AutoAugHAR: Automated Data Augmentation for Sensor-based Human Activity Recognition
Open accessThe DOI matches its Crossref record; 59 of the 59 references it cites were found in a registry or an index.
Abstract
Sensor-based HAR models face challenges in cross-subject generalization due to the complexities of data collection and annotation, impacting the size and representativeness of datasets. While data augmentation has been successfully employed in domains like natural language and image processing, its application in HAR remains underexplored. This study presents AutoAugHAR, an innovative two-stage gradient-based data augmentation optimization framework. AutoAugHAR is designed to take into account the unique attributes of candidate augmentation operations and the unique nature and challenges of HAR tasks. Notably, it optimizes the augmentation pipeline during HAR model training without substantially extending the training duration. In evaluations on eight inertial-measurement-units-based benchmark datasets using five HAR models, AutoAugHAR has demonstrated superior robustness and effectiveness compared to other leading data augmentation frameworks. A salient feature of AutoAugHAR is its model-agnostic design, allowing for its seamless integration with any HAR model without the need for structural modifications. Furthermore, we also demonstrate the generalizability and flexible extensibility of AutoAugHAR on four datasets from other adjacent domains. We strongly recommend its integration as a standard protocol in HAR model training and will release it as an open-source tool1.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“AutoAugHAR [223] facilitates cross-subject generalization in HAR through a two-stage, gradient-based data augmentation framework.”
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 [223]
Citations
Cites
A survey on Image Data Augmentation for Deep Learning
Shorten, C., & Khoshgoftaar, T. M. (2019) · Journal of Big Data · doi:10.1186/s40537-019-0197-0 · Cited by 13,203 · cited 1×
“The efficacy of DA has been well-established in fields like computer vision [15, 63] and natural language processing [18].”
BackgroundLearning Transferable Architectures for Scalable Image Recognition
Zoph, B., Vasudevan, V., Shlens, J., & Le, Q. V. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00907 · Cited by 6,249
EEGNet: a compact convolutional neural network for EEG-based brain-computer interfaces
Lawhern, V. J., Solon, A. J., Waytowich, N. R., Gordon, S. M., Hung, C. P., & Lance, B. J. (2018) · Journal of Neural Engineering · doi:10.1088/1741-2552/aace8c · Cited by 5,115 · cited 1×
“For EEG classification tasks, the EEG model [36] and the gated transformer model [66] were implemented.”
MethodEEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces
Lawhern, V. J., Solon, A. J., Waytowich, N. R., Gordon, S. M., Hung, C. P., & Lance, B. J. (2016) · arXiv · doi:10.48550/arxiv.1611.08024 · Cited by 5,105 · cited 1×
“For EEG classification tasks, the EEG model [36] and the gated transformer model [66] were implemented.”
MethodRandaugment: Practical automated data augmentation with a reduced search space
Cubuk, E. D., Zoph, B., Shlens, J., & Le, Q. V. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00359 · Cited by 3,223 · cited 2×
“To address the challenge of efficiently selecting effective augmentation sub-policies, we use a baseline approach, that is commonly used DA mechanism in computer vision model [15].”
BackgroundMethodRandAugment: Practical automated data augmentation with a reduced search space
Cubuk, E. D., Zoph, B., Shlens, J., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1909.13719 · Cited by 3,223 · cited 2×
“To address the challenge of efficiently selecting effective augmentation sub-policies, we use a baseline approach, that is commonly used DA mechanism in computer vision model [15].”
BackgroundMethodActivity recognition using cell phone accelerometers
Kwapisz, J. R., Weiss, G. M., & Moore, S. A. (2011) · ACM SIGKDD Explorations Newsletter · doi:10.1145/1964897.1964918 · Cited by 2,912 · cited 1×
“…Activity Monitoring Data Set ( PAMAP2 ) [54], Opportunity ( OPPO ) [11], RealWorld HAR ( RW ) [64], Daily and Sports Activities Data Set ( DSADS ) [7], Wireless Sensor Data Mining ( WISDM ) [35], Daphnet Gait ( DG ) [6] and GesHome [49]. with the configurations of previous studies [23, 43, 58, 76].”
ResultDeep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition
Ordóñez, F., & Roggen, D. (2016) · Sensors · doi:10.3390/s16010115 · Cited by 2,761 · cited 2×
“To improve the capacity to extract temporal information, the hybrid model DeepConvLSTM ( DCL ) [51] incorporates LSTM layers into the individual convolution network.”
BackgroundMethod(2013) · RECERCAT (Consorci de Serveis Universitaris de Catalunya) · Cited by 1,959
Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
Bengio, Y., Léonard, N., & Courville, A. (2013) · arXiv · doi:10.48550/arxiv.1308.3432 · Cited by 1,910 · cited 1×
“Attend-Discriminate ( Attend ) [1] further improves performance on multiple HAR datasets by specifically learning the interactions between channels at each time-step through an attention mechanism.”
BackgroundFBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search
Wu, B., Keutzer, K., Dai, X., Zhang, P., Wang, Y., Sun, F., Wu, Y., Tian, Y., Vajda, P., & Jia, Y. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01099 · Cited by 1,261 · cited 11×
“…AutoAugHAR against the following seven DA techniques in addition to a baseline (training without DA): These techniques can be categorized into three groups: traditional DA techniques (MixUp, CutMix), generative models (SFN [45], ActivityGAN, SF-DM), and DA optimization framework ( 𝑤 -augment).”
MethodInfluentialvan Hees, V. T., Gorzelniak, L., Dean León, E. C., Eder, M., Pias, M., Taherian, S., Ekelund, U., Renström, F., Franks, P. W., Horsch, A., et al. (2013) · PLoS ONE · doi:10.1371/journal.pone.0061691 · Cited by 926
The Opportunity challenge: A benchmark database for on-body sensor-based activity recognition
Chavarriaga, R., Sagha, H., Calatroni, A., Digumarti, S. T., Tröster, G., Millán, J. D. R., & Roggen, D. (2013) · Pattern Recognition Letters · doi:10.1016/j.patrec.2012.12.014 · Cited by 742 · cited 1×
“…Human Activities and Postural Transitions ( HAPT ) [55], PAMAP2 Physical Activity Monitoring Data Set ( PAMAP2 ) [54], Opportunity ( OPPO ) [11], RealWorld HAR ( RW ) [64], Daily and Sports Activities Data Set ( DSADS ) [7], Wireless Sensor Data Mining ( WISDM ) [35], Daphnet Gait ( DG )…”
BackgroundTransition-Aware Human Activity Recognition Using Smartphones
Reyes-Ortiz, J.-L., Oneto, L., Samà, A., Parra, X., & Anguita, D. (2016) · Neurocomputing · doi:10.1016/j.neucom.2015.07.085 · Cited by 740 · cited 1×
“These datasets include: Human Activities and Postural Transitions ( HAPT ) [55], PAMAP2 Physical Activity Monitoring Data Set ( PAMAP2 ) [54], Opportunity ( OPPO ) [11], RealWorld HAR ( RW ) [64], Daily and Sports Activities Data Set ( DSADS ) [7], Wireless Sensor Data Mining ( WISDM ) [35],…”
BackgroundUm, T. T., Pfister, F. M. J., Pichler, D., Endo, S., Lang, M., Hirche, S., Fietzek, U., & Kulić, D. (2017) · Proceedings of the 19th ACM International Conference on Multimodal Interaction · doi:10.1145/3136755.3136817 · Cited by 729 · cited 4×
“DA Combination Challenge : Research [32, 67, 70] has demonstrated notable improvements in HAR tasks by training models combining multiple DA methods.”
BackgroundMethodInfluentialTime Series Data Augmentation for Deep Learning: A Survey
Wen, Q., Sun, L., Yang, F., Song, X., Gao, J., Wang, X., & Xu, H. (2021) · Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/631 · Cited by 727 · cited 6×
“DA Combination Challenge : Research [32, 67, 70] has demonstrated notable improvements in HAR tasks by training models combining multiple DA methods.”
BackgroundMethodInfluentialAn 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 · cited 7×
“The settings of these hyper-parameters are summarized from related works [1, 2, 19, 28].”
BackgroundMethodInfluentialDeep Learning for Sensor-based Human Activity Recognition
Chen, K., Zhang, D., Yao, L., Guo, B., Yu, Z., & Liu, Y. (2022) · ACM Computing Surveys · doi:10.1145/3447744 · Cited by 690
Searching for a Robust Neural Architecture in Four GPU Hours
Dong, X., & Yang, Y. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00186 · Cited by 640 · cited 1×
“…AutoAugHAR against the following seven DA techniques in addition to a baseline (training without DA): These techniques can be categorized into three groups: traditional DA techniques (MixUp, CutMix), generative models (SFN [45], ActivityGAN, SF-DM), and DA optimization framework ( 𝑤 -augment).”
MethodDeep, Convolutional, and Recurrent Models for Human Activity Recognition Using Wearables
Hammerla, N. Y., Halloran, S., & Ploetz, T. (2016) · arXiv · doi:10.48550/arxiv.1604.08880 · Cited by 606 · cited 1×
“…Activity Monitoring Data Set ( PAMAP2 ) [54], Opportunity ( OPPO ) [11], RealWorld HAR ( RW ) [64], Daily and Sports Activities Data Set ( DSADS ) [7], Wireless Sensor Data Mining ( WISDM ) [35], Daphnet Gait ( DG ) [6] and GesHome [49]. with the configurations of previous studies [23, 43, 58, 76].”
ResultUm, T. T. (n.d.) · mediaTUM – the media and publications repository of the Technical University Munich (Technical University Munich) · Cited by 602
Synchronous Oscillatory Neural Ensembles for Rules in the Prefrontal Cortex
Buschman, T. J., Denovellis, E. L., Diogo, C., Bullock, D., & Miller, E. K. (2012) · Neuron · doi:10.1016/j.neuron.2012.09.029 · Cited by 436 · cited 1×
“The diffusion-based SF-DM model actually decreases performance on these two dataset, probably because motor imagery classification benefits from a wider and higher frequency range [10, 26].”
Statistical Theory of Extreme Values and Some Practical Applications : A Series of Lectures
Gumbel, E. J. (1954) · U.S. Government Printing Office eBooks · Cited by 378
On-body localization of wearable devices: An investigation of position-aware activity recognition
Sztyler, T., & Stuckenschmidt, H. (2016) · 2016 IEEE International Conference on Pervasive Computing and Communications (PerCom) · doi:10.1109/percom.2016.7456521 · Cited by 369 · cited 1×
“Baseline SFN SF-DM AutoAugHar AutoAugHAR(N) FTS Reverse STM ChannelDropout Drawing on an extensive review of the prevalent DA operators for EEG classification [57], we have selected four types of DA operators considered to be the most effective.”
BackgroundBarshan, B., & Yuksek, M. C. (2014) · The Computer Journal · doi:10.1093/comjnl/bxt075 · Cited by 346 · cited 1×
“…Activity Monitoring Data Set ( PAMAP2 ) [54], Opportunity ( OPPO ) [11], RealWorld HAR ( RW ) [64], Daily and Sports Activities Data Set ( DSADS ) [7], Wireless Sensor Data Mining ( WISDM ) [35], Daphnet Gait ( DG ) [6] and GesHome [49]. with the configurations of previous studies [23, 43, 58,…”
ResultDeep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities
Chen, K., Zhang, D., Yao, L., Guo, B., Yu, Z., & Liu, Y. (2020) · arXiv · doi:10.48550/arxiv.2001.07416 · Cited by 314
CNN-based sensor fusion techniques for multimodal human activity recognition
Münzner, S., Schmidt, P., Reiss, A., Hanselmann, M., Stiefelhagen, R., & Dürichen, R. (2017) · Proceedings of the 2017 ACM International Symposium on Wearable Computers · doi:10.1145/3123021.3123046 · Cited by 235 · cited 1×
“Multi-branch Convolutional Neural Network ( MCNN ) [47] applies a sensor-based late fusion technique.”
MethodHierarchical optimization: An introduction
Anandalingam, G., & Friesz, T. L. (1992) · Annals of Operations Research · doi:10.1007/bf02098169 · Cited by 229 · cited 18×
“As past comparisons between CutMix and MixUp indicate, each sample-pair-based technique has its unique advantages.”
MethodInfluentialChung, S., Lim, J., Noh, K. J., Kim, G., & Jeong, H. (2019) · Sensors · doi:10.3390/s19071716 · Cited by 215 · cited 2×
“Traditional DA techniques for HAR tasks typically involve random signal transformations such as adding noise, window slicing, magnitude scaling, and random warping [3, 13, 32], among others.”
BackgroundFaster AutoAugment: Learning Augmentation Strategies Using Backpropagation
Hataya, R., Zdenek, J., Yoshizoe, K., & Nakayama, H. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58595-2_1 · Cited by 174
Data augmentation for learning predictive models on EEG: a systematic comparison
Rommel, C., Paillard, J., Moreau, T., & Gramfort, A. (2022) · Journal of Neural Engineering · doi:10.1088/1741-2552/aca220 · Cited by 163
A novel approach of decoding EEG four-class motor imagery tasks via scout ESI and CNN
Hou, Y., Zhou, L., Jia, S., & Lun, X. (2019) · Journal of Neural Engineering · doi:10.1088/1741-2552/ab4af6 · Cited by 159 · cited 1×
“The diffusion-based SF-DM model actually decreases performance on these two dataset, probably because motor imagery classification benefits from a wider and higher frequency range [10, 26].”
On attention models for human activity recognition
Murahari, V. S., & Plötz, T. (2018) · Proceedings of the 2018 ACM International Symposium on Wearable Computers · doi:10.1145/3267242.3267287 · Cited by 157 · cited 1×
“In order to address the ’forgetting’ limitations of LSTMs, DeepConvLSTM-Attention ( DCL-A ) [48] augments DeepConvLSTM with temporal attention, facilitating global temporal information exchange in a single forward pass.”
BackgroundAn Accurate EEGNet-based Motor-Imagery Brain–Computer Interface for Low-Power Edge Computing
Wang, X., Hersche, M., Tömekçe, B., Kaya, B., Magno, M., & Benini, L. (2020) · IEEE International Symposium on Medical Measurements and Applications (MeMeA) · doi:10.1109/memea49120.2020.9137134 · Cited by 148
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
Abedin, 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
Bachlin, M., Roggen, D., Troster, G., Plotnik, M., Inbar, N., Meidan, I., Herman, T., Brozgol, M., Shaviv, E., Giladi, N., et al. (2009) · 2009 International Symposium on Wearable Computers · doi:10.1109/iswc.2009.14 · Cited by 98 · cited 2×
“Experiments were specifically conducted on datasets characterized by the presence of multiple modalities, thereby validating the contribution of multi-modality optimization in the proposed AutoAugHAR.”
MethodPMC: A Privacy-preserving Deep Learning Model Customization Framework for Edge Computing
Liu, B., Li, Y., Liu, Y., Guo, Y., & Chen, X. (2020) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3432208 · Cited by 95
TinyHAR: A Lightweight Deep Learning Model Designed for Human Activity Recognition
Zhou, Y., Zhao, H., Huang, Y., Riedel, T., Hefenbrock, M., & Beigl, M. (2022) · Proceedings of the 2022 ACM International Symposium on Wearable Computers · doi:10.1145/3544794.3558467 · Cited by 78 · cited 1×
“While deep learning models for HAR have shown promising results [51, 77, 78], their ability to generalize across different subjects remains a concern [25].”
BackgroundSelf-citationMeng, F., Liu, H., Liang, Y., Tu, J., & Liu, M. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2913544 · Cited by 71 · cited 4×
“Due to the extensive nature of the experimental work, the comparison was limited to two state of the art DA techniques: the SFN [45] and SF-DM [81], which have proven effective in previous experiments.”
BackgroundMethodInfluentialLi, X., Luo, J., & Younes, R. (2020) · Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2020 ACM International Symposium on Wearable Computers · doi:10.1145/3410530.3414367 · Cited by 71 · cited 4×
“Challenges in data collection and annotation [1], coupled with the high costs of user studies and volunteer participation [39], limit their representativeness and informativeness.”
BackgroundMethodInfluentialGated Transformer for Decoding Human Brain EEG Signals
Tao, Y., Sun, T., Muhamed, A., Genç, Ş., Jackson, D., Arsanjani, A., Yaddanapudi, S., Li, L., & Kumar, P. (2021) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc46164.2021.9630210 · Cited by 70
Zhang, T., Lan, Z., Xu, C., Li, Y., & Chen, Y. (2022) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3569482 · Cited by 58
Nguyen-Trong, K., Vu, H. N., Trung, N. N., & Pham, C. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3074642 · Cited by 49 · cited 1×
“Ok The change of phase 𝛥𝜑 ranges within 0 , 2 , (cid:2) 2 3 𝜋 2 3 𝜋 2 , 2 𝜋 ) .”
Sensor-data augmentation for human activity recognition with time-warping and data masking
Jeong, C. Y., Shin, H. C., & Kim, M. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-10600-0 · Cited by 38 · cited 6×
“Consequently, the implementation of inappropriate DA methods can distort the original data characteristics, possibly altering the label semantic information [30] and negatively impacting model performance [28].”
BackgroundMethodInfluentialLearning From Heterogeneous Eeg Signals with Differentiable Channel Reordering
Saeed, A., Grangier, D., Pietquin, O., & Zeghidour, N. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9413712 · Cited by 37
Synthetic Smartwatch IMU Data Generation from In-the-wild ASL Videos
Santhalingam, P. S., Pathak, P. H., Rangwala, H., & Košecká, J. (2023) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3596261 · Cited by 35
Improving CNN-based activity recognition by data augmentation and transfer learning
Kalouris, G., Zacharaki, E. I., & Megalooikonomou, V. (2019) · 2019 IEEE 17th International Conference on Industrial Informatics (INDIN) · doi:10.1109/indin41052.2019.8972135 · Cited by 28 · cited 2×
“DA Combination Challenge : Research [32, 67, 70] has demonstrated notable improvements in HAR tasks by training models combining multiple DA methods.”
BackgroundMethodData Augmentation Strategies for Human Activity Data Using Generative Adversarial Neural Networks
Hoelzemann, A., Sorathiya, N., & Laerhoven, K. V. (2021) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomworkshops51409.2021.9431046 · Cited by 26 · cited 1×
“While deep learning models for HAR have shown promising results [51, 77, 78], their ability to generalize across different subjects remains a concern [25].”
BackgroundZhou, Y., Hefenbrock, M., Huang, Y., Riedel, T., & Beigl, M. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-67667-4_28 · Cited by 23
Self-citationUsing 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 · cited 1×
“For instance, Goubeaud et al. [21] trained a variational autoencoder (VAE) on the original data and subsequently generated new samples to augment the training set.”
BackgroundDiffAR: Adaptive Conditional Diffusion Model for Temporal-augmented Human Activity Recognition
Huang, S., Chen, P.-Y., & McCann, J. A. (2023) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2023/424 · Cited by 22
A Study on Diffusion Modelling For Sensor-based Human Activity Recognition
Shao, S., & Sánchez, V. (2023) · International Workshop on Biometrics and Forensics (IWBF) · doi:10.1109/iwbf57495.2023.10157482 · Cited by 20 · cited 2×
“This includes applications in WiFi channel state information-based HAR [27], and wearable-based HAR [62, 81].”
MethodHelping Users Debug Trigger-Action Programs
Zhang, L., Zhou, C., Littman, M. L., Ur, B., & Lu, S. (2022) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3569506 · Cited by 16
Augmented Adversarial Learning for Human Activity Recognition with Partial Sensor Sets
Kang, H., Huang, Q., & Zhang, Q. (2022) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3550285 · Cited by 16
ALAE-TAE-CutMix+: Beyond the State-of-the-Art for Human Activity Recognition Using Wearable Sensors
Ahmad, N., & Leung, H.-F. (2023) · IEEE International Conference on Pervasive Computing and Communications · doi:10.1109/percom56429.2023.10099138 · Cited by 13
Unsupervised Diffusion Model for Sensor-based Human Activity Recognition
Zuo, S., Rey, V. F., Suh, S., Sigg, S., & Lukowicz, P. (2023) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3594739.3610797 · Cited by 8
EMG-EEG dataset for Upper-Limb Gesture Classification
Lee, B. (2023) · IEEE DataPort · doi:10.21227/5ztn-4k41 · Cited by 4
Letters of Polish Sign Language Alphabet
Piskozub, J. (2023) · IEEE DataPort · doi:10.21227/w90m-m764 · Cited by 1
Research works printed but not linked: 27
- Luay Alawneh, Tamam Alsarhan, Mohammad Al-Zinati, Mahmoud Al-Ayyoub, Yaser Jararweh, and Hongtao Lu. 2021. Enhancing Human Activity Recognition Using Deep Learning and Time Series Augmented Data. Journal of Ambient Intelligence and Humanized Computing (2021), 1--16.
- Clemens Brunner, Robert Leeb, Gernot Müller-Putz, Alois Schlögl, and Gert Pfurtscheller. 2008. BCI Competition 2008-Graz data set A. Institute for Knowledge Discovery (Laboratory of Brain-Computer Interfaces), Graz University of Technology 16 (2008), 1--6.
- Ekin D Cubuk, Barret Zoph, Dandelion Mane, Vijay Vasudevan, and Quoc V Le. 2018. Autoaugment: Learning augmentation policies from data. arXiv preprint arXiv:1805.09501 (2018). · arXiv
- Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion models beat gans on image synthesis. Advances in neural information processing systems 34 (2021), 8780--8794.
- Steven Y Feng, Varun Gangal, Jason Wei, Sarath Chandar, Soroush Vosoughi, Teruko Mitamura, and Eduard Hovy. 2021. A Survey of Data Augmentation Approaches for NLP. arXiv preprint arXiv:2105.03075 (2021). · arXiv
- Elizabeth Fons, Paula Dawson, Xiao-jun Zeng, John Keane, and Alexandros Iosifidis. 2021. Adaptive weighting scheme for automatic time-series data augmentation. arXiv preprint arXiv:2102.08310 (2021). · arXiv
- Ary L Goldberger, Luis AN Amaral, Leon Glass, Jeffrey M Hausdorff, Plamen Ch Ivanov, Roger G Mark, Joseph E Mietus, George B Moody, Chung-Kang Peng, and H Eugene Stanley. 2000. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. circulation 101, 23 (2000), e215-e220.
- Eric Jang, Shixiang Gu, and Ben Poole. 2016. Categorical reparameterization with gumbel-softmax. arXiv preprint arXiv:1611.01144 (2016). · arXiv
- Artur Jordao, Antonio C Nazare Jr, Jessica Sena, and William Robson Schwartz. 2018. Human Activity Recognition Based on Wearable Sensor Data: A Standardization of the State-of-the-art. arXiv preprint arXiv:1806.05226 (2018). · arXiv
- Diederik P Kingma and Jimmy Ba. 2014. Adam: A Method for Stochastic Optimization. arXiv preprint arXiv:1412.6980 (2014). · arXiv
- 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.
- Yonggang Li, Guosheng Hu, Yongtao Wang, Timothy Hospedales, Neil M Robertson, and Yongxin Yang. 2020. Dada: Differentiable automatic data augmentation. arXiv preprint arXiv:2003.03780 (2020). · arXiv
- Hanxiao Liu, Karen Simonyan, Oriol Vinyals, Chrisantha Fernando, and Koray Kavukcuoglu. 2017. Hierarchical representations for efficient architecture search. arXiv preprint arXiv:1711.00436 (2017). · arXiv
- Hanxiao Liu, Karen Simonyan, and Yiming Yang. 2018. Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055 (2018). · arXiv
- Chris J Maddison, Daniel Tarlow, and Tom Minka. 2014. A* sampling. Advances in neural information processing systems 27 (2014).
- Mostafa Neo Mohsenvand, Mohammad Rasool Izadi, and Pattie Maes. 2020. Contrastive representation learning for electroencephalogram classification. In Machine Learning for Health. PMLR, 238--253.
- Alexander Quinn Nichol and Prafulla Dhariwal. 2021. Improved denoising diffusion probabilistic models. In International Conference on Machine Learning. PMLR, 8162--8171.
- Daniel S Park, William Chan, Yu Zhang, Chung-Cheng Chiu, Barret Zoph, Ekin D Cubuk, and Quoc V Le. 2019. Specaugment: A simple data augmentation method for automatic speech recognition. arXiv preprint arXiv:1904.08779 (2019). · arXiv
- Attila Reiss and Didier Stricker. 2012. Introducing A New Benchmarked Dataset for Activity Monitoring. In 2012 16th international symposium on wearable computers. IEEE, 108--109.
- Cédric Rommel, Thomas Moreau, Joseph Paillard, and Alexandre Gramfort. 2021. CADDA: Class-wise automatic differentiable data augmentation for EEG signals. arXiv preprint arXiv:2106.13695 (2021). · arXiv
- Charissa Ann Ronao and Sung-Bae Cho. 2016. Human Activity Recognition with Smartphone Sensors Using Deep Learning Neural Networks. Expert systems with applications 59 (2016), 235--244.
- JTC Schwabedal, JC Snyder, A Cakmak, S Nemati, and GD Clifford. [n. d.]. Addressing Class Imbalance in Classification Problems of Noisy Signals by using Fourier Transform Surrogates. arXiv 2018. arXiv preprint arXiv:1806.08675 ([n. d.]). · arXiv
- Frank Wilcoxon. 1992. Individual comparisons by ranking methods. In Breakthroughs in Statistics: Methodology and Distribution. Springer, 196--202.
- Sirui Xie, Hehui Zheng, Chunxiao Liu, and Liang Lin. 2018. SNAS: stochastic neural architecture search. arXiv preprint arXiv:1812.09926 (2018). · arXiv
- Zhi-Qin John Xu, Yaoyu Zhang, and Tao Luo. 2022. Overview frequency principle/spectral bias in deep learning. arXiv preprint arXiv:2201.07395 (2022). · arXiv
- Arber Zela, Thomas Elsken, Tonmoy Saikia, Yassine Marrakchi, Thomas Brox, and Frank Hutter. 2019. Understanding and robustifying differentiable architecture search. arXiv preprint arXiv:1909.09656 (2019). · arXiv
- Barret Zoph and Quoc V Le. 2016. Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578 (2016). · arXiv
Cited by
Haresamudram, H., Tang, C. I., Suh, S., Lukowicz, P., & Plötz, T. (2025) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3729467 · Cited by 33
Machine Learning–Based Classification Framework for Human Health Care Monitoring
Kurdi, S. Z. (2026) · International Journal of Theoretical & Applied Computational Intelligence · doi:10.65278/ijtaci.2026.1 · Cited by 29
Karthikeyan, R., Usha, S., Dineshbabu, V., Jeena, R. S., Govindaram, A., & Jegatheesan, A. (2024) · Journal of Machine and Computing · doi:10.53759/7669/jmc202404098 · Cited by 16
“The novel AutoAugHAR, introduced by Zhou et al., [18], is an optimisation framework for data augmentation that uses a two-stage gradient approach.”
MethodKhayami, H., Wang, L., Kim, Y., Lee, B., Conroy, D. E., Lazar, A., Choe, E. K., & Kacorri, H. (2025) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3731749 · Cited by 8
Hong, Q.-S., & Lu, C.-H. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3574733 · Cited by 8
“Centaur [13] combines sensor data cleaning and attention-based fusion to capture intersensor correlations, while AutoAugHAR [14] automates augmentation for IMU-based HAR using a gradient-based optimization strategy.”
Metadata
- Authors
- Zhou, Y., Zhao, H., Huang, Y., Röddiger, T., Kurnaz, M., Riedel, T., & Beigl, M.
- Affiliations
- Karlsruhe Institute of Technology (DE)
- Venue
- Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Published
- 2024-05-13
- Volume
- 8
- Issue
- 2
- Pages
- 1-27
- ISSN
- 2474-9567 (ISSN-L)
- OpenAlex
- W4396920196
- Cited by
- 25
- References
- 54
- Citations by year
- 2026: 8 · 2025: 11 · 2024: 6
- FWCI
- 3.52
- Type
- journal article
- Language
- en
- Open access
- Licence
- Locations
- Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies (publishedVersion, public-domain)
- Repository KITopen (Karlsruhe Institute of Technology) (submittedVersion, public-domain)
- KITopen
- Funders
- Carl-Zeiss-Foundation (Jubot)
- German Ministry of Research and Education (01IS22095A, 01IS19030A)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- human activity recognition, data augmentation, cross-subject generalization, inertial measurement unit, wearable sensors, model robustness
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.