A cognitive-automated ingestive behavior and physical activity monitoring system using IoT

Main Article Content

V P Jayachitra
Mathangi M


Neural Network, Discrimination of Saliva, Swallowing detection, Chewing analysis, Calorie detection


Background and aim: To have a healthy lifestyle and to reduce the risk of chronic diseases, a fully balanced diet with enough quantity of nutrients is required. Maintaining the required levels of consumption of food and regularity in eating habits is important for preserving a healthy life and live without any health-related diseases. In regards to the above statement, the proposed work has been defined to provide novel smart dietary solutions and to monitor and detect the nutrition intake each day. Methods: Comfortable sensors are worn, used to record the observations in the form of signals during the consumption of foods. The data are pre-processed, and models are proposed to identify eating bouts and swallowing events, using the extracted features. The human body also needs physical movements which are recognized from an accelerometer to analyze the physical behavior. On the aggregation of both the eating and physical activity analyses, this paper proposes to monitor the ingestive habits and physical behavior related to health. Results: The detection of chewing occurrences was classified by RMWC, obtaining an accuracy of 97% while the determination of swallowing sounds to obtain accurate chewing rate, was performed by the proposed Temporally Efficient Bidirectional (TEB) algorithm attaining a higher accuracy of 97.51%. Conclusions: In this paper, misclassification of saliva from normal swallowing has been overcome. On the contrary, physical activities have been determined by constructing a hierarchy of clusters. Thus, the proposed paradigm determines the ingestive behavior and the energy balance by generating the daily report for the user in an effective way.

Abstract 54 | PDF Downloads 36


[1] Farooq M, Sazonov E. Accelerometer-Based Detection of Food Intake in Free-Living Individuals. IEEE Sens J. 2018;18(9):3752-3758.
[2] Hassan E A, Elbially M S, Morsy A A. Monitoring and evaluation of ingestive activities. IEEE EMBS Int Conf on BHI. 2018; 21-24.
[3] Delopoulos. A Novel Chewing Detection System Based on PPG, Audio, and Accelerometry. IEEE J of BHI. 2017;21(3):607-618.
[4] Papapanagiotou V, Diou C, Zhou L, et al. The SPLENDID chewing detection challenge. IEEE Int Conf of EMBC. 2017; 817-820.
[5] Bi Y, Lv M, Song C, et al. AutoDietary: A Wearable Acoustic Sensor System for Food Intake Recognition in Daily Life. IEEE Sensors J. 2016;16(3):806-816.
[6] Kalantarian, Haik, Nabil A, et al. Monitoring eating habits using a piezoelectric sensor-based necklace. Comput Biol Med. 2015;58:46-55.
[7] Zhang S, Mccullagh P, Callaghan V. An Efficient Feature Selection Method for Activity Classification. Int Conf on Intelligent Environments. 2014;16-22.
[8] Fontana JM, Sazonov ES. A robust classification scheme for detection of food intake through non-invasive monitoring of chewing. IEEE Int Conf of EMBS. 2012;4891-4894.
[9] Sazonov ES, Makeyev O, Schuckers S, et al. Automatic Detection of Swallowing Events by Acoustical Means for Applications of Monitoring of Ingestive Behavior. IEEE TBME 2010;57(3):626-633.
[10] Patel, Shyamal, Park, et al. A Review of Wearable Sensors and Systems with Application in Rehabilitation. JNER. 2012; 9:21-37.
[11] Fontana JM, Sazonov ES. Evaluation of Chewing and Swallowing Sensors for Monitoring Ingestive Behavior. Sensor letters. 2013;11:560-565.
[12] Migueles JH, Cadenas-Sanchez C, Ekelund U,et al. Accelerometer Data Collection and Processing Criteria to Assess Physical Activity and Other Outcomes: A Systematic Review and Practical Considerations. Sports medicine 2017; 47:1821-1845.
[13] Bujari A, Licar B, Palazzi CE. Road crossing recognition through smartphone's accelerometer. 2011 IFIP WD 2011;1-3.
[14] Martin-Harris, Bonnie, Bronwyn Jones. The videofluorographic swallowing study. Phys Med Rehabil Clin N Am. 2008;19:769-85.
[15] Farooq, Muhammad, Edward Sazonov. A Novel Wearable Device for Food Intake and Physical Activity Recognition. Sensors. 2017;16(7):1067-1079.
[16] Arnin J, Anopas D, Triponyuwasin P, Yamsa-ard T, Wongsawat Y. Development of a novel classification and calculation algorithm for physical activity monitoring and its application. APSIPA. 2014;1-4.
[17] Chen KY, Sun M. Improving energy expenditure estimation by using a triaxial accelerometer. J Appl Physiol. 1998;83(6):2112-2122.
[18] Altini M, Penders J, Vullers R, Amft O. Estimating Energy Expenditure Using Body-Worn Accelerometers: A Comparison of Methods, Sensors Number and Positioning. IEEE J of BHI. 2015;19(1):219-226.
[19] Rauh A, Arce GR. A fast weighted median algorithm based on Quickselect. IEEE Int Conf on Image Processing. 2010;105-108.
[20] Kobayashi H, Yoshifumi M. Distribution characteristics of salivary cortisol measurements in a healthy young male population. J Physiol Anthropol. 2015;34:30-33.
[21] Cai J, Luo J, Wang S, Yang S. Feature selection in machine learning: A new perspective. Neurocomputing. 2018;300:70-79.
[22] Sejdic E, Malandraki GA, Coyle JL. Computational Deglutition: Using Signal- and Image-Processing Methods to Understand Swallowing and Associated Disorders. IEEE Signal Process Mag. 2019;36(1): 138-146.
[23] Voicu RA, Dobre C, Bajenaru L, Ciobanu RI. Human Physical Activity Recognition Using Smartphone Sensors. Sensors. 2019;19(3):458-476.
[24] Jayatilake D, Ueno T, Teramoto Y, et al. Smartphone-Based Real-time Assessment of Swallowing Ability From the Swallowing Sound. IEEE JTEHM. 2015;3:1-10.
[25] Rajesh R, Baranilingesan I. Tilt Angle Detector Using 3-Axis Accelerometer. IJSRST. 2018;4(2): 784-791.
[26] Gjoreski H, Gams M. Accelerometer Data Preparation for Activity Recognition. International Multiconference Information Society. 2011;1014
[27] Zhang R, Oliver A. Retrieval and Timing Performance of Chewing-Based Eating Event Detection in Wearable Sensors. Sensors. 2020; 20(2):557-573.
[28] Santoso LF, Baqai F, Gwozdz ML, et al. Applying Machine Learning Algorithms for Automatic Detection of Swallowing from Sound. Int Conf of the IEEE EMBC.2019;2584-2588.
[29] Papapanagiotou V, Diou C, Delopoulos A. Chewing detection from an in-ear microphone using convolutional neural networks. Int Conf of the IEEE EMBC.2017;1258-1261.
[30] Weber JL, Reid PM, Greaves KA, et al. Validity of self reported energy intake in lean and obese young women, using two nutrient databases, compared with total energy expenditure assessed by doubly labeled water. Eur J Clin Nutr. 2001;55:940–950.
[31] Papapanagiotou V, Diou C, Lingchuan Z, et al. Fractal Nature of Chewing Sounds. ICIAP Workshops. 2015; 401-408.
[32] Borvornparadorn M, Sapampai V, Champakerdsap C, Kurupakorn W, Sapwarobol S. Increased chewing reduces energy intake, but not postprandial glucose and insulin, in healthy weight and overweight young adults. Nutrition & dietetics. 2019; 76:89–94.
[33] Selamat NA, Ali SHM. Automatic Food Intake Monitoring Based on Chewing Activity: A Survey. IEEE Access. 2020; 8:48846-48869.
[34] Shengjie B, Caine K, Halter R, et al. Auracle: Detecting Eating Episodes with an Ear-mounted Sensor. Proceedings of the ACM on IMWUT. 2018;2:1-27.
[35] MET values for 800+ Activities. ProCon.org. Access: https://golf.procon.org/met-values-for-800-activities/.
[36] USDA Nutrient Database for Standard Reference (SR). FoodData Central (FDC). Access: https://fdc.nal.usda.gov/.