Healthc Inform Res.  2011 Mar;17(1):76-86. 10.4258/hir.2011.17.1.76.

Integrated Solution for Physical Activity Monitoring Based on Mobile Phone and PC

• Lee MH
• Kim J
• Jee SH
• Yoo SK

• KMID: 2166598
• DOI: http://doi.org/10.4258/hir.2011.17.1.76

Abstract

OBJECTIVES
This study is part of the ongoing development of treatment methods for metabolic syndrome (MS) project, which involves monitoring daily physical activity. In this study, we have focused on detecting walking activity from subjects which includes many other physical activities such as standing, sitting, lying, walking, running, and falling. Specially, we implemented an integrated solution for various physical activities monitoring using a mobile phone and PC.
METHODS
We put the iPod touch has built in a tri-axial accelerometer on the waist of the subjects, and measured change in acceleration signal according to change in ambulatory movement and physical activities. First, we developed of programs that are aware of step counts, velocity of walking, energy consumptions, and metabolic equivalents based on iPod. Second, we have developed the activity recognition program based on PC. iPod synchronization with PC to transmit measured data using iPhoneBrowser program. Using the implemented system, we analyzed change in acceleration signal according to the change of six activity patterns.
RESULTS
We compared results of the step counting algorithm with different positions. The mean accuracy across these tests was 99.6 +/- 0.61%, 99.1 +/- 0.87% (right waist location, right pants pocket). Moreover, six activities recognition was performed using Fuzzy c means classification algorithm recognized over 98% accuracy. In addition we developed of programs that synchronization of data between PC and iPod for long-term physical activity monitoring.
CONCLUSIONS
This study will provide evidence on using mobile phone and PC for monitoring various activities in everyday life. The next step in our system will be addition of a standard value of various physical activities in everyday life such as household duties and a health guideline how to select and plan exercise considering one's physical characteristics and condition.

Keyword

Walking; Ambulatory Monitoring; Cellular Phone

MeSH Terms

Acceleration
Cellular Phone
Deception
Family Characteristics
Metabolic Equivalent
Monitoring, Ambulatory
Motor Activity
MP3-Player
Running
Walking

Figure

• 

  Figure 1 Overall system architecture of real-time monitoring and long-term activity monitoring.

• 

  Figure 2 (A) Axes on iPod Touch. (B) Accelerometer graph sample application graphs the motion of the device.

• 

  Figure 3 Acceleration signal measured from the waist during walking. The three dimensions of the sensor are shown separately (X shows acceleration ting the left-right direction, Y in the vertical direction, and Z in the back-forth direction). The gravitational force is visible in Y as a negative DC component in the signal. The vertical axes are arbitrary units. The horizontal axis is time in seconds. The sampling frequency of the signal is 60 Hz.

• 

  Figure 4 Vector magnitude of tri-axis accelerometer. iPod touch was worn on the right waist, over the right anterior superior iliac spine using a waist belt.

• 

  Figure 5 The different value of the positive and negative thresholds in the different measurement location conditions the same person.

• 

  Figure 6 The different values f the positive and negative thresholds of multiple users. iPod touch was wore user's right pants pocket.

• 

  Figure 7 The flowchart corresponding to operations of detection and counting of steps, executed by a processing unit of an algorithm. CalAcc: acceleration data, STS: step to step.

• 

  Figure 8 The flowchart corresponding to operations of self-adaptive modification of acceleration thresholds, executed by a processing unit of an algorithm. CalAcc: acceleration data.

• 

  Figure 9 The characteristic of parameter output according to the state of activity. ① standing, ② walking, ③ running, ④ fall, ⑤ lying, ⑥ sitting on the floor, ⑥' sitting on the chair.

• 

  Figure 10 Vector magnitude of tri-acceleration data from iPod. Time line of activities is indicated along the abscissa.

• 

  Figure 11 Implementation of the physical activity monitoring based on iPod Touch.

• 

  Figure 12 Analysis of the physical activity monitoring based on PC. Graphs out by step count, calorie consumption, metabolic equivalents level and activity pattern. (A) Step counts of the day. (B) An hourly change of activity pattern is shown with a bar chart.

Reference

1. Zimmet P, Alberti KG, Shaw J. Global and societal implications of the diabetes epidemic. Nature. 2001. 414:782–787.

2. Grundy SM, Hansen B, Smith SC Jr, Cleeman JI, Kahn RA. American Heart Association. National Heart, Lung, and Blood Institute. American Diabetes Association. Clinical management of metabolic syndrome: report of the American Heart Association/National Heart, Lung, and Blood Institute/American Diabetes Association conference on scientific issues related to management. Circulation. 2004. 109:551–556.

3. Eckel RH, Grundy SM, Zimmet PZ. The metabolic syndrome. Lancet. 2005. 365:1415–1428.

4. Thompson PD, Buchner D, Pina IL, Balady GJ, Williams MA, Marcus BH, Berra K, Blair SN, Costa F, Franklin B, Fletcher GF, Gordon NF, Pate RR, Rodriguez BL, Yancey AK, Wenger NK. American Heart Association Council on Clinical Cardiology Subcommittee on Exercise, Rehabilitation, and Prevention. American Heart Association Council on Nutrition, Physical Activity, and Metabolism Subcommittee on Physical Activity. Exercise and physical activity in the prevention and treatment of atherosclerotic cardiovascular disease: a statement from the Council on Clinical Cardiology (Subcommittee on Exercise, Rehabilitation, and Prevention) and the Council on Nutrition, Physical Activity, and Metabolism (Subcommittee on Physical Activity). Circulation. 2003. 107:3109–3116.

5. Tuomilehto J, Lindstrom J, Eriksson JG, Valle TT, Hamalainen H, Ilanne-Parikka P, Keinanen-Kiukaanniemi S, Laakso M, Louheranta A, Rastas M, Salminen V, Uusitupa M. Finnish Diabetes Prevention Study Group. Prevention of type 2 diabetes mellitus by changes in lifestyle among subjects with impaired glucose tolerance. N Engl J Med. 2001. 344:1343–1350.

6. Lee M, Kim J, Jee SH, Yoo SK. Review of daily physical activity monitoring system based on single triaxial accelerometer and portable data measurement unit. Lect Notes Electr Eng. 2010. 68:569–580.

7. Bassett DR Jr. Validity and reliability issues in objective monitoring of physical activity. Res Q Exerc Sport. 2000. 71:2 Suppl. S30–S36.

8. Craig CL, Marshall AL, Sjostrom M, Bauman AE, Booth ML, Ainsworth BE, Pratt M, Ekelund U, Yngve A, Sallis JF, Oja P. International physical activity questionnaire: 12-country reliability and validity. Med Sci Sports Exerc. 2003. 35:1381–1395.

9. Allor KM, Pivarnik JM. Stability and convergent validity of three physical activity assessments. Med Sci Sports Exerc. 2001. 33:671–676.

10. LaMonte MJ, Ainsworth BE, Tudor-Locke C. Andersen R, editor. Assessment of physical activity and energy expenditure. Obesity: etiology, assessment, treatment, and prevention. 2003. Champaign, IL: Human Kinetics;111–117.

11. Hong JH, Cha EJ, Lee TS. A belt-type biomedical mobile device. J Korean Soc Med Inform. 2009. 15:351–358.

12. Mladenov M, Mock M. A step counter service for Java-enabled devices using a built-in accelerometer. CAMS '09 Proceedings of the 1st International Workshop on Context-Aware Middleware and Services: affiliated with the 4th International Conference on Communication System Software and Middleware (COMSWARE 2009). 2009. New York, NY: Association for Computing Machinery;1–5.

13. Walters DL, Sarela A, Fairfull A, Neighbour K, Cowen C, Stephens B, Sellwood T, Sellwood B, Steer M, Aust M, Francis R, Lee CK, Hoffman S, Brealey G, Karunanithi M. A mobile phone-based care model for outpatient cardiac rehabilitation: the care assessment platform (CAP). BMC Cardiovasc Disord. 2010. 10:5.

14. Nokia Step Counter. Nokia Beta Labs. c2009. cited 2011 Mar 10. Helsinki: Nokia;Available from: http://betalabs.nokia.com/betas/view/nokia-step-counter.

15. Gyorbiro N, Fabian A, Homanyi G. An activity recognition system for mobile phones. Mob Netw Appl. 2009. 14:82–91.

16. Holzinger A, Dorner S, Fodinger M, Valdez AC, Ziefle M. Chances of increasing youth health awareness through mobile wellness applications. Lect Notes Comput Sci. 2010. 6389:71–81.

17. Rowlands D, James DA. An architecture for iPod/iPhone applications in field sports. In : 8th Conference of the International Sports Engineering Association (ISEA);

18. AccelerometerGraph version 2.5 [software]. Apple Inc. c2010. cited at 2010 Mar 10. Cupertino, CA: Apple Inc;Available from: http://developer.apple.com/library/ios/#samplecode/AccelerometerGraph/Introduction/Intro.html.

19. Accelerometer Data. Wavefront Labs. c2009-2010. cited at 2010 Mar 15. Wavefront Labs;Available from: http://www.wavefrontlabs.com/Wavefront_Labs/Accelerometer_Data.html.

20. Bezdek JC. Pattern recognition with fuzzy objective function algorithms. 1981. New York: Plenum Press.

21. Dunn JC. A fuzzy relative of the ISODATA process and its use in detecting compact well-separated clusters. J Cybern. 1973. 3:32–57.

22. Nascimento S, Mirkin B, Moura-Pires F. Modeling proportional membership in fuzzy clustering. IEEE Trans Fuzzy Syst. 2003. 11:173–186.

23. Eng JJ, Chu KS, Dawson AS, Kim CM, Hepburn KE. Functional walk tests in individuals with stroke: relation to perceived exertion and myocardial exertion. Stroke. 2002. 33:756–761.

24. Brooks D, Parsons J, Newton J, Dear C, Silaj E, Sinclair L, Quirt J. Discharge criteria from perioperative physical therapy. Chest. 2002. 121:488–494.

25. Bidargaddi N, Sarela A, Klingbeil L, Karunanithi M. Detecting walking activity in cardiac rehabilitation by using accelerometer. 2007. In : 3rd International Conference on Intelligent Sensors, Sensor Networks and Information; 555–560.