Automatic Ingestion Monitoring Device for Diet Control

 

S. Krishnakumar*, K. Monika, Brite Jose John, Nevin Samuel

Department of Biomedical Engineering, School of Bio and Chemical Engineering, Sathyabama University, Chennai-600119, Tamilnadu, India.

 

ABSTRACT:

Food ingestion is the process of intake of food by human beings through their mouth. The present study mainly focused on maintaining ingestion limit for the intake of food for obese person and intake of extra food for lean person. At every intake of food the device will be enabled and the ingestion is maintained by monitoring the jaw movements using EMG and MEMS sensors. Anorexia nervosa, bulimia nervosa and binge eating are the most common eating disorders that are resistant to most drugs treatment and causes serious physical and mental disorders can be identified by this study. Current methodologies used for food intake analysis largely rely on laboratory studies rather than objective observations. The doubly-labeled water is the most accurate method used to calculate the energy consumed over a period of several days. However, it is not capable of identifying individual for the entire episodes. Thus, new approaches for objective and accurate assessment for free living patterns are necessary for monitoring of eating behaviors. The working principles of hardware device and monitoring can be controlled by both manually and by using LABVIEW software. The data could be transmitting using ZIGBEE software to PC and the details can be viewed on the monitor.

 

 

 

 

INTRODUCTION:

Obesity is a major health problem that affects not only adult population but also adolescents and children. A reduction in life expectancy of individuals with severe obesity is plausible. The rise of obesity and eating disorders has led to new inventions on monitoring and controlling the food intake¹. In the United States, the prevalence of obesity reached a total of 35.5% among adults and 16.9% among adolescents during 2009–2010². On the other hand, eating disorders are serious mental disorders that cause disturbances on eating habits or weight-control behaviour of individuals³.

 

Anorexia nervosa, bulimia nervosa, and binge eating are the most common eating disorders with lifetime prevalence ranging from 0.6% to 4.5% in the United States⁴. Both obesity and eating disorders are medical conditions highly resistant to treatment and can have severe physical and physiological health consequences⁵. Thus, the implementation of accurate methods for monitoring of ingestive behavior (MIB) is critical to provide a suitable assessment of intake particularly in individuals who would most benefit from professional help.

 

Current methodologies used to understand and analyze food intake (FI) patterns associated with obesity and eating disorders largely rely on laboratory studies and on self-report rather than on objective observations^{6, 7}. The doubly-labeled water is the most precise method to measure energy intake over a period of several days; however, it is not capable of identifying individual eating episodes⁸. More recently, rapid advancements of technology in mobile computing, wearable sensors and computer networks have provided the tools to create reliable, objective and non-intrusive systems of monitoring dietary and nutrition habits. Crude approaches that use questionnaires in electronic/digital form (e.g. mobile phone-based logging systems) have given way to more sophisticated methods and systems that do not rely on manual user input, but on measuring specific physiological and behavioural parameters using wearable, and on real-time analysis of the collected data to infer useful and actionable information⁹. Previous approaches for monitoring eating occurrences have been based on audio recordings aiming to detect the distinct sound of food being crushed during each chew¹⁰. Various types of microphones have been used (such as open-air, bone conduction, etc.), usually placed inside the outer ear canal, where such chewing sounds are naturally amplified due to the ear physiology. Other approaches have opted for detecting swallowing sounds, as in based on evidence that the frequency of swallowing occurrences can be used as a detector of snacking events or meals¹¹.  More recently, proximity sensors placed on the head and hands of the subject to detect the hand movement that transfers the food from the plate to the mouth¹².

Usually all these methods of analyzing food ingestion does require laboratories to conduct the tests under certain conditions for a period of time. There is a major drawback in these systems because it is measured on a controlled basis and is not a subjective operation. Thus, new methods for more precise food intake measurements under free living conditions are necessary. In this context the present research has been initiated to measure the ingestion by measuring the jaw movement by using a motion sensor. This analysis helps to limit the food intake for an obese person and also helps to consume extra food for leaned person. The device is enabled at every food intake and the measured values are transmitted to PC from ZIGBEE. The values from PC can be read, displayed and uploaded to the server.

 

MATERIALS AND METHODS:

The microcontroller is the central controlling unit to which all the sensors and other hardware components are connected. The device consists of MEMS sensor, jaw motion sensor, ZIGBEE, ADC, buzzer, UART, voice board and speaker.

 

Fig. 1: Blok diagram of ingestion monitoring device

 

Hardware implementation:

The hardware components that are used for AIM (Automatic Ingestion Monitor) are:

 

LCD:

An LCD IS properly prepared before the character we need, has to be displayed. For this a number of commands have to be provided to the LCD before inputting the required data. The commands will be discussed in the later part of this tutorial. LCD doesn’t know about the content (data or commands) supplied to its data bus. It is the user who has to specify whether the content at its data pins are data or commands.   For this, if a command is inputted then a particular combination of 0s and 1s has to be applied to the Control lines so as to specify it is a Command on the other hand if a data is inputted at the data lines then an another combination of 0s and 1s has to be applied to the control lines to specify the Data.

Microcontroller:

 

Here 2 ports PORT B and PORT C of PIC 16F877A are taken. PORT B is used for providing control signals and PORT C is used for providing Data signals of which pins of PORT B are specified as below.

RB0 RS

RB1 R\W

RB2 E

 

ADC 0808/0809:

 

Fig. 2: ADC0809CCN

 

The ADC0808, ADC0809 data acquisition component is a monolithic CMOS device with an 8-bit analog-to-digital converter, 8-channel multiplexer and microprocessor compatible control logic.

 

General Description:

The ADC0809 data acquisition component is a monolithic CMOS device with an 8-bit analog to digital converter, 8-channel multiplexer and microprocessor compatible control logic. The 8-bit A/D converter uses successive approximation as the conversion technique. The converter features a high impedance chopper stabilized comparator, a 256R voltage divider with analog switch tree and stabilizer. Easy interfacing to microprocessors is provided by the latched and decoded multiplexer address inputs and latched TTL tri-state outputs. The ADC0808, ADC0809 offers high speed, high accuracy, minimal temperature dependence, excellent long term accuracy and repeatability, and consumes minimal power. These features make this device ideally suitable to applications from process and machine control to consumer and automotive applications.

 

Fig. 3: Pin diagram of ADC0808

Multiplexer:

The device contains an 8-channel single-ended analog signal multiplexer. A particular input channel is selected by using the address decoder. The input states for the address lines to select any channel. The address is latched into the decoder on the low-to-high transition of the address latch enable signal. The SAR is reset on the positive edge of START pulse and start the conversion process on the falling edge of START pulse. A conversion process will be interrupted on receipt of new START pulse. The End-Of-Conversion (EOC) will go low between 0 and 8 clock pulses after the positive edge of START pulse. The ADC can be used in continuous conversion mode by tying the EOC output to START input. In ADC conversion process the input analog value is quantized and each quantized analog value will have a unique binary equivalent.

 

BUZZER:

A buzzer is a signaling electronic device typically used in automobiles, household appliances such as a microwave oven. It consists of a number of switches and  sensors connected to a control unit that determines if and which button was pushed or a preset time has lapsed and usually illuminates a light on the appropriate button or control panel and sounds a warning in the form of a continuous or intermittent buzzing sound.

•Rate Frequency: 3,100 Hz

•Operating Voltage: 3-20 Vdc

•Current Consumption: 14mA@12Vdc

•Sound Pressure Level (30cm): 73dB@12Vdc

•King State Buzzer- KPE-200

•Dimensions: 22.5mm Diameter, 19mm High, 29mm between mounting holes

 

UART:

A universal asynchronous receiver/transmitter is a type of "asynchronous receiver/transmitter", a piece of computer hardware that translates data between parallel and serial forms. UARTs are commonly used in conjunction with other communication standards such as EIA RS-232.A UART is usually an individual (or part of an) integrated circuit used for serial communications over a computer or peripheral device serial port. UARTs are now commonly included in microcontrollers. A dual UART or DUART combines two UARTs into a single chip. Many modern ICs now come with a UART that can also communicate synchronously; these devices are called USARTs.

 

MAX232:

The MAX232 is an integrated circuit that converts signals from an RS-232 serial port to signals suitable for use in TTL compatible digital logic circuits. The MAX232 is a dual driver/receiver and typically converts the RX, TX, CTS and RTS signals. The drivers provide RS-232 voltage level outputs (approx. ± 7.5 V) from a single + 5 V supply via on-chip charge pumps and external capacitors. The receivers reduce RS-232 inputs (which may be as high as ± 25 V), to standard 5 V TTL levels. These receivers have a typical threshold of 1.3 V, and a typical hysteresis of 0.5 V.

 

Fig. 4: Pin diagram of MAX232

 

ZIGBEE:

ZigBee is a specification for a suite of high level communication protocols using small, low-power digital radios based on the IEEE 802.15.4-2003standard for Low-Rate Wireless Personal Area Networks (LR-WPANs), such as wireless light switches with lamps, electrical meters with in-home-displays, consumer electronics equipment via short-range radio needing low rates of data transfer.

 

The technology defined by the ZigBee specification is intended to be simpler and less expensive than other WPANs, such as Bluetooth. ZigBee is targeted at radio-frequency (RF) applications that require a low data rate, long battery life, and secure networking ZigBee is a low-cost, low-power, wireless mesh standard. First, the low cost allows the technology to be widely deployed in wireless control and monitoring applications. Second, the low power-usage allows longer life with smaller batteries. Third, the mesh networking provides high reliability and more extensive range.

 

Fig. 5 Zigbee transmitter

Software Implementation:

The main purpose of using the microcontroller in our project is because high-performance CMOS 8-bit microcontroller with 8K bytes of in-system programmable Flash memory. By combining a versatile 8-bit CPU with in-system programmable Flash on a monolithic chip, the Atmel AT89S52 is a powerful microcontroller which provides a highly-flexible and cost-effective solution to many embedded control applications. The programs of the microcontroller have been written in Embedded C language and were compiled using KEIL, a compiler used for microcontroller programming. The communication between PC and the microcontroller was established MAX 232 standard and those programs were also done in C language. The following programs are used at various stages for the mentioned functions. In this program, the various special function registers of the microcontroller are set such that they can send and receive data from the PC. This program uses the serial library to communicate with the ports.

 

 

RESULTS AND DISCUSSION:

Automatic Ingestion Monitor is a device for monitoring food intake at regular intervals by using mems sensor and jaw motion sensor and transmitting the information via Zigbee is made and is found to be successful. Fig. 6 showed Hardware implementation of ingestion monitoring device. The demo of the device is obtained by attaching the jaw motion sensor to the jaw and mems sensor to the chin and the movements are observed at regular intervals.  A buzzer system is alerts the individual incase the food is not taken. Further these sensor values are transmitted to the concerned person via zigbee protocol.

 

Use of low-frequency signals reduces the energy consumption for digital signal processing and feature extraction which is important for the envisioned wearable sensor system. Fig. 7 depicted Output of eating behavior. Further miniaturization of the sensor and integration of on-board signal processing is possible, potentially enabling creation of a small wireless “band-aid” wearable sensor system for objective monitoring of ingestive behaviour.

 

Fig. 6: Hardware implementation of ingestion monitoring device

 

 

It is possible to develop a method and wearable sensors for non-invasive monitoring of ingestion. Possibility of new methods and devices for monitoring of physical activity and energy expenditure Development of wearable platforms for rehabilitation of stroke patients and monitoring of the risk of falling in elderly; and other methods for noninvasive monitoring of human ingestion behavior.

 

Fig. 7: Output of eating behavior

 

CONCLUSION:

Automatic ingestion monitoring device consisted of sensor and signal processing and pattern recognition methodology to detect periods of food intake by monitoring characteristic jaw motion during food consumption. The most relevant features representing the sensor signals were chosen by a forward selection procedure. The population-based model created was able to classify chewing epochs with an averaged accuracy of 80.98% and a time resolution of 30 s. This epoch-based classification approach would allow the monitoring of short events of food consumption, such as snacking. Practical implementation of this methodology in a wearable device is highly possible due to the use of a simple and inexpensive strain gauge sensor to monitor chews plus a simple classification algorithm that can be easily implemented in a microcontroller. The development of such wearable device would allow the real-time monitoring of ingestive behavior under free-living conditions. The outcome of the present research is to learn for the lean people making them to eat and making alert system for food time and controlling the food habit for some extend in addition output send through the mail too.

 

CONFLICT OF INTEREST:

The authors declare no conflict of interest

 

ACKNOWLEDGMENT:

The authors are thankful to the management of Sathyabama University, Faculty of Bio and Chemical Engineering, Department of Biomedical Engineering, Chennai, Tamil Nadu, India for providing all the needed facilities to complete the research successfully.

 

REFERENCES:

1.       Olshansky SJ, et al. A potential decline in life expectancy in the United States in the 21st century. New Eng J Med. 2005; 352(11): 1138–1145.

2.       Flegal KM, Carroll MD, Kit BK, Ogden CL. Prevalence of obesity and trends in the distribution of body mass index among us adults, 1999–2010. J Amer Med Assoc. 2012; 307(5): 491–497.

3.       Fairburn CG, Harrison PJ. Eating disorders. Lancet. 2003; 361(9355): 407–416.

4.       Hudson JI, Hiripi E, Pope HG, Jr Kessler RC. The prevalence and correlates of eating disorders in the national co morbidity survey replication. Biol Psychiatry. 2007; 61(3): 348–358.

5.       Sánchez-Carracedo D, Neumark-Sztainer D, López-Guimerà G. Integrated prevention of obesity and eating disorders: Barriers, developments and opportunities. Public Health Nutrition. 2012; 15(12): 2295–2309.

6.       Thompson FE, Subar AF. Nutrition in the Prevention and Treatment of Disease. 2. San Diego, CA, USA: Academic Press; 2008. Dietary assessment methodology.

7.       Amft O. Ambient, on-body, and implantable monitoring technologies to assess dietary behavior. In: Preedy VR, Watson RR, Martin CR, editors. Handbook of Behavior, Food and Nutrition. New York, NY, USA: Springer; 2011; 3507–3526.

8.       Schoeller DA, Webb P. Five-day comparison of the doubly labeled water method with respiratory gas exchange. Amer J Clin Nutrition. 1984; 40(1): 153–158.

9.       Black AE, Cole TJ. Biased over or under-reporting is characteristic of individuals whether over time or by different assessment methods. J Amer Dietetic Assoc. 2001; 101(1): 70–80.

10.     Thompson FE, Subar AF, Loria CM, Reedy JL, Baranowski T. Need for technological innovation in dietary assessment. J Amer Dietetic Assoc. 2010; 110(1): 48–51.

11.     Sazonov E, Schuckers S, Lopez-Meyer P, Makeyev O, Sazonova N, Melanson EL, Neuman M. Non-invasive monitoring of chewing and swallowing for objective quantification of ingestive behavior. Physiol Meas. 2008; 29(5): 525–541.

12.     Dong Y, Hoover A, Scisco J, Muth E. A new method for measuring meal intake in humans via automated wrist motion tracking. Appl Psychophysiol Biofeedback. 2012; 37(3): 205–215.

 

 

 

 

Accepted on 01.08.2017          © RJPT All right reserved