Skip to main content
SpringerLink
Log in

A deformable convolutional time-series prediction network with extreme peak and interval calibration

  • Research
  • Published:
GeoInformatica Aims and scope Submit manuscript

Abstract

Deep modeling and analysis of human big data deepens our understanding of human activities. Periodic time-series signals, e.g., electrocardiographs, collected by health monitoring sensors reflect human health status and assist in disease diagnosis. However, long-term prediction of these signals using deep learning models poses three challenges, namely, sparse features, conservative prediction of extreme peaks, and varying periodic intervals. We address these issues by proposing a prediction framework called EPIC with extreme peak and interval calibrations. EPIC consists of a triple-channel prediction network and a calibration network. The prediction network learns the time-domain, frequency-domain, and deformable features of time-series patterns simultaneously. Amplitude residuals of extreme peaks are emphasized in the designed training loss function. In addition, to alleviate the problem of unaligned predictions resulting from inaccurate periodic intervals, we further design a calibration module to reduce the deviation of periodic intervals. The experimental results and ablation studies indicate that EPIC achieves excellent performance in long-term prediction tasks.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Algorithm 1
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

Availability of data and materials

All of the materials including figures is owned by the authors and no permissions are required. The dataset is public datasets available.

References

  1. Biel L, Pettersson O, Philipson L, Wide P (2001) Ecg analysis: a new approach in human identification. IEEE Trans Instrumentation Meas 50(3):808–812

    Article  Google Scholar 

  2. Cao F, Budhota A, Hao C, Rajput KS (2020) Feature matching based ECG generative network for arrhythmia event augmentation. In: 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society 296–299

  3. Sinha N, Das A (2021) Identification and localization of myocardial infarction based on analysis of ECG signal in cross spectral domain using boosted SVM classifier. IEEE Trans Instrum Meas 70:1–9

    Google Scholar 

  4. Loeffler SE, Starobin JM (2021) Reaction-diffusion informed approach to determine myocardial ischemia using stochastic in-silico ecgs and cnns. Comput Biol Med 136:104635

    Article  Google Scholar 

  5. Zhou P, Schwerin B, Lauder B, So S (2020) Deep learning for real-time ECG r-peak prediction. In: 14th International Conference on Signal Processing and Communication Systems 1–7

  6. Keshan N, Parimi PV, Bichindaritz I (2015) Machine learning for stress detection from ECG signals in automobile drivers. In: IEEE International Conference on Big Data 2661–2669

  7. Yin H, Song X, Yang S, Li J (2022) Sentiment analysis and topic modeling for covid-19 vaccine discussions. World Wide Web 25(3):1067–1083

    Article  Google Scholar 

  8. Bi X, Nie H, Zhang G, Hu L, Ma Y, Zhao X, Yuan Y, Wang G (2023) Boosting question answering over knowledge graph with reward integration and policy evaluation under weak supervision. Inf Process Manag 60(2):103242

    Article  Google Scholar 

  9. Bi X, Nie H, Zhang X, Zhao X, Yuan Y, Wang G (2022) Unrestricted multi-hop reasoning network for interpretable question answering over knowledge graph. Knowledge-Based Systems 243:108515

    Article  Google Scholar 

  10. Song X, Li J, Cai T, Yang S, Yang T, Liu C (2022) A survey on deep learning based knowledge tracing. Knowl-Based Syst 258:110036

    Article  Google Scholar 

  11. Xu C, Zhao W, Zhao J, Guan Z, Song X, Li J (2022) Uncertaintyaware multiview deep learning for internet of things applications. IEEE Trans Ind Inform 19(2):1456–1466

    Article  Google Scholar 

  12. Dai J, Qi H, Xiong Y, Li Y, Zhang G, Hu H, Wei Y (2017) Deformable convolutional networks. In: IEEE International Conference on Computer Vision 764–773

  13. Pant JK, Krishnan S (2016) Efficient compressive sensing of ECG segments based on machine learning for qrs-based arrhythmia detection. In: 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society 4731–4734

  14. Rymko J, Solinski M, Perka A, Rosinski J, Lepek M (2017) Classification of atrial fibrillation in short-term ECG recordings using a machine learning approach and hybrid QRS detection. In: Computing in Cardiology

  15. Mjahad A, Muñoz AR, Bataller-Mompeán M, Francés JV, Guerrero-Martínez J (2017) Ventricular fibrillation and tachycardia detection from surface ECG using time-frequency representation images as input dataset for machine learning. Comput Methods Programs Biomed 141:119–127

    Article  Google Scholar 

  16. Melgarejo-Meseguer FM, Gimeno-Blanes FJ, Rojo-Álvarez JL, Salar-Alcaraz M, Gimeno-Blanes J, García-Alberola A (2018) Cardiac fibrosis detection applying machine learning techniques to standard 12-lead ECG. In: Computing in Cardiology 1–4

  17. Jothiramalingam R, Jude A, Patan R, Ramachandran M, Duraisamy JH, Gandomi AH (2021) Machine learning-based left ventricular hypertrophy detection using multi-lead ECG signal. Neural Comput Appl 33(9):4445–4455

    Article  Google Scholar 

  18. Sannino G, Pietro GD (2018) A deep learning approach for ecg-based heartbeat classification for arrhythmia detection. Future Gener Comput Syst 86:446–455

    Article  Google Scholar 

  19. Wu M, Chang EJ, Chu T (2018) Personalizing a generic ECG heartbeat classification for arrhythmia detection: A deep learning approach. In: IEEE 1st Conference on Multimedia Information Processing and Retrieval 92–99

  20. Izci E, Degirmenci M, Özdemir MA, Akan A (2020) ECG arrhythmia detection with deep learning. In: 28th Signal Processing and Communications Applications Conference 1–4

  21. Petty T, Vu T, Zhao X, Hirsh RA, Murray G, Haas FM, Xue W (2020) Evaluating deep learning algorithms for real-time arrhythmia detection.In: 7th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies 19–26

  22. Hammad M, Iliyasu AM, Subasi A, Ho ESL, El-Latif AAA (2021) A multitier deep learning model for arrhythmia detection. IEEE Trans Instrum Meas 70:1–9

    Article  Google Scholar 

  23. Sun C, Hong S, Song M, Chou Y, Sun Y, Cai D, Li H (2021) TEESN: time encoding echo state network for prediction based on irregularly sampled time series data. In: Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence 3010–3016

  24. Liu W, Wang F, Huang Q, Chang S, Wang H, He J (2020) MFBCBRNN: A hybrid network for MI detection using 12-lead ecgs. IEEE J Biomed Health Inform 24(2):503–514

    Article  Google Scholar 

  25. Ganapathy N, Swaminathan R, Deserno TM (2021) Adaptive learning and cross training improves r-wave detection in ECG. Comput Methods Programs Biomed 200:105931

    Article  Google Scholar 

  26. Zahid MU, Kiranyaz S, Ince T, Devecioglu OC, Chowdhury MEH, Khandakar A, Tahir AM, Gabbouj M (2022) Robust r-peak detection in low-quality holter ecgs using 1d convolutional neural network. IEEE Trans Biomed Eng 69(1):119–128

    Article  Google Scholar 

  27. Golany T, Lavee G, Yarden ST, Radinsky K (2020) Improving ECG classification using generative adversarial networks. In: The Thirty-Fourth AAAI Conference on Artificial Intelligence 13280–13285

  28. Chen J, Zheng X, Yu H, Chen DZ, Wu J (2021) Electrocardio panorama: Synthesizing new ECG views with self-supervision. In: Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence 3597–3605

  29. Bagirathan A, Selvaraj J, Gurusamy A, Das H (2021) Recognition of positive and negative valence states in children with autism spectrum disorder (ASD) using discrete wavelet transform (DWT) analysis of electrocardiogram signals (ECG). J Ambient Intell Humaniz Comput 12(1):405–416

    Article  Google Scholar 

  30. Mihaylov I, Nisheva M, Vassilev D (2018) Machine learning techniques for survival time prediction in breast cancer. In: Artificial Intelligence: Methodology, Systems, and Applications - 18th International Conference 11089:186–194

  31. Dai X, Li JLY (2021) A recurrent neural network using historical data to predict time series indoor pm2. 5 concentrations for residential buildings.Indoor air 31(4):1228–1237

  32. Jalali A, Lee M (2020) Atrial fibrillation prediction with residual network using sensitivity and orthogonality constraints. IEEE J Biomed Health Inform 24(2):407–413

    Article  Google Scholar 

  33. Zhou P, Schwerin B, Lauder B, So S (2020) Deep learning for real-time ECG r-peak prediction. In: 14th International Conference on Signal Processing and Communication Systems 1–7

  34. Wang T, Leung H, Zhao J, Wang W (2020) Multiseries featural LSTM for partial periodic time-series prediction: A case study for steel industry. IEEE Trans Instrum Meas 69(9):5994–6003

    Article  Google Scholar 

  35. Morid MA, Sheng ORL, Kawamoto K, Abdelrahman SE (2020) Learning hidden patterns from patient multivariate time series data using convolutional neural networks: A case study of healthcare cost prediction. J Biomed Inform 111:103565

    Article  Google Scholar 

  36. Yin R, Luusua E, Dabrowski J, Zhang Y, Kwoh CK (2020) Tempel: time-series mutation prediction of influenza A viruses via attention-based recurrent neural networks. Bioinformatics 36(9):2697–2704

    Article  Google Scholar 

  37. Yang Z, Tian Y, Zhou T, Zhu Y, Zhang P, Chen J, Li J (2021) Time-series deep survival prediction for hemodialysis patients using an attention-based bi-gru network. Comput Methods Programs Biomed 212:106458

    Article  Google Scholar 

  38. Crabbé J, van der Schaar M (2021) Explaining time series predictions with dynamic masks. In: Proceedings of the 38th International Conference on Machine Learning 139:2166–2177

  39. Wang D, Zhang J, Cao W, Li J, Zheng Y (2018) When will you arrive? estimating travel time based on deep neural networks. In: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence 2500–2507

  40. Fan SS, Su C, Nien H, Tsai P, Cheng C (2018) Using machine learning and big data approaches to predict travel time based on historical and real-time data from taiwan electronic toll collection. Soft Comput 22(17):5707–5718

    Article  Google Scholar 

  41. Mohapatra UM, Majhi B, Satapathy SC (2019) Financial time series prediction using distributed machine learning techniques. Neural Comput Appl 31(8):3369–3384

    Article  Google Scholar 

  42. Wang H, Liu X, Song P, Tu X (2019) Sensitive time series prediction using extreme learning machine. Int J Mach Learn Cybern 10(12):3371–3386

    Article  Google Scholar 

  43. Stepec D, Martincic T, Klein F, Vladusic D, Costa JP (2020) Machine learning based system for vessel turnaround time prediction. In: 21st IEEE International Conference on Mobile Data Management 258–263

  44. Stefanovic P, Strimaitis R, Kurasova O (2020) Prediction of flight time deviation for lithuanian airports using supervised machine learning model. Comput Intell Neurosci 2020:8878681–1887868110

    Article  Google Scholar 

  45. Maldaner LF, de Paula Corrêdo L, Canata TF, Molin JP (2021) Predicting the sugarcane yield in real-time by harvester engine parameters and machine learning approaches. Comput Electron Agric 181:105945

    Article  Google Scholar 

  46. Ji J, Wang J, Jiang Z, Jiang J, Zhang H (2022) Stden: Towards physicsguided neural networks for traffic flow prediction. Proceedings of the AAAI Conference on Artificial Intelligence 36:4048–4056

    Article  Google Scholar 

  47. Xu M, Li X, Wang F, Shang JS, Chong T, Cheng W, Xu J (2023) Learning to effectively model spatial-temporal heterogeneity for traffic flow forecasting. World Wide Web 26(3):849–865

    Article  Google Scholar 

  48. Zheng C, Fan X, Wang C, Qi J (2020) Gman: A graph multi-attention network for traffic prediction. Proceedings of the AAAI Conference on Artificial Intelligence 34:1234–1241

    Article  Google Scholar 

  49. Acharya UR, Oh SL, Hagiwara Y, Tan JH, Adam M, Gertych A, San Tan R (2017) A deep convolutional neural network model to classify heartbeats. Comput biol med 89:389–396

    Article  Google Scholar 

  50. Zhang L, Na J, Zhu J, Shi Z, Zou C, Yang L (2021) Spatiotemporal causal convolutional network for forecasting hourly pm2. 5 concentrations in beijing, china. Comput Geosci 155:104869

  51. Li Y, Zhang X, Chen D (2018) Csrnet: Dilated convolutional neural networks for understanding the highly congested scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 1091–1100

  52. Gers FA, Schmidhuber J, Cummins F (2000) Learning to forget: Continual prediction with lstm. Neural comput 12(10):2451–2471

    Article  Google Scholar 

  53. Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D (2017) Grad-cam: Visual explanations from deep networks via gradient-based localization. In: IEEE International Conference on Computer Vision 618–626

Download references

Acknowledgements

The work is supported by National Key R &D Program of China (Grant No. 2022YFB3304302), the National Natural Science Foundation of China (Grant No. 61972077, 62002054, 62072087), LiaoNing Revitalization Talents Program (Grant No. XLYC2007079).

Funding

The authors would like to acknowledge the support provided by National Key R &D Program of China (Grant No. 2022YFB3304302), the National Natural Science Foundation of China (Grant No. 61972077, 62002054, 62072087), LiaoNing Revitalization Talents Program (Grant No. XLYC2007079).

Author information

Authors and Affiliations

  1. Key Laboratory of Ministry of Education on Safe Mining of Deep Metal Mines, Northeastern University, Shenyang, 110819, Liaoning, China

    Xin Bi, Guoliang Zhang & Lijun Lu

  2. Key Laboratory of Liaoning Province on Deep Engineering and Intelligent Technology, Northeastern University, Shenyang, 110819, Liaoning, China

    Xin Bi, Guoliang Zhang & Lijun Lu

  3. Thinvent Digital Technology Co.,Ltd., Nanchang, 330000, Jiangxi, China

    George Y Yuan

  4. College of Software, Northeastern University, Shenyang, 110819, Liaoning, China

    Xiangguo Zhao

  5. School of Computer Science and Engineering, Northeastern University, Shenyang, 110819, Liaoning, China

    Yongjiao Sun

  6. College of Information Science and Engineering, Northeastern University, Shenyang, 110819, Liaoning, China

    Yuliang Ma

Authors
  1. Xin Bi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Guoliang Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Lijun Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. George Y Yuan
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Xiangguo Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Yongjiao Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Yuliang Ma
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Xin Bi provided the conceptual design of the study, Guoliang Zhang and Lijun Lu wrote the main manuscript text and completed the experiments, George Y Yuan and Xiangguo Zhao prepared all the figures, Yongjiao Sun and Yuliang Ma provided supervision for the paper. All the authors reviewed the manuscript.

Corresponding author

Correspondence to Xin Bi.

Ethics declarations

Conflicts of interest

The authors declare no conflicts of interest.

Ethics standard

This article does not contain any studies involving human participants and/or animals by any of the authors.

Consent to participate

Informed consent was obtained from all individual participants.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Bi, X., Zhang, G., Lu, L. et al. A deformable convolutional time-series prediction network with extreme peak and interval calibration. Geoinformatica 28, 291–312 (2024). https://doi.org/10.1007/s10707-023-00502-8

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10707-023-00502-8

Keywords

Search

Navigation