Design and Development of Android Application for Recognition of Nutrition Intake Using Piezoelectric Sensor- A Review

Published on December 2016 | Categories: Documents | Downloads: 21 | Comments: 0 | Views: 112
of 2
Download PDF   Embed   Report

Factors such as food consumption levels, water intake, ingestion rate, and diet affect weight and resulted to overweight. A non-invasive monitoring of swallowing method is developed to study ingestive behavior. In this paper we have taken review of this method and proposed a system which recognize nutrition intake using piezoelectric sensor. Sensor detects swallows (skin motion) and gives output voltage. The sensor output is then transmitted to mobile. Android application is developed to analyze sensor output and classify food types also provides feedback to the user to control their food habits.

Comments

Content

IJSRD - International Journal for Scientific Research & Development| Vol. 3, Issue 12, 2016 | ISSN (online): 2321-0613

Design and Development of Android Application for Recognition of
Nutrition in Take using Piezoelectric Sensor – A Review
Ms.S.P.Shinde1 Mr.U.A.Bombale2
1,2
Department of Technology
1,2
Shivaji University, Kolhapur. India (MS)
Abstract— Factors such as food consumption levels, water
intake, ingestion rate, and diet affect weight and resulted to
overweight. A non-invasive monitoring of swallowing
method is developed to study ingestive behavior. In this
paper we have taken review of this method and proposed a
system which recognize nutrition intake using piezoelectric
sensor. Sensor detects swallows (skin motion) and gives
output voltage. The sensor output is then transmitted to
mobile. Android application is developed to analyze sensor
output and classify food types also provides feedback to the
user to control their food habits.
Key words: Piezoelectric sensor, ARM, Andriod
Application
I. INTRODUCTION
Rate of ingestion, hydration, levels of food intake, and
regular diet choices these factors responsible for the risk of
overweight. Appropriate levels of food intake and
maintaining regularity in eating habits is important to weight
loss and gives healthy lifestyle. Eating healthy diet can lead
to better physique, so one can feel his appearance , which
can boost his confidence and self-esteem this project
presents device which is capable of detecting individuals
eating pattern and determining appropriate health
recommendations for the user.
Current technologies for eating pattern detection
has these shortcomings, they infer eating indirectly from, for
example, hand movements or food images [11]; they require
manual data entry or user involvement in capturing data or
they are non-wearable, bulky, invasive, or semi-invasive.
There is a need for a system that is noninvasive and
detects individual’s eating patterns, and provides necessary
guidance to the user (see Figure 1). Recognition of Nutrition
Intake using a Piezoelectric Sensor was released in April
2015, and it presents the opportunity for a new way of
recognizing nutrition intake.
Piezoelectric sensor is a device that measures
changes in pressure, strain, temperature or force by
converting them into electrical signal. here it is used to
detect throat motion. Controller is used to convert sensor
data to digital signal and send it to mobile with Bluetooth
technology. Bluetooth is low cost wireless technology
developed to share data between paired devices. Mobiles has
become necessity in human being life. A mobile phone
covers maximum time of human daily life. Great software
applications provide novel services designed for mobile
phones.

Fig. 1:
Fig 1. System provides necessary guidance to the user’s
mobile like some common bad eating habits include eating
too fast, skipping meals, not eating enough, and being
dehydrated.
In this project a monitoring of food intake can be
done, motion in throat is captured by piezoelectric sensor
which is capable of detecting skin motion. Piezoelectric
sensor in the lower trachea is important to detect food intake
during ingestion.
The senor data is transmitting from controller to a
Smartphone, application can be developed which performs
the processing of the signals, classifies the food type with
feature selection and classification algorithm, and provides
data to the user to assist the user in monitoring their eating
habits. The throat motion generates an output voltage with
varying frequencies over time. An algorithm based on timefrequency decomposition, spectrogram analysis of
piezoelectric sensor signals is used to classify food types
such as liquid and solid, hot and cold and hard and soft
foods. We can compare our spectrogram analysis with other
time-frequency features. And extracting key features gives
unique swallow patterns of various foods.
II. LITERATURE SURVEY
There are various sensors which can be used to identify the
volume of food being consumed. The most popular method
is acoustic detection [4]. In this type of system, system
identifies chewing and swallowing. a microphone is placed
near the throat, and signal processing techniques are used
for classification.
The proposed system, Sazanov et al. [9]. In this
acoustic data taken from a small microphone placed near the
bottom of the throat. Also, their system is coupled with a
strain gauge placed near the ear but it is not practical for

All rights reserved by www.ijsrd.com

1000

Design and Development of Android Application for Recognition of Nutrition in Take using Piezoelectric Sensor – A Review
(IJSRD/Vol. 3/Issue 12/2016/263)

daily use. Another similar system, Nagae et al. [9] attempts
to distinguish between swallowing, coughing, and
vocalization using wavelet transform analysis of audio data.
Though results are good but this technology is given for
those who suffer from dysphasia, and identifying the volume
or characteristic of food intake is not the focus of their work.
Another approach presented by Aboofazeli et al. [2] such as
feed forward neural network classifier for acoustic swallow
detection, achieving basic classification between swallows
and breath sounds. Makayev et al. apply spectrograms for
swallow detection using machine learning algorithms [6],
here also only swallows are identified however no
classification is done.
Therefore, acoustic detection method of food intake
is good, but there are so many serious drawbacks such as a
lack of uniformity between individual eating styles, the
interference of background noise and no work is done for
validating classification between different types of food.
Other works place electrodes on the neck and
perform an EMG to identify deglutition, but the hardware
cannot be not easily handled and the system is limited to a
clinical environment [5].
Some other methods have been also used for
detecting swallows. The proposed system Amft et al. [3]
uses arm gestures identification to perform detection of
eating and drinking. Associated arm gestures identified
using accelerometers and gyroscopes. For example, the use
of cutlery, spoon, hand, and cup can be identified based on
the gestures associated with food intake using these objects.
However, the eating style may change from person to
person. Eating style does not necessarily useful to identify
the volume of food intake; this limits the usefulness of this
system.
Nabil Alshurafa[1].In this system, classification
performed by using a piezoelectric sensor placed around the
neck using features extracted in the time domain to
spectrogram-based approach that considers time and
frequency-based components. A spectrogram frequently
used for frequently speech recognition. The application of
spectrograms is done for analysis of piezoelectric sensor
data for detection and classification of food ingestion. In this
system features on a spectrogram of swallows are used to
distinguish solid and liquid foods.
III. CONCLUSION
This paper has reviewed the methods for detection of
swallows. Some drawbacks are there in these methods such
as accuracy for detection of swallows is less, less
classification of food types, or must be tightly wear around
the neck so its continuous use is not practical. Our system
uses piezoelectric sensor which can be loosely worn around
neck. This system classifies various Indian food
types,differentiate between solid and liquid foods as well as
reports the user about what they consumed also helps to
control their eating habits.
REFERENCES
[1] Nabil Alshurafa, haik kalatarian, mohammad
pourhomayoun. Rcognition of nutrition intake using
time –frequency decomposition in a wearable necklace
using piezoelectric sensor.

[2] Aboofazeli, M., and Moussavi, Z. Automated
classification of swallowing and breadth sounds. In
Engineering in Medicine and Biology Society, 2004.
IEMBS ’04. 26th Annual International Conference of
the IEEE, vol. 2 (Sept 2004), 3816–3819.
[3] Amft, O., Junker, H., and Troster, G. Detection of
eating and drinking arm gestures using inertial bodyworn sensors. In Wearable Computers, 2005.
Proceedings. Ninth IEEE International Symposium on
(Oct 2005), 160–163
[4] Kalantarian, H., Alshurafa, N., Pourhomayoun, M.,
Sarin, S., Le, T., and Sarrafzadeh, M. Spectrogrambased audio classification of nutrition intake. In IEEE
EMBS Healthcare Innovations & Point of Care
Technologies (HIPT) (2014).
[5] Limdi, A., McCutcheon, M., Taub, E., Whitehead, W.,
and Cook, E.W., I. Design of a microcontroller-based
device for deglutition detection and biofeedback. In
Engineering in Medicine and Biology Society, 1989.
Images of the Twenty-First Century., Proceedings of
the Annual International Conference of the IEEE
Engineering in (Nov 1989), 1393–1394 vol.5.
[6] Makeyev, O., Sazonov, E., Schuckers, S., LopezMeyer, P., Baidyk, T., Melanson, E., and Neuman, M.
Recognition of swallowing sounds using timefrequency decomposition and limited receptive area
neural classifier. In Applications and Innovations in
Intelligent Systems XVI, T. Allen, R. Ellis, and M.
Petridis, Eds. Springer London, 2009, 33–46.
[7] Nagae, M., and Suzuki, K. A neck mounted interface
for sensing the swallowing activity based on
swallowing sound. In Engineering in Medicine and
Biology Society,EMBC, 2011 Annual International
Conference of the IEEE (Aug 2011), 5224–5227.
[8] Savitzky, A., and Golay, M. J. E. Smoothing and
differentiation of data by simplified least squares
procedures. Analytical Chemistry 36, 8 (1964), 1627–
1639.
[9] Sazonov, E., and Fontana, J. A sensor system for
automatic detection of food intake through non-invasive
monitoring of chewing. Sensors Journal, IEEE 12, 5
(May 2012), 1340–1348.
[10] Sussillo, D., Kundaje, A., and Anastassiou, D.
Spectrogram analysis of genomes. EURASIP J. Appl.
Signal Process. 2004 (Jan. 2004), 29–42. Student sign
Guide sign
[11] Yao, N., Sclabassi, R., Liu, Q., and Sun, M. A videobased algorithm for food intake estimation in the study
of obesity. In Bioengineering Conference, 2007. NEBC
’07. IEEE 33rd Annual Northeast (March 2007), 298–
299.
[12] Kalantarian, H., Alshurafa, N., and Sarrafzadeh, M. A
wearable nutrition monitoring system. In IEEE Body
Sensor Networks (2014).
[13] Klap, T., and Shinar, Z. Using piezoelectric sensor for
continuouscontact- free monitoring of heart and
respiration rates in real-life hospital settings. In
Computing in Cardiology Conference (CinC), 2013
(Sept 2013), 671–674.

All rights reserved by www.ijsrd.com

1001

Sponsor Documents

Or use your account on DocShare.tips

Hide

Forgot your password?

Or register your new account on DocShare.tips

Hide

Lost your password? Please enter your email address. You will receive a link to create a new password.

Back to log-in

Close