Proc. ACM Interact. Mobile Wearable Ubiquitous Technol. 2(3), 92 (2018)
Shuzo, M., Komori, S., Takashima, T., Lopez, G., Tatsuta, S., Yanagimoto, S., Warisawa, S., Delaunay, J.-J., Yamada, I.: Wearable eating habit sensing system using internal body sound. J. Adv. Mech. Des. Syst. Manuf. 4(1), 158–166 (2010)
Zhang, H., Lopez, G., Tao, R., Shuzo, M., Delaunay, J.-J., Yamada, I.: Food texture estimation from chewing sound analysis. In: Healthinf, pp. 213–219 (2012)
Mirtchouk, M., Lustig, D., Smith, A., Ching, I., Zheng, M., Kleinberg, S.: (2017). Recognizing Eating from Body-Worn Sensors: Combining Free-living and Laboratory Data. Proc. ACM Interact. Mobile Wearable Ubiquitous Technol. 1(3), Article 85
Kondo, T., Shiro, H., Yokokubo, A., Lopez, G.: Optimized classification model for efficient recognition of meal-related activities in daily life meal environment. In: Proceedings of the 2019 joint 8th International Conference on Informatics, Electronics and Vision (ICIEV) and 3rd International Conference on Imaging, Vision and Pattern Recognition (icIVPR), PP. 146–151 (2019)
Kondo, T., Kamachi, H., Ishii, S., Yokokubo, A., Lopez, G.: Robust classification of eating sound collected in natural meal environment. In: Proceedings of the 2019 ACM International joint Conference on Pervasive and Ubiquitous Computing and 2019 ACM International Symposium on Wearable Computers, pp. 105–108 (2019)
Zhang, H., Lopez, G., Shuzo, M., Delaunay, J.-J., Yamada, I.: Mastication counting method robust to food type and individual. In: Healthinf, pp. 374–377 (2012)
Ando, J., Saito, T., Kawasaki, S., Katagiri, M., Ikeda, D., Mineno, H., Nishimura, M.: Conversation and eating behavior recognition by leveraging throat sound. Multimed. Distrib. Coop. Mobile Symp. 116–123 (2017)
Chawla, N.V., Bowyer, K.W., Hall, L.O., Philip, W., Kegelmeyer.: SMOTE: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357 (2002)
Yang, L., Li, P., Xue, R., Ma, X., Li, X., Wang, Z.: Intelligent classification model for railway signal equipment fault based on SMOTE and ensemble learning. IOP Conf. Ser. Mater. Sci. Eng. 383(1), 012042 (2018)
imblearn.over_sampling.SVMSMOTE. https://imbalanced-learn.readthedocs.io/en/stable/generated/imblearn.over_sampling.SVMSMOTE.html
Muller, A.C., Guido, S.: Introduction to Machine Learning with Python. O’Reily (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Kamachi, H., Kondo, T., Yokokubo, A., Lopez, G. (2021). Classification Method of Eating Behavior by Dietary Sound Collected in Natural Meal Environment. In: Ahad, M.A.R., Inoue, S., Roggen, D., Fujinami, K. (eds) Activity and Behavior Computing. Smart Innovation, Systems and Technologies, vol 204. Springer, Singapore. https://doi.org/10.1007/978-981-15-8944-7_9
Download citation
DOI: https://doi.org/10.1007/978-981-15-8944-7_9
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-8943-0
Online ISBN: 978-981-15-8944-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)