Activity recognition in health field

BYYOGESH K M

Research Scholar

EXPLORATION OF ADVANCED DATA MINING MODELS FOR KNOWLEDGE DISCOVERY FROM mHealth DATA SET

(DATA SCIENCE APPROACH)

1. Problem Statement2. Introduction 3. Motivation of mHealth Applications4. Literature Review on Related Work5. Objectives of the Proposed Research 6. Research Methodology7. Research Plane with Time Schedule8. Work Under Progress9. Conclusion 10. References

Presentation flow

1. Problem StatementDevelopment of data mining algorithms for Activity recognition and prediction of vital signs[blood pressure, body temperature, pulse rate and respiration rate] based on various human physical activities[ walking, sitting, jogging, upstairing, downstairing and etc.] through data science approach.

Tuesday, May 2, 2023

2. IntroductionMobile smart devices are becoming increasingly sophisticated. The latest generation of smart cell phones now incorporates many diverse and powerful smart sensors

GPS (Geographical position system ) sensor Magnetometer sensor Gyro meter sensor light sensor Temperature sensor Direction sensor Orientation sensorthe latest wearable sensors called mobile health

(mHealth)sensors for health related activities

measurements and basicvital sign of human. Deployment of these diverse

mHealth sensors at different spatial locations on human

body sets uphuman activity environment where different

human activitiesrecorded and measured can be used for Human

ActivityRecognition (HAR) for all basic function of human(VITAL SIGN).


IntroductionWHAT IS mHealth..?

mHealth is the use of mobile and wireless technologies, such as mobile phones, patient monitoring devices, personal digital assistants, and mobile software applications (apps),to support the achievement of health objectives

The adoption of mHealth seeks to take advantage of the explosion in mobile devices available worldwide

3. Motivation of mHealth applicationsmHealth Applications and BenefitsThe United Nations has identified seven application categories within the mHealth field,

including:

Remote monitoring Remote data collection Education and awareness Diagnostic and treatment support Disease and epidemic outbreak tracking Helpline

Benefits include the ability to:

Access healthcare information. Diagnose & track disease. Gather actionable public information. Deliver medical education & training

PHYSICAL ACTIVITY and VITAL SIGNWhat is physical activity?Physical activity simply means movement of the body that uses energy. Climbing Stairs, Cycling, Front elevation of arm Jogging, jump front andBack Knee bending Lying down Running, Sitting & relaxing Standing still Waist bend forward, Walking.

What is moderate and vigorous exercise?The words "moderate" and "vigorous" describe the intensity of exercise. Whether an exercise or physicalactivity is moderate or vigorous depends on how hard you're working to carry it out and how much energy you're using

Moderate: Moderate intensity aerobic exercise is where you're working hard enough to raise your heart rate and break into a sweat. If You're working at a moderate intensity if you're able to talk but unable to sing the words to a song.

Vigorous: Vigorous intensity aerobic exercise is where you're breathing hard and fast and your heart rate has increased significantly. If you're working at this level, you won't be able to say more than a few words without pausing for a breath.

Physical Activity and Good Physical HealthAt least 30 minutes duration of moderate intensity PA at least five days per week, or 20 minutes of vigorous physical activity at least three times per week Youth should strive for at least one hour of exercise a day.

Physical Activity Health BenefitsRegular PA has beneficial effects on most (if not all) organ systems, and helps to prevent a broad range of health problems and diseases.People of all ages derive substantial health benefits from physical activity

How much physical activity needed?Physical activity is important for everyone, but

how much you need depends on your age.ADULTS (18-60 YEARS):

Adults should do at least 2 hours and 30 minutes of physical activity each week.

Adult should do aerobic physical activity at a moderate level

At least 1 hour and 15 minutes each week of aerobic physical activity at a vigorous level.

Being active 5 or more hours each week can provide even more health benefits.

Spreading aerobic activity out over at least 3 days a week is best.

Also, each activity should be done for at least 10 minutes at a time.

Adults should also do strengthening activities, like push-ups, sit-ups and lifting weights, at least 2 days a week


2. CHILDREN AND ADOLESCENTS (6-17 YEARS)

Most of the 60 minutes should be either moderate- or Vigorous intensity aerobic

physical activity, Should include vigorous-intensity physical

activity at least 3 days a week. Children and adolescents should do 60 minutes

3. YOUNG CHILDREN (2-5 YEARS)

There is not a specific recommendation for the number of minutes young children should be active each day. Children ages 2-5 years should play actively several times each day. Their activity may happen in short bursts of time and not be all at once. Physical activities for young children should be developmentally appropriate, fun, and offer variety


VITAL SIGNVital signs are measurements of the body's most basic functions. The four main vital signs routinely monitored by medical professionals and health care.

There are four primary vital signs which are standard in most medical settings

Body temperature

Pulse rate(Heart rate)

Blood pressure

Respiration rate

4. LITERATURE REVIEW on Related Work1. HUMAN ACTIVITY RECOGNITION USING WEARABLE SENSORS2. HUMA ACTIVITY RECOGNITION AND ECG VITAL SIGNS


4. Related worksArticle Key concept LimitationsKwapiz et al [2011]

Sensor data mining, activity recognition Cell phone, accelerometer

Activity Recognition using cell phone Accelerometer.

Bingchuan et al [2014]

ADLs, Smartphone, Wearable Wireless Sensor, Machine Learning, Cloud Infrastructure, UnsupervisedLearning, Real-time Activity Recognition

Smartphone-based Activity Recognition Using Hybrid ClassifierUtilizing Cloud Infrastructure For Data Analysis.

Torres-Huitzil [2015]

Human activity recognition, accelerometer, smart phone, mHealth, time domain features

Wireless device used support mHealth services

Vincent S Tseng et al [2008]

Data mining, Electrocardiogram analysis, Patient monitoring system, Vital sign analysis

Vital Sign Data Mining System for Chronic Patient Monitoring.

Human Activity Recognition based on Mobile Sensor

Data Sets


Relevant classification methods implemented for Human Activity recognition for Mobile health Monitoring System

Kwapisz, Jennifer R., Gary M. Weiss, and Samuel A. Moore.(2011) "Activity recognition using cell phone accelerometers." ACM SigKDD Explorations Newsletter 12, .2, pp.74-82.

ActivityAlgorithms Accuracy(%)

J48 M P L P STRAW MAN

Walking 89.9 91.6 93.6 37.2

Jogging 96.5 98.0 98.0 29.2

Upstairs 59.3 61.5 27.5 12.2

Down stairs 55.5 44.3 12.3 10.0

sitting 95.7 92.95.0 92.2 6.4

Standing 93.3 91.9 87.0 5.0

Overall 85.1 91.7 78.1 37.2


Bingchuan., Herbert, J., & Emamian, Y. (2014). Smartphone-based activity recognition using hybrid classifier. In Proceedings of the 4th International Conference on Pervasive and Embedded Computing and Communication Systems (PECCS 2014)

ActivityOverall Model accuracy for Female user

Bayes Network Decision Tree K-NN Neural Network

FEMALEUSER

1st 84.45 68.37 72.35 95.97

2nd 89.67 79.51 79.51 96.54

3rd 95.48 96.61 82.84 88.43

Overall Model accuracy for the Male and Female user

1st 84.38 90.74 91.23 87.83

MALE2nd 92.57 93.02 94.14 90.69

3rd 92.93 94.77 94.41 91.86


3 Torres-Huitzil et al,(2015) "Accelerometer-Based Human Activity Recognition in Smartphone’s for Healthcare Services." Mobile Health. Springer International Publishing, pp.147-169. Activity NB K-NN SVM

Precision Recall Precision Recall Precision Recall

Static 100 99.36 100 99.36 100 99.36

Running 100 100 100 100 100 100

Walking 91.03 85.71 79.27 84.42 91.00 59.09

UP-stairs 80.98 88.69 78.07 86.90 57.30 93.45

Down stairs 82.28 79.27 79.41 65.85 57.52 39.63

Average 90.85 90.60 87.35 87.30 81.16 78.30

EGCG Signal Data Analaysis


HUMAN ACTIVITY RECOGNITION AND ECG VITAL SIGNS

Vincent S Tseng et al(2008), “Development of a Vital Sign Data Mining System for Chronic Patient Monitoring”, Proceedings of International Conference on Complex, Intelligent and

Software Intensive Systems, 2008. CISIS 2008, 4-7 March 2008, pp. 649 - 654.Sl.No Methods Recall

(True Positive)

Precision

(False Positive)

1 Naïve Bayes Simple 68% 67%

2 Naïve Bays 57% 56%

3 libSVM 61% 56%

4 Radial Bias Function 57% 67%

5 Random-Forest Tree 39% 21%

6 J48 32% 26%

7 1-NN classifier 29% 26%

8 Logistic Regression Tree 25% 36%

9 Classification tree 21% 19%

10 Probit-Regression Tree 21% 35%

11 ADTree 18% 25%

12 Random Forest 7% 4%

5. Objectives of the Proposed Research

The following objectives are determined

1. Development of Advanced Data mining classification models for human activities recognition.

2. Clustering models for grouping healthy and unhealthy persons based on their ECG signals.

3. Prediction models for determining the vital signs of persons based on the ECG signals during their activities.

4. Identification of physical human activities based on the mHealth sensor data sets.

5. Determination of basic health heart monitoring activities.

6. Determination of various arrhythmia or looking at the effects of exercise on the ECG values during physical activities.

7. Determination of body’s basic function using ECG

8. Determination of person’s vital signs , which are varying with age, weight, gender, and overall health

9. Determination of the pulse rate (Heart Rate), body temperature, respiratory rate and blood pressure of the normal and abnormal human being.


6. Research Methodology


DATA SCIENCE APPROACH FOR FOR HUMAN ACTIVITY RECOGNITION & VITAL SIGN PREDICTTIONS


Primary Data Sets The MHEALTH (Mobile HEALTH) dataset comprises

Physical activities and vital signs

Recordings for ten volunteers of diverse profile while performing several physical activities.

Sensors placed on the subject's chest, right wrist and left ankle are used to measure the motion experienced by diverse body parts,

namely, the acceleration, the rate of turn and the magnetic field orientation.

The sensor positioned on the chest also provides 2-lead ECG measurements, which can be potentially used for basic heart monitoring, checking for various arrhythmias or looking at the effects of exercise on the ECG.


7.Research Plane with Time Schedule

PLAN OF PROPOSED RESEARCHYear Sl.

NorProgress task/per Every six month I Year

2015II Year2016

III Year 2017

1-6 7-12 1-6 7-12 1-6 7-12I 1 Course Work Completion

2 Literature Survey on the proposed research issue/Data collection/Research Toll Understanding

II 3 Data Model Design/Design and Development of data processing Model

4 Development of Classification Model or HAR and comparing with exiting Algorithms and Evaluation(Model Deployment, Operations and optimization)

III 5 Development of Predictive Model for Vital Sign Analysis and their evaluation (Model Deployment, Operation and Optimization)

6 Publication of Research outcome at National and International Level journal/conference preceding

7 Preparation of Documentation of work for thesis submission Tuesday, May 2, 2023


8. Work Under Progress


WORK PROGRESS OF THE PROPOSED RESEARCHDuring the course work, machine learning algorithms such as J48, Naïve Bayesian

Classification, REPTREE, and SMO were implement and analyzed classification results on the data sets

using WEKA Tool. The results are summarized and tabulated in the

following Table 5. Analysis of ECG Lead -1 and Lead -II signals data are under.

Classification accuracies of various common exiting methods implemented on proposed mHealth Datasets (Banos et al, 2014) proposed for the prediction of vital signals of Human during their activities.

Analysis of ECG sets using WEKA Tool. The results

Sl nor Activity J48 N B REP TREE SMO Predictive Data Models

1 Walking 99.90 99.15 99.90 100 - -

SCOPE OF EXPLORATION

.

.

.??????

2 Jogging 97.23 93.33 97.94 95.46 - -

3 Running 96.19 92.74 91.86 91.33 - -

4 Knees Bending

100 99.86 100 100 - -

5 Lying down 100 100 100 100 - -

6 Jump F & B 93.18 93.18 97.77 91.61 - -

Further study is focused on the investigation of advance data mining algorithms and their evaluation on ECG Lead data signals of mHealth data sets


FURTHER WORK To identifying basic function of human(VITAL SIGN) for all our proposed

physical activities. In our proposed objectives have 12 different activities to identify vital sign

for all activitiesThe following activities need to predictive Vital sign

Climbing Stair

VITA SIGN PREDICTION FOR CLIMBING STAIR


Running person Heart rate, BP, Temperature, & respiration rate

Cycling Person HR, BP, Temperature, Respiration rate

The Vital sign varies, which are varying with

age, weight, gender, and different physical

activities

Running

Cycling


According to mHealth dataset it contains 12 different physical activities and do 12 different vital function of all activities

12 different physical from mHealth

Running person Heart rate, BP, Temperature,

& respiration rate


Conclusions: Aim is to Develop classification methods for human

activity recognition and Vital prediction models. Literature survey is done on both human activity

classification methods and vital sign classification. Data Science approach is proposed for design ,

deployment , operation of the proposed models.

Primary data sets are obtained from mHealth Sensors.

Plane of research is proposed. Little work carried out on the primary data sets

using WEKA Tool.


Reference1. Bakshi, A, Narasimhan, P, Li, JH, Chernih, N, Ray, PK & Macintyre, R (2011), ‘mHealth for the control

of TB/HIV in developing countries’, Proceedings of the 13th IEEE International Conference, pp. 9–14.

2. Banos, O., Garcia, R., Holgado, J. A., Damas, M., Pomares, H., Rojas, I., Saez, A., Villalonga, “mHealthDroid: a novel framework for agile development of mobile health applications” . Proceedings of the 6th International Work-conference on Ambient Assisted Living an Active Ageing (IWAAL 2014), Belfast, Northern Ireland, December 2-5, (2014). Data set available at Download mHealth data sets.

3. Beant Kaur and Williumjeet Singh, (2014), Review of Heart Disease Prediction system using Data Mining techniques, International Journal on Recent and Innovation Trends in Computing ad Communication, Vol.2,issues 10,Octobe 2014.

4. Chen, Chao, Barnan Das, and Diane J. Cook (2010). "A Data Mining Framework for Activity Recognition In Smart Environments." In Intelligent Environments (IE), 2010 Sixth International Conference on, pp. 80-83. IEEE, 2010.

5. Doshi M (2010) “Northbridge capital report on hospital sector,” November 2010, [retrieved: July, 2015]. [Online]. Available: http://www .northbridgeasia.com/research_reports.aspx.

6. Emiliano Miluzzo,(2011) “Smartphone Sensing”, A PhD Thesis, Dartmouth College, Hanover, New Hampshire June, 2011.

7. Gary M. Weiss (2013)," Smartphone Sensor Mining Research: Successes and Lessons”, WINTER 2013 Volume 34, No. 2, pp.17-21. Fordham University.

8. Geena Skaria,(2013), mHealth in Health Information Delivery; The Indian Scenario, Journal Of Mobile Technology In Medicine Vol 2. ISSUE 1. MAR 2013, pp.26-29.

9. Hadi Banaee, Mobyen Uddn Ahmed and Amy Loutfi(2013). Data Mining for Wearable Sensors in Health Moniting Systems: A Review of Recent Trends and Challenges, Sensor, 2013, issue 13,pp.17472-17500. Open access at www.mdpi.com/journal/sensors

http://www.ugr.es/~oresti/datasets.html




10. Han J and Kamber M. (2006). Data Mining: Concepts and Techniques. Morgan Kaufmann, 3rd ed., 2012.

11. Holland C A, Ferrell N, and James D. (2009), The nursing shortage: Exploring the situation and solutions. [retrieved: July 2015]. [Online]. Available: http://www.minoritynurse.com/article/ nursing-shortage-exploring-situation-and-solutions.

12. Istepanian, Robert, Laxminarayan, Swamy, Pattichis, Constantinos S (2006). M-Health- Emerging Mobile Health Systems, Spinger Publication, 2006

13. Jadhav S M, Nalbalwar S L, Ashok A. Ghatol(2011) ‘Modular Neural Network Based Arrhythmia Classification System Using ECG Signal Data”, in International Journal of Information Technology and Knowledge Management January-June 2011, Volume 4, No. 1, pp. 205-209.

14. Kaghyan, Sahak, and Hakob Sarukhanyan(2012) "Activity recognition using K-nearest neighbor algorithm on smartphone with Tri-axial accelerometer." International Journal of Informatics Models and Analysis (IJIMA), ITHEA International Scientific Society, Bulgaria 1 (2012): 146-156.

15. Kwapisz, Jennifer R., Gary M. Weiss, and Samuel A. Moore(2011). "Activity recognition using cell phone accelerometers." ACM SigKDD Explorations Newsletter 12.2 (2011): 74-82.

16. Lockhart. J W, Pulickal. T, Weiss. G M(2012): “Applications of mobile activity recognition”. In Proceedings: 2012 ACM Conference on Ubiquitous Computing. Pages 1054-1058. 2012.

17. Nina Zumel and John Mount,(2014) Practical Data Science with R ,Manning Publications Company, 3rd edition, 2014.

18. Paul D Leedy and Jeanne Ellis Ormrod, (2014). Fundamental of Research Methodology(Chaoter-1), Practical Research Planning and Design, 10th Edition, Pearson publication.

19. Rashidi. P and Cook. D J(2010): “Mining sensor streams for discovering human activity patterns over time”. In Proceedings: IEEE 10th International Conference on Data Mining (ICDM). Pages 431-440. 2010.

http://www.minoritynurse.com/article/


20. Scar D. Lara and Miguel A. Labrador (2013) “A Survey on Human Activity Recognition using Wearable Sensors”. IEEE communications surveys & tutorials, vol. 15, no. 3, third quarter 2013.

21. Sharmin Jahan, M. Mozammel Hoque Chowdhury,(2014), mHealth: A Sustainable Healthcare Model for Developing World,, American Journal of Modeling and Optimization, 2014, Vol. 2, No. 3, 73-76, Available online at http://pubs.sciepub.com/ajmo/2/3/2, DOI:10.12691/ajmo-2-3-2.

22. Sousa, P. S., D. Sabugueiro, V. Felizardo, R. Couto, I. Pires, and N. M. Garcia(2015). "MHealth Sensors and Applications for Personal Aid." In Mobile Health, pp. 265-281. Springer International Publishing, 2015.(Mhealth book)

23. Starostenko, Oleg, Vicente Alarcon-Aquino, Jorge Rodriguez-Asomoza, Oleg Sergiyenko, and Vera Tyrsa. (2015) "MHealth and Remote Vital Sign Monitoring: Trends and Applications for ECG Analysis on Cell Phones." Mobile Health: A Technology Road Map 5,2015, 222.( mobile health book)

24. Torres-Huitzil, Cesar, and Andres Alvarez-Landero (2015) "Accelerometer-Based Human Activity Recognition in Smartphone’s for Healthcare Services." Mobile Health. Springer International Publishing, 2015, pp.147-169.

25. Valenzuela, O., Rojas, F., Herrera, L. J., Ortuno, F., Banos, O., Ruiz, G., Tribak, H., Pomares, H., Rojas, I. (2013),“Intelligent systems to autonomously classify several arrhythmia using information from ECG”. Proceedings of the IEEE International Conference on Biomedical Computing (BioMedCom 2013), Washington D.C., USA, September 8-14, 2013.

mHealth data set available at http://www.ugr.es/~oresti/datasets.htm

http://www.ugr.es/~oresti/datasets.htm


Thanks

Your suggestions and comments

Yogesh K M

Date post:	15-Apr-2017
Category:	Data & Analytics
Upload:	yogesh-km
View:	58 times
Download:	3 times

Activity recognition in health field

Data & Analytics