Accurate Caloric Expenditure of Bicyclists using Cellphone SenSys2012 Andong Zhan, Marcus Chang, Yin Chen, Andreas Terzis Computer Science Department Johns.

Slides:



Advertisements
Similar presentations
Andreas Schrempf, Thomas Minarik Upper Austria University of Applied Sciences Medical Engineering Linz, Austria An interactive.
Advertisements

An Interactive-Voting Based Map Matching Algorithm
Biomechanics of Cycling
Energy Costs of Physical Activity
Slide Ruler. ? X 5" On today’s menu...  What happened with Gravity  Noise  The tool today  Fundamental Limitations  Magical Christmas Land  (Where.
Accurate Caloric Expenditure of Bicyclists using Cellphones Andong Zhan, Marcus Chang, Yin Chen, Andreas Terzis Johns Hopkins University 1.
VTrack: Accurate, Energy-Aware Road Traffic Delay Estimation Using Mobile Phones Arvind Thiagarajan, Lenin Ravindranath, Katrina LaCurts, Sivan Toledo,
SunCast: Fine-grained Prediction of Natural Sunlight Levels for Improved Daylight Harvesting Jiakang Lu and Kamin Whitehouse Department of Computer Science,
Propagation of Error Ch En 475 Unit Operations. Quantifying variables (i.e. answering a question with a number) 1. Directly measure the variable. - referred.
CITS2401 Computer Analysis & Visualisation
Tracking Fine-grain Vehicular Speed Variations by Warping Mobile Phone Signal Strengths Presented by Tam Vu Gayathri Chandrasekaran*, Tam Vu*, Alexander.
T-Drive : Driving Directions Based on Taxi Trajectories Microsoft Research Asia University of North Texas Jing Yuan, Yu Zheng, Chengyang Zhang, Xing Xie,
Presenter: Laura Pina CSE 291. Why Do We Need a System to Estimate Calorie Expenditure?  In 2007, 35% of US adults were considered overweight by the.
A Development and Parallelization of an air temperature Spatial Interpolation and Prediction Program Student: Erik LaBerge Advisor: Munihiro Fukuda.
Validated Caloric Expenditure Estimation using a Single Body-Worn Sensor Validated Caloric Expenditure Estimation using a Single Body-Worn Sensor.
Energy-Efficient Rate-Adaptive GPS-based Positioning for Smartphones Jeongyeup Paek USC Annenberg Graduate Fellowship Program The Second Annual Research.
WFM 6202: Remote Sensing and GIS in Water Management © Dr. Akm Saiful IslamDr. Akm Saiful Islam WFM 6202: Remote Sensing and GIS in Water Management Akm.
Monitoring of Activity Levels of the Elderly in Home and Community Environments using Off the Shelf Cellular Handsets Initial Presentation by Martin Newell.
Tracking Moving Objects in Anonymized Trajectories Nikolay Vyahhi 1, Spiridon Bakiras 2, Panos Kalnis 3, and Gabriel Ghinita 3 1 St. Petersburg State University.
An Evaluation of Interpolation Methods for MOLA Data Oleg Abramov and Alfred McEwen: Department of Planetary Sciences, University of Arizona INTRODUCTION.
Distributed Structural Health Monitoring A Cyber-Physical System Approach Chenyang Lu Department of Computer Science and Engineering.
Chapter 6 Numerical Interpolation
Barometric Altimetry Using the Vernier LabPro. Purpose of Report Improved altitude determination for Balloon Fest and other activities Improved altitude.
U.S. Department of the Interior U.S. Geological Survey Development of Inferential Sensors for Real-time Quality Control of Water- level Data for the EDEN.
Comparison of LIDAR Derived Data to Traditional Photogrammetric Mapping David Veneziano Dr. Reginald Souleyrette Dr. Shauna Hallmark GIS-T 2002 August.
Shanshan Chen, Christopher L. Cunningham, John Lach UVA Center for Wireless Health University of Virginia BSN, 2011 Extracting Spatio-Temporal Information.
Predicted VO 2 max. Maximal Oxygen Consumption What is it & Why measure it ? Greatest volume of oxygen that the body can consume per unit time Regarded.
Unit 8 POE Ballistic Device
Sensys 2009 Speaker:Lawrence.  Introduction  Overview & Challenges  Algorithm  Travel Time Estimation  Evaluation  Conclusion.
Speed and Direction Prediction- based localization for Mobile Wireless Sensor Networks Imane BENKHELIFA and Samira MOUSSAOUI Computer Science Department.
Applied Cartography and Introduction to GIS GEOG 2017 EL Lecture-3 Chapters 5 and 6.
Work and Energy. Outcomes Upon completion of this unit you will be able to: Analyze force problems in terms of energy. Define the term "work" as it relates.
Navigating and Browsing 3D Models in 3DLIB Hesham Anan, Kurt Maly, Mohammad Zubair Computer Science Dept. Old Dominion University, Norfolk, VA, (anan,
Presented by: Z.G. Huang May 04, 2011 Did You See Bob? Human Localization using Mobile Phones Romit Roy Choudhury Duke University Durham, NC, USA Ionut.
RunningStyle. Background Drag is used in physics and engineering. It’s central to the field of fluid dynamics and is also called air or fluid resistance.
Dynamic thermal rating of power transmission lines related to renewable resources Jiri Hosek Institute of Atmospheric Physics, Prague, Czech Rep.
U NIVERSITY OF M ASSACHUSETTS A MHERST Department of Computer Science 2011 Predicting Solar Generation from Weather Forecasts Using Machine Learning Navin.
APT: Accurate Outdoor Pedestrian Tracking with Smartphones TsungYun
Estimate of Swimming Energy Expenditure Utilizing an Omnidirectional Accelerometer and Swim Performance Measures Jeanne D. Johnston and Joel M. Stager,
A Hybrid Method for achieving High Accuracy and Efficiency in Object Tracking using Passive RFID Lei Yang 1, Jiannong Cao 1, Weiping Zhu 1, and Shaojie.
Analysis of Naturalistic Electric Bike Rider Behavior: Energy and Power Considerations Authors: Noelani Fishman, Breanna Piercy Affiliation: Kwaku Boakye,
Machine Learning Approach to Report Prioritization with an Application to Travel Time Dissemination Piotr Szczurek Bo Xu Jie Lin Ouri Wolfson.
Human Activity Recognition Using Accelerometer on Smartphones
Energy Efficient Location Sensing Brent Horine March 30, 2011.
Elastic Pathing: Your Speed Is Enough to Track You Presented by Ali.
HiQuadLoc: An RSS-Based Indoor Localization System for High-Speed Quadrotors 1 Tuo Yu*, Yang Zhang*, Siyang Liu*, Xiaohua Tian*, Xinbing Wang*, Songwu.
Relative Accuracy based Location Estimation in Wireless Ad Hoc Sensor Networks May Wong 1 Demet Aksoy 2 1 Intel, Inc. 2 University of California, Davis.
Siyuan Liu *#, Yunhuai Liu *, Lionel M. Ni *# +, Jianping Fan #, Minglu Li + * Hong Kong University of Science and Technology # Shenzhen Institutes of.
Propagation of Error Ch En 475 Unit Operations. Quantifying variables (i.e. answering a question with a number) 1. Directly measure the variable. - referred.
Heavier-than-air flight is made possible by a careful balance of four physical forces: lift, drag, weight, and thrust. For flight, an aircraft's lift.
Interpolation.
West Hills College Farm of the Future The Precision-Farming Guide for Agriculturalists Chapter Seven Variable Rate Technologies.
The Pothole Patrol: Using a Mobile Sensor Network for Road Surface Monitoring Jakob Eriksson, Lewis Girod, Bret Hull, Ryan Newton, Samuel Madden, Hari.
Dead Reckoning with Smart Phone Sensors for Emergency Rooms Ravi Pitapurapu, Ajay Gupta, Kurt Maly, Tameer Nadeem, Ramesh Govindarajulu, Sandip Godambe,
Real-Time Trip Information Service for a Large Taxi Fleet
Theory of Flight All are demonstrated by the flight of the bird!
Turning a Mobile Device into a Mouse in the Air
Statistics Presentation Ch En 475 Unit Operations.
Nonlinear differential equation model for quantification of transcriptional regulation applied to microarray data of Saccharomyces cerevisiae Vu, T. T.,
Measurement of Energy Expenditure The unit of measurement for energy is the kilocalorie (kcal) –Quantity of heat necessary to raise the temp. of 1 kg (liter)
ParkNet: Drive-by Sensing of Road-Side Parking Statistics Irfan Ullah Department of Information and Communication Engineering Myongji university, Yongin,
Integrating LiDAR Intensity and Elevation Data for Terrain Characterization in a Forested Area Cheng Wang and Nancy F. Glenn IEEE GEOSCIENCE AND REMOTE.
Body Area Sensor Networks I CSE 40437/60437-Spring 2015 Prof. Dong Wang 1.
MART: Music Assisted Running Trainer
Dynamic Fine-Grained Localization in Ad-Hoc Networks of Sensors
ABSTRACT   Recent work has shown that sink mobility along a constrained path can improve the energy efficiency in wireless sensor networks. Due to the.
Making Exercise Easy Matthew Penk.
MATH 2140 Numerical Methods
QGesture: Quantifying Gesture Distance and Direction with WiFi Signals
SpecSense: Crowdsensing for Efficient Querying of Spectrum Occupancy
Presentation transcript:

Accurate Caloric Expenditure of Bicyclists using Cellphone SenSys2012 Andong Zhan, Marcus Chang, Yin Chen, Andreas Terzis Computer Science Department Johns Hopkins University Baltimore, MD NSLab study group 2012/11/12 Speaker : Chia-Chih,Lin

Outline Introduction Background System design Evaluation Discussion Conclusion Comment

Motivation Diverse benefits Especially from a health perspective People usually care about caloric expenditure sensor such as – power meter – cadence sensors – and heart rate monitor but expensive (above $1000) and cumbersome

Motivation cont. Want to calculate accurate caloric expenditure Without high cost and cumbersome devices Can we just use a smart phone in pocket to solve the problem?

Challenges Existing apps do not directly measure the cyclist’s activity Errors in GPS measurement Do not consider the slope Energy consumption

contribution Pocket sensing approach replace on-bike hardware – Measure cadence less than 2% error – Overall caloric estimation error is 60% smaller than other apps – Reduce energy consumption by 57% Compare and analyze major elevation service – Find and minimize error on both USGS and Google Map caused by bridge Show that leveraging detailed map information from USGS and OpenStreetMap can save a significant amount of energy

Outline Introduction Background System design Evaluation Discussion Conclusion Comment

How to calculate? Four caloric expenditure estimators – Search Table – Cadence and Speed Sensing – Heart Rate Monitoring – Power Measurement

Search Table Input : average speed, trip duration, biker’s weight Low accuracy(do not consider slope)

Cadence and Speed Sensing Use sensor to measure pedaling speed(RPM) VO 2 : oxygen consumption(liter per minute) – V : bike velocity – S : pedaling speed Estimate caloric by VO 2 *5 (Kcal/min) Drawback : underestimate during uphill trips

Heart Rate Monitoring Takes heart rate and VO 2 max as input and adjusting for age, gender, body mass, and fitness level VO 2 max is a good measure of aerobic condition, requires 12 minutes rush to test where D is distance (m)

Heart Rate Monitoring cont. Then, where BPM is the heart rate in beats/min High accuracy but cumbersome for daily use

Power Measurement Related to the total amount of work necessary to move the combined mass of the biker and bike from start to finish Where Vg is a constant ground speed and F is the force generate by the rider along the direction of movement

Power Measurement cont.

Fr : rolling resistance from the bike Fg : component of gravity along the direction of movement Fa : force of aerodynamic drag m : mass of bike and biker Cr : lumped coefficient of rolling resistance S : slope,where Vw is wind vector : temperature dependent air density Ca : lumped constant for aerodynamic drag

Power Measurement cont. Then One can estimate the calories burned/s Calories burned = P*25%

Outline Introduction Background System design Evaluation Discussion Conclusion Comment

System design

Data Collection 15 bike routes located around Jonh Hopkins University’s Homewood campus in Baltimore All the routes can be complete in 20 mins Samples GPS, pressure sensor, and heart rate monitor once per sec. Accelerometer 50Hz

Cadence Sensing in the Pocket

Elevation measurement Digital barometric pressure sensor – – where p 0 is pressure at sea level Phone’s GPS receiver(estimate altitude indirectly) – Use latitude and longitude to query GIS US Geological Service, USGS(3-meter resolution dataset) Google Maps(19-meter resolution dataset)

Elevation measurement Cont. Have to minimize GPS error first – Assume that all bike trips take place on either marked paths or roads – Use OpenStreetMap to match the nearest roads and project each GPS coordinate to the nearest point on this road

Bridge Error Altitude return not correct when biking on bridge Pressure sensor is more accuracy USGS and Google Map are fail

Bridge Error cont. Smooth the curve using a robust local regression method Use a quadratic polynomial model to fit the elevation data and set the span to be nine data points Weights for each data point in the span Where ri is the residual of the i-th data point, MAD = median(|r|)

Calibration of Power Measurement Lumped coefficients of rolling resistance Cr and aerodynamic drag Ca Ca : use an empirical reference value 0.26 Weather condition(temperature, wind speed,wind direction)

Outline Introduction Background System design Evaluation Discussion Conclusion Comment

Cadence Sensing

Elevation Services

Caloric Expenditure Estimation Single biker : – Search Table(TAB) – Cadence and Speed Sensing(CAD) – F for fitting, W for weather, S for smoothing

Caloric Expenditure Estimation Multiple biker :

Reduce GPS Power Consumtion Only consider two extreme case: Reconstruct the missing bike route points by : – Interpolating between the known point – Apply the state-of-art rout reconstruction mechanism called EnAcq algorithm

Reduce GPS Power Consumtion

Outline Introduction Background System design Evaluation Discussion Conclusion Comment

Discussion Feasibility – Can implement the cadence sensing and power measurement approaches in a real-time app – Can upload the raw trace to server instead of offline data analysis – Ideally, calibration only needs to be done once when first start to use

Outline Introduction Background System design Evaluation Discussion Conclusion Comment

Conclusion On-bike sensor, although expensive, can significantly improve the overall biking experience This work, get all information by using smart phone only Extensive result from 20bikers over 70bike trips confirmed that it is accuracy and feasible

Outline Introduction Background System design Evaluation Discussion Conclusion Comment

Good architecture Interesting approaches Complete analysis and evaluation

Q&A? Thanks for your listening !