Gel Biter: food texture discriminator based on physical reservoir computing with multiple soft materials
Authors: 
Kosuke Hirose, Ikuma Sudo, Jun Ogawa, Yosuke Watanabe, M. D. Nahin Islam Shiblee, Ajit Khosla, Masaru Kawakami, Hidemitsu FurukawaAuthors Info & Claims
Pages 674 - 683
Abstract
The human oral structure contains organs with distinctly different physical properties, such as teeth, gums, and tongues. When food enters the oral cavity, we can recognize the tactile sensation and shape of the object from multiple perspectives through the texture of the teeth and tongue. Therefore, it is possible to regard oral structures as a group of tactile sensors based on these functions. In this study, we developed a soft-matter artificial mouth that can accurately detect subtle differences in texture by creating and combining oral structural organs using polymer materials with different physical properties and mounting them as end-effectors for a robot arm. The same piezoelectric film sensor was embedded inside each organ, making it possible to acquire tactile sensations from the same object as completely different signal waveforms. We tested whether the sensor data obtained from each soft-matter material could be used for excellent object recognition by applying various machine learning methods. In an actual experiment, we learned the waveform data obtained from chewing sweets and snacks, such as rice crackers, and applied machine learning to classify the data, which led to an accuracy rate of over 90%.
References
[1]
Keisuke H, Ezu K, Yasuo M, Masako H, Kaori K, Youko N, Akiko N (2004) Influence of the nutritional consciousness and knowledge of dietary on the eating habits in life span. Faculty of Education, Wakayama University Minutes. Natural Sciences, pp 53–61
[2]
Kaori K and Kazuya M Awareness structure of university students affecting eating behavior J Jpn Soc Shokuiku 2021 14 2 115-122
[3]
Masahiko I and Yuki H Texture technology Inst J Image Inf Telev 2007 61 10 1424-1426
[4]
Li X, Tsuta M, Hayakawa F, Nakano Y, Kazami Y, and Ikehata A Estimating the sensory qualities of tomatoes using visible and near-infrared spectroscopy and interpretation based on gas chromatography-mass spectrometry metabolomics Food Chem 2021 343 128470
[5]
Tae S and Yoshihiro M Objective evaluation of crispy and crunchy texture of foods by acoustic analysis Jpn Oil Chem Soc 2020 20 11 25-30
[6]
Naoya K, Hidekazu T, Yuji U, and Masahiko I Chewing JOCKEY-designing user interface to augment food texture with sound AR system Trans Virtual Real Soc Jpn 2013 18 2 141-150
[7]
Aika M, Tetsuji S (2021) A study on virtual texture presentation technique using muscle potential-based texture classification and electrical muscle stimulation. DEIM Forum C25-3
[8]
Jun T Types and methods of sensory evaluation in food research J Jpn Soc Shokuiku 1994 41 3 1424-1426
[9]
Central Laboratory (2022) Product development using sensory evaluation. Maruha Nichiro Corporation. https://www.maruha-nichiro.co.jp/laboratory/report/report01.html. Accessed 6 May 2022
[10]
Yoshimasa Y Evaluation of food texture J Jpn Soc Shokuiku 1994 41 3 218-223
[11]
Shimadzu Corporation (2022) Texture evaluation. https://www.an.shimadzu.co.jp/apl/food/texture.htm. Accessed 6 May 2022
[12]
Shunsuke Y, Makoto T (2020) Food texture analysis based on machine learning. In: The 34th annual conference of the Japanese society for artificial intelligence
[13]
Ikuma S, Jun O, Yosuke W, Shiblee NI, Ajit K, Masaru K, and Hidemitsu F Local discrimination based on piezoelectric sensing in robots composed of soft matter with different physical properties J Robot Mech 2022 34 2 339-350
[14]
Gouhei T, Ryousyo N, Akira H (2021) Reservoir computing—theory and hardware of fast machine learning for time series pattern recognition. Morikita Publishing Co
[15]
Gouhei T Concept of reservoir computing and its recent trends J Inst Electron Inf Commun Eng 2019 102 2 108-113
[16]
Chrisantha F, Sampsa S (2003) Pattern recognition in a bucket. In: European conference on artificial life. Springer, Berlin, pp 588–597
[17]
Lennert A, Miguel CS, Van der Guy S, Jan D, Serge M, Joni D, Benjamin S, Claudio MR, Ingo F (2011) Information processing using a single dynamical node as a complex system. Nat Commun
[18]
Atsushi U (2019) Progress in fast physical random number generation with complex photonics. In: Department of Information and Computer Sciences, vol 47(6)
[19]
der Sande V, Guy BD, and Soriano MC Advances in photonic reservoir computing Nanophotonics 2017 6 3 561-576
[20]
Daniel B, Miguel SC, Van der Guy S (2019) Photonic reservoir computing: optical recurrent neural networks. Walter de Gruyter GmbH & Co KG
[21]
Laurent L, Soriano MC, Brunner D, Appeltant L, Gutierrez JM, Peaquera L, Mirasso CR, and Fischer I Photonic information processing beyond turing: an optoelectronic implementation of reservoir computing Opt Express 2012 20 3 3241-3249
[22]
Paquot Y, Duport F, Smerieri A, Dambre J, Schrauwen B, Haelterman M, and Massar S Optoelectronic reservoir computing Sci Rep 2012 2 287
[23]
Yoshihiro T (2017) Vibration-related skin characteristics, tactile perception, and motion characteristics. J Soc Biomech 41(1)
[24]
Hiroyasu Y, Ryosuke K, Yoshinori T, Akihito H, and Akira H Self-assembly of gels through molecular recognition of cyclodextrins: shape selectivity for linear and cyclic guest molecules Macromolecules 2011 44 2395-2399
[25]
Takaaki K (2021) Physical contact soft matter interactive device that relies on the flexibility of the material. Master’s thesis, pp 8–70
[26]
Takaaki K (2021) Physical contact soft matter interactive device that relies on the flexibility of the material. Master’s thesis, pp 8–70
[27]
Tanaka Yoshihiro (2017) “Vibration-related skin characteristics, tactile perception, and motion characteristics,” Journal of the Society of Biomechanisms, vol.41, no.1
[28]
Takayoshi Y and Hironobu F Efficient features for object recognition IEICE 2008 108 328 221-236
[29]
Maximilian C and Julius NB Time series feature extraction on basis of scalable hypothesis tests (tsfresh—A Python package) Neurocomputing 2018 307 72-77
[30]
Takashi O (2008) Support vector machine overview. Trans Oper Res Soc Jpn 225–230
[31]
Asmita S, Malka HN, Rajasekaran L (2017) Impact of different data types on classifier performance of random forest, Naïve Bayes, and K-nearest neighbors algorithms. Int J Adv Comput Sci Appl 8(12)
[32]
Hitoshi H Fundamentals and recent trends in Random Forest J Inst Image Inf Telev Eng 2016 70 5 788-791
Index Terms
- Gel Biter: food texture discriminator based on physical reservoir computing with multiple soft materials
Index terms have been assigned to the content through auto-classification.
Recommendations
Does the Gel Biter create an illusion of food texture perception due to differences in mastication speed ?
AbstractOne of the new computational frameworks is physical reservoir computing. Focusing on this method, we have previously developed a soft-matter artificial mouth ”Gel Biter”, which is composed of multiple polymeric materials based on the structure of ...
Virtual food texture by electrical muscle stimulation
ISWC '16: Proceedings of the 2016 ACM International Symposium on Wearable ComputersWe have previously proposed a novel method to present virtual food texture by using electrical muscle stimulation (EMS) to the masseter muscle, which is one of the muscles of mastication. Our system is "Electric Food Texture System" consisting of "bite ...
Study on Control Method of Virtual Food Texture by Electrical Muscle Stimulation
UIST '16 Adjunct: Adjunct Proceedings of the 29th Annual ACM Symposium on User Interface Software and TechnologyWe propose Electric Food Texture System, which can present virtual food texture such as hardness and elasticity by electrical muscle stimulation (EMS) to the masseter muscle. In our previous study, we investigated the feasibility to detect user's bite ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
© The Author(s) 2022.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 01 November 2022
Accepted: 01 October 2022
Received: 30 May 2022
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 20 Dec 2024