Activity recognition from on-body sensors by classifier fusion: sensor scalability and robustness
The DOI matches its Crossref record; 22 of the 25 references it cites were found in a registry or an index.
Abstract
Activity recognition from on-body sensors is affected by sensor degradation, interconnections failures, and jitter in sensor placement and orientation. We investigate how this may be balanced by exploiting redundant sensors distributed on the body. We recognize activities by a meta-classifier that fuses the information of simple classifiers operating on individual sensors. We investigate the robustness to faults and sensor scalability which follows from classifier fusion. We compare a reference majority voting and a naive Bayesian fusion scheme. We validate this approach by recognizing a set of 10 activities carried out by workers in the quality assurance checkpoint of a car assembly line. Results show that classification accuracy greatly increases with additional sensors (50% with 1 sensor, 80% and 98% with 3 and 57 sensors), and that sensor fusion implicitly allows to compensate for typical faults up to high fault rates. These results highlight the benefit of large on- body sensor network rather than a minimum set of sensors for activity recognition and prompts further investigation.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Kittler, J., Hatef, M., Duin, R. P. W., & Matas, J. (1998) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.667881 · Cited by 5,290 · cited 1×
“Among classifier fusion methods [21], we consider a majority voting scheme as a reference and a naive Bayesian fusion method.”
MethodAn empirical study of the naive Bayes classifier
Rish, I. (2001) · Cited by 3,202
Towards a Better Understanding of Context and Context-Awareness
Abowd, G. D., Dey, A. K., Brown, P. J., Davies, N., Smith, M., & Steggles, P. (1999) · Lecture Notes in Computer Science · doi:10.1007/3-540-48157-5_29 · Cited by 2,634 · cited 1×
“Wearable computing aims to provide proactive support by exploiting the knowledge of the user’s context, determined from on-body sensors [ 1 ], [2].”
BackgroundMitra, S., & Acharya, T. (2007) · IEEE Transactions on Systems, Man and Cybernetics, Part C (Applications and Reviews) · doi:10.1109/tsmcc.2007.893280 · Cited by 1,981
Decision combination in multiple classifier systems
Ho, T. K., Hull, J. J., & Srihari, S. N. (1994) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.273716 · Cited by 1,511 · cited 1×
“In [14] the output of a classifier, seen as a ranking of the classes, is fused to obtain better overall classification.”
MethodReal-time American Sign Language recognition from video using hidden Markov models
Starner, T., & Pentland, A. (2002) · Proceedings of International Symposium on Computer Vision - ISCV · doi:10.1109/iscv.1995.477012 · Cited by 773 · cited 1×
“We use hidden Markov model as they showed to be a good approach in previous work [20], [8].”
MethodToward multimodal human-computer interface
Sharma, R., Pavlovic, V. I., & Huang, T. S. (1998) · Proceedings of the IEEE · doi:10.1109/5.664275 · Cited by 302 · cited 1×
“Sensor fusion may be performed at each level [16].”
BackgroundRecognizing Upper Body Postures using Textile Strain Sensors
Mattmann, C., Amft, O., Harms, H., Troster, G., & Clemens, F. (2007) · 2007 11th IEEE International Symposium on Wearable Computers · doi:10.1109/iswc.2007.4373773 · Cited by 209 · cited 1×
“In order to avoid relative motion, sensors attached on the body require the use of tight-fitting clothes [10] or relatively high attachment pressure, which limits comfort.”
BackgroundRecognition-based gesture spotting in video games
Kang, H., Lee, C. W., & Jung, K. (2004) · Pattern Recognition Letters · doi:10.1016/j.patrec.2004.06.016 · Cited by 172 · cited 1×
“The recognition of activities and gestures from body-worn sensors may be applied e.g. in human-computer interfaces [3], [4], sports [5], and also for context-aware support in automotive production [6], [7], [8].”
BackgroundWearNET: A Distributed Multi-sensor System for Context Aware Wearables
Lukowicz, P., Junker, H., Stäger, M., von Büren, T., & Tröster, G. (2002) · Lecture notes in computer science · doi:10.1007/3-540-45809-3_28 · Cited by 112 · cited 1×
“Wearable computing aims to provide proactive support by exploiting the knowledge of the user's context, determined from on-body sensors [1], [2].”
Background
Research works printed but not linked: 2
- stiefmeier, 2006, Event-based activity tracking in work environments, Third International Forum on Applied Wearable Computing
- roggen, 0, From sensors to miniature networked sensorbuttons, Proc of the 3rd Int Conf on Networked Sensing Systems (INSS06)
Cited by
A tutorial on human activity recognition using body-worn inertial sensors
Bulling, A., Blanke, U., & Schiele, B. (2014) · ACM Computing Surveys · doi:10.1145/2499621 · Cited by 1,668
“Fusion rules commonly used in activity recognition research are summation, majority voting [Stikic et al. 2008], Borda count [Ward et al. 2006], and Bayesian fusion [Zappi et al. 2007].”
MethodMulti-sensor fusion in body sensor networks: State-of-the-art and research challenges
Gravina, R., Alinia, P., Ghasemzadeh, H., & Fortino, G. (2017) · Information Fusion · doi:10.1016/j.inffus.2016.09.005 · Cited by 899
The Opportunity challenge: A benchmark database for on-body sensor-based activity recognition
Chavarriaga, R., Sagha, H., Calatroni, A., Digumarti, S. T., Tröster, G., Millán, J. D. R., & Roggen, D. (2013) · Pattern Recognition Letters · doi:10.1016/j.patrec.2012.12.014 · Cited by 742
“For these reason robust methods are required tackling issues ranging from the feature selection and classification (Preece et al., 2009), to decision fusion and fault-tolerance (e.g., Chavarriaga et al., 2012; Sagha et al., 2011b; Zappi et al., 2007).”
MethodSelf-citationA framework of energy efficient mobile sensing for automatic user state recognition
Wang, Y., Lin, J., Annavaram, M., Jacobson, Q. A., Hong, J., Krishnamachari, B., & Sadeh, N. (2009) · Proceedings of the 7th international conference on Mobile systems, applications, and services · doi:10.1145/1555816.1555835 · Cited by 434
“Different kinds of classifiers can be trained and compared in terms of the accuracy of classification [9, 10, 11, 12].”
BackgroundNweke, H. F., Teh, Y. W., Mujtaba, G., & Al-garadi, M. A. (2019) · Information Fusion · doi:10.1016/j.inffus.2018.06.002 · Cited by 394
Metadata
- Authors
- Zappi, P., Stiefmeier, T., Farella, E., Roggen, D., Benini, L., & Troster, G.
- Affiliations
- University of Bologna (IT)
- ETH Zurich (CH)
- Venue
- 2007 3rd International Conference on Intelligent Sensors, Sensor Networks and Information
- Publisher
- IEEE
- Published
- 2007
- Pages
- 281-286
- OpenAlex
- W2548335893
- Cited by
- 126
- References
- 25
- Citations by year
- 2026: 1 · 2025: 2 · 2024: 4 · 2023: 5 · 2022: 9 · 2021: 7 · 2020: 11 · 2019: 10 · 2018: 11 · 2017: 8 · 2016: 8 · 2015: 5 · 2014: 9 · 2013: 16 · 2012: 2
- FWCI
- 3.01
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Conference on Intelligent Sensors, Sensor Networks and Information Processing (publishedVersion)
- Archivio istituzionale della ricerca (Alma Mater Studiorum Università di Bologna) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Physical Sciences › Engineering › Biomedical Engineering › Wireless Body Area Networks
- Physical Sciences › Computer Science › Computer Networks and Communications › Wireless Sensor Networks for Data Analysis
- Keywords
- activity recognition, on-body sensors, classifier combination, fault tolerance, sensor degradation, majority voting, wearable sensor networks, quality assurance
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Activity recognition from on-body sensors by classifier fusion: sensor scalability and robustness. https://app.cochat.ai/papers/10.1109/issnip.2007.4496857
- The paper
- Zappi, P., Stiefmeier, T., Farella, E., Roggen, D., Benini, L., & Troster, G. (2007). Activity recognition from on-body sensors by classifier fusion: sensor scalability and robustness. 2007 3rd International Conference on Intelligent Sensors, Sensor Networks and Information. https://doi.org/10.1109/issnip.2007.4496857
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.