Download Application for Continuous Health Monitoring

Survey
yes no Was this document useful for you?
   Thank you for your participation!

* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project

Document related concepts

Signals intelligence wikipedia , lookup

Transcript
Application for Continuous
Health Monitoring using
Machine-to-Machine
Communications
February 2012
João Prudêncio
Supervisors: Ana Aguiar, Daniel Lucani
1. Context
•
•
•
Aging population 1;
48% of the US population suffer from at least one
chronic ailment 2;
Health care crisis, spending reached 15.5% of GDP by
year of 2010 3.
Mobile-healthcare
1 World
Health Organization. 2004. Active ageing: Towards age-friendly primary health care. WHO Library Cataloguing-in-Publication Data. http://whqlibdoc.who.int/publications/2004/9241592184.pdf
(accessed November 22, 2011).
2 D.B.
Kendall, K.Tremain, J. Lemieux, and S.R. Levine. 2003. Heatlhy Aging v. Chronic Illness Preparing Medicare for the New Health Care Challenge. Quoted in Shieh, Y.Y.; Tsai, F.Y.; Arash; Wang,
M.D.; Lin. 2007. Mobile Healthcare: Opportunities and Challenges. Paper presented at International Conference on the Management of Mobile Business, July 9-11, in Toronto, Canada
3 Centers
for Medicare and Medicaid Services (CMS). 2011. National Health Expenditures 2000-2010. http://www.cms.gov/ (accessed November 27, 2001)
2. Problem
•
•
•
•
1
How to monitor the patients in near real time?;
Achieve energy efficiency, security and reliability;
Interoperability 1;
Lack of open solutions for mobile healthcare.
Shin, Donghoon. 2011. M-healthcare revolution: an e-commerce perspective. Paper presented at First ACIS/JNU International Conference on Computers, Networks, Systems and Industrial Engineering,
May 23-25.
3. Objectives
4. System architecture
5. Example of applications
MOTOACTV
Motorola. 2011. Motorola brings personalized media and mobile experiences together to meet the exploding consumer demand for video and interactive
services. http://www.motorola.com/Consumers/US-EN/Consumer-Product-and-Services/MOTOACTV/MOTOACTV/MOTOACTV-US-EN (accessed January 20, 2012)
5. Example of applications
Endomodo
Endomondo. 2007. Endomondo is a sports community based on free real-time GPS tracking of running, cycling, etc. http://www.endomondo.com (accessed January 20,
2012)
6. Machine-to-Machines
Communications
• Communication among Machines without human
intervention 1 ;
• The most promising solution for the intelligent pervasive
applications 1 2;
• Standardization is the wise step to enable interoperability
and integration of the worldwide systems;
• Use cases, service requirements and capabilities of a M2M
architecture in an healthcare scenario is currently being
developed by ETSI 3.
1
Rongxing Lu; Xu Li; Xiaohui Liang; Xuemin Shen; Xiaodong Lin; , "GRS: The green, reliability, and security of emerging machine to machine
communications," Communications Magazine, IEEE , vol.49, no.4, pp.28-35, April 2011
2 Geng Wu; Talwar, S.; Johnsson, K.; Himayat, N.; Johnson, K.D.; , "M2M: From mobile to embedded internet," Communications Magazine, IEEE , vol.49, no.4, pp.36-43, April
2011
3
ETSI(The European Telecommunications Standards Institute). 2011. Draft ETSI TR 102 732 V0.4.1. Machine to Machine Communications (M2M): Use cases of M2M applications for eHealth. France:
The European Telecommunications Standards Institute.
6. Machine-to-Machines
Communications
Shao-Yu Lien; Kwang-Cheng Chen; Yonghua Lin; , "Toward ubiquitous massive accesses in 3GPP machine-to-machine communications," Communications Magazine, IEEE , vol.49, no.4, pp.66-74,
April 2011
7. Heart abnormalities
• Bradycardia: heart rate less than 60
bps;
•Tachycardia: heart rate greater that
100 bps;
• QRS complexes: QRS interval
greater than 120 miliseconds and
heart rate greater than 100 bps;
• Supraventricular tachycardia with
narrow QRS complexes: QRS
interval less than 120 miliseconds and
heart rate greater than 100 bps.
Liszka, K.J.; Mackin, M.A.; Lichter, M.J.; York, D.W.; Dilip Pillai; Rosenbaum, D.S.; , "Keeping a beat on the heart," Pervasive Computing, IEEE , vol.3, no.4, pp. 42- 49, Oct.-Dec. 2004
Yonglin Ren; Pazzi, R.W.N.; Boukerche, A.; , "Monitoring patients via a secure and mobile healthcare system," Wireless Communications, IEEE , vol.17, no.1, pp.59-65,
February 2010
8. Geo Fencing
• Perimeter in a geographic area;
• When the user exits the virtual fence an alarm is
generated 1 2;
• Useful for patients with dementia 3.
1
Armstrong, N.; Nugent, C.D.; Moore, G.; Finlay, D.D.; , "Developing smartphone applications for people with Alzheimer's disease," Information Technology and Applications in
Biomedicine (ITAB), 2010 10th IEEE International Conference on , vol., no., pp.1-5, 3-5 Nov. 2010
2 Bilgic, Hasan Tahsin; Alkar, Ali Ziya; , "A secure tracking system for GPS-enabled mobile phones," Information Technology and Multimedia (ICIM), 2011 International Conference
on , vol., no., pp.1-5, 14-16 Nov. 2011
3 Alotaibi, F.D.; Abdennour, A.; Ali, A.A.; , "A Real-Time Intelligent Wireless Mobile Station Location Estimator with Application to TETRA Network," Mobile Computing, IEEE
Transactions on , vol.8, no.11, pp.1495-1509, Nov. 2009
8. Geo Fencing
• Ray casting algorithm;
• Simple polygons not selfinterconnected 1.
f(ei ) has the value of:
 -1, if ei crossed up to down;
 1, if ei crossed down to up;
 0, if ei not crossed .
P: P3P4, P4P5,
P5P6 and P6P7.
F(P) = 1+(-1)+1+(-1)
If F = 1 then it’s an internal point
If F = 0 then it’s an external point
Wu Jian; Cai Zongyan; , "A method for the decision of a point whether in or not in polygon and self-intersected polygon," Fuzzy Systems and Knowledge Discovery (FSKD), 2011 Eighth International Conference
on , vol.1, no., pp.16-18, 26-28 July 2011
8. Geo Fencing
9. Human Activity
Recognition
Khan, A. M.; Lee, Y. K.; Kim, T.-S.; , "Accelerometer signal-based human activity recognition using augmented autoregressive model coefficients and artificial neural nets," Engineering in Medicine and
Biology Society, 2008. EMBS 2008. 30th Annual International Conference of the IEEE , vol., no., pp.5172-5175, 20-25 Aug. 2008
Khan, A.M.; Young-Koo Lee; Lee, S.Y.; Tae-Seong Kim; , "A Triaxial Accelerometer-Based Physical-Activity Recognition via Augmented-Signal Features and a Hierarchical Recognizer," Information
Technology in Biomedicine, IEEE Transactions on , vol.14, no.5, pp.1166-1172, Sept. 2010
9. Human Activity
Recognition
Autoregressive Modeling
•
•
•
Linear prediction methods: predicts the output based on
previous inputs1 2;
Finite impulse response (FIR) filter;
Methods: The least squares; Yule-Walker ; Burg’s 3 4.
Y(t) original signal
a(i) unknown coefficients
P the order of the model
E(t) residual error
1
C.Jennings M.Kulahci Montgomery,C.Douglas. Introduction toTime Series Analysis and Forecasting.John Wiley and Sons.Inc.,first edition,2008
Khan, A.M.; Young-Koo Lee; Lee, S.Y.; Tae-Seong Kim; , "A Triaxial Accelerometer-Based Physical-Activity Recognition via Augmented-Signal Features and a Hierarchical
Recognizer," Information Technology in Biomedicine, IEEE Transactions on , vol.14, no.5, pp.1166-1172, Sept. 2010
3 H.Schoonewelle M.J.L.De Hoon,T.H.J.J.Van Der Hagenand H.Van Dam. Why Yule-Walker should not be used for autoregressive modelling.
4 K. Roth, I. Kauppinen,P.A.A.Esquef,and V.Valimaki. Frequency warped Burg’s method for AR-modeling.
2
9. Human Activity
Recognition
Signal Magnitude Area (SMA)
•
•
Analyze the magnitude of the variations of the signal;
Distinguish between static and dynamic activities 1 2.
Where x(i), y(i), z(i) : acceleration in the x,y,z axis at the time i
1 Khan,
A. M.; Lee, Y. K.; Kim, T.-S.; , "Accelerometer signal-based human activity recognition using augmented autoregressive model coefficients and artificial neural
nets," Engineering in Medicine and Biology Society, 2008. EMBS 2008. 30th Annual International Conference of the IEEE , vol., no., pp.5172-5175, 20-25 Aug. 2008
2 Khan, A.M.; Young-Koo Lee; Lee, S.Y.; Tae-Seong Kim; , "A Triaxial Accelerometer-Based Physical-Activity Recognition via Augmented-Signal Features and a Hierarchical
Recognizer," Information Technology in Biomedicine, IEEE Transactions on , vol.14, no.5, pp.1166-1172, Sept. 2010
9. Human Activity
Recognition
Tilt Angle
•
•
1
Angle between the vector of gravity
and the z axis 1 2;
Distinguish between static activities:
sitting and lying 3.
Karantonis, D.M.; Narayanan, M.R.; Mathie, M.; Lovell, N.H.; Celler, B.G.; , "Implementation of a real-time human movement classifier using a triaxial accelerometer for
ambulatory monitoring," Information Technology in Biomedicine, IEEE Transactions on , vol.10, no.1, pp.156-167, Jan. 2006
2 Do-Un Jeong; Se-Jin Kim; Wan-Young Chung; , "Classification of Posture and Movement Using a 3-axis Accelerometer," Convergence Information Technology, 2007.
International Conference on , vol., no., pp.837-844, 21-23 Nov. 2007
3 Veltink, P.H.; Bussmann, HansB.J.; de Vries, W.; Martens, WimL.J.; Van Lummel, R.C.; , "Detection of static and dynamic activities using uniaxial
accelerometers,"Rehabilitation Engineering, IEEE Transactions on , vol.4, no.4, pp.375-385, Dec 1996
9. Human Activity
Recognition
New features proposal
Stage 1
Stage 2
9. Human Activity
Recognition
New features proposal
Stage 3
Stage 4
10. Activity Data
Acquisition
6 individuals
10 hours of activity
11. Technologies
•
•
Machine-to-Machine Communications
The Extensible Messaging and Presence
Protocol (XMPP)
•
•
•
•
•
•
MyContext: Context Framework developed by PT
Inovação
Android SDK
Web technologies: PHP, HTML, CSS, Javascript
R
Java
Neuroph: Java neural network framework
12. Work Plan
Application for Continuous
Health Monitoring using
Machine-to-Machine
Communications
February 2012
João Prudêncio
Supervisors: Ana Aguiar, Daniel Lucani