An Online Swallow Detection Algorithm Based on the Quadratic Variation of Dual-Axis Accelerometry
The DOI matches its Crossref record; 27 of the 28 references it cites were found in a registry or an index.
Abstract
Swallow accelerometry is an emerging tool for noninvasive dysphagia screening. However, the automatic detection of a swallowing event is challenging due to contaminant vibrations arising from head motion, speech and coughing. In this paper, we consider the acceleration signal as a stochastic diffusion where movement is associated with drift and swallowing with volatility. Using this model, we develop a volatility-based swallow event detector that operates on the raw acceleration signal in an online fashion. With data from healthy participants and patients with dysphagia, the proposed detector achieves performance comparable to previously proposed swallow segmentation algorithms, with the added benefit of online detection and no signal pre-processing. The volatility-based detector may be useful for event identification in other biomechanical applications that rely on accelerometry signals.
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 best performing channel was the A-P accelerometer axis with an average accuracy of 89.44% for single swallows (75.9% for the whole dataset) and superior sensitivity and specificity which is comparable to the results in7.”
From Non-invasive identification of swallows via deep learning in high resolution cervical auscultation recordings (2020) · cites this paper as [7]
In the citing paper
“Damouras et al.7 used quadratic variation that is extracted directly from acceleration signals to perform segmentation and the algorithm was computationally effective to execute.”
From Non-invasive identification of swallows via deep learning in high resolution cervical auscultation recordings (2020) · cites this paper as [7]
In the citing paper
“Their algorithm achieved recall values up to 94% but it was highly affected by the presence of noise and the used dataset wasn’t diverse enough considering the maneuvers and material consistencies.”
From Non-invasive identification of swallows via deep learning in high resolution cervical auscultation recordings (2020) · cites this paper as [7]
In the citing paper
“a typical swallow segment can range in duration from 1 second (4k samples in this case) to more than 3 seconds which makes the selected window sizes robust to statistical error and efficient to detect the shortest swallows7,36.”
From Non-invasive identification of swallows via deep learning in high resolution cervical auscultation recordings (2020) · cites this paper as [7]
Citations
Cites
Brownian Motion and Stochastic Calculus
(2007) · Springer Finance · doi:10.1007/978-1-84628-696-4_13 · Cited by 7,422
Econometric Analysis of Realized Volatility and its Use in Estimating Stochastic Volatility Models
Barndorff-Nielsen, O. E., & Shephard, N. (2002) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/1467-9868.00336 · Cited by 2,215 · cited 1×
“measuring stock market variability [17].”
Seidler, J. (1991) · Acta Applicandae Mathematicae · doi:10.1007/bf00046894 · Cited by 2,090
A Tale of Two Time Scales: Determining Integrated Volatility with Noisy High Frequency Data
Zhang, L., Mykland, P., & Ait-Sahalia, Y. (2003) · National Bureau of Economic Research · doi:10.3386/w10111 · Cited by 1,373
A Tale of Two Time Scales: Determining Integrated Volatility With Noisy High-Frequency Data
Zhang, L., Mykland, P. A., & Aït-Sahalia, Y. (2005) · Journal of the American Statistical Association · doi:10.1198/016214505000000169 · Cited by 1,306
A study of retrospective and on-line event detection
Yang, Y., Pierce, T., & Carbonell, J. (1998) · Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval · doi:10.1145/290941.290953 · Cited by 731 · cited 1×
“Based on these quantities we use the following standard measures from information retrieval [22], [ 23 ] to assess the performance of our algorithm.”
MethodKernels for Nonparametric Curve Estimation
Gasser, T., MÜller, H.-G., & Mammitzsch, V. (1985) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1985.tb01350.x · Cited by 470 · cited 2×
“We do this by estimating the second derivative of using a kernel smoother, as (10) where is optimal for estimating second derivatives [20], and and have the same values as those used for estimating .”
BackgroundMethodDrowsy Driver Detection Through Facial Movement Analysis
Vural, E., Cetin, M., Ercil, A., Littlewort, G., Bartlett, M., & Movellan, J. (2007) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-75773-3_2 · Cited by 232 · cited 1×
“Example applications include the detection of feeding activities [1] and driver drowsiness [2], the assessment of fall risk in the aged [3], the quantification of muscle contractions [4], the monitoring of cardio-respiratory activity [5], the study of head angular accelerations in impact injuries [6], the tracking of…”
BackgroundDurational aspects of the oral-pharyngeal phase of swallow in normal adults
Sonies, B. C., Parent, L. J., Morrish, K., & Baum, B. J. (1988) · Dysphagia · doi:10.1007/bf02406274 · Cited by 185 · cited 1×
“For all three measures, values closer to one indicate better performance.”
BackgroundMicrostructure noise, realized volatility, and optimal sampling
Bandi, F. M. (2008) · Cited by 92
A comparative study of speech detection methods
Gerven, S. V., & Xie, F. (1997) · European Conference on Speech Communication and Technology (Eurospeech) · doi:10.21437/eurospeech.1997-108 · Cited by 88
Estimation of respiratory waveform and heart rate using an accelerometer
Phan, D. H., Bonnet, S., Guillemaud, R., Castelli, E., & Pham Thi, N. Y. (2008) · 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society · doi:10.1109/iembs.2008.4650316 · Cited by 84 · cited 1×
“Example applications include the detection of feeding activities [1] and driver drowsiness [2], the assessment of fall risk in the aged [3], the quantification of muscle contractions [4], the monitoring of cardio-respiratory activity [5], the study of head angular accelerations in impact injuries…”
BackgroundA radial basis classifier for the automatic detection of aspiration in children with dysphagia
Lee, J., Blain, S., Casas, M., Kenny, D., Berall, G., & Chau, T. (2006) · Journal of NeuroEngineering and Rehabilitation · doi:10.1186/1743-0003-3-14 · Cited by 74
Self-citationTime and time–frequency characterization of dual-axis swallowing accelerometry signals
Lee, J., Steele, C. M., & Chau, T. (2008) · Physiological Measurement · doi:10.1088/0967-3334/29/9/008 · Cited by 73 · cited 2×
“…of muscle contractions [4], the monitoring of cardio-respiratory activity [5], the study of head angular accelerations in impact injuries [6], the tracking of neck and thoracic vibrations for sleep apnea diagnosis [7], and the noninvasive characterization of swallowing activity [8], [9].”
BackgroundInfluentialSelf-citationSejdic, E., Steele, C. M., & Chau, T. (2009) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2008.2010504 · Cited by 73 · cited 10×
“signal segments associated with the passage of foodstuffs from the mouth, through the pharynx and into the esophagus [10].”
BackgroundMethodResultInfluentialSelf-citationDetection of Activities by Wireless Sensors for Daily Life Surveillance: Eating and Drinking
Zhang, S., Ang, M. H., Xiao, W., & Tham, C. (2009) · Sensors · doi:10.3390/s90301499 · Cited by 69 · cited 1×
“I. INTRODUCTION T HE biomechnical characterization of human activity hasfrequently been facilitated through multi axis accelerometry.”
BackgroundInvestigating the stationarity of paediatric aspiration signals
Chau, T., Chau, D., Casas, M., Berall, G., & Kenny, D. J. (2005) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2004.841384 · Cited by 64 · cited 3×
“…of muscle contractions [4], the monitoring of cardio-respiratory activity [5], the study of head angular accelerations in impact injuries [6], the tracking of neck and thoracic vibrations for sleep apnea diagnosis [7], and the noninvasive characterization of swallowing activity [8], [9].”
BackgroundSelf-citationMeasurements of acceleration during videofluorographic evaluation of dysphagic patients
Reddy, N. P., Katakam, A., Gupta, V., Unnikrishnan, R., Narayanan, J., & Canilang, E. P. (2000) · Medical Engineering & Physics · doi:10.1016/s1350-4533(00)00047-3 · Cited by 60
Noninvasive acceleration measurements to characterize the pharyngeal phase of swallowing
Reddy, N. P., Canilang, E. P., Casterline, J., Rane, M. B., Joshi, A. M., Thomas, R., & Candadai, R. (1991) · Journal of Biomedical Engineering · doi:10.1016/0141-5425(91)90018-3 · Cited by 56
Microstructure noise, realized volatility, and optimal samplingPreprint
Russell, J. R., & Bandi, F. M. (2004) · RePEc: Research Papers in Economics · Cited by 48
Toward classification of dysphagic patients using biomechanical measurements.
Reddy, N. P., Thomas, R., Ep, C., & Casterline, J. (1994) · PubMed · Cited by 42
Mapping the Human Body for Vibrations using an Accelerometer
Rendon, D. B., Ojeda, J. L. R., Foix, L. F. C., Morillo, D., & Fernandez, M. A. (2007) · Conference proceedings · doi:10.1109/iembs.2007.4352629 · Cited by 40 · cited 1×
“…risk in the aged [3], the quantification of muscle contractions [4], the monitoring of cardio-respiratory activity [5], the study of head angular accelerations in impact injuries [6], the tracking of neck and thoracic vibrations for sleep apnea diagnosis [7], and the noninvasive characterization…”
BackgroundNeck Forces and Moments and Head Accelerations in Side Impact
Yoganandan, N., Pintar, F. A., Maiman, D. J., Philippens, M. M. G. M., & Wismans, J. S. H. M. (2009) · Traffic Injury Prevention · doi:10.1080/15389580802524876 · Cited by 25 · cited 1×
“…of feeding activities [1] and driver drowsiness [2], the assessment of fall risk in the aged [3], the quantification of muscle contractions [4], the monitoring of cardio-respiratory activity [5], the study of head angular accelerations in impact injuries [6], the tracking of neck and thoracic…”
BackgroundShekhar, S., Xiong, H. Y., & Zhou, X. S. (2017) · Encyclopedia of GIS · doi:10.1007/978-3-319-17885-1_100610 · Cited by 25
Hanna, F., Molfenter, S. M., Polacco, R. C., Chau, T. T., & Steele, C. M. (2009) · Dysphagia · doi:10.1007/s00455-009-9229-9 · Cited by 22 · cited 1×
“Other swallowing accelerometry studies have relied on manual segmentation of vibration signals either by referencing events detected from simultaneously acquired videofluroscopic image sequences [8], [11], or by human expert inspection of acceleration traces [15].”
Self-citationPurwar, A., Myllylä, R. A., & Chung, W. (2008) · Sensor Letters · doi:10.1166/sl.2008.044 · Cited by 13 · cited 1×
“Example applications include the detection of feeding activities [1] and driver drowsiness [2], the assessment of fall risk in the aged [3], the quantification of muscle contractions [4], the monitoring of cardio-respiratory activity [5], the study of head angular accelerations in impact injuries…”
BackgroundVision-Based Segmentation of Continuous Mechanomyographic Grasping Sequences
Alves, N., & Chau, T. T. (2008) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2007.902223 · Cited by 8
Self-citation
Cited by
Lee, K., Ni, X., Lee, J. Y., Arafa, H., Pe, D. J., Xu, S., Avila, R., Irie, M., Lee, J. H., Easterlin, R. L., et al. (2019) · Nature Biomedical Engineering · doi:10.1038/s41551-019-0480-6 · Cited by 349
A Novel Wearable Device for Food Intake and Physical Activity Recognition
Farooq, M., & Sazonov, E. (2016) · Sensors · doi:10.3390/s16071067 · Cited by 128
“However, they are not able to reliably distinguish swallows from the head and neck movements and, therefore, their use in free-living conditions is limited [34].”
BackgroundKang, Y. J., Arafa, H., Yoo, J., Kantarcigil, Ç., Kim, J., Jeong, H., Yoo, S., Oh, S., Kim, J., Wu, C., et al. (2022) · npj Digital Medicine · doi:10.1038/s41746-022-00691-w · Cited by 102
Dudik, J. M., Coyle, J. L., & Sejdic, E. (2015) · IEEE Transactions on Human-Machine Systems · doi:10.1109/thms.2015.2408615 · Cited by 86
Khalifa, Y., Coyle, J. L., & Sejdić, E. (2020) · Scientific Reports · doi:10.1038/s41598-020-65492-1 · Cited by 82
“Since numerous physiologic and kinematic events occur simultaneously during swallowing recordings (e.g. breathing, coughing), collected signals contain vibratory and acoustic information from multiple sources 7 .”
BackgroundMethodResultInfluential
Metadata
- Authors
- Damouras, S., Sejdic, E., Steele, C. M., & Chau, T.
- Affiliations
- Bloorview Research Institute (CA)
- University of Toronto (CA)
- Venue
- IEEE Transactions on Signal Processing
- Published
- 2010-06
- Volume
- 58
- Issue
- 6
- Pages
- 3352-3359
- ISSN
- 1053-587X (ISSN-L)
- 1941-0476
- OpenAlex
- W2167113242
- Cited by
- 43
- References
- 28
- Citations by year
- 2026: 1 · 2025: 3 · 2024: 3 · 2023: 1 · 2022: 3 · 2021: 1 · 2020: 6 · 2019: 3 · 2017: 3 · 2016: 3 · 2015: 4 · 2014: 6 · 2013: 1 · 2012: 3
- FWCI
- 5.34
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Signal Processing (publishedVersion)
- Topics
- Health Sciences › Health Professions › Speech and Hearing › Dysphagia Assessment and Management
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Health Sciences › Health Professions › Speech and Hearing › Voice and Speech Disorders
- Keywords
- dysphagia screening, accelerometry, dual-axis accelerometer, quadratic variation, online detection, stochastic diffusion model
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.