Skip to main content
SpringerLink
Log in

Multivariate Deep Learning Model with Ensemble Pruning for Time Series Forecasting

  • Conference paper
  • First Online:
Proceedings of the Seventh International Conference on Mathematics and Computing

Part of the book series: Advances in Intelligent Systems and Computing ((AISC,volume 1412))

  • 589 Accesses

Abstract

To predict future events using historical data, Time Series Forecasting (TSF) should be used to get precise and accurate predictions. It has been a challenging issue to deal with the errors and value loss while predicting the future; hence, a dynamic error correction is proposed to overcome the errors. Additionally, it is important to find out a fast optimization technique to avoid this difficulty. Therefore, it is proposed in this study to use an improved stacking-based ensemble pruning method, namely Genetic Algorithm (GA)-II to produce high accuracy and strong stability in time series forecasting. A meta predictor known as Kernel Ridge Regression (KRR) is proposed for stacking ensemble models for its improved forecasting performance. The main goal of this study is to attain reliable and precise time-series forecasting. In the process of extracting various types of data features, particular types of Deep Neural networks are effective. Therefore, these types of models combine and increase the use of Deep Learning and Ensemble Learning techniques. It is better to use different Deep Neural Networks as Deep Learning models and use boosting and stacking techniques as neural networks take more time by using these types of methods, and the results would be better with low calculations. In time-series data, the value changes dynamically which may increase or decrease the accuracy of the prediction, so to overcome this type of problem, some error correction methods like Dynamic Error Correction (DEC) and a technique like Non-Dominated Sorting Genetic Algorithm (NSGA) and Multi-Populated Non-Dominated Sorting Genetic Algorithm-II (GA-II) to get optimal solutions in terms of accuracy are used.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 189.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 249.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Chen S, Billings S, Grant P (1990) Non-linear system identification using neural networks. Int J Control 51(6):1191–1214

    Article  Google Scholar 

  2. Deb K, Pratap A, Agarwal S, Meyarivan T (2002) A fast and elitist multiobjective genetic algorithm: Nsga-ii. IEEE Trans Evol Comput 6(2):182–197

    Article  Google Scholar 

  3. Drucker H (1997) Improving regressors using boosting techniques. In: ICML. vol 97, pp 107–115

    Google Scholar 

  4. Dutta S, Das KN (2019) A survey on pareto-based eas to solve multi-objective optimization problems. In: Soft computing for problem solving. Springer, pp 807–820

    Google Scholar 

  5. Ferreira A, Giraldi G (2017) Convolutional neural network approaches to granite tiles classification. Expert Syst Appl 84:1–11

    Google Scholar 

  6. Gautam S, Maiti J, Syamsundar A, Sarkar S (2017) Segmented point process models for work system safety analysis. Saf Sci 95:15–27

    Google Scholar 

  7. Hastie T, Rosset S, Zhu J, Zou H (2009) Multi-class adaboost. Stat Interface 2(3):349–360

    Article  MathSciNet  Google Scholar 

  8. Jiménez F, Sánchez G, García JM, Sciavicco G, Miralles L (2017) Multi-objective evolutionary feature selection for online sales forecasting. Neurocomputing 234:75–92

    Google Scholar 

  9. Knowles JD, Corne DW (2000) Approximating the nondominated front using the pareto archived evolution strategy. Evol Comput 8(2):149–172

    Article  Google Scholar 

  10. Kourentzes N, Barrow DK, Crone SF (2014) Neural network ensemble operators for time series forecasting. Expert Syst Appl 41(9):4235–4244

    Article  Google Scholar 

  11. Krishna OB, Maiti J, Ray PK, Samanta B, Mandal S, Sarkar S (2015) Measurement and modeling of job stress of electric overhead traveling crane operators. Saf Health Work 6(4):279–288

    Article  Google Scholar 

  12. Liu RY, Parelius JM, Singh K et al (1999) Multivariate analysis by data depth: descriptive statistics, graphics and inference,(with discussion and a rejoinder by liu and singh). Ann Stat 27(3):783–858

    Article  Google Scholar 

  13. Panigrahi S, Behera HS (2017) A hybrid ets-ann model for time series forecasting. Eng Appl Artif Intell 66:49–59

    Google Scholar 

  14. Pramanik A, Djeddi C, Sarkar S, Maiti J and others (2020) Region proposal and object detection using Hog-based cnn feature map. In: International conference on data analytics for business and industry 2020, Way Towards a Sustainable Economy (ICDABI), IEEE, pp 1–5

    Google Scholar 

  15. Pramanik A, Pal SK, Maiti J, Mitra P (2021) Granulated rcnn and multi-class deep sort for multi-object detection and tracking. IEEE Trans Emerg Top Comput Intell (2021)

    Google Scholar 

  16. Qiu X, Zhang L, Ren Y, Suganthan PN, Amaratunga G (2014) Ensemble deep learning for regression and time series forecasting. In: 2014 IEEE symposium on computational intelligence in ensemble learning (CIEL). IEEE, pp 1–6

    Google Scholar 

  17. Raymer ML, Punch WF, Goodman ED, Kuhn LA, Jain AK (2000) Dimensionality reduction using genetic algorithms. IEEE Trans Evol Comput 4(2):164–171

    Article  Google Scholar 

  18. Sarkar S, Verma A, Maiti J (2018) Prediction of occupational incidents using proactive and reactive data: A data mining approach. In: Industrial safety management- 21st century perspective of Asia. Springer, Singapore, pp 65–79

    Google Scholar 

  19. Sarkar S, Baidya S, Maiti J (2017) Application of rough set theory in accident analysis at work: A case study. In: ICRCICN 2017. pp 245–250 (2017)

    Google Scholar 

  20. Sarkar S, Ejaz N, Maiti J (2018) Application of hybrid clustering technique for pattern extraction of accident at work: A case study of a steel industry. In: 2018 4th international conference on recent advances in information technology (RAIT), IIT Dhanbad. IEEE, pp 1–6

    Google Scholar 

  21. Sarkar S, Lohani A, Maiti J (2017) Genetic algorithm-based association rule mining approach towards rule generation of occupational accidents. In: Communications in computer and information science, vol 776. Springer, Singapore, pp 517–530

    Google Scholar 

  22. Sarkar S, Maiti J (2020) Machine learning in occupational accident analysis: A review using science mapping approach with citation network analysis. Saf Sci 131:104900

    Google Scholar 

  23. Sarkar S, Patel A, Madaan S, Maiti J (2017) Prediction of occupational accidents using decision tree approach. In: INDICON 2017. IEEE, pp. 1–6

    Google Scholar 

  24. Sarkar S, Pateshwari V, Maiti J (2017) Predictive model for incident occurrences in steel plant in India. In: ICCCNT 2017, pp 1–5

    Google Scholar 

  25. Sarkar S, Pramanik A, Khatedi N, Balu A, Maiti J (2020) Gsel: A genetic stacking-based ensemble learning approach for incident classification. In: Proceedings of ICETIT 2019. Springer, pp 719–730

    Google Scholar 

  26. Sarkar S, Pramanik A, Maiti J, Reniers G (2020) Predicting and analyzing injury severity: a machine learning-based approach using class-imbalanced proactive and reactive data. Saf Sci 125:104616

    Google Scholar 

  27. Sarkar S, Raj R, Sammangi V, Maiti J, Pratihar D (2019) An optimization-based decision tree approach for predicting slip-trip-fall accidents at work. Saf Sci 118:57–69

    Google Scholar 

  28. Sarkar S, Sammangi V, Raj R, Maiti J, Mitra P (2019) Application of optimized machine learning techniques for prediction of occupational accidents. Comput Oper Res 106:210–224

    Google Scholar 

  29. Sarkar S, Vinay S, Pateshwari V, Maiti J (2017) Study of optimized svm for incident prediction of a steel plant in India. In: INDICON 2017. IEEE, pp 1–6

    Google Scholar 

  30. Singh K, Raj N, Sahu S, Behera R, Sarkar S, Maiti J (2015) Modelling safety of gantry crane operations using petri nets. Int J Injury Control Saf Promot 1–12

    Google Scholar 

  31. Verma A, Chatterjee S, Sarkar S, Maiti J (2018) Data-driven mapping between proactive and reactive measures of occupational safety performance. In: Industrial safety management- 21st century perspective of Asia. Springer, Singapore, pp 53–63

    Google Scholar 

  32. Wang L, Teo KK, Lin Z (2001) Predicting time series with wavelet packet neural networks. In: IJCNN’01. international joint conference on neural networks. Proceedings (Cat. No. 01CH37222). vol 3. IEEE, pp 1593–1597

    Google Scholar 

  33. Zhang S, Chen Y, Zhang W, Feng R, A novel ensemble deep learning model with dynamic error correction and multi-objective ensemble pruning for time series forecasting. Inf Sci 544:427–445

    Google Scholar 

  34. Zhi R, Zhou C, Li T (2019) Dynamic facial feature learning by deep evolutionary neural networks. In: Cyberspace data and intelligence, and cyber-living, syndrome, and health. Springer, pp 312–327

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Mechanical Engineering, IIT Kharagpur, Kharagpur, 721302, India

    Mohit Kosuri

  2. Department of Ocean Engineering and Naval Architecture, IIT Kharagpur, Kharagpur, 721302, India

    Cherry Tandu

  3. Business School, University of Edinburgh, 29 Buccleuch Pl, EH8 9JS, Edinburgh, UK

    Sobhan Sarkar

  4. Department of Industrial and Systems Engineering, IIT Kharagpur, Kharagpur, 721302, India

    J. Maiti

Authors
  1. Mohit Kosuri
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Cherry Tandu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Sobhan Sarkar
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. J. Maiti
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Sobhan Sarkar .

Editor information

Editors and Affiliations

  1. Department of Information Technology, Maulana Abul Kalam Azad University of Technology, Haringhata, India

    Debasis Giri

  2. The University of Texas at San Antonio, San Antonio, TX, USA

    Kim-Kwang Raymond Choo

  3. Department of Mathematics, Indian Institute of Technology Madras, Chennai, India

    Saminathan Ponnusamy

  4. Technical University of Denmark, Kongens Lyngby, Denmark

    Weizhi Meng

  5. Department of Computer Engineering, Ondokuz Mayis University, Atakum, Turkey

    Sedat Akleylek

  6. Department of Information Technology, Indian Institute of Engineering Science and Technology, West Bengal, India

    Santi Prasad Maity

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Kosuri, M., Tandu, C., Sarkar, S., Maiti, J. (2022). Multivariate Deep Learning Model with Ensemble Pruning for Time Series Forecasting. In: Giri, D., Raymond Choo, KK., Ponnusamy, S., Meng, W., Akleylek, S., Prasad Maity, S. (eds) Proceedings of the Seventh International Conference on Mathematics and Computing . Advances in Intelligent Systems and Computing, vol 1412. Springer, Singapore. https://doi.org/10.1007/978-981-16-6890-6_24

Download citation

Publish with us

Policies and ethics

Search

Navigation