Online citations, reference lists, and bibliographies.

Activity Recognition From User-Annotated Acceleration Data

L. Bao, S. Intille
Published 2004 · Computer Science

Cite This
Download PDF
Analyze on Scholarcy
Share
In this work, algorithms are developed and evaluated to de- tect physical activities from data acquired using five small biaxial ac- celerometers worn simultaneously on different parts of the body. Ac- celeration data was collected from 20 subjects without researcher su- pervision or observation. Subjects were asked to perform a sequence of everyday tasks but not told specifically where or how to do them. Mean, energy, frequency-domain entropy, and correlation of acceleration data was calculated and several classifiers using these features were tested. De- cision tree classifiers showed the best performance recognizing everyday activities with an overall accuracy rate of 84%. The results show that although some activities are recognized well with subject-independent training data, others appear to require subject-specific training data. The results suggest that multiple accelerometers aid in recognition because conjunctions in acceleration feature values can effectively discriminate many activities. With just two biaxial accelerometers - thigh and wrist - the recognition performance dropped only slightly. This is the first work to investigate performance of recognition algorithms with multiple, wire-free accelerometers on 20 activities using datasets annotated by the subjects themselves.
This paper references
UbiComp 2002: Ubiquitous Computing
G. Borriello (2002)
Validity and reliability of the ExperienceSampling Method
M. Csikszentmihalyi (1987)
10.3758/BF03195388
Measuring daily behavior using ambulatory accelerometry: The Activity Monitor
J. B. J. Bussmann (2001)
10.1007/978-94-017-9088-8_3
Validity and Reliability of the Experience-Sampling Method
M. Csikszentmihalyi (1987)
dy - namic identification of physiological and activity context in wearable computing
D. P. Siewiorek A. Krause (2003)
10.1007/3-540-45809-3_28
WearNET: A Distributed Multi-sensor System for Context Aware Wearables
P. Lukowicz (2002)
10.1109/ICSMC.2001.973004
Recognizing human motion with multiple acceleration sensors
Jani Mäntyjärvi (2001)
Data mining: practical machine learning tools and techniques, 3rd Edition
I. Witten (1999)
10.1007/BF02513304
Physical activity monitoring based on accelerometry: validation and comparison with video observation
K. Aminian (2006)
10.1109/ISWC.2003.1241398
Unsupervised, dynamic identification of physiological and activity context in wearable computing
Andreas Krause (2003)
10.1109/ISWC.2000.888488
Context awareness by analysing accelerometer data
C. Randell (2000)
10.1109/IMTC.1994.352073
Estimation of speed and incline of walking using neural network
K. Aminian (1994)
A useful method for measuring daily physical activity by a three-direction monitor.
A. Sugimoto (1997)
Life patterns : structure from wearable sensors
B. Clarkson (2002)
Physical activity recognition from acceleration data under semi-naturalistic conditions
L. Bao (2003)
10.1007/978-3-540-39863-9_17
Multi-sensor Activity Context Detection for Wearable Computing
Nicky Kern (2003)
10.1080/00401706.2000.10486090
Data Mining
I. Witten (2000)
10.1145/985692.985693
Acquiring in situ training data for context-aware ubiquitous computing applications
S. Intille (2004)
10.1109/10.554760
A triaxial accelerometer and portable data processing unit for the assessment of daily physical activity
C. Bouten (1997)
Real-time motion classi ca-tion for wearable computing applications
R. W. DeVaul (2001)
10.1097/00005768-200009001-00007
The utility of the Digi-walker step counter to assess daily physical activity patterns.
G. Welk (2000)
Hoarder Board Specifications
V. Gerasimov (2002)
10.1109/ISWC.2002.1167218
Multi-sensor context aware clothing
Kristof Van Laerhoven (2002)
10.1109/ISWC.2000.888468
What shall we teach our pants?
Kristof Van Laerhoven (2000)
10.1109/CCA.2001.974027
Recognition of walking behaviors for pedestrian navigation
Seon-Woo Lee (2001)
Ph
李幼升 (1989)
10.1145/507338.507355
Data mining: practical machine learning tools and techniques with Java implementations
I. Witten (1999)
10.1109/MPRV.2002.1037719
Activity and Location Recognition Using Wearable Sensors
Seon-Woo Lee (2002)
10.1109/ICPR.2002.1048493
Hierarchical recognition of intentional human gestures for sports video annotation
Graeme S. Chambers (2002)
10.1097/00005768-199907000-00020
The prediction of speed and incline in outdoor running in humans using accelerometry.
R. Herren (1999)
10.3109/03091909809032535
Ambulatory monitoring of physical activity in working situations, a validation study.
M. Uiterwaal (1998)
Hoarder Board Specifications, Access date
V Gerasimov (2002)
10.1016/S0747-5632(99)00037-0
Detection of posture and motion by accelerometry : a validation study in ambulatory monitoring
F. Förster (1999)



This paper is referenced by
10.1109/ROBOT.2010.5509180
Person identification by integrating wearable sensors and tracking results from environmental sensors
T. Ikeda (2010)
10.1145/1851600.1851616
User experiences with activity-based navigation on mobile devices
A. J. Bernheim Brush (2010)
10.1109/APCCAS.2012.6419104
Real time accelerometer-based gait recognition using adaptive windowed wavelet transforms
Jian-Hua Wang (2012)
10.1109/PerCom45495.2020.9127376
Human Activity Recognition with Deep Reinforcement Learning using the Camera of a Mobile Robot
Teerawat Kumrai (2020)
10.1109/ICC.2019.8761931
PerRNN: Personalized Recurrent Neural Networks for Acceleration-Based Human Activity Recognition
Xufei Wang (2019)
10.1109/IC-NC.2010.50
Power Saving in Mobile Devices Using Context-Aware Resource Control
Kosuke Nishihara (2010)
Towards energy efficient mobile sensing
Yi Wang (2011)
10.1016/j.pmcj.2012.03.001
Formal verification of context and situation models in pervasive computing
Andrey Boytsov (2013)
10.1186/1743-0003-10-83
Monitoring motor capacity changes of children during rehabilitation using body-worn sensors
Christina Strohrmann (2012)
Inertial Sensors for Kinematic Measurement and Activity Classification of Gait Post-Stroke
Annemarie Laudanski (2013)
10.1016/j.apmr.2010.12.040
Review of accelerometry for determining daily activity among elderly patients.
Vivian Hoi Yee Cheung (2011)
10.3929/ETHZ-A-7335107
Stress arousal monitoring in natural environments
Martin Kusserow (2012)
10.1109/ICASSP.2012.6288232
Feature selection based on mutual information for human activity recognition
Benjamin Fish (2012)
10.1109/PerComW.2014.6815161
Dealing with human variability in motion based, wearable activity recognition
Matthias Kreil (2014)
10.1007/978-3-319-46681-1_1
Classifying Human Activities with Temporal Extension of Random Forest
Shih Yin Ooi (2016)
10.1109/CHICC.2016.7553975
MEMS-based human activity recognition using smartphone
Ya Tian (2016)
Exploring unconstrained mobile sensor based human activity recognition
Luis Mojica de La Vega (2013)
10.1587/TRANSINF.E94.D.1062
A Recognition Method for One-Stroke Finger Gestures Using a MEMS 3D Accelerometer
Lei Jing (2011)
10.1109/GCCE.2016.7800431
Gait monitoring for human activity recognition using perceptive shoe based on hetero-core fiber optics
Yuya Koyama (2016)
10.1109/ICMLA.2011.92
Manifold Learning and Recognition of Human Activity Using Body-Area Sensors
Mi Zhang (2011)
10.4108/ICST.PERVASIVEHEALTH.2011.246037
PEAR: Power efficiency through activity recognition (for ECG-based sensing)
Feng-Tso Sun (2011)
10.1109/TIM.2013.2258772
Detecting Object Motion Using Passive RFID: A Trauma Resuscitation Case Study
Siddika Parlak (2013)
Algorithm development and implementation of activity recognition system utilizing wearable MEMS sensors
Piyush Gupta (2014)
Realistic rendering of 3D avatar using physics simulation and minimal sensors
B SrikrishnaAcharya (2014)
Subject-dependent physical activity recognition using single sensor accelerometer
Ali (2015)
10.1109/CCNC.2013.6488584
Activity recognition using smartphone sensors
Alvina Anjum (2013)
10.1109/INFCOM.2013.6567123
Predicting length of stay at WiFi hotspots
Justin Manweiler (2013)
10.1109/RTAS.2013.6531089
AdaSense: Adapting sampling rates for activity recognition in Body Sensor Networks
X. Qi (2013)
10.1145/2968219.2968286
Wearable electric potential sensing: a new modality sensing hair touch and restless leg movement
Arash Pouryazdan (2016)
The Impact of Feature Vector Length on Activity Recognition Accuracy on Mobile Phone
Sulaimon A. Bashir (2015)
10.1109/TIFS.2016.2611489
We Can Track You if You Take the Metro: Tracking Metro Riders Using Accelerometers on Smartphones
J. Hua (2017)
10.1016/j.inffus.2017.01.004
Kernel fusion based extreme learning machine for cross-location activity recognition
Zhelong Wang (2017)
See more
Semantic Scholar Logo Some data provided by SemanticScholar