On-body localization of wearable devices: An investigation of position-aware activity recognition
The DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.
Abstract
Human activity recognition using mobile device sensors is an active area of research in pervasive computing. In our work, we aim at implementing activity recognition approaches that are suitable for real life situations. This paper focuses on the problem of recognizing the on-body position of the mobile device which in a real world setting is not known a priori. We present a new real world data set that has been collected from 15 participants for 8 common activities were they carried 7 wearable devices in different positions. Further, we introduce a device localization method that uses random forest classifiers to predict the device position based on acceleration data. We perform the most complete experiment in on-body device location that includes all relevant device positions for the recognition of a variety of different activities. We show that the method outperforms other approaches achieving an F-Measure of 89% across different positions. We also show that the detection of the device position consistently improves the result of activity recognition for common activities.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The performance of supervised learning methods is particularly dependent on large-scale labeled datasets, which require significant human efforts and financial costs [62].”
From Spatial-Temporal Masked Autoencoder for Multi-Device Wearable Human Activity Recognition (2023) · cites this paper as [62]
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538 · cited 1×
“Random forest classifiers are one of these ensemble methods that have been proposed by Breimann [17].”
MethodThe random subspace method for constructing decision forests
Ho, T. K. (1998) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.709601 · Cited by 6,842 · cited 1×
“This is necessary to ensure that the different generated decision trees are uncorrelated [18].”
BackgroundActivity 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 2×
“The development of wearable devices such as smart-phones, smart-watches and fitness wristbands feature a variety of sensors that are carried all day long by many people (compare [3]) provide new opportunities for continuous monitoring of human activities such as running, sitting, standing, or walking [5].”
BackgroundActivity recognition using cell phone accelerometers
Kwapisz, J. R., Weiss, G. M., & Moore, S. A. (2011) · ACM SIGKDD Explorations Newsletter · doi:10.1145/1964897.1964918 · Cited by 2,912 · cited 2×
“The sampling rate was chosen with consideration of battery life as well as with reference to previous studies [7], [14].”
BackgroundMethodA Survey on Human Activity Recognition using Wearable Sensors
Lara, O. D., & Labrador, M. A. (2013) · IEEE Communications Surveys & Tutorials · doi:10.1109/surv.2012.110112.00192 · Cited by 2,662 · cited 1×
“Preceding studies in the context of activity recognition already examined different settings regarding the window size and meaningful features [15].”
BackgroundActivity recognition from accelerometer data
Ravi, N., Dandekar, N., Mysore, P., & Littman, M. L. (2005) · Innovative Applications of Artificial Intelligence · Cited by 1,775
Preece, S. J., Goulermas, J. Y., Kenney, L. P. J., & Howard, D. (2009) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2008.2006190 · Cited by 551 · cited 2×
“Nevertheless, some researchers have compared different groups of features and also stated that frequency-based features improve the accuracy of the recognition [16].”
BackgroundSensor Positioning for Activity Recognition Using Wearable Accelerometers
Atallah, L., Lo, B., King, R., & Yang, G.-Z. (2011) · IEEE Transactions on Biomedical Circuits and Systems · doi:10.1109/tbcas.2011.2160540 · Cited by 346 · cited 5×
“Further studies have shown that the optimal sensor placement depends on the activity to be recognized [6].”
BackgroundResultInfluentialYang, J.-Y., Wang, J.-S., & Chen, Y.-P. (2008) · Pattern Recognition Letters · doi:10.1016/j.patrec.2008.08.002 · Cited by 335 · cited 1×
“A similar distinction has been made in [19] to improve the accuracy of activity recognition.”
BackgroundSun, L., Zhang, D., Li, B., Guo, B., & Li, S. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-16355-5_42 · Cited by 251 · cited 2×
“Activity Recognition is an active field of research in pervasive computing [1]–[4].”
Background
Cited by
Items 501–509 of 509
W-JEPA: Wavelet Joint-Embedding Predictive Architecture for Wearable Activity RecognitionPreprint
Prabhu, Y., Natarajan, L., & Zou, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.19411
“The RealWorld activity recognition dataset includes 15 participants and eight activities: walking, running or jogging, sitting, standing, lying, jumping, and ascending and descending stairs (Sztyler & Stuckenschmidt, 2016).”
Lee, Y.-R., & Tseng, V. S. M. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11728704
“RealWorld (RW) [13] represents a more heterogeneous setting with higher original sampling rate and a wider range of body positions (Head, Chest, Waist, Left Upper Arm, Left Forearm, Left Thigh, Left Shin).”
Strączkiewicz, M. (2026) · Sensors · doi:10.3390/s26206652
Costantini, S., Giachetti, B., A., S. F., Biffi, E., Mugellini, E., M., B. A., & Andreoni, G. (2026) · Virtual Community of Pathological Anatomy (University of Castilla La Mancha)
Balditsyn, V., Lalanda, P., & Chollet, S. (2026) · CCF Transactions on Pervasive Computing and Interaction · doi:10.1007/s42486-026-00271-x
Leng, Z., & Plötz, T. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2611.02393
Rethinking the Role of the Classification Head in CNN-BiLSTM-Based Human Activity Recognition
Shi, J., Wang, Y., & Yang, L. (2026) · Electronics · doi:10.3390/electronics15215194
Aktivitäts- und kontextsensitive Prozesserkennung in der Intralogistik
Niemann, F. (2026) · Technische Universität Dortmund Eldorado (Technische Universität Dortmund) · doi:10.17877/de290r-27025
UniMiB SHAR: A Dataset for Human Activity Recognition Using Acceleration Data from Smartphones
Micucci, D., Mobilio, M., & Napoletano, P. (2017) · doi:10.20944/preprints201706.0033.v1 · Cited by 596
“This section describes the method used to acquire and pre-process samples in order to produce the UniMiB SHAR dataset.”
Influential
Metadata
- Authors
- Sztyler, T., & Stuckenschmidt, H.
- Affiliations
- University of Mannheim (DE)
- Venue
- 2016 IEEE International Conference on Pervasive Computing and Communications (PerCom)
- Publisher
- IEEE
- Published
- 2016-03
- Pages
- 1-9
- ISSN
- 2474-249X (ISSN-L)
- OpenAlex
- W2340025709
- Cited by
- 369
- References
- 19
- Citations by year
- 2026: 30 · 2025: 55 · 2024: 60 · 2023: 38 · 2022: 39 · 2021: 35 · 2020: 41 · 2019: 33 · 2018: 22 · 2017: 11 · 2016: 5
- FWCI
- 8.21
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Conference on Pervasive Computing and Communications (publishedVersion)
- MADOC (University of Mannheim) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Indoor and Outdoor Localization Technologies
- Social Sciences › Transportation › Human Mobility and Location-Based Analysis
- Keywords
- wearable devices, activity recognition, accelerometer data, random forest classification, mobile device sensors, real-world data, ubiquitous computing
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.