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 201–300 of 736
Contrastive Self-Supervised Learning for Sensor-Based Human Activity Recognition: A Review
Chen, H., Gouin-Vallerand, C., Bouchard, K., Gaboury, S., Couture, M., Bier, N., & Giroux, S. (2024) · IEEE Access · doi:10.1109/access.2024.3480814 · Cited by 29
A Deep Learning-Based Human Identification System With Wi-Fi CSI Data Augmentation
Mo, H., & Kim, S. (2021) · IEEE Access · doi:10.1109/access.2021.3092435 · Cited by 24
Shu, K., Mao, S., Coyle, J. L., & Sejdić, E. (2021) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2021.3106565 · Cited by 22
Give Me a Sign: Using Data Gloves for Static Hand-Shape Recognition
Achenbach, P., Laux, S., Purdack, D., Müller, P. N., & Göbel, S. P. (2023) · Sensors · doi:10.3390/s23249847 · Cited by 26
“For example, Um et al. [22] conducted one of the most comprehensive evaluations of data augmentation techniques for wearable sensor data used in dynamic approaches.”
BackgroundMethodChoo, S., Park, H., Jung, J., Flores, K., & Nam, C. S. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106665 · Cited by 25
Long Short-Term Memory and Kolmogorov Arnold Network Theorem for epileptic seizure prediction
Hasan, M., Zhao, X., Wu, W., Dai, J., Gu, X., & Noreen, A. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110757 · Cited by 26
Ogunseiju, O. R., Olayiwola, J., Akanmu, A. A., & Nnaji, C. A. (2021) · Smart and Sustainable Built Environment · doi:10.1108/sasbe-11-2020-0170 · Cited by 20
CNN-Based Continuous Authentication on Smartphones with Auto Augmentation Search
Deng, S., Luo, J., & Li, Y. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-86890-1_10 · Cited by 19
Generating Synthetic Data to Reduce Prediction Error of Energy Consumption
Hazra, D., Shafqat, W., & Byun, Y.-C. (2021) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2022.020143 · Cited by 24
“• Jittering–Jittering [19] is the transformation process which has been used to add noise in our energy consumption time series tabular data.”
MethodData Augmentation for 12-Lead ECG Beat Classification
Do, E., Boynton, J., Lee, B. S., & Lustgarten, D. L. (2021) · SN Computer Science · doi:10.1007/s42979-021-00924-x · Cited by 26
“Currently existing ECG data augmentation methods (Pan et al. [17]), (Cui et al. [18]), (Um et al. [19]), (Cao et al. [20]), (Le Guennec et al. [21]), (Jun et al. [22]), (He et al. [8]), (Yao et al. [23]), (Acharya et al. [24]) are inadequate or limited for use for our purpose (i.e., classifying…”
BackgroundMethodMicro-activity recognition in industrial assembly process with IMU data and deep learning
Sopidis, G., Haslgrübler, M., Azadi, B., Anzengruber-Tánase, B., Ahmad, A., Ferscha, A., & Baresch, M. (2022) · International Conference on PErvasive Technologies Related to Assistive Environments (PETRA) · doi:10.1145/3529190.3529204 · Cited by 23
“The techniques that were tested were rotating, jittering and dynamic warping [Um et al. 2017] and combinations of those.”
Methodde Araújo, J. C., Landwehr, T., Alencar, P. H. L., & Paulino, W. D. (2022) · Journal of South American Earth Sciences · doi:10.1016/j.jsames.2022.104102 · Cited by 21
Kargarandehkordi, A., Slade, C. R., & Washington, P. Y. (2024) · JMIR Research Protocols · doi:10.2196/55615 · Cited by 28
“For example, for accelerometer data, rotations simulate different sensor placements and cropping is used to diminish the dependency of event locations [16].”
Virtual Fusion With Contrastive Learning for Single-Sensor-Based Activity Recognition
Nguyen, D., Pham, C., & Le‐Khac, N. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3412397 · Cited by 30
“2) Augmentation: We employ several additional augmentation techniques from [34].”
MethodArtificial Intelligence for Climate Change Biology: From Data Collection to Predictions
Levy, O., & Shahar, S. (2024) · Integrative and Comparative Biology · doi:10.1093/icb/icae127 · Cited by 22
Activity recognition in wearables using adversarial multi-source domain adaptation
Chakma, A., Faridee, A. Z. M., Khan, M. A. A. H., & Roy, N. (2020) · Smart Health · doi:10.1016/j.smhl.2020.100174 · Cited by 28
Smartphone-Based IRI Estimation for Pavement Roughness Monitoring: A Data-Driven Approach
Sang, Y., Yu, Q., Fang, Y., Vo, V., & Wix, R. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3369109 · Cited by 24
“These techniques diversify the data while preserving the temporal characteristics [57], [58], [59], [60], and these techniques could be applied individually or together to add to the robustness against response data variations in real-world scenarios [57].”
Methodvan Dreven, J., Cheddad, A., Alawadi, S., Ghazi, A. N., Koussa, J. A., & Vanhoudt, D. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110662 · Cited by 23
Zhang, Y., D’Haeseleer, I., Coelho, J., Abeele, V. V., & Vanrumste, B. (2021) · Sensors · doi:10.3390/s21062176 · Cited by 19
“For washing hands, brushing teeth and combing hair, wearable sensors were attached to the wrist [6,75], to the hand [26] or integrated in the toothbrush [25].”
MethodTowards a multimodal human activity dataset for healthcare
Hu, M., Luo, M., Huang, M., Meng, W., Xiong, B., Yang, X., & Sang, J. (2022) · Multimedia Systems · doi:10.1007/s00530-021-00875-6 · Cited by 21
“Therefore, it is an important future work to find some effective strategies to deal with the imbalance, such as using the dynamic window sampling [34] and sensor data augmentation [47].”
BackgroundDeep-Learning-Driven Techniques for Real-Time Multimodal Health and Physical Data Synthesis
Haleem, M. S., Ekuban, A., Antonini, A., Pagliara, S. M., Pecchia, L., & Allocca, C. (2023) · Electronics · doi:10.3390/electronics12091989 · Cited by 22
“Other methods include, for instance, rotation [5], scaling [7], magnitude warping time [8], time warping [7], Fourier transform [9], and spectrograms [10].”
Tian, S., Zhang, Y., Feng, Y., Elsagan, N., Ko, Y. J., Mozaffari, M. H., Xi, D. D. Z., & Lee, C.-G. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.120914 · Cited by 19
A Multi-Layer Gaussian Process for Motor Symptom Estimation in People With Parkinson's Disease
Lang, M., Hirche, S., Pfister, F., Fröhner, J., Abedinpour, K., Pichler, D., Fietzek, U. M., Um, T. T., Kulić, D., & Endo, S. (2019) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2019.2900002 · Cited by 21
Self-citationSynthetic Data Generation System for AI-Based Diabetic Foot Diagnosis
Hyun, J., Lee, Y., Son, H. M., Lee, S. H., Pham, V., Park, J., & Chung, T. (2021) · SN Computer Science · doi:10.1007/s42979-021-00667-9 · Cited by 19
“[20] as a time series data augmentation method to copy the effects of additive noise in accelerometer sensor data from Parkinson’s disease patients.”
BackgroundMethodInfluentialSTranGAN: Adversarially-learnt Spatial Transformer for scalable human activity recognition
Faridee, A. Z. M., Chakma, A., Misra, A., & Roy, N. (2021) · Smart Health · doi:10.1016/j.smhl.2021.100226 · Cited by 21
The bottlenecks of AI: challenges for embedded and real-time research in a data-centric age
Abdelzaher, T., Hu, Y. C., Kara, D., Kimura, T., Misra, A., Ramani, V., Tardieu, O., Wang, T., Wigness, M., & Youssef, A. (2025) · Real-Time Systems · doi:10.1007/s11241-025-09452-w · Cited by 29
Moon, J., Lee, D., Jung, H., Choi, A., & Mun, J. H. (2022) · Sensors · doi:10.3390/s22093499 · Cited by 22
“03 is added to the original time series [47].”
BackgroundMethodData Augmentation for Time Series Classification with Deep Learning Models
Pialla, G., Devanne, M., Weber, J., Idoumghar, L., & Forestier, G. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-24378-3_8 · Cited by 19
“We use the same parameters as in [19]: µ = 1 and σ = 0 .”
MethodAn Efficient and Private ECG Classification System Using Split and Semi-Supervised Learning
Ayad, A., Barhoush, M., Frei, M., Völker, B., & Schmeink, A. (2023) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2023.3281977 · Cited by 20
“have adapted augmentation strategies proposed in [55], [56], which include jittering, scaling, rotation, magnitude warping, and time warping.”
BackgroundAdversarial Data Augmentation for HMM-Based Anomaly Detection
Castellini, A., Masillo, F., Azzalini, D., Amigoni, F., & Farinelli, A. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3303099 · Cited by 19
Davidashvilly, S., Cardei, M. A., Hssayeni, M. D., Chi, C., & Ghoraani, B. (2024) · BioMedical Engineering OnLine · doi:10.1186/s12938-024-01214-2 · Cited by 22
“Following the methodology proposed in [8], three data augmentation techniques were employed on the MHEALTH and PAMAP2 datasets.”
MethodGräfe, M. J., Pettas, V., Dimitrov, N., & Cheng, P. W. (2024) · Wind energy science · doi:10.5194/wes-9-2175-2024 · Cited by 24
Model-based data augmentation for user-independent fatigue estimation
Jiang, Y., Malliaras, P., Chen, B. K., & Kulić, D. (2021) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2021.104839 · Cited by 19
Self-citationAugToAct: scaling complex human activity recognition with few labels
Faridee, A. Z. M., Khan, M. A. A. H., Pathak, N., & Roy, N. (2019) · Proceedings of the 16th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services · doi:10.1145/3360774.3360831 · Cited by 17
“This approach works as properly parameterized augmentation transformations can approximate the minute variations noticed when humans perform their activities [49], thus helping to cover unexplored input space and increase the generalizability [13] of the trained model.”
BackgroundImproving PET-CT Image Segmentation via Deep Multi-modality Data Augmentation
Cao, K., Bi, L., Feng, D. D., & Kim, J. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-61598-7_14 · Cited by 17
Relabeling for Indoor Localization Using Stationary Beacons in Nursing Care Facilities
Garcia, C. A., & Inoue, S. (2024) · Sensors · doi:10.3390/s24020319 · Cited by 18
Hasan, M. A., Li, F., Gouverneur, P., Piet, A., & Grzegorzek, M. (2025) · PLoS ONE · doi:10.1371/journal.pone.0315343 · Cited by 22
MLGaze: Machine Learning-Based Analysis of Gaze Error Patterns in Consumer Eye Tracking Systems
Kar, A. (2020) · Vision · doi:10.3390/vision4020025 · Cited by 20
“…with a raised cosine kernel with a window size of N = 30 with the form of Equation (13) below to produce a smoothed variant of the original data [25]: The convolution operation was given by: , (5) time shifting: The gaze data were shifted by 10 samples to estimate new variants in error values…”
MethodA novel sEMG data augmentation based on WGAN-GP
Coelho, F. O., Pinto, M. F., Melo, A. G., Ramos, G. S., & Marcato, A. L. M. (2022) · Computer Methods in Biomechanics & Biomedical Engineering · doi:10.1080/10255842.2022.2102422 · Cited by 21
An ECG generative model of myocardial infarction
Que, W., Han, C., Zhao, X., & Shi, L. (2022) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2022.107062 · Cited by 18
Efficient anomaly recognition using surveillance videos
Saleem, G., Bajwa, U. I., Raza, R. H., Alqahtani, F. H., Tolba, A. K. R., & Xia, F. (2022) · PeerJ Computer Science · doi:10.7717/peerj-cs.1117 · Cited by 17
Chen, X., Zhao, L., Xu, J., Liu, Z., Zhang, C., Xu, L., & Guo, N. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3341134 · Cited by 20
An Android Malware Detection Method Based on CNN Mixed-Data Model
Нічепорук, А. О., Савенко, О., Nicheporuk, A., & Nicheporuk, Y. (2020) · International Conference on ICT in Education, Research and Industrial Applications: Integration, Harmonization and Knowledge Transfer (ICTERI) · doi:10.55056/ceur-ws.org/vol-2732/20200198.pdf · Cited by 16
“This is due to the fact that after the next pair of CONV + POOL layers, the dimension of the data decreases, which leads to the loss of some information about the input object [19, 20].”
BackgroundZhang, Y., Gu, T., & Zhang, X. (2020) · ACM Conference on Embedded Networked Sensor Systems (SenSys) · doi:10.1145/3384419.3430716 · Cited by 19
Chronic Pain Protective Behavior Detection with Deep Learning
Wang, C., Olugbade, T., Mathur, A., Williams, A. C. D. C., Lane, N. D., & Bianchi‐Berthouze, N. (2021) · ACM Transactions on Computing for Healthcare · doi:10.1145/3449068 · Cited by 20
“• Jittering [48], which is to simulate the signal noise that may exist during data capturing.”
BackgroundShayestegan, M., Kohout, J., Štícha, K., & Mareš, J. (2022) · Applied Sciences · doi:10.3390/app12125902 · Cited by 16
Heart Rate Estimated from Body Movements at Six Degrees of Freedom by Convolutional Neural Networks
Lee, H., & Whang, M. (2018) · Sensors · doi:10.3390/s18051392 · Cited by 17
“This study employed data augmentation, which was developed to generate new motion data from existing motion data, such as permutation, jittering, and scaling, as shown in Figure 6 [35].”
MethodOn-Device Fault Diagnosis With Augmented Acoustic Emission Data: A Case Study on Carbon Fiber Panels
Zhang, Y., Pullin, R., Oelmann, B., & Bader, S. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3577849 · Cited by 15
“For example, noise injection, time-warping, and signal transformation techniques have been widely adopted in fields like image recognition and audio classification to expand training datasets and improve model performance [21].”
Kobir, M. I., Machado, P., Lotfi, A., Haider, D., & Ihianle, I. K. (2025) · Sensors · doi:10.3390/s25133955 · Cited by 18
“This observation aligns with the principle of diminishing returns often associated with excessive data augmentation [38].”
InfluentialBamani, E., Kahanowich, N. D., Ben-David, I., & Sintov, A. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3118087 · Cited by 15
“Furthermore, these techniques have been shown to be effective for reducing overfitting [20], [21] and can help networks overcome small datasets [22] or datasets with imbalanced classes [23], [24].”
BackgroundAn Artificial Intelligence Based Effective Diagnosis of Parkinson Disease Using EEG Signal
Al‐Khasawneh, M. A., Alzahrani, A., & Alarood, A. A. (2023) · Cognitive technologies · doi:10.1007/978-981-99-2154-6_14 · Cited by 31
Aggarwal, N., Saini, B. S., & Gupta, S. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.106008 · Cited by 17
Real-Time Sensor-Based Human Activity Recognition for eFitness and eHealth Platforms
Czekaj, Ł., Kowalewski, M., Domaszewicz, J., Kitłowski, R., Szwoch, M., & Duch, W. (2024) · Sensors · doi:10.3390/s24123891 · Cited by 19
“We performed data augmentation (cf., [9]) using 3 natural transformations: rotation of the reference frame (constant for the whole window), global time scaling, and local time scaling.”
BackgroundMethodZhang, Z., Liu, H., Shao, Y., Yang, J., Liu, S., & Yuan, G. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.108835 · Cited by 16
Deep Learning for Detecting Human Activities From Piezoelectric-Based Kinetic Energy Signals
Manjarrés, J., Lan, G., Gorlatova, M. A., Hassan, M., & Pardo, M. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3093245 · Cited by 16
The Impact of Data Augmentation on Tactile-Based Object Classification Using Deep Learning Approach
Maus, P., Kim, J., Nocentini, O., Bashir, M. Z., & Cavallo, F. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3175153 · Cited by 15
Cai, M., Sun, H., Yang, T., Hu, H., Li, X., & Jia, Y. (2025) · Micromachines · doi:10.3390/mi16080902 · Cited by 22
“Moreover, data augmentation through signal perturbation, synthetic sample generation, or domain-adaptive pretraining has proven effective in improving model stability and reducing sensitivity to signal artifacts [190].”
Fu, B., Kirchbuchner, F., & Kuijper, A. (2020) · International Conference on PErvasive Technologies Related to Assistive Environments (PETRA) · doi:10.1145/3389189.3392606 · Cited by 25
“Magnitudewarpingmultiplies smoothly varying factors with the time series, which can be modeled with piece-wise cubic polynomial functions around 1 as proposed by [24].”
BackgroundUsing Variational Autoencoder to augment Sparse Time series Datasets
Goubeaud, M., Jousen, P., Gmyrek, N., Ghorban, F., Schelkes, L., & Kummert, A. (2021) · International Conference on Optimization and Applications (ICOA) · doi:10.1109/icoa51614.2021.9442619 · Cited by 22
“Different methods to augment time series datasets such as rotating, scaling, and jittering have been tested in [4].”
MethodShip Diesel Engine Fault Diagnosis Using Data Science and Machine Learning
Pająk, M., Kluczyk, M., Muślewski, Ł., Lisjak, D., & Kolar, D. (2023) · Electronics · doi:10.3390/electronics12183860 · Cited by 27
Wearable-Sensor-Based Weakly Supervised Parkinson’s Disease Assessment with Data Augmentation
Yue, P., Li, Z., Zhou, M., Wang, X., & Yang, P. (2024) · Sensors · doi:10.3390/s24041196 · Cited by 20
“One approach involves generating more diverse samples through slight transformations in the original signal to enhance feature representation, as demonstrated in [28].”
BackgroundPhysically rational data augmentation for energy consumption estimation of electric vehicles
Ma, Y., Sun, W., Zhao, Z., Gu, L., Zhang, H., Jin, Y., & Yuan, X. (2024) · Applied Energy · doi:10.1016/j.apenergy.2024.123871 · Cited by 16
Unsupervised Contrastive Learning for Robust RF Device Fingerprinting Under Time-Domain Shift
Chen, J., Wong, W.-K., & Hamdaoui, B. (2024) · International Conference on Communications · doi:10.1109/icc51166.2024.10622173 · Cited by 17
“Following [30], we employ both weak and strong data augmentations for time series.”
MethodPCGmix: A Data-Augmentation Method for Heart-Sound Classification
Susič, D., Gradišek, A., & Gams, M. (2024) · IEEE journal of biomedical and health informatics · doi:10.1109/jbhi.2024.3458430 · Cited by 13
“For the cubic splines used in the magnitude warping, we followed the same procedure as in [47] and used four knots at random magnitudes with μ = 1 and σ = 0 .”
MethodCrowe, C., Sica, M., Kenny, L., O’Flynn, B., Mueller, D. S., Timmons, S., Barton, J. J., & Tedesco, S. A. (2024) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2024.3477003 · Cited by 19
“Data were augmented by rotation and sliding-window-based data augmentation methods [82].”
MethodJian, Y., Zhang, N., Bi, Y., Liu, X., Fan, J., Wu, W., & Liu, T. (2024) · ACS Sensors · doi:10.1021/acssensors.4c02073 · Cited by 14
NurseNet: Monitoring Elderly Levels of Activity with a Piezoelectric Floor
Minvielle, L., & Audiffren, J. (2019) · Sensors · doi:10.3390/s19183851 · Cited by 16
“Data augmentation is a key part of training complex neural networks, particularly when only small labeled datasets are available [67].”
BackgroundHernandez, V., Kulić, D., & Venture, G. (2020) · Journal of Biomechanics · doi:10.1016/j.jbiomech.2020.109684 · Cited by 14
Self-citationDeep Learning-based Data Augmentation for Hydraulic Condition Monitoring System
Kim, K., & Jeong, J. (2020) · Procedia Computer Science · doi:10.1016/j.procs.2020.07.007 · Cited by 14
SonicFace: Tracking Facial Expressions Using a Commodity Microphone Array
Gao, Y., Jin, Y., Choi, S., Li, J., Pan, J., Shu, L., Zhou, C., & Jin, Z. (2021) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3494988 · Cited by 28
Data Augmentation On-the-fly and Active Learning in Data Stream Classification
Malialis, K., Papatheodoulou, D., Filippou, S., Panayiotou, C. G., & Polycarpou, M. M. (2022) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci51031.2022.10022133 · Cited by 18
“Time Warping [22] is a time domain transformation method, which aims to disrupt a pattern in the temporal”
Reinforcement Learning for Options Trading
Wen, W., Yuan, Y., & Yang, J. (2021) · Applied Sciences · doi:10.3390/app112311208 · Cited by 15
Multichannel convolution neural network for gas mixture classification
Oh, Y., Lim, C., Lee, J., Kim, S., & Kim, S. (2022) · Annals of Operations Research · doi:10.1007/s10479-022-04715-2 · Cited by 14
InSEption: A Robust Mechanism for Predicting FoG Episodes in PD Patients
Dimoudis, D., Tsolakis, N., Maga‐Nteve, C., Μεδίτσκος, Γ., Vrochidis, S., & Kompatsiaris, I. Y. (2023) · Electronics · doi:10.3390/electronics12092088 · Cited by 13
Zhou, F., Hu, S., Xiaoli, W., Lu, Z., & Wu, J. (2023) · Electronics · doi:10.3390/electronics12122581 · Cited by 14
A Deep Learning Framework for Soft Robots with Synthetic Data
Sapai, S., Loo, J. Y., Ding, Z. Y., Tan, C. P., Baskaran, V. M., & Nurzaman, S. G. (2023) · Soft Robotics · doi:10.1089/soro.2022.0188 · Cited by 17
“For example, data augmentation applies random transformations to the original training data by introducing random noise also known as jittering, 45 scaling, 46 rotation or flipping, 47 and time-warping.”
Yalcin, M., Halbig, A., Fischbach, M., & Latoschik, M. E. (2024) · Frontiers in Virtual Reality · doi:10.3389/frvir.2024.1364207 · Cited by 17
Mohammadzadeh, M., Ghadami, A., Taheri, A., & Behzadipour, S. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.107476 · Cited by 17
“In these models, the dataset has a decisive effect on the model performance [6].”
BackgroundMethodInfluentialYuan, Y., Lin, L., Xin, Q., Zhou, Z.-G., & Liu, Q. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3527017 · Cited by 20
Data Augmentation and Transfer Learning for Data Quality Assessment in Respiratory Monitoring
Rozo, A., Moeyersons, J., Morales, J., van der Westen, R. G., Lijnen, L., Smeets, C. J. P. P., Jantzen, S., Monpellier, V. M., Ruttens, D., Hoof, C. A. V., et al. (2022) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2022.806761 · Cited by 13
“Note that for supervised machine learning algorithms, the labels of the original data need to be preserved when generating the new data (Um et al., 2017).”
BackgroundDeep Learning Enabled High-Performance Speech Command Recognition on Graphene Flexible Microphones
Zhang, X.-Y., Liu, H., Ma, X., Wang, Z., Li, G., Han, L., Sun, K., Yang, Q., Ji, S., Yu, D., et al. (2022) · ACS Applied Electronic Materials · doi:10.1021/acsaelm.2c00125 · Cited by 13
Kurt, M., Kurt, Z., & Işık, Ş. (2022) · The Journal of Indian Prosthodontic Society · doi:10.4103/jips.jips_149_22 · Cited by 17
“[27,28] The sigma value was defined as 1e‑4, and the mean values varied between 1e‑4 and 1e‑3.”
BackgroundAdvances in machine and deep learning for ECG beat classification: a systematic review
Prakash, A. J., Belkacem, A. N., Elfadel, I. M., Jelinek, H. F., & Atef, M. (2025) · Frontiers in Digital Health · doi:10.3389/fdgth.2025.1649923 · Cited by 40
“Employing data augmentation techniques to artificially expand the training dataset by introducing variations, such as scaling, rotation, or adding noise to existing ECG signals, enhances the model’s robustness (184).”
PDKit: A data science toolkit for the digital assessment of Parkinson’s Disease
Stamate, C., Pons, J. S., Weston, D. J., & Roussos, G. (2021) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1008833 · Cited by 13
“…to account for start up and cool down effects in test performance and verification of movement correctness in the case of active monitoring to validate unsupervised data collection [17] as well as the injection of higher-order quality features such as data augmentation and signal segmentation [18].”
SemiHAR: Improving Semisupervised Human Activity Recognition via Multitask Learning
Wei, C., Wang, Z., Yuan, J., Wang, X., Liu, H., & Zhao, Q. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3330879 · Cited by 14
Radar-Based People Counting Under Heterogeneous Clutter Environments
Choi, J.-H., Kim, J.-E., & Kim, K. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3332299 · Cited by 13
“By introducing the random magnitude warping algorithm [54], which was developed for warping the amplitudes of wearable inertial signals, we randomize the radar peak amplitudes.”
MethodZhang, J., Feng, L., Liu, Z., Wu, Y., He, Y., Dong, Y., & Xu, D. (2024) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3637528.3671828 · Cited by 18
“In our analysis, the standard data augmentation (DA) techniques [45] are identical to those employed in [36], such as scaling and jittering.”
MethodFarmanesh, A., Sanchis, R. G., & Ordieres-Meré, J. B. (2025) · Sensors · doi:10.3390/s25103048 · Cited by 17
“Traditional image-based augmentation techniques are not directly applicable, requiring specialized approaches that preserve temporal dependencies and physical constraints [87].”
Deep Learning for Anomaly Detection
Wang, R., Nie, K., Chang, Y., Gong, X., Wang, T., Yang, Y., & Long, B. (2020) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3394486.3406481 · Cited by 16
“(1) Basic Building Blocks [6, 7, 10] (a) MultiLayer Perceptron (MLP) (b) Convolutional Neural Networks (CNN) (c) Recurrent Neural Networks (RNN) (2) Fundamental Model Structures Applied to Anomaly Detection Tasks (a) Deep One-Class Models (Deep OC) [17] (b) AutoEncoder (AE) [5, 16, 27] (c) Variational AutoEncoder (VAE…”
MethodLee, J., Lee, M., Kim, G., & Hwang, J. (2020) · Virtual Reality Software and Technology · doi:10.1145/3385956.3418959 · Cited by 21
“Considering the relatively small size of the dataset, we applied data augmentation [39], e.g., adding small arbitrary jitters in the non-principal axes in head position data, and also scaling them along the principal axis.”
MethodToward Multi-area Contactless Museum Visitor Counting with Commodity WiFi
Jiang, Y., Zheng, X., & Feng, C. (2022) · Journal on Computing and Cultural Heritage · doi:10.1145/3530694 · Cited by 14
“proposed various data augmentation methods for wearable sensor data and applied them to enhance the classification performance of motor states for Parkinson’s disease patients [72].”
MethodImpact of augmentation methods in online signature verification
Najda, D., & Saeed, K. (2022) · Innovations in Systems and Software Engineering · doi:10.1007/s11334-022-00464-4 · Cited by 16
A data generation framework for extremely rare case signals
Chalongvorachai, T., & Woraratpanya, K. (2021) · Heliyon · doi:10.1016/j.heliyon.2021.e07687 · Cited by 13
ANN Prediction Model of Concrete Fatigue Life Based on GRW-DBA Data Augmentation
Shi, J., Zhang, W., & Zhao, Y. (2023) · Applied Sciences · doi:10.3390/app13021227 · Cited by 12
Fernández, L. P. S., Garza-Rodríguez, A., Sánchez-Pérez, L. A., & Martínez-Hernández, J. M. (2023) · Bioengineering · doi:10.3390/bioengineering10050588 · Cited by 12
“Other works present different neural network architectures to assess motor symptoms, such as convolutional neural networks (CNNs) for classifying the severity of PD patients [4,14,15].”
BackgroundA Review of IoT Security: Machine Learning and Deep Learning Perspective
Dubey, K., Dubey, R., Panedy, S., & Kumar, S. (2024) · Procedia Computer Science · doi:10.1016/j.procs.2024.04.034 · Cited by 15
Wakita, K., Miyauchi, Y., Akimoto, Y., & Maki, A. (2024) · Journal of Marine Science and Technology · doi:10.1007/s00773-024-01036-w · Cited by 14
Towards Parkinson’s Disease Prognosis Using Self-Supervised Learning and Anomaly Detection
Jiang, H., Lim, W. Y. B., Ng, J. S., Wang, Y., Chi, Y., & Miao, C. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414840 · Cited by 13
“During training, we apply data augmentations from [24] which simulates rotation of the device and permutations of signals in a fixed window.”
MethodStabenau, H. F., Bridge, C. P., & Waks, J. W. (2021) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2021.104408 · Cited by 11
Yang, W., Yuan, J., & Wang, X. (2022) · Neural Processing Letters · doi:10.1007/s11063-022-10965-9 · Cited by 16
“As such, data augmentation as a feasible technique is widely adopted in various TSC tasks.”
BackgroundMethodInfluential
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.