Unsupervised Activity Clustering to Estimate Energy Expenditure with

  • Slides: 15
Download presentation
Unsupervised Activity Clustering to Estimate Energy Expenditure with a Single Sensor Shanshan Chen, John

Unsupervised Activity Clustering to Estimate Energy Expenditure with a Single Sensor Shanshan Chen, John Lach Oliver Amft Marco Altini, Julien Penders

1 Existing Solutions BSN?

1 Existing Solutions BSN?

2 Research on Energy Expenditure (EE) Estimation with BSN • Detailed Activity Recognition (AR)

2 Research on Energy Expenditure (EE) Estimation with BSN • Detailed Activity Recognition (AR) + Metabolic Equivalents (METs) • Annotation labeling work at the development stage • Lots of sensors to wear for the users • Lack of accuracy due to static number of METs • Detailed AR + regression • Labeling work at the development stage • More inertial sensors needed for better recognition accuracy • Detailed AR Grouped AR + regression • Reduced number of sensors – ECG + Accelerometer • Reduced challenges in high accuracy recognition • Data-driven clustering + regression • Bypass activity recognition • No labeling at the development stage

3 Proposed method • Focus on accurate EE estimation, not AR • Clustering based

3 Proposed method • Focus on accurate EE estimation, not AR • Clustering based on motion and heart rate, not activities • Data-driven clustering • Apply regression model based on data cluster • Unsupervised learning • No need to label activities during development stage • EE accuracy independent of AR accuracy Features from Data Group 1 Model 1 Group 2 Model 2 Group N Model N Clustering

4 Experiment Setup ▪ Single sensor node data (acceleration + heart rate) and validation

4 Experiment Setup ▪ Single sensor node data (acceleration + heart rate) and validation data (circulatory calorimeter) collection ▪ 10 subjects of various BMI ▪ 52 types of activities (sedentary activities and physical exercises)

5 Feature Extraction -- Preprocessing ▪ Heart rate ▪ Removing the motion artifact ▪

5 Feature Extraction -- Preprocessing ▪ Heart rate ▪ Removing the motion artifact ▪ Count peaks every 15 seconds ▪ Extract heart rate above rest ▪ Acceleration features extraction ▪ 4 seconds time window ▪ 18 features extracted in total Feature Extraction Machine Learning

6 Framework of Machine Learning Feature Selection (LASSO) 19 Features Dimension Reduction Multiple Linear

6 Framework of Machine Learning Feature Selection (LASSO) 19 Features Dimension Reduction Multiple Linear Regression

7 Model Comparison • Proposed model • Apply different regression models to different data

7 Model Comparison • Proposed model • Apply different regression models to different data clusters • Single multiple-linear regression model • Also activity-oblivious • Single regression model • AR-based model (Grouped AR + Regression) • Perfectly separated based on known activity labels • Non-ideally separated based on AR algorithms

8 Regression Results ▪ Proposed model is better than the single regression model ▪

8 Regression Results ▪ Proposed model is better than the single regression model ▪ With perfect labeling, activity specific model is the best ▪ However, accuracy of AR based method drop quickly when misclassification happens

9 Future Work • Explore other unsupervised learning techniques • Study interpretations of clusters

9 Future Work • Explore other unsupervised learning techniques • Study interpretations of clusters • Histogram of activities inside each cluster • Real-time implementation • Monitoring intensive activities only to save battery • Greater subject diversity • Combine with emerging energy intake techniques

10 Conclusion • Data-driven clustering for EE estimation • One light-weight sensor patch, easy

10 Conclusion • Data-driven clustering for EE estimation • One light-weight sensor patch, easy for the users to wear • No labeling of activities at the development stage • Final estimation accuracy does not depend on accuracy of AR • Improve linear regression model and AR based clustering • Drawback: • Does not track activities – orthogonal problem of accurate energy expenditure estimation

THANKS!

THANKS!

12 Histogram of Activities in Clusters å

12 Histogram of Activities in Clusters å

13 Clustering Results Training set clustering Testing set clustering

13 Clustering Results Training set clustering Testing set clustering

14 Physical Activities Comparison ▪ Physical activities are more interesting to monitor instead of

14 Physical Activities Comparison ▪ Physical activities are more interesting to monitor instead of the sedentary ones ▪ The proposed model achieves almost as good accuracy as activity specific model