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 601–700 of 736
A Smart IoT Gateway Capable of Prescreening for Atrial Fibrillation
Flanagan, E. P., & Sadleir, R. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20936-9_9
Ma, W., Zeng, Q., Song, G., & Zou, M. (2022) · IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC) · doi:10.1109/imcec55388.2022.10020092 · Cited by 1
Pet Multiple Behavior Recognition Through Sensor Data Synthesis
Kim, H., Park, C., Park, J.-H., & Moon, N. (2023) · Lecture notes in electrical engineering · doi:10.1007/978-981-99-1252-0_19
Doniec, R., Sieciński, S., Piaseczna, N., Duraj, K. M., Chwał, J., Gawlikowski, M., & Tkacz, E. (2023) · Lecture notes in networks and systems · doi:10.1007/978-3-031-38430-1_18 · Cited by 1
Biometric Gait Analysis Using Wrist-Mounted Wearable Sensors
Sawicki, A. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-42823-4_3
Exploring the i3DVAE-LSTM Framework for Generating Exceptionally Rare Anomaly Signals
Kaewkiriya, T., & Woraratpanya, K. (2023) · doi:10.1109/icitee59582.2023.10317760
“(ii) Aug-menting the samples using various techniques [8], such as upsampling-downsampling, fast Fourier transform [9], and time series decomposition [10], across different domains.”
MethodLSCR: Latent Space Coordination Relation for Anomaly Prediction
Chalongvorachai, T., & Woraratpanya, K. (2023) · doi:10.1109/icitee59582.2023.10317782
“…for the target, like an increase in sales of the product [13], many instances have negative effects, such as malicious cyber attacks by hackers [1], [2], breakdowns of the important machinery along the factory production line [14], and the relapse of critical health issues or symptoms [15].”
BackgroundExploring Abstract Pattern Representation in The Brain and Non-symbolic Neural NetworksPreprint
Avcu, E., & Gow, D. W. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.11.27.568877
Risk Prediction in Daily Activities and Falls based on Deep Learning
Lee, S., Koo, B., Yang, S., Kim, D.-K., & Kim, Y. (2023) · Journal of the Korean Society for Precision Engineering · doi:10.7736/jkspe.023.102
Robust Radar Micro-Doppler Target Classification of Small Drones by Data Augmentation
Rydström, S., Björklund, S., & Wadströmer, N. (2023) · IEEE International Radar Conference · doi:10.1109/radar54928.2023.10371174
Shen, Y., Yang, X., Zhao, J., & Li, Z. (2023) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata59044.2023.10386136
“In time series analysis, augmentation methods like Permutation, Time warping, Scaling, Jittering, and Magnitude Warping [5] have been applied to augment sensor data.”
MethodMedeiros, L., Ottoni, A. L. C., & Novo, M. S. (2023) · Congresso Brasileiro de Inteligência Computacional (CBIC) · doi:10.21528/cbic2023-063
Jamil, M., Oman, S. A. F., Raju, S. M. T. U., & Soshi, F. (2023) · International Conference on Computer and Information Technology (ICCIT) · doi:10.1109/iccit60459.2023.10441346
“T. T. Um et al. [4] proposed data augmentation methods for wearable sensor data, including arbitrary rotations, permutation, scaling, magnitude-warping, time-warping, jittering, and cropping for the clas-sification of the motor state of Parkinson’s Disease patients.”
BackgroundPark, S., Jeong, B., & Kim, H. (2024) · Journal of the Korea Institute of Military Science and Technology · doi:10.9766/kimst.2023.26.5.422
Time Series Data Augmentation Methods for Deep Learning Models in Conveyor Belt Load Classification
Žvirblis, T., Pikšrys, A., Bzinkowski, D., Rucki, M., & Kilikevičius, A. (2024) · IEEE Open Conference of Electrical, Electronic and Information Sciences (eStream) · doi:10.1109/estream61684.2024.10542589
“For time series, Gaussian, Laplace, or uniform noise [1], [2] are commonly used.”
BackgroundMethodEnhancing Human Activity Recognition with IMU-based Motion Analysis
Singh, A., Verma, A., & Cherukuri, B. (2023) · International Conference on Advances in Computing, Communication Control and Networking (ICAC3N) · doi:10.1109/icac3n60023.2023.10541396 · Cited by 1
“restricted data scale, fluctuating annotations, and substantial within-class variation [21].”
BackgroundŽvirblis, T., Pikšrys, A., Bzinkowski, D., & Kilikevičius, A. (2024) · IEEE Workshop on Advances in Information, Electronic and Electrical Engineering (AIEEE) · doi:10.1109/aieee62837.2024.10586674
Nonintrusive Load Monitoring Based on Spectrum Information Preserving Data Augmentation Method
Wan, X., & Wang, B. (2024) · IEEE International Electrical and Energy Conference (CIEEC) · doi:10.1109/cieec60922.2024.10583751
MMDL-Based Data Augmentation with Domain Knowledge for Time Series Classification
Li, X., Wu, Y., Jiang, W., Li, Y., & Li, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70352-2_24
Haresamudram, H., Essa, I. A., & Plötz, T. (2024) · International Conference on Activity and Behavior Computing (ABC) · doi:10.1109/abc61795.2024.10651688 · Cited by 1
“We perform pairwise iteration over eight transformations described in [31] (and utilized in [2]), and apply them to batches of sensor data.”
BackgroundMethodClustering-based Augmentation for Effective Self-supervised Learning in Sleep Staging
Tsoi, P., Kweon, Y.-S., & Lee, S. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650938
“Additionally, for each approach, we compare masking, three conventional augmentation techniques for time series (noising, scaling, and permutation) with our augmentation method [30].”
BackgroundMethodA review of enhancement techniques based on flight parameters time series data
Wang, H., Sun, Q., Liu, W., & Zhang, Z. (2024) · International Conference on Artificial Intelligence, Big Data and Algorithms (CAIBDA) · doi:10.1145/3690407.3690560
Optimising Deep Learning for Wearable Sensor-Based Fall Detection
Zhou, H., Nguyen, D., & Le‐Khac, N. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-74127-2_14
Hyperspectral data augmentation with transformer-based diffusion models
Ferrari, M., & Bruzzone, L. (2024) · Image and signal processing for remote sensing. Conference · doi:10.1117/12.3032957 · Cited by 1
“The evaluated methods include: Jittering, which adds random Gaussian noise to spectral signatures; Scaling, which adjusts spectral signatures by a uniform scaling factor; and Magnitude Warping, 31 which involves selecting anchor points, applying cubic interpolation, and scaling these values to the spectral signature.”
A Prototype Federated Learning Based Approach to Industrial Fault Diagnosis
徐, 丹. (2024) · Modeling and Simulation · doi:10.12677/mos.2024.136565
Liu, Y., Ren, Q., & Lv, X. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78169-8_8
Improving the Robustness of Time Series Neural Networks from Adversarial Attacks Using Time Warping
Yamashita, Y., & Iwana, B. K. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78341-8_2
Pedraza, N. H., Villegas, C. M., Aqueveque, D. C., & Das, R. (2024) · International Conference of the Chilean Computer Science Society (SCCC) · doi:10.1109/sccc63879.2024.10767645 · Cited by 1
Augmentation of Human Activity Data: Convert, Generate, Transform
Nair, N. R., Matei, A., Krön, D., Rueda, F. M., Reining, C., & Fink, G. A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78192-6_5
Towards Data Augmentation for Parkinson’s Disease Gait Data Using Neuromusculoskeletal Simulations
Kaminishi, K., Chiba, R., Takakusaki, K., & Ota, J. (2024) · Biosystems & biorobotics · doi:10.1007/978-3-031-77584-0_41
Peng, X., Xu, Z., Yang, Y., & Yang, P. (2024) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10822543
CNN and Cross-Attention Mechanism Based Surface Electromyography Gesture Recognition
Wang, W., Li, X., Tian, H., Jiang, K. Y., & Ma, X. (2025) · Springer eBooks · doi:10.1007/978-981-96-1108-9_47
Class-Agnostic Repetitive Action Counting Using Wearable Devices
Nguyen, D. D., Nguyen, L. T., Huang, Y., Pham, C., & Hoai, M. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3548131 · Cited by 3
U-Net-Based Contrastive Blind Denoising Method for Micro-Thrust Measurement Signal
Chen, X., Zhao, L., Xu, J., Li, Z., Han, M., & Dai, Z. (2024) · International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD) · doi:10.1109/icsmd64214.2024.10920511
Li, H., Zhou, D., Liu, Q., Zhang, Y., & Wang, L. (2025) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2025.3557696
“In the second step, different operations include Identity, Jittering, Scaling, Magnitude-warping (MagW) [10], and Cutout are used to perturb the amplitude of the signal sample, where Identity adds no disturbance to the sample, Jittering changes the magnitude of the sample by adding Gaussian white…”
Accelerometer-derived classifiers for early detection of degenerative joint disease in cats
Montout, A. X., Maniaki, E., Burghardt, T., Hezzell, M., Blackwell, E. J., & Dowsey, A. W. (2025) · The Veterinary Journal · doi:10.1016/j.tvjl.2025.106352 · Cited by 1
Adaptive Data Augmentation: Elliptical Masking and Dynamic Regularization with Feedback
Singh, A. K., Ambalavanan, N., Sirakov, N., & Nakhmani, A. (2025) · IEEE SoutheastCon · doi:10.1109/southeastcon56624.2025.10971474
“In time-series data, SoutheastCon 2025 979-8-3315-0484-7/25/$31.00 ©2025 IEEE augmentation techniques such as window slicing, warping, and jittering [19] have shown potential in improving the performance of models by introducing temporal variations in the data.”
InfluentialIncorporating Human Intuitions into Data Augmentation to Detect Concentration on Conversation
Ueno, K., & Shimakawa, H. (2024) · International Conference on Sustainable Technology and Engineering (i-COSTE) · doi:10.1109/i-coste63786.2024.11024960
“The above four methods are proposed by Terry et al. [16] as data augmentation methods for classification tasks using time series data of acceleration acquired from wearable sensors.”
β-Decode: Attention-based Decoding Temporal Artifacts via Unsupervised β-Variational Autoencoder
Ghosh, I., Chugh, G., Jayarajah, K., & Roy, N. (2024) · Joint International Conference on Data Science & Management of Data (CODS-COMAD) · doi:10.1145/3703323.3703758 · Cited by 2
“Features in time, spatial, and frequency domains [4, 36, 50] are effective in capturing underlying patterns.”
Li, Y., Xie, J., Zeng, Y., Pan, T., Wang, T., Li, W., Bi, R., & Chen, X. (2025) · IEEE Conference on Prognostics and Health Management · doi:10.1109/icphm65385.2025.11061816
“Jitter denotes adding random variations that follow a normal distribution with a mean value of loc and a standard deviation of sigma [15].”
Xie, J., Yang, M., Li, W., & Hou, R. (2024) · IEEE International Conference on High Performance Computing and Communications; IEEE International Conference on Smart City; IEEE International Conference on Data Science and Systems (HPCC/SmartCity/DSS) · doi:10.1109/hpcc64274.2024.00125
“The raw data were standardized, and data augmentation was applied separately to the training set [24].”
Data Augmentation for Radar Active Jamming Signals Based on Diffusion ModelsPreprint
Cao, T., qi, J., Su, H., & Liu, Y. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5367597
Enhancing Contrastive Learning in Sequence Classification via Data Augmentation
Huang, H., Tang, C.-Y., & Pao, H.-K. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-6291-3_20
Recovering and Classifying Upper Limb Impairment Trajectories After Stroke
Méndez-López, M., Fornés, A., & Agudo, A. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084561
“For inertial sensor signals, geometric transformations like Gaussian noise, resampling, scaling, and interpolation have shown an improvement in accuracy in standard datasets such as UCI-HAR and USC-HAR [7].”
Vu, Q. N. P., Lago, P., Bader, S., & Inoue, S. (2025) · International Conference on Activity and Behavior Computing (ABC) · doi:10.1109/abc64332.2025.11118576
“For the magnitude warping evaluation, we set the hyperparameter knot the same as the experiment proposed by [47].”
Real-Time Control of Ankle Orthosis Assistance Using a Locomotion Mode Prediction Tool
Moreira, L., Figueiredo, J., & Santos, C. P. (2025) · IEEE Transactions on Medical Robotics and Bionics · doi:10.1109/tmrb.2025.3604135
“These data augmentation techniques were employed to increase the diversity of the available data while preserving accurate labels [33], [34].”
Long, H.-W., Tang, Z., Zhang, J., Zhan, Z., Lu, T., & Zhang, X. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-06118-8_13 · Cited by 1
Hierarchical Coarse-to-Fine cGAN for Subtype-Specific Freezing of Gait Signal Generation
Yu, X., Cockx, H. M., Wang, Y., Wezel, R. J. A. V., Martens, K. A. E., & Arami, A. (2026) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2026.3685961
Song, T.-S., Chen, Z.-P., Hou, H.-R., Ding, H.-H., & Meng, Q. (2025) · Chinese Control Conference (CCC) · doi:10.23919/ccc64809.2025.11178620
Mast: interpretable stress testing via meta-learning for forecasting model robustness evaluation
Inácio, R., Cerqueira, V., Barandas, M., & Soares, C. (2025) · Machine Learning · doi:10.1007/s10994-025-06881-3
Overcoming Data Scarcity in Non-Contact Respiratory Monitoring: A DTW-Enhanced CNN-LSTM Approach
Kim, J. O., & Lee, D. (2025) · Electronics · doi:10.3390/electronics14204120
AutoMedTS: Automated modeling of physiological time series for surgical suturing action recognition
Zhang, B., Sullivan, P. M., Tang, B., Nabi, G., & Erden, M. S. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.112880 · Cited by 2
Kim, Y. N., & Lee, E. H. (2025) · Korean Society of Hazard Mitigation · doi:10.9798/kosham.2025.25.5.241
Deep Learning Model for Prediction of Fall-Risk Using Gait Biomarkers in Geriatric Population
Khera, P., Kour, G., & Kumar, A. (2025) · International Conference on Intelligent Algorithms for Computational Intelligence Systems (IACIS) · doi:10.1109/iacis65746.2025.11211343
NI-MTSC: Neighborhood Interpolation Data Augmentation-based Multivariate Time Series Classification
Yang, C., Fan, Z., Gou, J., & Wang, C. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11229225
“While permutation [17] rearranges the order of segments in a time series to generate a new series may disrupt the original temporal logic of the data and make the chronological order chaotic.”
End-to-end discriminative representation learning for fault diagnosis in safety-critical time series
Dong, F., Xiao, Y., Chen, S., Demachi, K., Takaya, S., & Yoshikawa, M. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.104094
Detection of Bark Beetle Attacks using Hyperspectral PRISMA Data and Few-Shot Learning
Ferrari, M., Papitto, G., Deligios, G., & Bruzzone, L. (2025) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss55030.2025.11243083
“Then we transform each sample in the batch x 1 , ... , x b , ... , x B scaling and noising it and then applying a magnitude warping [10].”
Alexopoulos, D., & Delopoulos, A. N. (2025) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc58623.2025.11254258
“Following extensive experimentation inspired by [18] and our intuition regarding the data collection process, the following augmentations were selected: • Left-to-Right Flipping: This augmentation simulates time inversion by flipping the signal along the temporal axis.”
Variational Autoencoder-Enhanced Data Augmentation Method for Ship-motion Trajectory Prediction
Shi, Y., Xiang, J., Li, M., & Gao, R. (2025) · International Conference on Computer Communication and Artificial Intelligence (CCAI) · doi:10.1109/ccai65422.2025.11189834
“Traditional time series data augmentation methods include time window slicing [7] , jittering [8] , scaling (amplitude warping [9] , time warping [10] , frequency warping [11] ), and permutation [12] .”
A Geometric Constraints based Bayesian Neural Network for Virtual Surgery Assessment
Yuan, H., Dong, F., Dai, W., Cao, D., Hu, M., & Gu, Y. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227367
“Due to the limited quantity of data sample available for D KT , D NP , and D SU , an Time-warping upsampling method was applied [29].”
Minowa, H., Sekiguchi, R., & Kawakatsu, M. (2025) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3714394.3759240
Decomposition-Based Augmentation of Multivariate Time-Series Measurement Data
Erpalov, A. V., Sinitsin, V. V., Ibryaeva, O. L., & Shestakov, A. (2025) · International Scientific Symposium Metrology and Metrology Assurance (MMA) · doi:10.1109/mma67107.2025.11311246
“Traditional augmentation methods – such as amplitude warping, time-window distortion, or noise injection [1] – modify datasets through transformations.”
Current Status, Trends and Challenges in AI-Based Bradykinesia and Tremor Detection on Edge Devices
Stefanou, E. E., Bitilis, P., & Kotis, K. (2025) · International Conference on Information, Intelligence, Systems & Applications (IISA) · doi:10.1109/iisa66859.2025.11311304
Psychological Traits Estimation Using Generative Adversarial Networks for Personalized Intervention
Yamamoto, T., Hayakawa, S., Shiraishi, M., Masuda, Y., Matsuki, M., & Kamimura, T. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-12767-9_20 · Cited by 1
Camara, P. J. M., Troncoso, J. M. C., Rincón, M., & López, P. J. T. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-10661-2_25
Data Augmentation Using Large Language Models: Methods, Challenges, and Perspectives
Kozina, A., Pikus, M., & Wąs, J. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-13869-9_5
Robust Material Classification and General Methods for Multiregion Miniature ToF Sensors
Millam, J., Gammelgaard, K., & Koerner, L. J. (2026) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2026.3652745
“Augmentation synthetically increases the number and range of inputs to improve model generalization and is particularly valuable when the amount of data is limited for both image classification [28] and time series classification [34].”
Ding, W., Liu, A., Cui, H., Shan, J., & Chen, X. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.109600
SkillNet: Human Actions Assessment via Human-AI Collaboration
Ghosh, I., Chakma, A., Anwar, M. S., Ramamurthy, S. R., & Roy, N. (2026) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3788290
“To rigorously assess the robustness of the SkillNet framework, we introduced controlled jitter noise [53] into one of the task-specific layers during the training process.”
Fourier Latent Transformer for Anomaly Signal with High-Frequency Reconstruction
Chalongvorachai, T., & Woraratpanya, K. (2025) · doi:10.1109/icitee66631.2025.11338305
“Anomaly-related signal analysis is essential in real-world applications, particularly in preventing failures in critical infrastructure and industrial machinery [1]–[3], and in some cases, protecting human lives [4].”
Affect Recognition in Deaf Children Using Physiological Signal Measurements
Choudhary, K., & Prajapati, G. L. (2026) · SN Computer Science · doi:10.1007/s42979-025-04711-w
“( 2 )) [57 , 58]and a wavelet-domain noise injection operator (Eq.”
Benyoucef, Y., Harmouch, J., Asadi, B., Melliti, I., Mastro, A. D., Herrero, P., Carcasona-Otal, A., & Lapuente‐Hernández, D. (2026) · Life · doi:10.3390/life16020193
“This entropy-sensitive design contrasts with the widespread use of symmetric augmentation strategies reported in previous gait classification studies, which apply identical transformations indiscriminately to both classes [32,33].”
Data Augmentation for Radar Active Jamming Signals Based on Diffusion Models
Qi, J., Liu, Y., Lei, C., Cao, T., Wan, Q., Su, H., & Zhao, Y. (2025) · International Conference on Signal Processing Systems (ICSPS) · doi:10.1109/icsps66615.2025.11347932 · Cited by 1
“Scaling techniques [3] adjust local values while preserving overall signal shape.”
Gao, C., Rao, Z., Fu, Y., Chen, J., Huang, M., & Song, Q. (2025) · International Conference on Big Data and Internet of Things · doi:10.1145/3779153.3779180
“For example, in Parkinson’s disease motor state classification, researchers proposed rotation (Rot), permutation (Perm), and time warping (TimeW) augmentation methods combined with CNNs, effectively mitigating challenges posed by small datasets and high noise [11].”
Advancing Human Activity Recognition with Meta-Learning for Continual Learning
Ghedini, C. G., Silva, A., & Colombini, E. L. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343696
“Following Iglesias et al. [15], [16], we applied several augmentation strategies to improve meta-training performance, including: • Permutation (P): Reorders the sequence by shuffling data points within fixed-length window.”
Adaptive Performance Regression Detection Using A Semi-Supervised Siamese Network
Sun, Y., Li, M., Xiong, X., Tao, L., Zuo, Y., Gu, W., Zhang, S., Kuang, J., Yu, L., Zhuang, H., et al. (2025) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase63991.2025.00289
“By transforming the original data to generate additional samples, this technique enhances the diversity of the regression KPIs data, thereby improving DynamicRegress ’s capacity to learn regression data patterns and increasing its robustness [29], [30].”
Zhang, Y., Wang, C. H., Wang, B., Wang, Z., Zhu, H., & Jiang, C. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343455
“In the field of time series data augmentation, traditional methods include Jitter, Scaling, Time Warp, Permutation, Inversion, and Rotation [15].”
Bh$$\bar{a}$$luk: Learning the Unknown Basis of Human Olfactory System Using Deep Learning
Kushwaha, A., Kulkarni, P. D., Thakur, R., Chowdhury, S. R., Nigam, A., & Singh, D. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-16632-6_22
Song, S., Chen, Y., Zhang, Y., Yang, X., Gao, J., & Wang, X. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2026.2618554 · Cited by 1
“The scarcity of rich and varied datasets is a common issue in PD (Um et al., 2017) and many other medical specialties, making its deployment optimization particularly illustrative.”
Align and Adapt: Multimodal Multiview Human Activity Recognition Under Arbitrary View Combinations
Nguyen, D., & Le‐Khac, N. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2026.3718255
“The scaling and time-warping augmentation techniques [44] are applied to training data.”
Nguyen, D., & Le‐Khac, N. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6216286
Enhancing chromium coating thickness estimation with multi-head attention LSTM and data augmentation
Jeon, M., Choi, W., Park, J. W., Lee, J., & Mun, D. (2026) · Scientific Reports · doi:10.1038/s41598-026-39258-0
Yamagiwa, S., MORIYA, S., & Noma, T. (2026) · IEEE Access · doi:10.1109/access.2026.3666115
“Especially, the techniques have been evolving these days according to emerged applications such as for clustering patients of Parkinson disease from medical records by applying a premutation, time warping technique, scaling, magnitude warping, jittering, cropping and so on [29].”
Re-framing Time Series Augmentation Through the Lens of Generative Models
Ismail-Fawaz, A., Devanne, M., Berretti, S., Weber, J., & Forestier, G. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-15535-1_3
Sankeerthi, S. L., Srinivasan, S., Nohitha, M., Chandana, N., & Abhishek, S. (2025) · International Conference on Smart and Intelligent Systems (SISCON) · doi:10.1109/siscon66686.2025.11409318
“Deep learning (DL) models, especially CNN and LSTM architectures, have been able to learn representations directly from the unprocessed IMU signals [9].”
Li, G., Nakamura, Y., Choi, H., & Arakawa, Y. (2025) · IIAI International Congress on Advanced Applied Informatics (IIAI-AAI) · doi:10.1109/iiai-aai-winter69777.2025.00010 · Cited by 1
“In [7], Um et al. propose a series of signal transform methods to process wearable sensor signals for Parkinson’s disease monitoring, including jittering, scaling, rotation, etc.”
Lee, J.-O., & Kim, Y. S. (2025) · Journal of the Korean society for quality management · doi:10.7469/jksqm.2025.53.4.523
“최근에는 이미지 영역을 넘어 텍스트(Wei and Zou, 2019), 음성(Park et al., 2019), 시계열(Um et al., 2017) 등 다양한 데이터 유형으로 적용 범위가 확장되고 있다.”
Causal mediation pathways in continuous postprandial glucose monitoring for type 1 diabetes patients
Hilligoss, S., & Qu, A. (2026) · npj Metabolic Health and Disease · doi:10.1038/s44324-026-00127-z
“We explicitlydo not advocatedata augmentation 62,63 asa remedyfor the present sample size: augmenting within twelve subjects cannot recover generalization error and risks entrenching artefacts of the current sample.”
Recognition of Human Gait Under Asymmetric Loading
Derlatka, M. (2026) · Sensors · doi:10.3390/s26061940
“A more detailed description of these methods is presented in [39,40], while their employment for the classification of human gait has been demonstrated in [41].”
MSCFormer: a multiscale convolutional transformer for multivariate time series classification
Xie, J., Yang, M., Wu, Y., Hou, R., Li, W., Dong, M., & Ota, K. (2026) · Applied Intelligence · doi:10.1007/s10489-026-07158-5
Deep learning for time series classification
Fawaz, H. I. (2020) · theses.fr (ABES) · doi:10.70675/4be65ba1z3327z4573zb045z15c1d1435785 · Cited by 11
Method of Operational Loading Process Augmentation Based on a Given Damage Criterion
Erpalov, A. V., Khoroshevskii, K. A., & Gadolina, I. V. (2026) · Journal of Machinery Manufacture and Reliability · doi:10.1134/s1052618825701663
de Beaulieu, M. H. (2023) · theses.fr (ABES) · doi:10.70675/93e42ee6z458az4979zba92za662d6dde626
Development of ML model for triboelectric nanogenerator based sign language detection system
Patel, M., Baro, B., Bayan, S., & Roy, M. (2026) · IEEE Guwahati Subsection Conference (GCON) · doi:10.1109/gcon69192.2026.11649240
“Temporal warping data augmentation and noise injection have proved essential for enhancing model generalisation when utilising small quantities of training data [5], [11].”
Sikandar, T., Izzeldin, I. M., Ghazali, K. H., Rahman, S. A. M. M., & Rabbi, M. F. (2026) · SN Computer Science · doi:10.1007/s42979-026-04969-8
MTS-GAN: Synthetic multivariate time series generation with the Mamba architecture
Escuder, S., Graupera-Serra, O., Calvo, A., Tornos, B., Gutiérrez, G., Escrig, J., & Compastié, M. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.115996 · Cited by 1
KineticWear: Battery-Free On-Device Human Activity Recognition for Wearables
Sandhu, M. M., Deumer, M., Khalifa, S., Kusý, B., Geissdoerfer, K., Zimmerling, M., & Jurdak, R. (2026) · ACM Transactions on Internet of Things · doi:10.1145/3811542
“As the collected activity data is limited, we employ various data augmentation techniques [88, 89] before developing deep learning models, as described in the following section.”
Transformer-Based Human Activity Recognition Using Wearable Devices
Kumar, A., & Kumar, D. I. (2026) · National Conference on Communications · doi:10.1109/ncc68160.2026.11478937 · Cited by 1
“To enhance model generalization and robustness, Gaussian jitter augmentation is applied during training to simulate real-world sensor perturbations [2], [19].”
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.