A Wearable Real-time Activity Tracker

다국어 초록 (Multilingual Abstract)

Purpose Exercise and physical activity is a driving force for mental health. Major challenges in the treatment of psychological diseases are accurate activity profiles and the adherence to exercise intervention programs. We present the development and validation of CHRONACT, a wearable realtime activity tracker based on inertial sensor data to support mental health.
Methods CHRONACT comprised a Human Activity Recognition (HAR) algorithm that determined activity levels based on their Metabolic Equivalent of Task (MET) with sensors on ankle and wrist. Special emphasis was put on wearability, real-time data analysis and runtime to be able to use the system as augmented feedback device. For the development, data of 47 healthy subjects performing clinical intervention program activities were collected to train different classification models. The most suitable model according to the accuracy and processing power tradeoff was selected for an embedded implementation on CHRONACT.
Results A validation trial (six subjects, 6 h of data) showed the accuracy of the system with a classification rate of 85.6%.
The main source of error was identified in acyclic activities that contained activity bouts of neighboring classes. The runtime of the system was more than 7 days and continuous result logging was available for 39 h.
Conclusions In future applications, the CHRONACT system can be used to create accurate and unobtrusive patient activity profiles. Furthermore, the system is ready to assess the effects of individual augmented feedback for exercise adherence.

참고문헌 (Reference)

1 Ghasemzadeh H, "Wireless medical-embedded systems : a review of signalprocessing techniques for classification" 13 (13): 423-437, 2013

2 Mata J, "Walk on the bright side : physical activity and affect in major depressive disorder" 121 (121): 297-308, 2012

3 Smith SW, "The scientist and engineer’s guide to digital signal processing" California Technical Pub 1997

4 Dunn AL, "The effect of exercise on mental health" 9 (9): 202-207, 2010

5 Dogan-Aslan M, "The effect of electromyo-graphic biofeedback treatment in improving upper extremity functioning of patients with hemiplegic stroke" 21 (21): 187-192, 2012

6 Rethorst CD, "The antidepressive effects of exercise : a meta-analysis of randomized trials" 39 (39): 491-511, 2009

7 Knuth DE, "The Art of Computer Programming, Volume 2:Seminumerical Algorithms" Addison-Wesley Professional 1997

8 Ring M, "Software-based performance and complexity analysis for the design of embedded classification systems" 1 : 2266-2269, 2012

9 Burns A, "ShimmerTM-a wireless sensor platform for noninvasive biomedical research" 10 (10): 1527-1534, 2010

10 Jerome GJ, "Physical activity levels of persons with mental illness attending psychiatric rehabilitation programs" 108 (108): 252-257, 2009

11 Reiss A, "Personalized mobile physical activity monitoring for everyday life" Technical University of Kaiserslauten 2014

12 Leutheuser H, "Performance comparison of two step segmentation algorithms using different step activities" 1 : 143-148, 2014

13 Duda RO, "Pattern Classification" Wiley-Interscience 2000

14 Albu D, "On-node processing of ECG signals" 1 : 1-5, 2010

15 Matta Mello Portugal E, "Neuroscience of exercise: from neurobiology mechanisms to mental health" 68 (68): 1-14, 2013

16 Changhong Wang, "Low-power Technologies for Wearable Telecare and Telehealth Systems: A Review" 대한의용생체공학회 5 (5): 1-9, 2015

17 Theodoridis S, "Koutroumbas K" Academic Press; 2008

18 Blumenthal JA, "Is exercise a viable treatment for depression?" 16 (16): 14-21, 2012

19 Karantonis DM, "Implementation of a real-time human movement classifier using a triaxial accelerometer for ambulatory monitoring" 10 (10): 156-167, 2006

20 Leutheuser H, "Hierarchical, multisensor based classification of daily life activities: comparison with state-of-the-art algorithms using a benchmark dataset" 8 (8): e75196-, 2013

21 Strath SJ, "Guide to the assessment of physical activity: Clinical and research applications - a scientific statement from the american heart association" 128 (128): 2259-2279, 2013

22 World Health Organization, "Global Recommendations on Physical Activity for Health" WHO Press 1-58, 2010

23 Jensen U, "Generic features for biosignal classification" Sportinformatik 162-168, 2012

24 Pébay P, "Formulas for Robust, One-Pass Parallel Computation of Covariances and Arbitrary-Order Statistical Moments" Sandia National Laboratories 2008

25 Callaghan P., "Exercise: a neglected intervention in mental health care?" 11 (11): 476-483, 2004

26 Cooney GM, "Exercise for depression" 9 : CD0043566-, 2013

27 Brosse AL, "Exercise and the treatment of clinical depression in adults" 32 (32): 741-760, 2002

28 Raglin JS, "Exercise and mental health. Beneficial and detrimental effects" 9 (9): 323-329, 1990

29 Mohd Nordin INA, "EZ430-Chronos watch as a wireless health monitoring device" 35 : 305-307, 2011

30 "EZ430-Chronos" Texas Instruments Inc

31 Ermes M, "Detection of daily activities and sports with wearable sensors in controlled and uncontrolled conditions" 12 (12): 20-26, 2008

32 Witten IH, "Data Mining - Practical Machine Learning Tools and Techniques" Morgan Kaufmann 2011

33 Knöchel C, "Cognitive and behavioural effects of physical exercise in psychiatric patients" 96 (96): 46-68, 2012

34 Mathie MJ, "Classification of basic daily movements using a triaxial accelerometer" 42 (42): 679-687, 2004

35 Polikar R, "Bootstrap-inspired techniques in computational intelligence: ensemble of classifiers, incremental learning, data fusion and missing features" 24 (24): 59-72, 2007

36 Zijlstra A, "Biofeedback for training balance and mobility tasks in older populations: a systematic review" 7 : 58-, 2010

37 Martinsen EW, "Benefits of exercise for the treatment of depression" 9 (9): 380-389, 1990

38 Sigrist R, "Augmented visual, auditory, haptic, and multimodal feedback in motor learning: a review" 20 (20): 21-53, 2013

39 Hanson MA, "Application-focused energy-fidelity scalability for wireless motion-based health assessment" 11 (11): 50-, 2012

40 Reiss A, "An integrated mobile system for long-term aerobic activity monitoring and support in daily life" 1 : 2021-2028, 2012

41 Reiss A, "Aerobic activity monitoring: towards a long-term approach" 13 (13): 101-114, 2014

42 "ActivityNet Benchmark Datasets" Friedrich-Alexander-Universität Erlangen-Nüurnberg BaSA -Basic Step Activities

43 Avci A, "Activity recognition using inertial sensing for healthcare, wellbeing and sports applications: a survey" 1 : 1-10, 2010

44 Bulling A, "A tutorial on human activity recognition using body-worn inertial sensors" 46 (46): 33-, 2014

45 Bouten CVC, "A triaxial accelerometer and portable data processing unit for the assessment of daily physical activity" 44 (44): 136-147, 1997

46 Lara OD, "A survey on human activity recognition using wearable sensors" 15 (15): 1192-1209, 2013

47 Gordon R., "A calculated look at fixed-point arithmetic" 11 (11): 72-79, 1998

48 Ainsworth BE, "2011 Compendium of Physical Activities : a second update of codes and MET values" 43 (43): 1575-1581, 2011