Blood Sugar Level Indication Through Chewing and Swallowing from Acoustic MEMS Sensor and Deep Learning Algorithm for Diabetic Management

Kumari, Supriya; Mathana, J.M.

doi:10.1007/s10916-018-1115-2

Cited by 60 publications

(9 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With time, the concept of Microelectromechanical Systems (MEMS) has developed in a much easier manner to create a miniaturised version of the sensing prototypes using the microfabrication technique. The usage of MEMS-based sensors has, with time, broadened to a wide range of applications [4,5,6], including different kinds of alloys and pure material [7,8,9]. Among the different kinds of MEMS-based sensors, silicon sensors have always been crucial [10,11] for quick and efficient sensing purposes.…”

Section: Introductionmentioning

confidence: 99%

Silicon-Based Sensors for Biomedical Applications: A Review

Kundu

et al. 2019

Sensors

107

View full text Add to dashboard Cite

The paper highlights some of the significant works done in the field of medical and biomedical sensing using silicon-based technology. The use of silicon sensors is one of the pivotal and prolonged techniques employed in a range of healthcare, industrial and environmental applications by virtue of its distinct advantages over other counterparts in Microelectromechanical systems (MEMS) technology. Among them, the sensors for biomedical applications are one of the most significant ones, which not only assist in improving the quality of human life but also help in the field of microfabrication by imparting knowledge about how to develop enhanced multifunctional sensing prototypes. The paper emphasises the use of silicon, in different forms, to fabricate electrodes and substrates for the sensors that are to be used for biomedical sensing. The electrical conductivity and the mechanical flexibility of silicon vary to a large extent depending on its use in developing prototypes. The article also explains some of the bottlenecks that need to be dealt with in the current scenario, along with some possible remedies. Finally, a brief market survey is given to estimate a probable increase in the usage of silicon in developing a variety of biomedical prototypes in the upcoming years.

show abstract

Section: Introductionmentioning

confidence: 99%

Silicon-Based Sensors for Biomedical Applications: A Review

Kundu

et al. 2019

Sensors

107

View full text Add to dashboard Cite

show abstract

“…Such types of sensors cannot capture both mechanical and acoustic aspects of MA signals simultaneously, with high fidelity. Compact, skin-mounted accelerometers and/or gyroscopes based on microelectromechanical systems (MEMS) offer important capabilities in this context, with demonstrated examples in capturing signatures of cardiac mechanics such as seismocardiograms or ballistocardiograms [11][12][13][14] , respiratory rate and sounds [15][16][17][18][19][20][21] , sounds of swallowing [22][23][24][25] , vocals 26,27 , changes in body position and motion [28][29][30] and others 31 . Certain of these measurements have direct relevance to medical applications, particularly when implemented in devices that monitor multiple physiological signals 1,3,32 .…”

mentioning

confidence: 99%

Mechano-acoustic sensing of physiological processes and body motions via a soft wireless device placed at the suprasternal notch

et al. 2019

View full text Add to dashboard Cite

Skin-mounted soft electronics incorporating high-bandwidth triaxial accelerometers can provide broad classes of physiologically relevant information, such as mechanoacoustic signatures of underlying body processes (such as those captured by a stethoscope) and precision kinematics of core body motions. Here, we describe a wireless device designed to be conformally placed on the suprasternal notch for the continuous measurement of mechanoacoustic signals, from subtle vibrations of the skin at accelerations of ~10 −3 m•s −2 to large motions of the entire body at ~10 m•s −2 , and at frequencies up to ~800 Hz. Because th measurements are a complex superposition of signals that arise from locomotion, body orientation, swallowing, respiration, cardiac activity, vocal-fold vibrations and other sources, we used frequency-domain analysis and machine learning to obtain, from human subjects during natural daily activities and exercise, real-time recordings of heart rate, respiration rate, energy intensity and other essential vital signs, as well as talking time and cadence, swallow counts and patterns, and other unconventional biomarkers. We also used the device in sleep laboratories, and validated the measurements via polysomnography. Natural processes of the human body yield a multitude of mechano-acoustic (MA) signals, many of which strongly attenuate at the skin-air interface 1-5. Motions with amplitudes and Lee et al.

show abstract

“…The larger particle size results in less starch hydrolysis, suggesting that the lesser the breakdown, the lower the susceptibility to amylase (43) . Rapid consumption without proper chewing results in an increased glycaemic response (44) . This may be because rapid consumption may result in a large volume of food ingestion whereas wellchewed food can decrease food intake by one third; also, when bite sizes are large, oral processing time is less and vice versa (45) .…”

Section: Oral Phasementioning

confidence: 99%

Determining the glycaemic responses of foods: conventional and emerging approaches

2021

View full text Add to dashboard Cite

A low-glycemic diet is crucial for those with diabetes and cardiovascular diseases. Information on the glycemic index (GI) of different ingredients can help in designing novel food products for such target groups. This is because of the intricate dependency of material source, composition, food structure, and processing conditions, among other factors, on the glycemic responses. Different approaches have been used to predict the GI of foods, certain discrepancies exist because of factors including the inter-individual variation among human subjects. Besides other aspects, it is important to understand the mechanism of food digestion because an approach to predict GI must essentially mimic the complex processes in the human gastrointestinal tract. The focus of this work is to review the advances in various approaches for predicting the glycemic responses of foods. This has been explained by detailing conventional approaches, their merits and limitations, and the need to focus on emerging approaches. Given the fact that no single approach can be generalized for all applications, the review emphasizes the scope of deriving insights for improvements in methodologies. Reviewing the conventional and emerging approaches for the determination of GI in foods, this detailed work is intended to serve as a state-of-the-art resource for food and nutritionists who work on developing low GI foods.

show abstract

Blood Sugar Level Indication Through Chewing and Swallowing from Acoustic MEMS Sensor and Deep Learning Algorithm for Diabetic Management

Cited by 60 publications

References 14 publications

Silicon-Based Sensors for Biomedical Applications: A Review

Silicon-Based Sensors for Biomedical Applications: A Review

Mechano-acoustic sensing of physiological processes and body motions via a soft wireless device placed at the suprasternal notch

Determining the glycaemic responses of foods: conventional and emerging approaches

Contact Info

Product

Resources

About