Www.monash.edu.au Mobile Data Mining for Intelligent Healthcare Support By: Pari Delir Haghighi,...

27
www.monash.edu.au Mobile Data Mining for Intelligent Healthcare Support By: Pari Delir Haghighi, Arkady Zaslavsky, Shonali Krishnaswamy, Mohamed Medhat Gaber Center for Distributed Systems and Software Engineering Monash University, Australia

Transcript of Www.monash.edu.au Mobile Data Mining for Intelligent Healthcare Support By: Pari Delir Haghighi,...

Page 1: Www.monash.edu.au Mobile Data Mining for Intelligent Healthcare Support By: Pari Delir Haghighi, Arkady Zaslavsky, Shonali Krishnaswamy, Mohamed Medhat.

www.monash.edu.au

Mobile Data Mining for Intelligent Healthcare Support

By: Pari Delir Haghighi, Arkady Zaslavsky, Shonali Krishnaswamy, Mohamed Medhat GaberCenter for Distributed Systems and Software EngineeringMonash University, Australia

Page 2: Www.monash.edu.au Mobile Data Mining for Intelligent Healthcare Support By: Pari Delir Haghighi, Arkady Zaslavsky, Shonali Krishnaswamy, Mohamed Medhat.

www.monash.edu.au

2

An Overview

• Introduction• The State-of-the-Art • Situation-Aware Adaptive Processing (SAAP) of

Data Streams • Fuzzy Situation Inference (FSI)• Adaptation Engine (AE) • Implementation• Evaluation• Future Work• Conclusion

Page 3: Www.monash.edu.au Mobile Data Mining for Intelligent Healthcare Support By: Pari Delir Haghighi, Arkady Zaslavsky, Shonali Krishnaswamy, Mohamed Medhat.

www.monash.edu.au

3

Introduction

Mobile healthcare services: • provide a convenient, safe and constant way of

monitoring of vital signs • development of mobile healthcare applications

encouraged by– innovations in mobile communications – low-cost of wireless biosensors

• the issues:– maintaining continuity of running applications on mobile

devices– enabling real-time analysis of data and decision making

Page 4: Www.monash.edu.au Mobile Data Mining for Intelligent Healthcare Support By: Pari Delir Haghighi, Arkady Zaslavsky, Shonali Krishnaswamy, Mohamed Medhat.

www.monash.edu.au

4

The State-of-the-Art (1)

• recent works in mobile healthcare – mostly focused on using, enhancing or combining existing

technologies> projects: EPI-MEDICS [RFN05],MobiHealth [MWH07]

– limited use of context-awareness – lack of resource-aware data analysis techniques

• a need for a general approach:– performing smart and cost-efficient analysis of data

in real-time– providing a general model for representation of

real-world and health-related situations

Page 5: Www.monash.edu.au Mobile Data Mining for Intelligent Healthcare Support By: Pari Delir Haghighi, Arkady Zaslavsky, Shonali Krishnaswamy, Mohamed Medhat.

www.monash.edu.au

5

The State-of-the-Art (2)

Ubiquitous Data Stream Mining (UDM) – real-time analysis of data streams on-board

small/mobile devices > techniques and algorithms for resource-aware data

stream mining [GKZ05]

• However, to perform smart and intelligent analysis of data on mobile devices

– imperative to factor in contextual information

Page 6: Www.monash.edu.au Mobile Data Mining for Intelligent Healthcare Support By: Pari Delir Haghighi, Arkady Zaslavsky, Shonali Krishnaswamy, Mohamed Medhat.

www.monash.edu.au

6

Situation-aware Adaptive Processing (SAAP) of Data Streams

SAAP:

1. incorporates situation-awareness into data stream mining

2. performing situation-aware adaptation of data streaming parameters according to occurring situations and available resources

3. situation-awareness achieved by Fuzzy Situation Inference (FSI) model– FSI combines fuzzy logic principles with the

Context Spaces (CS) model> a general context modeling and reasoning approach for

pervasive computing environments

Page 7: Www.monash.edu.au Mobile Data Mining for Intelligent Healthcare Support By: Pari Delir Haghighi, Arkady Zaslavsky, Shonali Krishnaswamy, Mohamed Medhat.

www.monash.edu.au

7

The Framework of SAAP

Page 8: Www.monash.edu.au Mobile Data Mining for Intelligent Healthcare Support By: Pari Delir Haghighi, Arkady Zaslavsky, Shonali Krishnaswamy, Mohamed Medhat.

www.monash.edu.au

9

Fuzzy Situation Inference (FSI)

• FSI inspired by the Context Spaces (CS) Model [PAD04]• The CS model

advantages:> deals with uncertainty associated with sensors’

inaccuracies

disadvantages:> does not deal with other aspect of uncertainty related to

human concepts and real-world situations

• FSI integrates fuzzy logic principles into the CS model FSI– enables representation of vague situations – reflects minor and delta changes in the inference results

Page 9: Www.monash.edu.au Mobile Data Mining for Intelligent Healthcare Support By: Pari Delir Haghighi, Arkady Zaslavsky, Shonali Krishnaswamy, Mohamed Medhat.

www.monash.edu.au

10

FSI: Situation Modeling

• linguistic variables: e.g. heart rate• terms/Fuzzy sets: e.g. low, normal, fast• membership functions to map input data into fuzzy sets

• A FSI Rule defines a situation– consists of multiple conditions joined with the AND operator

> each condition can be a disjunction of conditions

e.g. if Room-Temperature is ‘hot’ and Heart-Rate is ‘fast’ and ( Age is ‘middle-aged’ or ‘old) then situation is ’heat stroke’ ’

Page 10: Www.monash.edu.au Mobile Data Mining for Intelligent Healthcare Support By: Pari Delir Haghighi, Arkady Zaslavsky, Shonali Krishnaswamy, Mohamed Medhat.

www.monash.edu.au

11

n

iiicwConfidence

1

n

iii xwConfidence

1

)(

Reasoning technique 1Heuristics: weight and contribution

CS

FSI

Reasoning technique 2Heuristics: sensors’ inaccuracy

CS

FSI

n

ii

tii AawConfidence

1

)ˆPr(.

)),((1

n

iiii exfwConfidence

Reasoning technique 3 and 4Heuristics: Symmetric and Asymmetric context attributes, partial and complete containment

CS

FSI

CS

FSI

n

ii

tii AawConfidence

1

)ˆPr(.ˆASi CACAa where

)),((ˆ1

n

iiii exfwConfidence where FSxi AS LVLVFS and

Reasoning Techniques (1,2, 3)

m

kk

tk

n

ii

tii AapqAapwqConfidence

12

11 )ˆ()ˆ(.ˆ 121 qqwhere

SkASi CAaCACAa ,and

m

kkk

n

iiii exfqexfwqConfidence

12

11 )),((),((.ˆ

Page 11: Www.monash.edu.au Mobile Data Mining for Intelligent Healthcare Support By: Pari Delir Haghighi, Arkady Zaslavsky, Shonali Krishnaswamy, Mohamed Medhat.

www.monash.edu.au

12

SAAP

• Fuzzy Situation Inference (FSI) Engine• Adaptation Engine (AE)

– Resource-aware strategies– Situation-aware strategies– Hybrid strategies

Page 12: Www.monash.edu.au Mobile Data Mining for Intelligent Healthcare Support By: Pari Delir Haghighi, Arkady Zaslavsky, Shonali Krishnaswamy, Mohamed Medhat.

www.monash.edu.au

13

Adaptation Engine (AE)

Page 13: Www.monash.edu.au Mobile Data Mining for Intelligent Healthcare Support By: Pari Delir Haghighi, Arkady Zaslavsky, Shonali Krishnaswamy, Mohamed Medhat.

www.monash.edu.au

14

The Controller

Cases Adaptation Strategy

1 – R at safe level and S at safe Level Situation-aware

2 – R at safe level and S at medium level Situation-aware

3 – R at safe level and S at critical level Situation-aware

4 – R at medium level and S at safe level Resource-aware

5 – R at medium level and S at medium level Hybrid

6 – R at medium level and S at critical level Hybrid

7 – R at critical level and S at safe level

8 – R at critical level and S at medium level

9 – R at critical level and S at critical level

Other strategies e.g. migration

Page 14: Www.monash.edu.au Mobile Data Mining for Intelligent Healthcare Support By: Pari Delir Haghighi, Arkady Zaslavsky, Shonali Krishnaswamy, Mohamed Medhat.

www.monash.edu.au

15

• Lightweight data stream mining algorithms– Adjusting mining parameters according to resource

availability – E.g: LWC (LightWeight Clustering) [GKZ05]

> considers a threshold distance measure for clustering

> Increasing the threshold discourages forming of new clusters

– in turn reduces memory consumption

Resource-aware Adaptation

Page 15: Www.monash.edu.au Mobile Data Mining for Intelligent Healthcare Support By: Pari Delir Haghighi, Arkady Zaslavsky, Shonali Krishnaswamy, Mohamed Medhat.

www.monash.edu.au

16

Situation-aware Adaptation

• based on the concept of resource-aware adaptation

• but adjustment of parameters according to results of situation inference (FSI engine)

• starts with pre-set values of parameters for each situation

• at run-time based on degree of fuzziness of each situation these parameters adjusted

n

i

n

iijij pp

1 1

/ˆ µ: degree of fuzziness of each situation

p: parameter value

Page 16: Www.monash.edu.au Mobile Data Mining for Intelligent Healthcare Support By: Pari Delir Haghighi, Arkady Zaslavsky, Shonali Krishnaswamy, Mohamed Medhat.

www.monash.edu.au

17

Hybrid Adaptation

• when both resources and situations are getting critical

• a trade-off between the results of these two strategies

• hybrid method combines resource-aware and situation-aware strategies and deals with the trade-off:

SR

SSRRI ycriticalitycriticalit

ycriticalitpycriticalitpp

).ˆ().ˆ(

ˆcriticality of resources and situations represented by a value between 0 and 1

Page 17: Www.monash.edu.au Mobile Data Mining for Intelligent Healthcare Support By: Pari Delir Haghighi, Arkady Zaslavsky, Shonali Krishnaswamy, Mohamed Medhat.

www.monash.edu.au

18

Implementation

• healthcare monitoring application

• Implemented in J2ME

• deployed on a Nokia N95 mobile phone

• situations: ‘normal’, ‘Pre-Hypotension’, ‘Hypotension’, ‘Hypertension’ and ‘Pre-Hypertension’

• context: SBP, DBP and HR

• using a Bluetooth-enabled ECG sensor

Page 18: Www.monash.edu.au Mobile Data Mining for Intelligent Healthcare Support By: Pari Delir Haghighi, Arkady Zaslavsky, Shonali Krishnaswamy, Mohamed Medhat.

www.monash.edu.au

19

Evaluation of FSI

A Comparative Evaluation • The reasoning approaches

– FSI– CS– Dempster-Shafer (DS)

• to highlight the benefits of the FSI for reasoning about uncertain situations

Page 19: Www.monash.edu.au Mobile Data Mining for Intelligent Healthcare Support By: Pari Delir Haghighi, Arkady Zaslavsky, Shonali Krishnaswamy, Mohamed Medhat.

www.monash.edu.au

20

FSI Evaluation: Dataset

• The dataset:– generated continuously (data rate is 30 records/minute) in ascending

order– 131 context states– used our data synthesizer

> to represent the different events (of the DS model) – contribute to the occurrence of each pre-defined situation as well as the

uncertain situations

Context attribute scales Corresponding DS events SBP:40-65, DBP: 20-45, HR: 20-45 SBPLow, DBPLow, HRSlow SBP:66-80, DBP: 46-60, HR: 46-60 SBPLow, DBPLow, HRMed SBP:81-85, DBP: 61-65, HR: 61-65 SBPLow, DBPMed, HRMed SBP:86-105, DBP: 66-85, HR: 66-85 SBPMed, DBPMed, HRMed SBP:106-130, DBP: 86-110, HR: 86-110 SBPMed, DBPMed, HRHigh SBP:131-135, DBP: 111-115, HR: 111-115 SBPLow, DBPHigh, HRHigh SBP:136-170, DBP: 116-150, HR: 116-150 SBPHigh, DBPHigh, HRHigh

Page 20: Www.monash.edu.au Mobile Data Mining for Intelligent Healthcare Support By: Pari Delir Haghighi, Arkady Zaslavsky, Shonali Krishnaswamy, Mohamed Medhat.

FSI Evaluation: Results

Comparison of DS, CS and FSI for Normal

0

0.2

0.4

0.6

0.8

1

1.2

1 11 21 31 41 51 61 71 81 91 101 111 121 131

Data Rows

Lev

el o

f C

on

fid

ence

FSI_N

CS_N

DS_N

Comparison of DS, CS and FSI for Hypertension

0

0.2

0.4

0.6

0.8

1

1.2

1 11 21 31 41 51 61 71 81 91 101 111 121 131

Data Rows

Lev

el o

f C

on

fid

ence

FS_Hyper

CS_Hyper

DS_Hyper

Comparison of DS, CS and FSI Hypotension

0

0.2

0.4

0.6

0.8

1

1.2

1 11 21 31 41 51 61 71 81 91 101 111 121 131

Data RowsL

evel

of

Co

nfi

den

ce

FS_Hypo

CS_Hypo

DS_Hypo

Page 21: Www.monash.edu.au Mobile Data Mining for Intelligent Healthcare Support By: Pari Delir Haghighi, Arkady Zaslavsky, Shonali Krishnaswamy, Mohamed Medhat.

www.monash.edu.au

22

FSI Evaluation: Results

• when situations are stable and pre-defined (not vague) – all have a relatively similar trend– more noticeable with the CS and FSI models

• when situations change and evolve – the CS and DS methods show sudden rises and falls with

sharp edges> not matching the real-life situations

– Yet FSI reflects very minor changes between situations> represent changes in a more gradual and smooth manner

> more appropriate approach for health monitoring applications

Page 22: Www.monash.edu.au Mobile Data Mining for Intelligent Healthcare Support By: Pari Delir Haghighi, Arkady Zaslavsky, Shonali Krishnaswamy, Mohamed Medhat.

www.monash.edu.au

23

Evaluation of Situation-aware Adaptation

• Data stream mining algorithm used – the LWC algorithm

• situations– ‘normal’, ‘hypertension’ and ‘hypotension’ – situations’ importance: 0.1, 0.9 and 0.5– parameter set values: 42 (normal), 10 (hypertension) and 26

(hypotension) – context attributes: SBP, DBP and HR

• Dataset– the same used in the FSI evaluation

> 131 context states (rows)

Page 23: Www.monash.edu.au Mobile Data Mining for Intelligent Healthcare Support By: Pari Delir Haghighi, Arkady Zaslavsky, Shonali Krishnaswamy, Mohamed Medhat.

www.monash.edu.au

24

SA Evaluation: Results

0

0.2

0.4

0.6

0.8

1

1.2

26 26 26 29 32 42 42 35 35 29 10 10 10 10

Data Stream Algorithm Threshold

Lev

el o

f C

on

fid

ence

of

Sit

uat

ion

FSI_N

FS_Hypo

FS_Hyper

Page 24: Www.monash.edu.au Mobile Data Mining for Intelligent Healthcare Support By: Pari Delir Haghighi, Arkady Zaslavsky, Shonali Krishnaswamy, Mohamed Medhat.

www.monash.edu.au

25

SA Evaluation: Results

• threshold value automatically adjusted according to the fuzziness and membership degree of each situation

• when situations are normal, threshold increases– increasing the threshold value for normal situations

decreases the mining output – reduces resource consumption

• when situation get critical, threshold decreases – increases the number of the output (clusters) and

accuracy level of results that is required for closer monitoring

Page 25: Www.monash.edu.au Mobile Data Mining for Intelligent Healthcare Support By: Pari Delir Haghighi, Arkady Zaslavsky, Shonali Krishnaswamy, Mohamed Medhat.

www.monash.edu.au

26

Future work

• currently finalizing implementation and evaluation of hybrid adaptation using RA-Cluster

• using RA-Cluster enables adaptation of sampling rate according to battery charge

• integrating time-constraint into adaptation of battery usage

• working on testing of our prototype in real-world situation in conjunction with relevant healthcare professionals

Page 26: Www.monash.edu.au Mobile Data Mining for Intelligent Healthcare Support By: Pari Delir Haghighi, Arkady Zaslavsky, Shonali Krishnaswamy, Mohamed Medhat.

www.monash.edu.au

27

References

[GZK04] Gaber MM, Zaslavsky A, Krishnaswamy S (2004), A Cost-Efficient Model for Ubiquitous Data Stream Mining, Proceedings of the Tenth International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems, Perugia Italy.

[GKZ05]Gaber MM, Krishnaswamy S, Zaslavsky A (2005) On-board Mining of Data Streams in Sensor Networks”, A Book Chapter in Advanced Methods of Knowledge Discovery from Complex Data, (Eds.) S. Badhyopadhyay, U. Maulik, L. Holder and D. Cook, Springer Ver-lag.

[MWH07] Mei, H., Widya, I., Halteren, A.V., and Erfianto, B., A Flexible Vital Sign Representation Framework for Mobile Healthcare. 2007.

[PLZ05] Padovitz, A., Loke, S.W., Zaslavsky, A., Burg, B. and Bartolini, C.: An Approach to Data Fusion for Context-Awareness. Fifth International Conference on Modeling and Using Context, CONTEXT’05, Paris, France (2005).

[PZL06] Padovitz, A., Zaslavsky, A. and Loke, S.W.:. A Unifying Model for Representing and Reasoning About Context under Uncertainty, 11th International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems (IPMU), July 2006, Paris, France (2006).

[RFN05] Rubel, P., Fayn, J., Nollo, G., Assanelli, D., Li, B., Restier, L., Adami, S., Arod, S.,Atoui, H., Ohlsson, M., Simon-Chautemps, L., Te´lisson, D., Malossi, C., Ziliani, G., Galassi, A., Edenbrandt, L., and Chevalier, Ph., Toward Personal eHealth in Cardiology: Results from the EPI-MEDICS Telemedicine Project. Journal of Electrocardiology 2005. 38: p. 100-106

Page 27: Www.monash.edu.au Mobile Data Mining for Intelligent Healthcare Support By: Pari Delir Haghighi, Arkady Zaslavsky, Shonali Krishnaswamy, Mohamed Medhat.

www.monash.edu.au

28

Thank you

Questions?