Data augmentation of wearable sensor data for parkinson’s disease monitoring using convolutional neural networks
Open accessThe DOI matches its Crossref record; 12 of the 12 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 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.”
MethodKubota, K. J., Chen, J. A., & Little, M. A. (2016) · Movement Disorders · doi:10.1002/mds.26693 · Cited by 210 · cited 1×
“…motor tasks is much smaller than that what could be available without the motor-task constraint, thus, not suitable 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…”
Background
Research works printed but not linked: 6
- Ian Goodfellow , Yoshua Bengio , and Aaron Courville . 2016. Deep Learning . MIT Press . Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep Learning. MIT Press.
- 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. 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.
- 10.5555/2886521.2886562 · doi:10.5555/2886521.2886562
- 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 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
- 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. 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.
- 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 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
Cited by
A Survey of Machine and Deep Learning Methods for Internet of Things (IoT) Security
Al-Garadi, M. A., Mohamed, A., Al-Ali, A. K., Du, X., Ali, I., & Guizani, M. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.2988293 · Cited by 1,392
“The key challenge in data augmentation is producing new data samples that preserve the appropriate data distribution for each class, normally necessitating domain knowledge [192, 261].”
BackgroundAn empirical survey of data augmentation for time series classification with neural networks
Iwana, B. K., & Uchida, S. (2021) · PLOS ONE · doi:10.1371/journal.pone.0254841 · Cited by 725
“3) Time Domain Transformations: Similar to Rotation, Permutation had severe detrimental effects on accuracy.”
BackgroundMethodInfluentialSkin-Interfaced Wearable Sweat Sensors for Precision Medicine
Min, J., Tu, J., Xu, C., Lukas, H., Shin, S., Yang, Y., Solomon, S. A., Mukasa, D., & Gao, W. (2023) · Chemical Reviews · doi:10.1021/acs.chemrev.2c00823 · Cited by 712
Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances
Zhang, S., Li, Y., Zhang, S., Shahabi, F., Xia, S., Deng, Y., & Alshurafa, N. (2022) · Sensors · doi:10.3390/s22041476 · Cited by 625
“In general, using the dataset augmented with synthetic training samples yields higher classification accuracy when compared to using the original dataset [36,56,261,262].”
BackgroundMethodFan, C., Chen, M., Wang, X., Wang, J., & Huang, B. (2021) · Frontiers in Energy Research · doi:10.3389/fenrg.2021.652801 · Cited by 445
A survey on wearable sensor modality centred human activity recognition in health care
Wang, Y., Cang, S., & Yu, H. (2019) · Expert Systems with Applications · doi:10.1016/j.eswa.2019.04.057 · Cited by 409
Self-Supervised ECG Representation Learning for Emotion Recognition
Sarkar, P., & Etemad, A. (2022) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2020.3014842 · Cited by 383
Data Augmentation techniques in time series domain: a survey and taxonomy
Iglesias, G., Talavera, E., González-Prieto, Á., Mozo, A., & Gómez-Canaval, S. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-08459-3 · Cited by 347
“This technique was used in [70] where the data was captured from a wearable device to detect if a patient suffers from Parkinson’s disease.”
BackgroundMethodInfluentialMulti-task Self-Supervised Learning for Human Activity Detection
Saeed, A., Ozcelebi, T., & Lukkien, J. (2019) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3328932 · Cited by 346
“In [67] task-specific transformations (such as added noise and rotation) are applied to wearable sensor data to augment and improve the performance of Parkinson’s disease monitoring systems.”
MethodInfluentialDeep Learning for Time Series Classification and Extrinsic Regression: A Current Survey
Mohammadi Foumani, N., Miller, L., Tan, C. W., Webb, G. I., Forestier, G., & Salehi, M. (2024) · ACM Computing Surveys · doi:10.1145/3649448 · Cited by 268
“Jittering, as explored by Um et al. [156], involves the addition of random noise to the time series.”
BackgroundMethodSelf-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects
Zhang, K., Wen, Q., Zhang, C., Cai, R., Jin, M., Liu, Y., Zhang, J. Y., Liang, Y., Pang, G., Song, D., et al. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3387317 · Cited by 295
Steven Eyobu, O., & Han, D. S. (2018) · Sensors · doi:10.3390/s18092892 · Cited by 259
“In [14], a sizeable number of data augmentation methods for time series data are mentioned and implemented.”
BackgroundAzam, Z., Islam, M. M., & Huda, M. N. (2023) · IEEE Access · doi:10.1109/access.2023.3296444 · Cited by 265
“A variety of data augmentation techniques, including shifting the locations of sensors, arbitrary rotations, permuting the locations where sensor events occurred, time warping, and scaling, will significantly improve the performance of deep learning-based human activity recognition [233].”
BackgroundChung, S., Lim, J., Noh, K. J., Kim, G., & Jeong, H. (2019) · Sensors · doi:10.3390/s19071716 · Cited by 215
“We apply the jittering method to simulate additive sensor noise using random parameters as described in [47] for label-preserving augmentation.”
MethodKumar, P., Chauhan, S., & Awasthi, L. K. (2024) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-023-09986-x · Cited by 206
“Specifically, many publications have detailed different approaches to monitoring and assessing the signs and symptoms of Parkinson’s disease (PD) [254, 255].”
Evolution, Current Challenges, and Future Possibilities in ECG Biometrics
Ribeiro Pinto, J., Cardoso, J. S., & Lourenco, A. (2018) · IEEE Access · doi:10.1109/access.2018.2849870 · Cited by 195
“[147] reached improved performance with a CNN for classification of motor state of Parkinson’s patients.”
MethodQuantitative Phase Imaging and Artificial Intelligence: A Review
Jo, Y., Cho, H., Lee, S. Y., Choi, G., Kim, G., Min, H.-S., & Park, Y. (2019) · IEEE Journal of Selected Topics in Quantum Electronics · doi:10.1109/jstqe.2018.2859234 · Cited by 192
GRU-INC: An inception-attention based approach using GRU for human activity recognition
Mim, T. R., Amatullah, M., Afreen, S., Yousuf, M. A., Uddin, S., Alyami, S. A., Hasan, K. F., & Moni, M. A. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.119419 · Cited by 178
Self-supervised learning for human activity recognition using 700,000 person-days of wearable data
Yuan, H., Chan, S., Creagh, A. P., Tong, C., Acquah, A., Clifton, D. A., & Doherty, A. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01062-3 · Cited by 166
“To fully appreciate the benefit of SSL in HAR, we chose the tasks that would prioritise the temporal dependencies of human motion, namely, arrow of time (AoT), permutation and time-warping (TW) (Um et al., 2017).”
Deng, Y., Lu, L., Aponte, L., Angelidi, A. M., Novak, V., Karniadakis, G. E., & Mantzoros, C. S. (2021) · npj Digital Medicine · doi:10.1038/s41746-021-00480-x · Cited by 152
Self-Supervised Learning for ECG-Based Emotion Recognition
Sarkar, P., & Etemad, A. (2020) · ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp40776.2020.9053985 · Cited by 146
“For our developed signal transformation recognition network, 6 different transformations are performed [15,17].”
MethodCao, P., Li, X., Mao, K., Lü, F., Ning, G., Fang, L., & Pan, Q. (2019) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2019.101675 · Cited by 157
SelfHAR: Improving Human Activity Recognition through Self-training with Unlabeled Data
Tang, C. I., Perez-Pozuelo, I., Spathis, D., Brage, S., Wareham, N., & Mascolo, C. (2021) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3448112 · Cited by 140
“Once the samples with the highest softmax scores are selected to form S , eight signal transformation functions, as used in [50] and [39], are used to augment the dataset: adding random noise, scaling using a random scalar, applying a random 3D rotation, inverting the signals, reversing the direction of time, randomly…”
MethodA Systematic Study of Unsupervised Domain Adaptation for Robust Human-Activity Recognition
Chang, Y., Mathur, A., Isopoussu, A., Song, J., & Kawsar, F. (2020) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3380985 · Cited by 138
“[44], which have shown a good performance.”
LSTM-Based Zero-Velocity Detection for Robust Inertial Navigation
Wagstaff, B., & Kelly, J. W. (2018) · International Conference on Indoor Positioning and Indoor Navigation · doi:10.1109/ipin.2018.8533770 · Cited by 139
“[17] recently proposed several data augmentation methods for wearable sensors, and showed that augmentation significantly improved classification performance (for inertial data).”
BackgroundMethodDorschky, E., Nitschke, M., Martindale, C. F., van den Bogert, A. J., Koelewijn, A. D., & Eskofier, B. M. (2020) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2020.00604 · Cited by 166
“Um et al. (2017) used label-preserving transformations of the sensor data (e.g., rotations, permutations, and time-warping) to augment the training dataset.”
MethodContrastive learning based self-supervised time-series analysis
Pöppelbaum, J., Chadha, G. S., & Schwung, A. (2022) · Applied Soft Computing · doi:10.1016/j.asoc.2021.108397 · Cited by 131
Time Series Data Augmentation for Neural Networks by Time Warping with a Discriminative Teacher
Iwana, B. K., & Uchida, S. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412812 · Cited by 166
“[16] used a variety of augmentations, such as jittering, scaling, rotation, slicing, permutation, magnitude warping, and time warping, to improve wearable sensor data for deep temporal CNNs.”
BackgroundMethodInfluentialTunca, C., Salur, G., & Ersoy, C. (2019) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2019.2958879 · Cited by 140
“time-warping may alter the intensity and the temporal characteristics of the motor activities, respectively, possibly altering the label of the measurement [38].”
BackgroundTime-Series Data Augmentation based on Interpolation
Oh, C., Han, S., & Jeong, J. (2020) · Procedia Computer Science · doi:10.1016/j.procs.2020.07.012 · Cited by 149
Anomaly recognition from surveillance videos using 3D convolution neural network
Maqsood, R., Bajwa, U. I., Saleem, G., Raza, R. H., & Anwar, M. W. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-10570-3 · Cited by 127
“The tube convolution neural network (T-CNN) [14] expands the recursive convolution neural network (R-CNN) [33] for the detection of objects from a video stream.”
BackgroundZhong, B., Wu, H., Ding, L., Love, P. E. D., Li, H., Luo, H., & Li, J. (2019) · Automation in Construction · doi:10.1016/j.autcon.2019.102919 · Cited by 135
TimeCLR: A self-supervised contrastive learning framework for univariate time series representation
Yang, X., Zhang, Z., & Cui, R. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.108606 · Cited by 114
Demir, S., Mincev, K., Kok, K.-E., & Paterakis, N. (2021) · Applied Energy · doi:10.1016/j.apenergy.2021.117695 · Cited by 106
“Commencing with augmentation methods that have been utilised to boost classification accuracies, feature space augmentors, exploiting simple transformations such as symmetry, position, or style, have been observed to successfully generate data for both image and time series classification problems [3,4].”
MethodInfluentialWu, Y., Daoudi, M., & Amad, A. (2023) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2023.3263907 · Cited by 144
“Meanwhile, according to the review of time series augmentation strategies [30], [31], though most of the suggested transformations have been adopted in previous SSL-based work, two transformations have not been thoroughly evaluated: Magnitudewarping and Cropping.”
BackgroundAbedin, A., Ehsanpour, M., Shi, Q., Rezatofighi, H., & Ranasinghe, D. C. (2021) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3448083 · Cited by 107
“However, achieving labelpreserving transformations for wearable HAR sensor data is not obvious and intuitively recognizable [41].”
BackgroundMethodResultInfluentialAssessing the State of Self-Supervised Human Activity Recognition Using Wearables
Haresamudram, H., Essa, I., & Plötz, T. (2022) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3550299 · Cited by 107
Parkinson’s Disease Tremor Detection in the Wild Using Wearable Accelerometers
San-Segundo, R., Zhang, A., Cebulla, A., Panev, S., Tabor, G. F., Stebbins, K., Massa, R. E., Whitford, A. S., de la Torre, F. N., & Hodgins, J. K. (2020) · Sensors · doi:10.3390/s20205817 · Cited by 125
“More recently, researchers have explored the efficacy of deep learning techniques for automated UPDRS testing [25] or bradykinesia detection [26,27].”
BackgroundObjective and automatic classification of Parkinson disease with Leap Motion controller
Butt, A. H., Rovini, E., Dolciotti, C., Petris, G. D., Bongioanni, P., Carboncini, M. C., & Cavallo, F. (2018) · BioMedical Engineering OnLine · doi:10.1186/s12938-018-0600-7 · Cited by 108
“2 Leap Motion features on a gesture example: a fingertips distance [41], b thumb and index finger distance, c palm angle [21], d finger tips velocity [15]”
BackgroundSMOTE and Gaussian Noise Based Sensor Data Augmentation
Arslan, M. S., Güzel, M., Demirci, M., & Özdemir, S. (2019) · International Conference on Computer Science and Engineering (UBMK) · doi:10.1109/ubmk.2019.8907003 · Cited by 121
Data augmentation for univariate time series forecasting with neural networks
Semenoglou, A.-A., Spiliotis, E., & Assimakopoulos, V. (2022) · Pattern Recognition · doi:10.1016/j.patcog.2022.109132 · Cited by 122
A Comprehensive Survey on Data Augmentation
Wang, Z., Wang, P., Liu, K., Wang, P., Fu, Y., Lu, C.-T., Aggarwal, C. C., Pei, J., & Zhou, Y. (2025) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2025.3622600 · Cited by 278
“In [67], jitter-ing is used to simulate additive noise (cid:2) of wearable sensors: ˜ x ( (cid:2) ) = { x 1 + (cid:2) 1 , . . . , x t + t , . . . , x T + T } .”
InfluentialRuiz-Parrado, V., Linares, I., Sánchez, Á., & Vélez, J. F. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.09.041 · Cited by 97
Detection of Parkinson’s disease from handwriting using deep learning: a comparative study
Taleb, C., Likforman-Sulem, L., Mokbel, C., & Khachab, M. Y. (2020) · Evolutionary Intelligence · doi:10.1007/s12065-020-00470-0 · Cited by 91
“Scaling Scaling changes the magnitude of the data in a window by multiplying by a random scalar [26].”
BackgroundMethodInfluentialSleepPoseNet: Multi-View Learning for Sleep Postural Transition Recognition Using UWB
Piriyajitakonkij, M., Warin, P., Lakhan, P., Leelaarporn, P., Kumchaiseemak, N., Suwajanakorn, S., Pianpanit, T., Niparnan, N., Mukhopadhyay, S. C., & Wilaiprasitporn, T. (2020) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2020.3025900 · Cited by 95
“Time-Warping (TW) and Magnitude-Warping (MW), which were proposed in 2017 for wearable sensor data [46], were also”
BackgroundMultimodal EEG and Keystroke Dynamics Based Biometric System Using Machine Learning Algorithms
Rahman, A., Chowdhury, M. E. H., Khandakar, A. A., Kiranyaz, S., Zaman, K. S., Reaz, M. B. I., Islam, M. T., Ezeddin, M., & Kadir, M. A. (2021) · IEEE Access · doi:10.1109/access.2021.3092840 · Cited by 94
Sample-Based Data Augmentation Based on Electroencephalogram Intrinsic Characteristics
Li, R., Wang, L., Suganthan, P. N., & Sourina, O. (2022) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2022.3185587 · Cited by 84
Ortiz, B. L., Gupta, V., Kumar, R., Jalin, A. F., Cao, X., Ziegenbein, C., Singhal, A., Tewari, M., & Choi, S. W. (2024) · JMIR mhealth and uhealth · doi:10.2196/59587 · Cited by 125
High-Resolution Motor State Detection in Parkinson’s Disease Using Convolutional Neural Networks
Pfister, F., Um, T. T., Pichler, D., Goschenhofer, J., Abedinpour, K., Lang, M., Endo, S., Ceballos-Baumann, A., Hirche, S., Bischl, B., et al. (2020) · Scientific Reports · doi:10.1038/s41598-020-61789-3 · Cited by 88
Self-citationSTEP: A Spatio-Temporal Fine-Granular User Traffic Prediction System for Cellular Networks
Yu, L., Li, M., Jin, W., Guo, Y., Wang, Q., Yan, F., & Li, P. (2020) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2020.3001225 · Cited by 92
“While first inspired from computer vision community, with its idea of extracting slices from time series to construct synthetic dataset, window slicing has been investigated for augmenting training dataset for time series for quite some time [42], [44], [46].”
BackgroundEnergy consumption prediction in water treatment plants using deep learning with data augmentation
Harrou, F., Dairi, A., Dorbane, A., & Sun, Y. (2023) · Results in Engineering · doi:10.1016/j.rineng.2023.101428 · Cited by 83
PlethAugment: GAN-Based PPG Augmentation for Medical Diagnosis in Low-Resource Settings
Kiyasseh, D., Tadesse, G. A., Nhan, L. N. T., Tan, L. V., Thwaites, L., Zhu, T., & Clifton, D. A. (2020) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2020.2979608 · Cited by 94
“In the time-domain, on the other hand, the addition of noise and time-warping is performed [9].”
Seismic signal augmentation to improve generalization of deep neural networks
Zhu, W., Mousavi, S. M., & Beroza, G. C. (2020) · Advances in geophysics · doi:10.1016/bs.agph.2020.07.003 · Cited by 99
Fan, C., Chen, M., Tang, R., & Wang, J. (2021) · Building Simulation · doi:10.1007/s12273-021-0807-6 · Cited by 94
“As shown in Figure 3, instead of simply compressing the original data into a latent vector, the encoder of VAE transforms the original data into a set of means and variances (i.e., denoted as μ and 2 σ respectively), which specify the characteristics of normal distributions (Um et al. 2017).”
BackgroundMethodData Augmentation with Suboptimal Warping for Time-Series Classification
Kamycki, K., Kapuściński, T., & Oszust, M. (2019) · Sensors · doi:10.3390/s20010098 · Cited by 74
“[7] perturb a temporal location of within-window event in time-series of wearable sensor data for Parkinson’s disease monitoring, or Le”
BackgroundLi, B., Yao, Z., Wang, J., Wang, S., Yang, X., & Sun, Y. (2020) · Electronics · doi:10.3390/electronics9111919 · Cited by 74
“Therefore, in this study, a method similar to that in [51] was used to augment the FOG data through arbitrary rotation, so that we can get a balanced training set for the model.”
BackgroundMethodAssessing inertial measurement unit locations for freezing of gait detection and patient preference
O’Day, J. J., Lee, M. R., Seagers, K. A., Hoffman, S. L., Jih-Schiff, A., Kidziński, Ł., Delp, S. L., & Bronte-Stewart, H. M. (2022) · Journal of NeuroEngineering and Rehabilitation · doi:10.1186/s12984-022-00992-x · Cited by 77
Tan, H. X., Aung, N. N., Tian, J., Chua, M. C. H., & Yang, Y. O. (2019) · Gait & Posture · doi:10.1016/j.gaitpost.2019.09.007 · Cited by 77
TS-GAN: Time-series GAN for Sensor-based Health Data Augmentation
Yang, Z., Li, Y., & Zhou, G. (2023) · ACM Transactions on Computing for Healthcare · doi:10.1145/3583593 · Cited by 101
“For example, adding random noise [17, 32], slicing or cropping, scaling [32, 44], random warping in the time dimension [17, 44], and frequency warping [27].”
BackgroundMachine Learning in the Parkinson’s disease smartwatch (PADS) dataset
Varghese, J., Brenner, A., Fujarski, M., van Alen, C. M., Plagwitz, L., & Warnecke, T. (2024) · npj Parkinson s Disease · doi:10.1038/s41531-023-00625-7 · Cited by 79
Digital twin-driven framework for improving self-management of ergonomic risks
Ogunseiju, O. R., Olayiwola, J., Akanmu, A. A., & Nnaji, C. A. (2021) · Smart and Sustainable Built Environment · doi:10.1108/sasbe-03-2021-0035 · Cited by 81
Detection and Localization of Breast Cancer Using UWB Microwave Technology and CNN-LSTM Framework
Lu, M. X., Xiao, X., Pang, Y., Liu, G., & Lu, H. (2022) · IEEE Transactions on Microwave Theory and Techniques · doi:10.1109/tmtt.2022.3209679 · Cited by 70
“D signal data augmentation are permutation, time-warping, scaling, magnitude-warping (Mag-Warp), and cropping [35].”
BackgroundIntelliRehabDS (IRDS)—A Dataset of Physical Rehabilitation Movements
Miron, A., Sadawi, N., Ismail, W., Hussain, H., & Groşan, C. (2021) · Data · doi:10.3390/data6050046 · Cited by 81
“Another set of techniques is provided in [16].”
MethodUsing recurrent neural networks for continuous authentication through gait analysis
Giorgi, G., Saracino, A., & Martinelli, F. (2021) · Pattern Recognition Letters · doi:10.1016/j.patrec.2021.03.010 · Cited by 76
Nita, S., Bitam, S., Heidet, M., & Mellouk, A. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2022.103580 · Cited by 80
Hong, Z., Li, Z., Zhong, S., Lyu, W., Wang, H., Ding, Y., He, T., & Zhang, D. (2024) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3659597 · Cited by 67
“Note that, the number of generated IMU samples can be infinite due to the infinite space of device orientations [74].”
BackgroundMethodSigRep: Toward Robust Wearable Emotion Recognition With Contrastive Representation Learning
Dissanayake, V., Seneviratne, S., Rana, R. K., Wen, E., Kaluarachchi, T. I., & Nanayakkara, S. C. (2022) · IEEE Access · doi:10.1109/access.2022.3149509 · Cited by 70
“Informed by previous research, we randomly select a transformation τ from the following pool τ = {amplitude re-scaling, random DC shift, zero maskings, additive noise} [32], [33].”
MethodSemi-Supervised Time Series Classification by Temporal Relation Prediction
Fan, H., Zhang, F., Wang, R., Huang, X., & Li, Z. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9413883 · Cited by 74
“During training, we use data augmentations (magnitude warping and time warping [25]) for all models.”
MethodRenani, M. S., Eustace, A., Myers, C. A., & Clary, C. W. (2021) · Sensors · doi:10.3390/s21175876 · Cited by 77
“Most augmentation approaches for IMU-based applications employ labelpreserving transformations such as adding noise or simulating variation in sensor positioning [31].”
MethodSurgical motion analysis using discriminative interpretable patterns
Forestier, G., Petitjean, F., Senin, P., Despinoy, F., Huaulmé, A., Fawaz, H. I., Weber, J., Idoumghar, L., Müller, P.-A., & Jannin, P. (2018) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2018.08.002 · Cited by 63
“For example in [67] a deep convolutional neural network was proposed to classify the motor state of Parkinson’s Disease using patients’ accelerometer coordinates captured by wearable sensors.”
Zhu, Y., Xie, B., Wang, A., & Qian, Z. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.123080 · Cited by 69
Data Augmentation of Surface Electromyography for Hand Gesture Recognition
Tsinganos, P., Cornelis, B., Cornelis, J. P., Jansen, B., & Skodras, A. N. (2020) · Sensors · doi:10.3390/s20174892 · Cited by 74
“Magnitude warping (MW), used in [9] to change the shape of accelerometer signals for the motion recognition task, is applied in a similar fashion in this work to deform the sEMG amplitude.”
BackgroundMethodKiprijanovska, I., Gjoreski, H., & Gams, M. (2020) · Sensors · doi:10.3390/s20185373 · Cited by 75
“Some of the most commonly used data augmentation methods for IMU data include time-warping, scaling, and rotation [34].”
MethodBearing Fault Diagnosis Based on Multiscale Convolutional Neural Network Using Data Augmentation
Han, S., Oh, S., & Jeong, J. (2021) · Journal of Sensors · doi:10.1155/2021/6699637 · Cited by 59
Chan, S., Hang, Y., Tong, C., Acquah, A., Schonfeldt, A., Gershuny, J., & Doherty, A. (2024) · Scientific Data · doi:10.1038/s41597-024-03960-3 · Cited by 61
Mahmud, T., Sazzad Sayyed, A. Q. M., Fattah, S. A., & Kung, S.-Y. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2020.3015781 · Cited by 58
“In this work, we have utilized the combination of five techniques that incorporate realistic variations in the data and make the process more robust [27].”
MethodBi, X.-A., Hu, X., Xie, Y., & Wu, H. (2021) · Medical Image Analysis · doi:10.1016/j.media.2020.101830 · Cited by 58
“With the rise of deep learning methods, Um et al. (2017) used the popular convolutional neural metwork (CNN) method to analyze the sensor data of wearable devices.”
Semi-supervised Time Series Classification Model with Self-supervised Learning
Xi, L., Yun, Z., Liu, H., Wang, R., Huang, X., & Fan, H. (2022) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.105331 · Cited by 56
Practically Adopting Human Activity Recognition
Xu, H., Zhou, P., Tan, R., & Li, M. (2023) · Proceedings of the 29th Annual International Conference on Mobile Computing and Networking · doi:10.1145/3570361.3613299 · Cited by 55
“Prior studies [4, 36, 40, 52, 55, 57] directly borrow such a technique and apply many augmentation methods on IMU data for improved performance, e.”
BackgroundMethodInfluentialCai, Z., Ma, W., Wang, X., Wang, H., & Feng, Z. (2022) · IEEE Transactions on Reliability · doi:10.1109/tr.2022.3178707 · Cited by 57
“Umm et al. [28] proposed to use the perturbation of the amplitude spectrum and phase spectrum in the frequency domain to augment the data.”
MethodAn Explainable Deep Learning Approach for Stress Detection in Wearable Sensor Measurements
Moser, M., Ehrhart, M., & Resch, B. (2024) · Sensors · doi:10.3390/s24165085 · Cited by 75
“To improve generalization while preventing overfitting on the training data, we added random Gaussian noise to the stress moments and scaled the amplitude randomly, ultimately arriving at new samples for the training dataset [40].”
MethodDetection of Alzheimer Disease on Online Handwriting Using 1D Convolutional Neural Network
Dao, Q., El-Yacoubi, M. A., & Rigaud, A. (2023) · IEEE Access · doi:10.1109/access.2022.3232396 · Cited by 37
“For the cases of Jittering, Scaling and Time Warping, the parameters are defined as suggested in [25].”
MethodDeep learning in systems medicine
Wang, H., Pujos‐Guillot, E., Comte, B., de Miranda, J. L., Spiwok, V., Chorbev, I., Castiglione, F., Tieri, P., Watterson, S., McAllister, R., et al. (2020) · Briefings in Bioinformatics · doi:10.1093/bib/bbaa237 · Cited by 58
Ehrhart, M., Resch, B., Havas, C. R., & Niederseer, D. (2022) · Sensors · doi:10.3390/s22165969 · Cited by 64
“In the work of [21], the authors propose techniques such as scaling, cropping, wrapping, or rotating the wearable sensor data to improve the classification performance for Parkinson’ disease monitoring.”
Deep learning-based detection of COVID-19 using wearables dataPreprint
Bogu, G. K., & Snyder, M. P. (2021) · medRxiv · doi:10.1101/2021.01.08.21249474 · Cited by 53
“12,13 To do this, we applied different data augmentation techniques 12,13 on our limited training data by transforming each user’s training data into approximately eight times the size.”
MethodTai, C.-Y., Wang, W.-J., & Huang, Y. (2023) · Sustainability · doi:10.3390/su15107834 · Cited by 65
Gholami, M., Rezaei, A., Cuthbert, T. J., Napier, C., & Menon, C. (2019) · Sensors · doi:10.3390/s19235325 · Cited by 61
“There are opportunities for using the fabric-based wearable device proposed in this study and CNN models for other purposes such as gait phase detection, rehabilitation monitoring, and Parkinson’s disease monitoring according to previous works [8,39].”
MethodGao, J., Han, H., Ren, Z., & Fan, Y. (2020) · Journal of Building Engineering · doi:10.1016/j.jobe.2020.102043 · Cited by 51
Aldhaheri, S., Alghazzawi, D., Cheng, L., Barnawi, A., & Alzahrani, B. A. (2020) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2020.102537 · Cited by 68
Augmenting Dementia Cognitive Assessment With Instruction-Less Eye-Tracking Tests
Mengoudi, K., Ravì, D., Yong, K. X. X., Primativo, S., Pavisic, I. M., Brotherhood, E., Lu, K., Schott, J. M., Crutch, S. J., & Alexander, D. C. (2020) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2020.3004686 · Cited by 55
“tween person variability and the limited amount of eye movement data, data augmentation can be used to prevent overfitting and improve the generalisability of the models [22].”
MethodKraft, D., Srinivasan, K. K., & Bieber, G. (2020) · Technologies · doi:10.3390/technologies8040072 · Cited by 55
“88 % in the domain of Parkinson’s Disease classification in Alzheimer patients [49].”
Anomaly Detection in Financial Time Series by Principal Component Analysis and Neural Networks
Crépey, S., Lehdili, N., Madhar, N., & Thomas, M. (2022) · Algorithms · doi:10.3390/a15100385 · Cited by 66
Liu, S., Chen, J., Feng, Y., Xie, Z., Pan, T., & Xie, J. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124511 · Cited by 63
Parkinson’s disease diagnosis using neural networks: Survey and comprehensive evaluation
Tanveer, M., Rashid, A. H., Kumar, R., & Raman, B. (2022) · Information Processing & Management · doi:10.1016/j.ipm.2022.102909 · Cited by 54
Bloch, V., Frondelius, L., Arcidiacono, C., Mancino, M., & Pastell, M. (2023) · Sensors · doi:10.3390/s23052611 · Cited by 53
“where aX, aY and aZ are the components of the tag acceleration measured along the X, Y and Z axes and α is a random rotational angle, as per several authors [12,18,26].”
Cross-Domain HAR: Few-Shot Transfer Learning for Human Activity Recognition
Thukral, M., Haresamudram, H., & Plötz, T. (2024) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3704921 · Cited by 70
“In order to inject diversity and variation into the source data, we employ eight data transformations designed for accelerometry in [47]: (i) adding random Gaussian noise; (ii) scaling signal by a random factor; (iii) applying a random 3D rotation; (iv) reversing the time direction of input signal;…”
InfluentialCross-Domain HAR: Few Shot Transfer Learning for Human Activity Recognition
Thukral, M., Haresamudram, H., & Ploetz, T. (2023) · arXiv · doi:10.48550/arxiv.2310.14390 · Cited by 45
“In order to inject diversity and variation into the source data, we employ eight data transformations designed for accelerometry in [47]: (i) adding random Gaussian noise; (ii) scaling signal by a random factor; (iii) applying a random 3D rotation; (iv) reversing the time direction of input signal;…”
InfluentialLearning Long-Range Relationships for Temporal Aircraft Anomaly Detection
Zhang, D., Gao, J., & Li, X. (2024) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2024.3404360 · Cited by 49
“(d ) Permutation [37].”
BackgroundInfluentialWu, X., Zhao, Z., Tian, R., Niu, Y., Gao, S., & Liu, H. (2020) · Spectrochimica Acta Part A Molecular and Biomolecular Spectroscopy · doi:10.1016/j.saa.2020.118841 · Cited by 44
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.