Data augmentation of wearable sensor data for parkinson’s disease monitoring using convolutional neural networks
Open accessThe DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Abstract
While convolutional neural networks (CNNs) have been successfully applied to many challenging classification applications, they typically require large datasets for training. When the availability of labeled data is limited, data augmentation is a critical preprocessing step for CNNs. However, data augmentation for wearable sensor data has not been deeply investigated yet.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“We apply the jittering method to simulate additive sensor noise using random parameters as described in [47] for label-preserving augmentation.”
From Sensor Data Acquisition and Multimodal Sensor Fusion for Human Activity Recognition Using Deep Learning (2019) · cites this paper as [47]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“We considered three self-supervised tasks from ref. 27, which were first used in ref. 34 as data augmentation techniques.”
From Self-supervised learning for human activity recognition using 700,000 person-days of wearable data (2024) · cites this paper as [34]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Um et al. [193] tackle the scarcity of labeled motor states in Parkinson's disease patients by introducing a variety of augmentation techniques, including jittering, scaling, and rotation.”
From Past, Present, and Future of Sensor-based Human Activity Recognition Using Wearables: A Surveying Tutorial on a Still Challenging Task (2025) · cites this paper as [193]
The cited source says what the claim attributes to it.
In the citing paper
“In sensor-based HAR leveraging the temporal nature of IMU signals allows for the application of augmentation methods grounded in signal processing [32,34,99,132,141,178,193].”
From Past, Present, and Future of Sensor-based Human Activity Recognition Using Wearables: A Surveying Tutorial on a Still Challenging Task (2025) · cites this paper as [193]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“The choice of augmentations is key to performance, and in this tutorial, we utilize all pairwise combinations of augmentations introduced by Um et al. [193].”
From Past, Present, and Future of Sensor-based Human Activity Recognition Using Wearables: A Surveying Tutorial on a Still Challenging Task (2025) · cites this paper as [193]
7 more claims about this paper
Create a free account to see every claim other papers make about this one.
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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 1×
“A reason for employing a CNN rather than a Long Short-term Memory (LSTM) [13], which is often used for learning time-series data, is to reduce the number of parameters to work with the small-scale PD data.”
MethodLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1512.03385 · Cited by 4,196 · cited 2×
“…(CNNs) have shown excellent performance on classification problems when large-scale labeled datasets are available. successes of CNNs include static image classification (e.g. [17], [12]), and extend to other nonstatic domains, for example, video [15], speech [26], and sentence [16] classification.”
BackgroundReturn of the Devil in the Details: Delving Deep into Convolutional Nets
Chatfield, K., Simonyan, K., Vedaldi, A., & Zisserman, A. (2014) · Proceedings of the British Machine Vision Conference 2014 · doi:10.5244/c.28.6 · Cited by 3,335
Return of the Devil in the Details: Delving Deep into Convolutional NetsPreprint
Chatfield, K., Simonyan, K., Vedaldi, A., et al. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1405.3531 · Cited by 663 · cited 1×
“Because of its practical importance, data augmentation has been investigated with systematic experiments, e.g., for image [2] and speech recognition [4].”
BackgroundMonitoring Motor Fluctuations in Patients With Parkinson's Disease Using Wearable Sensors
Patel, S., Lorincz, K., Hughes, R., Huggins, N., Growdon, J., Standaert, D., Akay, M., Dy, J., Welsh, M., & Bonato, P. (2009) · IEEE Transactions on Information Technology in Biomedicine · doi:10.1109/titb.2009.2033471 · Cited by 623 · cited 3×
“Several researchers have attempted to automate PD motor state classification using machine learning techniques based on wearable sensor data (e.g. [25], [10], [7]).”
BackgroundMethodClinical Approach to Parkinson's Disease: Features, Diagnosis, and Principles of Management
Massano, J., & Bhatia, K. P. (2012) · Cold Spring Harbor Perspectives in Medicine · doi:10.1101/cshperspect.a008870 · Cited by 422 · cited 2×
“…accurate evaluation of a patient’s phenomenology is needed for determining the right dose of medication to alleviate the symptoms of bradykinesia and prevent overtreatment-induced dyskinesia. current evaluation process relies on patient’s self-reports and visual observation by the clinician [22].”
BackgroundData Augmentation for Deep Neural Network Acoustic Modeling
Cui, X., Goel, V., & Kingsbury, B. (2015) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2015.2438544 · Cited by 376
Free‐living monitoring of Parkinson's disease: Lessons from the field
Del Din, S., Godfrey, A., Mazzà, C., Lord, S., & Rochester, L. (2016) · Movement Disorders · doi:10.1002/mds.26718 · Cited by 370 · cited 1×
“…for a large-scale PD monitoring [18]. ability to assess motor state from free-living conditions has been identified as an important need for improved assessment and treatment; but to date there is no fully validated system to monitor clinical features or activities in free-living environments [6].”
BackgroundLin, M., Chen, Q., & Yan, S. (2013) · arXiv · doi:10.48550/arxiv.1312.4400 · Cited by 252 · cited 1×
“Fully connected layers which are frequently-used in CNN architectures for classification are substituted with a global averaging pooling (GAP) layer [21] to reduce the number of parameters.”
Method
Research works printed but not linked: 8
- [6] Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep Learning . MIT Press. -
- [7] Robert I. Griffiths, Katya Kotschet, Sian Arfon, Zheng Ming Xu, William Johnson, John Drago, Andrew Evans, Peter Kempster, Sanjay Raghav, and Malcolm K. Horne. 2012. Automated assessment of bradykinesia and dyskinesia in Parkinson's disease. Journal of Parkinson's disease 2, 1 (2012), 47-55. -
- [11] Sergey Ioffe and Christian Szegedy. 2015. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. ArXiv e-prints (Feb. 2015). arXiv:cs.LG/1502.03167 -
- [12] Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2012. ImageNet Classification with Deep Convolutional Neural Networks. In Advances in Neural Information Processing Systems 25 , F. Pereira, C. J. C. Burges, L. Bottou, and K. Q. Weinberger (Eds.). Curran Associates, Inc., 1097-1105. -
- [14] Arthur Le Guennec, Simon Malinowski, and Romain Tavenard. 2016. Data Augmentation for Time Series Classification using Convolutional Neural Networks. In ECML/PKDD Workshop on Advanced Analytics and Learning on Temporal Data . Riva Del Garda, Italy. https://halshs.archives-ouvertes.fr/halshs-01357973 -
- [15] Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. Nature 521, 7553 (28 May 2015), 436-444. Insight. -
- [19] Shyamal Patel, Konrad Lorincz, Richard Hughes, Nancy Huggins, John Growdon, David Standaert, Metin Akay, Jennifer Dy, Matt Welsh, and Paolo Bonato. 2009. Monitoring Motor Fluctuations in Patients With Parkinson's Disease Using Wearable Sensors. IEEE Transactions on Information Technology in Biomedicine 13, 6 (Nov 2009), 864-873. -
- [20] Terry Taewoong Um, Vahid Babakeshizadeh, and Dana Kulić. 2017. Exercise Motion Classification from Large-Scale Wearable Sensor Data Using Convolutional Neural Networks. In 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) . 1-6.
Cited by
Items 401–500 of 736
The benefit of the doubt: Uncertainty aware sensing for edge computing platforms
Qendro, L., Chauhan, J., Ramos, A. G. C. P., & Mascolo, C. (2021) · arXiv · doi:10.48550/arxiv.2102.05956 · Cited by 6
“For both HAR datasets, we used the data augmentation techniques proposed in [54] which consist of seven variations for IMU data on wearables: rotation, permutation, time-warping, scaling, magnitudewarping, jittering, and cropping.”
MethodDeep Regression Modeling for Imbalanced and Incomplete Time-Series Data
Hssayeni, M. D., & Ghoraani, B. (2024) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2024.3372435 · Cited by 12
Gong, P., Ragab, M., Wu, M., Chen, Z., Su, Y., Li, X., & Zhang, D. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3690624.3709239 · Cited by 8
“To cater for this, we introduce magnitude warping augmentation to alleviate magnitude variability by integrating information from both raw and augmentated views [52].”
Choi, H.-T., Mi, E. A. B. E., Kim, B.-K., & Chang, W.-D. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.108211 · Cited by 7
Nshimyimana, D., Rey, V. F., Suh, S., Zhou, B., & Lukowicz, P. (2025) · International Conference on Activity and Behavior Computing (ABC) · doi:10.1109/abc64332.2025.11118365 · Cited by 7
“Multitask learning pretext tasks rely on different signal processing-based data augmentations and transformations introduced by Um et al. [12] including rotations, flipping channels, time-warping, channel shuffling, and adding random Gaussian noise.”
Airaksinen, M., Vanhatalo, S., & Räsänen, O. J. (2023) · Sensors · doi:10.3390/s23073773 · Cited by 5
“and audio processing applications [17,18] as well as in HAR applications [19].”
BackgroundZhang, C., Qin, H., Zhang, Y., Jiang, C., Zhang, D., & Deng, W. (2024) · International Journal of Electrical Power & Energy Systems · doi:10.1016/j.ijepes.2024.110190 · Cited by 8
Tasks Reflected in the Eyes: Egocentric Gaze-Aware Visual Task Type Recognition in Virtual Reality
Wang, Z., & Lu, F. (2024) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2024.3456164 · Cited by 7
“Common augmentations for time-series data include jitter, magnitude-warping, time-warping, scaling, and flipping [49].”
BackgroundRahman, A., Nahid, N., Schuller, B. W., & Ahad, M. A. R. (2024) · Scientific Reports · doi:10.1038/s41598-024-81228-x · Cited by 6
EEG Data Augmentation Method Based on the Gaussian Mixture Model
Liao, C., Zhao, S., Wang, X., Zhang, J., Liao, Y., & Wu, X. (2025) · Mathematics · doi:10.3390/math13050729 · Cited by 10
Yousef, I., Shah, S. L., & Gopaluni, R. B. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110914 · Cited by 6
Landwehr, T., Kantoush, S. A., Nohara, D., Sumi, T., & Pahl‐Wostl, C. (2022) · Journal of Hydroinformatics · doi:10.2166/hydro.2022.013 · Cited by 5
Efficient Augmentation of Human Action Recognition Datasets with Warped Windows
Warchoł, D., & Oszust, M. (2022) · Procedia Computer Science · doi:10.1016/j.procs.2022.09.360 · Cited by 7
Lab to Multiscene Generalization for Non-Line-of-Sight Identification With Small-Scale Datasets
Hua, Q., Nielsen, M. H., An, Z., Ren, J., Wiśniewski, R., Kold, S., Rahbek, O., & Shen, M. (2023) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2023.3262763 · Cited by 7
Detecting Hand Hygienic Behaviors In-the-Wild Using a Microphone and Motion Sensor on a Smartwatch
Zhuang, H., Xu, L., Nishiyama, Y., & Sezaki, K. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-34609-5_34 · Cited by 7
Robust Machine Learning for Low-Power Wearable Devices: Challenges and Opportunities
Bhat, G., Hussein, D., & Yamin, N. (2023) · Springer eBooks · doi:10.1007/978-3-031-40677-5_3 · Cited by 5
A multimodal screening system for elderly neurological diseases based on deep learning
Park, S., No, C., Kim, S., Han, K., Jung, J., Kwon, K., & Lee, M. (2023) · Scientific Reports · doi:10.1038/s41598-023-48071-y · Cited by 7
“Um et al. 25 classified the motor state of PD, i.e., bradykinesia and dyskinesia, using a Microsoft Band2 sensor and CNNs. Pedro et al. 26 proposed a method for detecting the symptoms of Alzheimer’s disease and psychomotor agitation using electrocardiograms and electrodermal activity sensors and…”
MethodGeneration of probabilistic synthetic data for serious games: A case study on cyberbullying
Pérez, J., Castro, M., Awad, E., & López, G. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.111440 · Cited by 10
Enhancing Anomaly Detection in Maritime Operational IoT Time Series Data with Synthetic Outliers
Kim, H., & Joe, I. (2024) · Electronics · doi:10.3390/electronics13193912 · Cited by 11
“When focusing on methods that modify the sizes of time series data based on the Y axis, techniques include jittering [17], flip-ping [20], scaling [17], and magnitude warping [21].”
Wen, J., & Angryk, R. A. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-84353-2_31 · Cited by 5
Augmenting Transferred Representations for Stock Classification
Fons, E., Dawson, P., Zeng, X., Keane, J. A., & Iosifidis, A. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9413530 · Cited by 10
“05 is added to the time series [19].”
Background3DVAE-ERSG: 3D Variational Autoencoder for Extremely Rare Signal Generation
Chalongvorachai, T., & Woraratpanya, K. (2021) · doi:10.1109/icitee53064.2021.9611955 · Cited by 5
Augmentation of Vegetation Index Curves Considering the Crop-Specific Phenological Characteristics
Arun, P. V., & Karnieli, A. (2022) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2022.3142395 · Cited by 8
Transfer Learning Model Knowledge Across Multi-Sensors Locations Over Body Sensor Network
Qian, X., Chen, H., Cai, Y. M., Chu, K., Xu, W., & Huang, M.-C. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3166187 · Cited by 6
“The tasks are designed to recognize the signal transformations motivated by references [12], [41].”
BackgroundTransfer Learning Approach for Indoor Localization with Small Datasets
Yoon, J., Oh, J., & Kim, S. (2023) · Remote Sensing · doi:10.3390/rs15082122 · Cited by 6
Sun, Y., Brockhauser, S., Hegedűs, P., Plückthun, C., Gelisio, L., & de Lima, D. E. F. (2023) · Scientific Reports · doi:10.1038/s41598-023-36456-y · Cited by 6
Intelligent Fault Diagnosis of Robotic Strain Wave Gear Reducer Using Area-Metric-Based Sampling
Noh, Y. R., Khalid, S., Kim, H. S., & Choi, S.-K. (2023) · Mathematics · doi:10.3390/math11194081 · Cited by 5
“, 2017 [12] Computed tomography (CT) image GAN Frid-Adar et al.”
BackgroundOh, Y., Choi, S.-A., Shin, Y., Jeong, Y., Lim, J., & Kim, S. (2023) · doi:10.2196/preprints.53479 · Cited by 5
Zhang, C., Wang, H., Mao, W., Xie, Y., & Yu, B. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/adcadc · Cited by 4
“Jittering, which adds noise to each time step to generate new samples, can have a detrimental effect on the learning process [35].”
Rey, V. F., Rezende, P. M. B., Zhou, B., Suh, S., & Lukowicz, P. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.129288 · Cited by 14
Large Language Model-guided Semantic Alignment for Human Activity Recognition
Yan, H., Tan, H., Ding, Y. C., Zhou, P., Namboodiri, V., & Yang, Y. (2025) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3770652 · Cited by 31
“…mitigate domain shifts, they often struggle with large domain discrepancies, depend heavily on abundant source data Data augmentation [30, 35, 42, 43, 48, 52] in human activity recognition aims to increase the diversity and quality of training data, thereby enhancing the model’s generalization…”
Xia, C., Chen, X., Huang, L., Min, T., & Zhang, D. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3548063 · Cited by 7
“Um et al. [26] used the signals of Parkinson’s patients and proposed to use several data modification approaches for the data augmentation, including time-wrapping, rotation, and cropping.”
Oishi, N., Birch, P. M., Roggen, D., & Lago, P. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2026.3661047 · Cited by 9
“While these approaches demonstrate the potential of virtual IMU simulation for data augmentation, these simulations suffer from a domain gap between virtual and real IMU data.”
InfluentialHosseini-Kivanani, N., Salobrar‐García, E., Elvira‐Hurtado, L., Salas, M., Schommer, C., & Leiva, L. A. (2024) · IEEE International Conference on eScience · doi:10.1109/e-science62913.2024.10678661 · Cited by 4
“4 On-line version : The discrete point sequences were modified according to commonly used transformation methods for time series, such as jittering and scaling [50].”
MethodResultInfluentialData Augmentation for Classification of Multi-Domain Tension Signals
Žvirblis, T., Pikšrys, A., Bzinkowski, D., Rucki, M., Kilikevičius, A., & Kurasova, O. (2024) · Informatica · doi:10.15388/24-infor578 · Cited by 12
Identifying Parkinson’s disease and its stages using static standing balance
Jung, D., Yoo, D., Kim, J. W., Ahn, T. B., & Mun, K.-R. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01351-x · Cited by 4
A Data-level Augmentation Framework for Time Series Forecasting with Ambiguously Related Source Data
Ye, R., & Dai, Q. (2025) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2025.3555530 · Cited by 9
Data augmentation using masked principal component representation for deep learning-based SSVEP-BCIs
Ding, W., Liu, A., Cheng, L., & Chen, X. (2025) · Journal of Neural Engineering · doi:10.1088/1741-2552/add9d1 · Cited by 4
“ME [7], MixUp [39], Gaussian noise addition [29], flipping [27], and scaling [40], to establish its superiority.”
OpenMAE: Efficient Masked Autoencoder for Vibration Sensing with Open-domain Data Enrichment
Hu, C., Chen, Y., Kara, D., Liu, S., Abdelzaher, T., Wu, F., & Chen, G. (2025) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3729485 · Cited by 6
Evaluating Time-series Augmentation Techniques for Deep Learning–Based Solar Flare Prediction
Li, P., Bahri, O., Boubrahimi, S. F., & Hamdi, S. M. (2025) · The Astrophysical Journal Supplement Series · doi:10.3847/1538-4365/adfa2a · Cited by 8
Hemoglobin Estimation from Smartphone-Based Photoplethysmography with Small Data
Silva, D. F., M, J. G. B. D., Domingues, L. V., & Mazzu-Nascimento, T. (2023) · Proceedings - IEEE Symposium on Computer-Based Medical Systems · doi:10.1109/cbms58004.2023.00195 · Cited by 7
“In the time series domain, data augmentation techniques are designed according to what the time series literature observed to be common distortions in that kind of data [15].”
MethodChu, X., Kim, S., & Park, K.-S. (2023) · ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM-BCB) · doi:10.1145/3584371.3612999 · Cited by 6
“Recent studies aim to enhance performance by combining multiple ML techniques [10] and augmenting data to compensate for limited datasets in skeleton-based human action recognition [11-17].”
Unsupervised Deep Feature Learning for Icequake Discrimination at Neumayer Station, Antarctica
Kinzel, L., Fromm, T., Schlindwein, V., & Maaß, P. (2024) · Seismological Research Letters · doi:10.1785/0220230078 · Cited by 6
Data Augmentation for Multivariate Time Series Classification: An Experimental Study
Ilbert, R., Hoang, T. V., & Zhang, Z. (2024) · IEEE International Conference on Data Engineering Workshops (ICDEW) · doi:10.1109/icdew61823.2024.00023 · Cited by 11
“Classification can be misled by scaling in datasets where intensity distinguishes labels [70].”
BackgroundMethodInfluentialZhu, Q., Zhang, L., Lü, F., Fang, L., & Pan, Q. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125619 · Cited by 4
Multi-modal sensing insoles for identity authentication across diverse walking activities
Zeng, H., Mei, Z., Lin, C., Mao, L., Yang, G., & Li, Y. (2024) · Measurement · doi:10.1016/j.measurement.2024.116198 · Cited by 4
Kamikokuryo, K., Venture, G., & Hernandez, V. (2025) · Smart Health · doi:10.1016/j.smhl.2024.100537 · Cited by 5
Gravity Control-Based Data Augmentation Technique for Improving VR User Activity Recognition
Han, D., Lee, C., & Kang, H. (2021) · Symmetry · doi:10.3390/sym13050845 · Cited by 7
“[4] applied many well-known data augmentation methods used for image data to the wearable sensor data and investigated which method improves the classification performance.”
BackgroundMethodBahador, N., Zhao, G., Jokelainen, J., Mustola, S. T., & Kortelainen, J. (2021) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.103052 · Cited by 6
Segment-Based Unsupervised Learning Method in Sensor-Based Human Activity Recognition
Takenaka, K., Kondo, K., & Hasegawa, T. (2023) · Sensors · doi:10.3390/s23208449 · Cited by 5
“As data augmentations [49], we applied jitter, scaling, and permutation for UCI-HAR [48] and USC-HAD [39] and jitter, scaling, and rotate for the other datasets.”
MethodHigh-Intensity Interval Training Exercise Recognition using Smartwatch
Sivakumar, S., Kun, Y. J., & Gopalai, A. A. (2021) · IEEE-EMBS Conference on Biomedical Engineering and Sciences · doi:10.1109/iecbes48179.2021.9398735 · Cited by 4
“Dataset II is augmented using the scaling and time warping method presented at Um et al. [15].”
MethodBearing Fault Detection with Data Augmentation Based on 2-D CNN and 1-D CNN
Han, S., Oh, J., & Jeong, J. (2020) · International Conference on Big Data and Internet of Things (BDIOT) · doi:10.1145/3421537.3421546 · Cited by 4
“D CNN [8,].”
Smartphone speech privacy concerns from side-channel attacks on facial biomechanics
Griswold-Steiner, I., LeFevre, Z., & Serwadda, A. (2020) · Computers & Security · doi:10.1016/j.cose.2020.102110 · Cited by 5
Self-Supervised Learning for Complex Activity Recognition Through Motif Identification Learning
Xia, Q., Morales, J., Huang, Y., Hara, T., Wu, K., Oshima, H., Fukuda, M., Namioka, Y., & Maekawa, T. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3514736 · Cited by 7
DisCovHAR: Contrastive Attention for Human Activity Recognition Under Distribution Shifts
Chen, L., Odema, M., & Faruque, M. A. A. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3551263 · Cited by 5
“D vector rotation equations for each axis [28], [43].”
InfluentialVanacore, A., & Ciardiello, A. (2025) · Socio-Economic Planning Sciences · doi:10.1016/j.seps.2025.102240 · Cited by 3
Purnama, M. R., Adriano, B., Lahcene, E., Suppasri, A., Imamura, F., Farid, M., & Adityawan, M. B. (2025) · Ocean Engineering · doi:10.1016/j.oceaneng.2025.121496 · Cited by 3
Yang, Z., Li, K., Huang, Z., Xu, Z., Zhu, X., & Xiao, Y. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.112317 · Cited by 3
Alexandrino, F. Q. D. L., Pacheco, C. C., Mello, A. C. S., Vaz, A. L., Coutinho, R. D. C., Carvalho, D., & Ogasawara, E. (2026) · Computational Economics · doi:10.1007/s10614-025-11281-9 · Cited by 5
Amraouy, E. H., Yahyaouy, A., Faquir, S., Chaoui, H., & Gualous, H. (2026) · Transportation Research Interdisciplinary Perspectives · doi:10.1016/j.trip.2026.101894 · Cited by 4
Augmentation of Human Action Datasets with Suboptimal Warping and Representative Data Samples
Warchoł, D., & Oszust, M. (2022) · Sensors · doi:10.3390/s22082947 · Cited by 6
“They perform operations that stretch, cut, shrink, or perturb input time series [4,5].”
BackgroundIntelligent Optimal Gated Recurrent Unit based Malicious PDF Detection and Classification Model
Chandran, P. P., Hema Rajini, N., & Jeyakarthic, M. (2022) · International Conference on Applied Artificial Intelligence and Computing (ICAAIC) · doi:10.1109/icaaic53929.2022.9793116 · Cited by 4
“Since the dramatically growing number of data, deep neural network is gaining more interest in several areas like natural language processing, image processing, speech recognition, and sensor data processing [3].”
BackgroundCan Data Augmentation Improve Daily Mood Prediction from Wearable Data? An Empirical Study
Manjunath, N., Li, Z. Y., Choi, E. S., Sen, S., Wang, F., & Adler, D. A. (2023) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3594739.3612876 · Cited by 5
“For instance, [30] utilized techniques such as jittering (adding random noise) and scaling (multiplying by random noise) to improve the performance of a machine learning model that monitored Parkinson’s Disease symptoms.”
BackgroundMethodPostural Sway Classification using Modified Vision Transformer
Nehary, E. A., Rajan, S., & Andò, B. (2023) · IEEE Biomedical Circuits and Systems Conference (BioCAS) · doi:10.1109/biocas58349.2023.10389098 · Cited by 3
“Jittering is employed to enhance the model’s generalizability by assuming that the unseen test data differs from the training data based on the noise [31], [32].”
MethodData Augmentation Techniques for Accurate Action Classification in Stroke Patients with Hemiparesis
Oh, Y. (2024) · Sensors · doi:10.3390/s24051618 · Cited by 4
“…techniques, three methods known to effective in boosting classification The rotation transformation rotated a vector formed by the three axes of either the accelerometer or the gyroscope in three-dimensional space. performance [12]—rotation, permutation, and time-warping—were tested in this study.”
MethodInfluentialMachine Learning Approach for Early Detection of Diabetes Using Raman Spectroscopy
Quang, T. N., Nguyen, T. T., & Viet, H. P. T. (2024) · Mobile Networks and Applications · doi:10.1007/s11036-024-02340-w · Cited by 4
“2 c and d. from wearable sensor with target of monitoring Parkinson’s disease with deep learning model [18].”
Stress Detection Using HRV Features Augmentation Based on Heart Rate Signal Transformation
Chen, P.-J., Chien, W.-S., Chen, H., & Lee, C.-C. (2024) · Wearable and Implantable Body Sensor Networks · doi:10.1109/bsn63547.2024.10780687 · Cited by 4
Sun, T., Tan, T., Li, D., Markert, B. A., Shull, P. B., & Bamer, F. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3521896 · Cited by 4
“For comparison, two traditional augmentation techniques, jittering and time warp, were also implemented to augment the dataset [28].”
InfluentialJiao, S., Huo, H., Liu, W., Zhao, C., Ma, L., Wang, J., Xu, N., Zhang, C., & Li, D. (2025) · Complex & Intelligent Systems · doi:10.1007/s40747-025-01830-y · Cited by 6
“For example, Terry T. et al. [20] proposed various data augmentation methods for wearable sensor data.”
Graph-Based Physics-Guided Urban PM2.5 Air Quality Imputation with Constrained Monitoring Data
Du, S., Wei, H., Lee, D. Y., Hu, Z., & Pan, S. (2026) · ACM Transactions on Sensor Networks · doi:10.1145/3734869 · Cited by 11
“However, transfer learning and data augmentation can make them viable options in some cases [31, 51, 62, 66].”
Han, A., He, X., & Huang, X. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3564990 · Cited by 4
“For example, the permutation operation [55] that swaps the order of two temporal segments may disrupt temporal dependencies, affecting the context–timestamp relationship.”
Xu, L., Pombo, N. G. C. C., Pires, I. M., & García, N. M. (2019) · EAI International Conference on Smart Objects and Technologies for Social Good (GOODTECHS) · doi:10.1145/3342428.3342698 · Cited by 3
“In general, the use of Deep Neural Networks (DNN) may increase the probability of occurrence of overfitting, because it has a complex structure containing massive amounts of weights, but sometimes the results reported are better than others [17].”
BackgroundMulti-sensor data augmentation for robust sensing
Saeed, A., Li, Y., Özçelebi, T., & Lukkien, J. J. (2020) · IEEE International Conference on Omni-layer Intelligent Systems (COINS) · doi:10.1109/coins49042.2020.9191412 · Cited by 3
“Specifically, we propose six operations for input sequence deformations to enrich the search space, in addition to the various functions that exists in literature [3].”
BackgroundMethodImprovement of Human Action Recognition Using 3D Pose Estimation
Adachi, K., Lago, P., Okita, T., & Inoue, S. (2020) · Smart innovation, systems and technologies · doi:10.1007/978-981-15-8944-7_2 · Cited by 3
Shared learning activity labels across heterogeneous datasets
Ye, J. (2021) · Journal of Ambient Intelligence and Smart Environments · doi:10.3233/ais-210590 · Cited by 4
“Also, recent data augmentation techniques [4,14,24] can be applied to either simulate data samples and augment data with variations.”
Random Noise Boxes: Data Augmentation for Spectrograms
Goubeaud, M., Gmyrek, N., Ghorban, F., Schelkes, L., & Kummert, A. (2021) · IEEE International Conference on Progress in Informatics and Computing · doi:10.1109/pic53636.2021.9687058 · Cited by 6
Oszust, M., & Warchoł, D. (2022) · IEEE International Conference on Tools with Artificial Intelligence (ICTAI) · doi:10.1109/ictai56018.2022.00108 · Cited by 3
Sensor placement determination for a wearable device in dual-arm manipulation tasks
Urukalo, D., Nates, F. M., & Blazevic, P. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109217 · Cited by 5
Hybrid Statistical and AI Methods for Synthetic Time Series Generation in Practical Applications
Ungureanu, I. I., Portase, R. L., Dînșoreanu, M., Lemnaru, C., & Potolea, R. (2024) · IEEE International Conference on Intelligent Computer Communication and Processing (ICCP) · doi:10.1109/iccp63557.2024.10793008 · Cited by 3
“A simple way of perturbing the input can be noise injection ( [1], [4]), or a more complex method is the one proposed in the paper [2], which involves calculating the average of a set of series of time and using the resulting time series as a synthetic data set.”
Kang, T. Y., & Hong, S. (2025) · IEEE Access · doi:10.1109/access.2025.3536287 · Cited by 3
“For one-dimensional (1D) data, including time series and frequency domain data, traditional approaches have utilized techniques such as time slicing [37], permutation, jittering [38], scaling [39], and rotation [40].”
Tang, L., Wilkman, D., Feng, L., & Törngren, M. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113409 · Cited by 3
TFFC: time-frequency fusion consistency for semi-supervised time series classification
Xi, L., Meng, X., & Liu, H. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06695-9 · Cited by 3
“Moreover, we employ data augmentations of magnitude warping, time warping, and cutout [40, 41] for all models.”
A Novel Approach to Classify Electrocardiogram Signals Using Deep Neural Networks
Ahmed, T., Rahman, A., Chowdhury, T. M., Kushol, R., & Raihan, M. N. (2020) · doi:10.1109/iccis49240.2020.9257700 · Cited by 3
“The augmentation of these time series data is done based on the method described by T. T. Um et al. [22] and instead of using static parameters authors used probabilistic parameters for augmenting samples.”
MethodFrom Virtual to Real World: Applying Animation to Design the Activity Recognition System
Xia, C., & Sugiura, Y. (2021) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3411763.3451677 · Cited by 3
“Referencing the work of [15], the DA for wearable sensor data can be performed in the original dataset or feature domain.”
BackgroundKnee Osteoarthritis Classification System Examination on Wearable Daily-Use IMU Layout
Xia, C., Maruyama, T., Toda, H., Tada, M., Fujita, K., & Sugiura, Y. (2022) · ACM International Symposium on Wearable Computers (ISWC) · doi:10.1145/3544794.3558459 · Cited by 4
“The data augmentation method from [14] was employed during the LOOCV test to balance the healthy dataset (during the evaluation, the tester’s data was not augmented while other healthy people’s data used for training were augmented).”
MethodADGAS: An Advanced Data Generation for Anomalous Signals
Chalongvorachai, T., & Woraratpanya, K. (2021) · Lecture notes in networks and systems · doi:10.1007/978-3-030-79757-7_14 · Cited by 3
Self-supervised learning for early detection of neurodegenerative diseases with small data
Jiang, H. (2023) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/166402 · Cited by 9
Kargarandehkordi, A., & Washington, P. Y. (2023) · medRxiv · doi:10.1101/2023.12.18.23300060 · Cited by 3
“For example, for accelerometer data, rotations simulate different sensor placements and cropping is used to diminish the dependency of event locations [16].”
BackgroundMethodIDMatchHAR: Semi-Supervised Learning for Sensor-Based Human Activity Recognition Using Pretraining
Takenaka, K., Sakai, S., & Hasegawa, T. (2025) · IEEE Sensors Letters · doi:10.1109/lsens.2025.3546985 · Cited by 3
“During model training, rotation [25] and jittering [25] with a standard deviation of 0.2 were used as data augmentation techniques.”
InfluentialCCDb-HG: Novel Annotations and Gaze-Aware Representations for Head Gesture Recognition
Vuillecard, P., Farkhondeh, A., Villamizar, M., & Odobez, J. (2024) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg59268.2024.10581954 · Cited by 2
“Here we explore the efficacy of similar standard time series augmentation [30] (TS-DA) and the temporal version of Mixup [7] (Mixup-DA).”
MethodFrom Vision to Motion: Translating Large-Scale Knowledge for Data-Scarce IMU Applications
Yoon, H., Cha, H., Nguyen, H. C., Gong, T., & Lee, S.-J. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3556998 · Cited by 10
Cross-Dataset Representation Learning for Unsupervised Deep Clustering in Human Activity Recognition
Takatsu, T., Hayama, T., & Cui, H. (2025) · IEEE Access · doi:10.1109/access.2025.3562897 · Cited by 4
“Furthermore, while data augmentation techniques have shown promise in other domains, extensive research [33], [34], [35], [36] has demonstrated that no universally effective method exists for HAR data.”
Zhang, J., Peng, C., Liu, Z., Feng, L., Wu, Y., Dong, Y., & Xu, D. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3572220 · Cited by 6
On Neural Inertial Classification Networks for Pedestrian Activity Recognition
Yampolsky, Z., Kruzel, O., Fekson, V. K., & Klein, I. (2025) · IEEE/ION Position Location and Navigation Symposium · doi:10.1109/plans61210.2025.11028462 · Cited by 5
“To address this problem, multiple research fields have developed techniques for adding additional training data [33], For inertial data, some of the augmentation techniques include rotation, permutation, scaling, cropping, additive bias, and additive noise [34].”
Wang, W., & Li, B. (2025) · IEEE Access · doi:10.1109/access.2025.3585968 · Cited by 2
“Um et al. [25] used cropping, rotation, permutation, and other methods to manipulate the original time series to augment time series data from wearable sensors.”
SigGen: Signal Generation for Wireless Sensing Based on Disentangled Representation
He, H., Huan, X., Luo, Y., Fan, R., Xu, J., & Hu, H. (2025) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2025.3594547 · Cited by 2
“Um et al. [17] modified the signal’s strength by multiplying it by a random scalar.”
Wu, H., Feng, J., Liu, X., Liu, Y., Liu, N., Yang, Y., & Zhou, S. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3621119 · Cited by 3
“Such techniques have been successfully applied in various domains, including speech recognition (frequency-band random masking) [48], time-series forecasting (spectrum perturbation) [49], and medical image classification (frequency-domain blending interpolation) [50].”
Yang, M., Liu, M., Wang, X., Lv, H., Du, Y., Qi, Y., Wang, Z., Yang, Q., & Liu, Q. (2025) · ACS Photonics · doi:10.1021/acsphotonics.5c01694 · Cited by 2
A 2-D-Variation Modeling of Aggregated Load Data With Times Block for Nonintrusive Load Monitoring
Wang, B., She, W., Wan, X., Han, Y., & Liu, W. (2026) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2026.3652752 · Cited by 3
“Additionally, shifting [25], jitter [26], and frequency dropout [27] are also commonly used as DA methods for time series.”
Mehra, N., Mittal, P., Sharma, Y. K., Lilhore, U. K., Mohamed, H. G., Ghith, E. S., & Tekeste, L. G. (2026) · International Journal of Computational Intelligence Systems · doi:10.1007/s44196-025-01148-0 · Cited by 3
“Previous studies [45 ] shown that such technique is highly effective in enhancing model generalization.”
Metadata
- Authors
- Um, T. T., Pfister, F. M. J., Pichler, D., Endo, S., Lang, M., Hirche, S., Fietzek, U., & Kulić, D.
- Affiliations
- University of Waterloo (CA)
- Ludwig-Maximilians-Universität München (DE)
- Technical University of Munich (DE)
- Schön Klinik München Schwabing (DE)
- Venue
- Proceedings of the 19th ACM International Conference on Multimodal Interaction
- Publisher
- ACM
- Published
- 2017-11-03
- Pages
- 216-220
- OpenAlex
- W2620664872
- Cited by
- 729
- References
- 8
- Citations by year
- 2026: 80 · 2025: 131 · 2024: 128 · 2023: 112 · 2022: 101 · 2021: 77 · 2020: 64 · 2019: 26 · 2018: 10
- FWCI
- 7.99
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- mediaTUM (Technical University of Munich) (submittedVersion, cc-by)
- arXiv (Cornell University)
- Funders
- FP7 Ideas: European Research Council (337654)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Life Sciences › Neuroscience › Cognitive Neuroscience › EEG and Brain-Computer Interfaces
- Keywords
- data augmentation, wearable sensor data, Parkinson's disease, disease surveillance, convolutional neural networks, limited labeled data
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.