The DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Multi-sensor physical activity recognition in free-living
Open accessAbstract
Physical activity monitoring in free-living populations has many applications for public health research, weight-loss interventions, context-aware recommendation systems and assistive technologies. We present a system for physical activity recognition that is learned from a free-living dataset of 40 women who wore multiple sensors for seven days. The multi-level classification system first learns low-level codebook representations for each sensor and uses a random forest classifier to produce minute-level probabilities for each activity class. Then a higher-level HMM layer learns patterns of transitions and durations of activities over time to smooth the minute-level predictions. [Formula: see text].
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
MS-TCNs have been applied for action recognition by videos and for sensor data on food intake prediction and physical activity recognition.
“Recently, multi-stage temporal convolutional networks (MSTCNs) were applied for action recognition by videos [11]. Then, there were several studies applying MS-TCNs for sensor data on food intake prediction [12] and physical activity recognition [13].”
From DS-MS-TCN: Otago Exercises Recognition With a Dual-Scale Multi-Stage Temporal Convolutional Network (2024) · cites this paper as [12]
The citation [13] is attached to the claim that this study applied MS-TCNs to sensor-based physical activity recognition. The paper does study that task, but its Introduction and classifier sections describe a random forest followed by a Hidden Markov model, not an MS-TCN. The video-action and food-intake claims are attached to other citations. (LLM, conf=0.90)
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredSensor data can be processed with sequence-to-sequence systems, making each sample a training example.
“Inspired by this, the sensor data could also be processed with sequence-to-sequence (seq-to-seq) systems [12], [13], which makes it possible that each sample serves as a training example (sample-wise classification).”
From DS-MS-TCN: Otago Exercises Recognition With a Dual-Scale Multi-Stage Temporal Convolutional Network (2024) · cites this paper as [12]
The High-level classifier section (page unavailable) describes an HMM that turns a sequence of minute-level predictions into a sequence of activity labels. The Data Representation and Low-level classifier sections (pages unavailable) show that classification uses labeled one-minute windows as training examples, not each individual sensor sample. The paper therefore supports sequence-based, window-wise classification but not the claim that each sensor sample serves as a training example. (LLM, conf=0.84)
Experimental — accuracy not yet measuredStudies applying MS-TCNs reported advantages of MS-TCNs over state-of-the-art CNN-LSTM.
“All of these studies reported the advantages of MS-TCNs over the state-of-the-art CNN-LSTM.”
From DS-MS-TCN: Otago Exercises Recognition With a Dual-Scale Multi-Stage Temporal Convolutional Network (2024) · cites this paper as [12]
The Low-level classifier and High-level classifier sections describe a random forest followed by a hidden Markov model, not an MS-TCN. Searches for MS-TCN and CNN-LSTM found no passage reporting a comparison between them, so our copy does not verify the attributed advantage. (LLM, conf=0.78)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Ermes, M., Pärkkä, J., Mäntyjärvi, J., & Korhonen, I. (2008) · IEEE Transactions on Information Technology in Biomedicine · doi:10.1109/titb.2007.899496 · Cited by 707
Modeling, Clustering, and Segmenting Video with Mixtures of Dynamic Textures
Chan, A. B., & Vasconcelos, N. M. (2008) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2007.70738 · Cited by 460
Staudenmayer, J., Pober, D., Crouter, S., Bassett, D., & Freedson, P. (2009) · Journal of Applied Physiology · doi:10.1152/japplphysiol.00465.2009 · Cited by 361
Surgical gesture classification from video and kinematic data
Zappella, L., Béjar, B., Hager, G. D., & Vidal, R. (2013) · Medical Image Analysis · doi:10.1016/j.media.2013.04.007 · Cited by 146
Flagged first, then by citations
Research works printed but not linked: 5
- 10.15420/usc.2004.1.1.17 · DOI
- 10.1109/TASL.2010.2090148 · DOI
- 10.1023/A:1021669406132 · DOI
- 10.1145/2526667.2526685 · DOI
- Kellokumpu , V. , Zhao , G. , and Pietikäinen , M . Human activity recognition using a dynamic texture based method . In BMVC ( 2008 ), 1--10. Kellokumpu, V., Zhao, G., and Pietikäinen, M. Human activity recognition using a dynamic texture based method. In BMVC (2008), 1--10.
Cited by
Sorted by citations
Recognizing Detailed Human Context in the Wild from Smartphones and Smartwatches
Vaizman, Y., Ellis, K., & Lanckriet, G. (2017) · IEEE Pervasive Computing · doi:10.1109/mprv.2017.3971131 · Cited by 324
Self-citationWilletts, M., Hollowell, S., Aslett, L., Holmes, C., & Doherty, A. (2018) · Scientific Reports · doi:10.1038/s41598-018-26174-1 · Cited by 250
“This approach provides an automated analysis of objectively measured behavioural variation in lifestyle behaviours and can be used by researchers to study social and health behaviours at a resolution not previously available.”
Vaizman, Y., Weibel, N., & Lanckriet, G. (2018) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3161192 · Cited by 122
Self-citationExtraSensory App: Data Collection In-the-Wild with Rich User Interface to Self-Report Behavior
Vaizman, Y., Ellis, K., Lanckriet, G., & Weibel, N. (2018) · Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3174128 · Cited by 115
Self-citationOtago Exercises Monitoring for Older Adults by a Single IMU and Hierarchical Machine Learning Models
Shang, M., Dedeyne, L., Dupont, J., Vercauteren, L., Amini, N., Lapauw, L., Gielen, E., Verschueren, S., Varon, C., De Raedt, W., et al. (2024) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2024.3355299 · Cited by 21
Activity detection in uncontrolled free-living conditions using a single accelerometer
Lee, S. I., Ozsecen, M. Y., Della Toffola, L., Daneault, J.-F., Puiatti, A., Patel, S., & Bonato, P. (2015) · 2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks (BSN) · doi:10.1109/bsn.2015.7299372 · Cited by 9
DS-MS-TCN: Otago Exercises Recognition With a Dual-Scale Multi-Stage Temporal Convolutional Network
Shang, M., Dedeyne, L., Dupont, J., Vercauteren, L., Amini, N., Lapauw, L., Gielen, E., Verschueren, S., Varon, C., De Raedt, W., et al. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3455426 · Cited by 5
“It segments the input sensors data into windows with equal size [10]–[12].”
Background
Metadata
- Authors
- Ellis, K., Kerr, J., Godbole, S., & Lanckriet, G.
- Affiliations
- University of California San Diego (US)
- Venue
- Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct Publication
- Publisher
- ACM
- Published
- 2014-09-13
- Volume
- 2014
- Pages
- 431-440
- PMC
- PMC4523301
- OpenAlex
- W2155351925
- Cited by
- 44
- References
- 4
- Citations by year
- 2024: 2 · 2023: 1 · 2022: 2 · 2021: 3 · 2020: 2 · 2019: 5 · 2018: 8 · 2017: 6 · 2016: 10 · 2015: 3 · 2014: 1
- FWCI
- 3.58
- Type
- conference paper
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Locations
- ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) (publishedVersion)
- PubMed (publishedVersion)
- Europe PMC (PubMed Central) (acceptedVersion)
- PubMed Central (acceptedVersion)
- Funders
- National Cancer Institute (R01CA164993)
- 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
- Social Sciences › Transportation › Human Mobility and Location-Based Analysis
- Keywords
- physical activity recognition, multi-sensor fusion, free-living activity monitoring, wearable sensors, random forest classification, hidden Markov models, multi-level classification, women
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
