Many-to-Many Prediction for Effective Modeling of Frequent Label Transitions in Time Series
Open accessAbstract
Time-series classification is vital in health monitoring and human activity recognition, as well as in areas such as financial forecasting, process control, and a wide array of forecasting tasks. Traditional time-series models segment data into windows and assign one label per window, often missing label transitions within those windows. This paper presents a novel many-to-many time-series model and post-processing using hybrid recurrent neural networks with attention mechanisms, which more effectively captures label transitions over traditional many-to-one models. Further, unlike typical other many-to-many models, our approach doesn’t require a decoder. Instead, it employs an RNN, generating a label for every input time step. During inference, a weighted voting scheme consolidates overlapping predictions into one label per time step. Experiments show our model remains effective on time-series with sparse label shifts, but particularly excels in detecting frequent transitions. This model is ideal for tasks demanding accurate pinpointing of rapid label changes in time-series data, such as gesture recognition, making it ideal for fast-paced human activity recognition. 1
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
Temporal attention is highly successful for time-series sensor data.
“Given that sensor data is structured as a time series, the use of temporal attention can prove highly successful [34].”
From Adaptive temporal attention mechanism and hybrid deep CNN model for wearable sensor-based human activity recognition (2025) · cites this paper as [34]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Goldberger, A. L., Amaral, L. A. N., Glass, L., Hausdorff, J. M., Ivanov, P. C., Mark, R. G., Mietus, J. E., Moody, G. B., Peng, C.-K., & Stanley, H. E. (2000) · Circulation · doi:10.1161/01.cir.101.23.e215 · Cited by 14,809 · see citing works
He, H., & Garcia, E. A. (2009) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2008.239 · Cited by 10,359 · see citing works
Learning from imbalanced data: open challenges and future directions
Krawczyk, B. (2016) · Progress in Artificial Intelligence · doi:10.1007/s13748-016-0094-0 · Cited by 2,459 · see citing works
A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction
Qin, Y., Song, D., Chen, H., Cheng, W., Jiang, G., & Cottrell, G. W. (2017) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2017/366 · Cited by 1,700 · see citing works
Recurrent Neural Networks for Time Series Forecasting: Current status and future directions
Hewamalage, H., Bergmeir, C., & Bandara, K. (2021) · International Journal of Forecasting · doi:10.1016/j.ijforecast.2020.06.008 · Cited by 1,371 · see citing works
Learning to Diagnose with LSTM Recurrent Neural Networks
Lipton, Z. C., Kale, D. C., Elkan, C., & Wetzel, R. (2015) · arXiv · doi:10.48550/arxiv.1511.03677 · Cited by 879 · see citing works
Effective Approaches to Attention-based Neural Machine TranslationPreprint
Luong, M.-T., Pham, H., & Manning, C. D. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1508.04025 · Cited by 742 · see citing works
Vito, S. D., Massera, E., Piga, M., Martinotto, L., & Francia, G. D. (2007) · Sensors and Actuators B Chemical · doi:10.1016/j.snb.2007.09.060 · Cited by 546 · see citing works
Recurrent neural networks for time series classification
Hüsken, M., & Stagge, P. (2003) · Neurocomputing · doi:10.1016/s0925-2312(01)00706-8 · Cited by 352 · see citing works
Banos, O., Villalonga, C., Garcia, R., Saez, A., Damas, M., Holgado-Terriza, J. A., Lee, S., Pomares, H., & Rojas, I. (2015) · BioMedical Engineering OnLine · doi:10.1186/1475-925x-14-s2-s6 · Cited by 321 · see citing works
Temporal segmentation and activity classification from first-person sensing
Spriggs, E., la Torre, F. D., & Hebert, M. (2009) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2009.5204354 · Cited by 234 · see citing works
AT-LSTM: An Attention-based LSTM Model for Financial Time Series Prediction
Zhang, X., Liang, X., Zhiyuli, A., Zhang, S., Xu, R., & Wu, B. (2019) · IOP Conference Series Materials Science and Engineering · doi:10.1088/1757-899x/569/5/052037 · Cited by 186 · see citing works
Time Series Forecasting Using Sequence-to-Sequence Deep Learning Framework
Du, S., Li, T., & Horng, S. (2018) · International Symposium on Parallel Architectures, Algorithms and Programming · doi:10.1109/paap.2018.00037 · Cited by 65 · see citing works
Recovering the temporal structure of natural gesture
Wilson, A. D., Bobick, A., & Cassell, J. (2002) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/afgr.1996.557245 · Cited by 58 · see citing works
Gesture unit segmentation using support vector machines
Madeo, R. C. B., Lima, C. A. M., & Peres, S. M. (2013) · ACM Symposium on Applied Computing · doi:10.1145/2480362.2480373 · Cited by 53 · see citing works
Ranjan, K. G., Tripathy, D. S., Prusty, B. R., & Jena, D. (2020) · International Journal of Numerical Modelling Electronic Networks Devices and Fields · doi:10.1002/jnm.2816 · Cited by 42 · see citing works
Price Forecast with High-Frequency Finance Data
Gu, Y., Yan, D., Yan, S., & Jiang, Z. (2020) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3340531.3412738 · Cited by 20 · see citing works
Attention-Based Sequence-to-Sequence Model for Time Series Imputation
Li, Y., Du, M., & He, S. (2022) · Entropy · doi:10.3390/e24121798 · Cited by 19 · see citing works
Artificial Intelligence in Medicine
Wittal, C. G. (2024) · doi:10.14293/s2199-1006.1.sor-med.cl5jhyx.v1 · Cited by 17 · see citing works
Metro Interstate Traffic Volume
Hogue, J. (2019) · UC Irvine · doi:10.24432/c5x60b · Cited by 15 · see citing works
Raftery, A. E. (1985) · European Journal of Operational Research · doi:10.1016/0377-2217(85)90052-9 · Cited by 14 · see citing works
More effective time-series analysis and forecasting
Anderson, O. D. (1995) · Journal of Computational and Applied Mathematics · doi:10.1016/0377-0427(95)00011-9 · Cited by 10 · see citing works
Wild, P., Foster, J. W., & Hinich, M. J. (2010) · Macroeconomic Dynamics · doi:10.1017/s1365100509090543 · Cited by 9 · see citing works
Time series activity classification using gated recurrent units
Tan, Y.-F., Guo, X., & Poh, S.-C. (2021) · International Journal of Power Electronics and Drive Systems/International Journal of Electrical and Computer Engineering · doi:10.11591/ijece.v11i4.pp3551-3558 · Cited by 6 · see citing works
Prediction model for high-volatile time series based on SVM regression approach
Falát, L., Pancikova, L., & Hlinkova, M. (2015) · International Conference on Information and Digital Technologies (IDT) · doi:10.1109/dt.2015.7222954 · Cited by 4 · see citing works
Time Series Data Prediction Based on Sequence to Sequence Model
Yang, C., Guo, Z., & Xian, L. (2019) · IOP Conference Series Materials Science and Engineering · doi:10.1088/1757-899x/692/1/012047 · Cited by 4 · see citing works
Recurrent Neural Networks for Time Series Data
McClarren, R. G. (2021) · Springer eBooks · doi:10.1007/978-3-030-70388-2_7 · Cited by 2 · see citing works
Temporal Attention Signatures for Interpretable Time-Series Prediction
Katrompas, A., & Metsis, V. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-44223-0_22 · Cited by 1 · see citing works
Self-citation
Flagged first, then by citations
Research works printed but not linked: 3
- Dzmitry Bahdanau, Kyunghyun Cho, and Y. Bengio. 2014. Neural Machine Translation by Jointly Learning to Align and Translate. ArXiv 1409 (09 2014).
- Zelda Mariet and Vitaly Kuznetsov. 2019. Foundations of Sequence-to-Sequence Modeling for Time Series. In Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research, Vol. 89), Kamalika Chaudhuri and Masashi Sugiyama (Eds.). PMLR, 408- 417.
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention Is All You Need. 31st Conference on Neural Information Processing Systems (NIPS 2017) (06 2017).
Cited by
Sorted by citations
Wang, Z., & Kang, K. (2025) · Scientific Reports · doi:10.1038/s41598-025-18444-6 · Cited by 5 · see citing works
- Authors
- Katrompas, A., & Metsis, V.
- Affiliations
- Texas State University (US)
- Venue
- Proceedings of the 17th International Conference on PErvasive Technologies Related to Assistive Environments
- Publisher
- ACM
- Published
- 2024-06-26
- Pages
- 265-272
- OpenAlex
- W4400037248
- Cited by
- 1
- References
- 27
- Citations by year
- 2025: 1
- FWCI
- 0.38
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- International Conference on PErvasive Technologies Related to Assistive Environments (PETRA) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
- Social Sciences › Decision Sciences › Management Science and Operations Research › Stock Market Forecasting Methods
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Keywords
- recurrent neural networks, attention mechanism, weighted voting, time series classification, human activity recognition, gesture recognition
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
