Creating and benchmarking a new dataset for physical activity monitoring
The DOI matches its Crossref record; 24 of the 24 references it cites were found in a registry or an index.
Abstract
Physical activity monitoring has recently become an important field in wearable computing research. However, there is a lack of a commonly used, standard dataset and established benchmarking problems. In this work, a new dataset for physical activity monitoring --- recorded from 9 subjects, wearing 3 inertial measurement units and a heart rate monitor, and performing 18 different activities --- is created and made publicly available. Moreover, 4 classification problems are benchmarked on the dataset, using a standard data processing chain and 5 different classifiers. The benchmark shows the difficulty of the classification tasks and exposes some challenges, defined by e.g. a high number of activities and personalization.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
The WEKA data mining software: an update
Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., & Witten, I. H. (2009) · ACM SIGKDD Explorations Newsletter · doi:10.1145/1656274.1656278 · Cited by 17,750
Compendium of physical activities: an update of activity codes and MET intensities
AINSWORTH, B. E., HASKELL, W. L., WHITT, M. C., IRWIN, M. L., SWARTZ, A. M., STRATH, S. J., O???BRIEN, W. L., BASSETT, D. R., SCHMITZ, K. H., EMPLAINCOURT, P. O., et al. (2000) · Medicine & Science in Sports & Exercise · doi:10.1097/00005768-200009001-00009 · Cited by 8,497
Activity Recognition from User-Annotated Acceleration Data
Bao, L., & Intille, S. S. (2004) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-24646-6_1 · Cited by 3,147 · cited 1×
“[2] presents a data recording of 20 different activities with 20 subjects, wearing five 2-axis accelerometers, and shows results in activity recognition with 4 different classifiers.”
BackgroundActivity recognition from accelerometer data
Ravi, N., Dandekar, N., Mysore, P., & Littman, M. L. (2005) · Innovative Applications of Artificial Intelligence · Cited by 1,812
Introducing a New Benchmarked Dataset for Activity Monitoring
Reiss, A., & Stricker, D. (2012) · 2012 16th International Symposium on Wearable Computers · doi:10.1109/iswc.2012.13 · Cited by 1,456 · cited 1×
“The key facts of the created dataset, and the key results of an initial classification are presented in [17].”
BackgroundSelf-citationAccurate activity recognition in a home setting
van Kasteren, T., Noulas, A., Englebienne, G., & Kröse, B. (2008) · Proceedings of the 10th international conference on Ubiquitous computing · doi:10.1145/1409635.1409637 · Cited by 874 · cited 1×
“In this work, a new dataset for physical activity monitoring recorded from 9 subjects, wearing 3 inertial measurement units and a heart rate monitor, and performing 18 di.erent activities is created and made publicly available.”
MethodCollecting complex activity datasets in highly rich networked sensor environments
Roggen, D., Calatroni, A., Rossi, M., Holleczek, T., Forster, K., Troster, G., Lukowicz, P., Bannach, D., Pirkl, G., Ferscha, A., et al. (2010) · 2010 Seventh International Conference on Networked Sensing Systems (INSS) · doi:10.1109/inss.2010.5573462 · Cited by 788
Ermes, M., Parkka, J., Mantyjarvi, J., & Korhonen, I. (2008) · IEEE Transactions on Information Technology in Biomedicine · doi:10.1109/titb.2007.899496 · Cited by 707 · cited 1×
“in [5, 11]), since an extra IMU on the thigh would be needed for a reliable differentiation of these postures.”
BackgroundUsing a Live-In Laboratory for Ubiquitous Computing Research
Intille, S. S., Larson, K., Tapia, E. M., Beaudin, J. S., Kaushik, P., Nawyn, J., & Rockinson, R. (2006) · Lecture Notes in Computer Science · doi:10.1007/11748625_22 · Cited by 354 · cited 1×
“the PlaceLab dataset [8] or a dataset using simple binary sensing nodes to observe activities performed in a home environment [25].”
MethodAnalyzing features for activity recognition
Huynh, T., & Schiele, B. (2005) · Proceedings of the 2005 joint conference on Smart objects and ambient intelligence: innovative context-aware services: usages and technologies · doi:10.1145/1107548.1107591 · Cited by 339
Handling Missing Values when Applying Classification Models
Saar‐Tsechansky, M., & Provost, F. J. (2007) · Faculty Digital Archive (New York University Florence) · doi:10.5555/1314498.1314553 · Cited by 315 · cited 1×
“more complex methods [21] in future improved approaches.”
MethodPerformance metrics for activity recognition
Ward, J. A., Lukowicz, P., & Gellersen, H. W. (2011) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/1889681.1889687 · Cited by 182
Benchmarking classification techniques using the Opportunity human activity dataset
Sagha, H., Digumarti, S. T., del R. Millan, J., Chavarriaga, R., Calatroni, A., Roggen, D., & Troster, G. (2011) · 2011 IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/icsmc.2011.6083628 · Cited by 109 · cited 2×
“Moreover, [22] presents a benchmark of 4 classification techniques applied to multiple tasks defined on the latter dataset.”
MethodAdvancing from offline to online activity recognition with wearable sensors
Ermes, M., Parkka, J., & Cluitmans, L. (2008) · 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society · doi:10.1109/iembs.2008.4650199 · Cited by 95 · cited 1×
“Spectral entropy of the normalized PSD is a useful feature for differentiating between locomotion activities (walking, running) and cycling [4].”
BackgroundPärkkä, J., Cluitmans, L., & Ermes, M. (2010) · IEEE Transactions on Information Technology in Biomedicine · doi:10.1109/titb.2010.2055060 · Cited by 86 · cited 1×
“in [5, 11]), since an extra IMU on the thigh would be needed for a reliable differentiation of these postures.”
BackgroundPärkkä, J., Ermes, M., Antila, K., van Gils, M., Mänttäri, A., & Nieminen, H. (2007) · Conference proceedings · doi:10.1109/iembs.2007.4352588 · Cited by 74 · cited 2×
“in [12]), that for different tasks in physical activity monitoring (e.”
BackgroundA naturalistic 3D acceleration-based activity dataset & benchmark evaluations
Xue, Y., & Jin, L. (2010) · 2010 IEEE International Conference on Systems, Man and Cybernetics · doi:10.1109/icsmc.2010.5641790 · Cited by 52 · cited 2×
“Benchmarking on the activity recognition task is presented in [28], using an SVM classifier with different sets of features.”
MethodPatel, S., Mancinelli, C., Healey, J., Moy, M., & Bonato, P. (2009) · 2009 Sixth International Workshop on Wearable and Implantable Body Sensor Networks · doi:10.1109/bsn.2009.53 · Cited by 51 · cited 1×
“[13]) showed, that in the trade-off between classification performance and number of sensors, using 3 sensor locations is the most effective.”
BackgroundRoggen, D., Magnenat, S., Waibel, M., & Tröster, G. (2011) · IEEE Robotics & Automation Magazine · doi:10.1109/mra.2011.940992 · Cited by 51
Exploring and extending the boundaries of physical activity recognition
Reiss, A., Weber, M., & Stricker, D. (2011) · 2011 IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/icsmc.2011.6083640 · Cited by 42 · cited 5×
“The idea of the background activity class, and how it significantly increases the complexity of the classification problem, is further explained in [18].”
BackgroundMethodResultSelf-citationIntroducing a modular activity monitoring system
Reiss, A., & Stricker, D. (2011) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/iembs.2011.6091360 · Cited by 38 · cited 3×
“75 Hz and 0–5 Hz proved to be useful in [15], while peak frequency of the power spectral density (PSD) was used for the detection of cyclic activities in e.”
BackgroundMethodSelf-citationEffective Performance Metrics for Evaluating Activity Recognition Methods.
van Kasteren, T. L. M., Alemdar, H. O., & Ersoy, C. (2011) · ARCS Workshops · Cited by 38
Roggen, D., Magnenat, S., Waibel, M., & Tröster, G. (2011) · Repository for Publications and Research Data (ETH Zurich) · doi:10.3929/ethz-a-010001702 · Cited by 34
Towards global aerobic activity monitoring
Reiss, A., & Stricker, D. (2011) · International Conference on PErvasive Technologies Related to Assistive Environments (PETRA) · doi:10.1145/2141622.2141637 · Cited by 30 · cited 5×
“The following specifications — based on the conditions and limitations of the public datasets briefly described above, and experience made in previous work [16, 18] — are defined for this: a wide range of everyday, household and sport activities should be performed by an adequate number of subjects, wearing a few 3D-I…”
BackgroundMethodSelf-citation
Research works printed but not linked: 3
- Lukowicz P., 2010, 23rd International Conference on Architecture of Computing Systems (ARCS), 1
- 10.5555/1620092.1620107 · doi:10.5555/1620092.1620107
- Xue Y., 2010, International Conference on Systems, Man and Cybernetics (SMC), 4081
Cited by
PMLB: a large benchmark suite for machine learning evaluation and comparison
Olson, R. S., La Cava, W., Orzechowski, P., Urbanowicz, R. J., & Moore, J. H. (2017) · BioData Mining · doi:10.1186/s13040-017-0154-4 · Cited by 365
“…will always be a need to identify and generate custom benchmarks for new or specialized problem domains, e.g. physical activity monitoring data Reiss and Stricker (2012) or dynamical systems simulation La Cava et al. (2016), it is vital for the bioinformatics and ML community to have a…”
BackgroundDeep PPG: Large-Scale Heart Rate Estimation with Convolutional Neural Networks
Reiss, A., Indlekofer, I., Schmidt, P., & Van Laerhoven, K. (2019) · Sensors · doi:10.3390/s19143079 · Cited by 377
“Large performance difference between subject/session-dependent and -independent evaluation has been reported for example in the human activity recognition domain [41].”
BackgroundSelf-citationHuman activity recognition in artificial intelligence framework: a narrative review
Gupta, N., Gupta, S. K., Pathak, R. K., Jain, V., Rashidi, P., & Suri, J. S. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-021-10116-x · Cited by 337
“2015; Reiss and Stricker 2012a, b; Lv et al.”
BackgroundApproximated and User Steerable tSNE for Progressive Visual Analytics
Pezzotti, N., Lelieveldt, B. P. F., Maaten, L. V. D., Hollt, T., Eisemann, E., & Vilanova, A. (2017) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2016.2570755 · Cited by 308
Transformers and large language models in healthcare: A review
Nerella, S., Bandyopadhyay, S., Zhang, J., Contreras, M., Siegel, S., Bumin, A., Silva, B., Sena, J., Shickel, B., Bihorac, A., et al. (2024) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2024.102900 · Cited by 197
“They studied sequences of human movements through multimodal data (such as RGB, depth and skeletal-data) [390-392] or modeled human activity through accelerometer and gyroscope [393-396].”
Metadata
- Authors
- Reiss, A., & Stricker, D.
- Affiliations
- German Research Centre for Artificial Intelligence (DE)
- ORCID
- Stricker, Didier
- Venue
- Proceedings of the 5th International Conference on PErvasive Technologies Related to Assistive Environments
- Publisher
- ACM
- Published
- 2012-06-06
- Pages
- 1-8
- OpenAlex
- W2063598276
- Cited by
- 295
- References
- 24
- Citations by year
- 2026: 7 · 2025: 28 · 2024: 21 · 2023: 23 · 2022: 39 · 2021: 29 · 2020: 25 · 2019: 29 · 2018: 19 · 2017: 23 · 2016: 21 · 2015: 13 · 2014: 7 · 2013: 10 · 2012: 1
- FWCI
- 7.04
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Conference on PErvasive Technologies Related to Assistive Environments (PETRA) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Health Sciences › Medicine › Public Health, Environmental and Occupational Health › Physical Activity and Health
- Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
- Keywords
- physical activity monitoring, wearable computing, inertial measurement unit, heart rate monitoring, activity recognition, benchmarking, dataset construction, personalization, classifier comparison
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.