Presentation is loading. Please wait.

Presentation is loading. Please wait.

Accurate Caloric Expenditure of Bicyclists using Cellphones Andong Zhan, Marcus Chang, Yin Chen, Andreas Terzis Johns Hopkins University 1.

Similar presentations


Presentation on theme: "Accurate Caloric Expenditure of Bicyclists using Cellphones Andong Zhan, Marcus Chang, Yin Chen, Andreas Terzis Johns Hopkins University 1."— Presentation transcript:

1 Accurate Caloric Expenditure of Bicyclists using Cellphones Andong Zhan, Marcus Chang, Yin Chen, Andreas Terzis Johns Hopkins University 1

2 Biking Renaissance A biking renaissance has been underway over the past two decades in North America 2 Pucher et al., Bicycling renaissance in North America? An update and re-appraisal of cycling trends and policies, Transportation Research Part A 45 (2011) Introduction

3 Biking Renaissance (Cont’d) 3 The National Bicycling and Walking Study: 15-Year Status Report, May 2010 Pedestrain and Bicycle Information Center, U.S. Department of Transportation Introduction

4 Go with Mobile Bikers’ cellphones become smarter Bikers start to use mobile apps to track their trips –E.g., iMapMyRIDE, endomondo A important feature is to estimate caloric expenditure 4 Introduction

5 Estimate Caloric Expenditure However, current approach – search table – is not accurate 5 State of Wisconsin Department of Health and Family Services: Calories Burned Per Hour Introduction

6 How to track caloric expenditure accurately? –Integrate more sensors! –Pay more! money, battery, …, burden Estimate Caloric Expenditure (Cont’d) 6 Power meter crankset Heart rate monitor Cadence sensor Introduction

7 Contribution We design and implement a modular mobile sensing system to enable four major calorie estimators We introduce our “software method” on smartphone to replace external “hardware sensors” –Cadence: Cadence sensor  phone-held accelerometer analysis –Elevation: Pressure sensor  fitted and smoothed USGS elevation Finally, we achieve the goal – accurately estimate caloric expenditure with just one smartphone 7 Introduction

8 1.Search Table –Cal = f(speed, time, weight) 2.Heart Rate Monitor –Cal = f(bpm, weight, age, time) 3.Cadence Sensing [AI-Haboubi et. al.] –Cal = f(rpm, speed, weight) Caloric Estimators 8 Al-Haboubi et al., Modeling energy expenditure during cycling, Ergonomics, 42:3: , 1999 System Design

9 Caloric Estimators (Cont’d) 4.Power measurement [ Martin et al. ] –Calorie is linear with the total amount of work to move the combined mass of the bike and the biker 9 Martin et al., Validation of a Mathematical Model for Road Cycling Power. Journal of Applied Physiology, 82:345, coefficient of rolling resistance slope coefficient of aerodynamic drag Wind velocity System Design

10 System overview 10 System Design

11 Data collection 15 bike routes around JHU campus Each can be completed within 20 min Stable weather condition sample GPS, heart rate, and pressure sensor once per second Accelerometer sample rate at 50 Hz 11 JHU System Design RouteDist. (km)Road Conditions R11.5Neighborhood, uphill R22.1Neighborhood, uphill R30.8Neighborhood, downhill R40.8Neighborhood, uphill R52.1Neighborhood, downhill R61.1Neighborhood, downhill SMDN& SMDS 1.5Woods, river valley, ups and downs, winding path SMDC2.4Woods, river valley, ups and downs, winding path DL2.5Lakeside, flat, open field WW1.7Bridges, ups and downs WE1.7Bridges, ups and downs HJ2.9Neighborhood, bridge, downhill JH2.9Neighborhood, bridge, uphill C3.9Flat, circle, open field

12 Cadence Sensing in the Pocket Get rpm from raw accelerometer data 12 T1 T2 T3 Step 1. remove T1 vibrations and get the axis with the largest variance Step 2. apply a low-pass filter and get the derivative of the data Step 3. utilize k-means to cluster two types based on the amplitude of the immediately previous peak System Design

13 Elevation measurement Where to get elevation? –Pressure sensor –GPS –U.S. Geological Survey (USGS) –Google 13 “bridge error” System Design

14 Elevation measurement (Cont’d) Fitting –Fit (x, y) to the most likely road in OpenStreetMap Smoothing –Use a robust local regression method: fit to a quadratic polynomial model with robust weights: 14 System Design Bridge error is corrected by smoothing

15 Evaluation Hardware sensors vs. software approaches –Cadence sensor vs. Accelerometer sensing in the pocket –Pressure sensor vs. Elevation services Caloric expenditure estimation for multiple bikers 15 Evaluation

16 Cadence sensing Use cadence sensor as ground truth 29 traces collected by two volunteers –Total length is 30.3 km –Total 5,377 revolutions The relative error is less than 2% The error per km is less than 4 revolutions 16 Relative error per trip (%)0.19 ± 1.59 Error per kilometer-0.09 ± 3.40 Evaluation

17 Elevation services 15 traces on 12 routes from Mar. to Apr Total of 4,780 GPS and pressure sample pairs 95% of USGS’s RMS are less than 1.2 m 95% of Google’s RMS are less than 5.4 m 17 Evaluation Elevation ServiceRRMS (m) USGS USGS fitted USGS fitted & smoothed Google Google fitted Google fitted & smoothed GPS

18 Caloric Expenditure Estimation for Multiple Bikers Use Heart Rate Monitor as ground truth Compare calories estimated from Search table (TAB), Cadence sensing (CAD), and power measurement (USGS+FSW) Recruited 20 volunteers from JHU –Wear a heart rate strap + a smartphone in the pocket –17 male and 3 female –Age from 24 to 32, weight from 110 to 175 lbs. Calibrated 8 bikes –3 road, 4 cruiser, and 1 mountain bikes –Cr = 0.07 ~ 0.21, Ca = 0.26 Collect 70 trips during one week –At least 3 trips for each volunteer 18 Evaluation

19 Flat route: Druid Lake 2.5 km flat circular bike lane Collected 10 trips from 7 bikers 19 Evaluation

20 Route: Roland 1 & km, cross neighborhood Uphill and downhill path m 70m Evaluation

21 Route: Roland 1, uphill 21 Evaluation Both CAD and TAB fail to provide an accurate caloric expenditure estimation for uphill trips

22 Route: Roland 6, downhill 22 Evaluation USGS+FSW adapt to both uphill and downhill trips

23 Route: St. Martin Dr. A winding road along with a river valley The elevation difference between two sides of the road can be 10 meters 11 trips across 8 bikers 23 Evaluation

24 Route: St. Martin Dr. 24 Evaluation Fitting method eliminates most of the errors in this situation

25 Route: Wyman Park Cross two bridges: 140, and 67 meters long 25 Evaluation

26 Route: Wyman Park 26 Evaluation Smoothing corrects “bridge errors” without adding new errors

27 Overall – 70 Trips 27 Evaluation USGS+FSW achieves the lowest error with lowest variance

28 Reducing GPS Power Consumption Duty-cycling the GPS receiver *Fang et. al., EnAcq: energy-efficient GPS trajectory data acquisition based on improved map matching. In Proc. of GIS ‘11, 2011 * 28 Evaluation

29 Pocket Sensing Approach 29 GPS Accelerometer USGS Weather Cadence Calories

30 Conclusion Just using a smartphone provides comparable accuracy to the best methods that uses external sensors Our work immediately gives millions of bikers a zero-cost solution towards significantly improved biking experiences The shift from physical to virtual or software sensors will find other applications in quantifying daily lives and activities 30

31 Acknowledgement We are grateful to 20 volunteers that participated in the biking test Thanks to our shepherd Vijay Raghunathan and the anonymous reviewers This work is partially supported by NSF and by Google through a generous equipment gift 31

32 Q&A 32

33 Q1: about innovation of accelerometer sensing for biking Previous work, e.g., BikeNet, focuses on activity classification –Identify cycling, or walking, etc. Our work is different –We assume the biker is biking, and try to qualify the activity intensity, e.g., RPM. 33

34 Q2: about online or offline of our application In this work, –Data collection is an online application –Evaluation is done offline But, our approach can be implemented as an online application –The details is described on our paper 34

35 Q3: do you need to manually smooth the bridge part of the data No, we use smoothing method on the whole data/trace Since the smoothing method only ignores outliers/bridge, it does not generate new errors So we do not need to manually choose bridge part to smooth, instead, we use smooth on all data/trace. 35


Download ppt "Accurate Caloric Expenditure of Bicyclists using Cellphones Andong Zhan, Marcus Chang, Yin Chen, Andreas Terzis Johns Hopkins University 1."

Similar presentations


Ads by Google