Probabilistic prediction with locally weighted jackknife predictive system

Complex & Intelligent Systems - Tập 9 - Trang 5761-5778 - 2023
Di Wang1,2, Ping Wang1,2, Pingping Wang3, Cong Wang1,2, Zhen He4, Wei Zhang4
1School of Electrical and Information Engineering, Tianjin University, Tianjin, People’s Republic of China
2Joint Laboratory of Intelligent Identification and Nowcasting Service for Convective System, CMA Public Meteorological Service Center, Beijing, People’s Republic of China
3Qingdao Academy of Chinese Medical Science, Shandong University of Traditional Chinese Medicine, Qingdao, People’s Republic of China
4College of Management and Economics, Tianjin University, Tianjin, People’s Republic of China

Tóm tắt

Probabilistic predictions for regression problems are more popular than point predictions and interval predictions, since they contain more information for test labels. Conformal predictive system is a recently proposed non-parametric method to do reliable probabilistic predictions, which is computationally inefficient due to its learning process. To build faster conformal predictive system and make full use of training data, this paper proposes the predictive system based on locally weighted jackknife prediction approach. The theoretical property of our proposed method is proved with some regularity assumptions in the asymptotic setting, which extends our earlier theoretical researches from interval predictions to probabilistic predictions. In the experimental section, our method is implemented based on our theoretical analysis and its comparison with other predictive systems is conducted using 20 public data sets. The continuous ranked probability scores of the predictive distributions and the performance of the derived prediction intervals are compared. The better performance of our proposed method is confirmed with Wilcoxon tests. The experimental results demonstrate that the predictive system we proposed is not only empirically valid, but also provides more information than the other comparison predictive systems.

Tài liệu tham khảo

MT Abdulkhaleq TA Rashid A Alsadoon 2022 Harmony search: current studies and uses on healthcare systems Artif Intell Med 131 102348 https://doi.org/10.1016/j.artmed.2022.102348

MT Abdulkhaleq TA Rashid BA Hassan 2023 Fitness dependent optimizer with neural networks for COVID-19 patients Comput Methods Programs Biomed Update 3 100090 https://doi.org/10.1016/j.cmpbup.2022.100090

JM Abdullah TA Rashid BB Maaroof 2023 Multi-objective fitness-dependent optimizer algorithm Neural Comput Appl https://doi.org/10.1007/s00521-023-08332-3

J Alcala-Fdez A Fernandez J Luengo 2011 KEEL data-mining software tool: data set repository, integration of algorithms and experimental analysis framework J Mult-Valued Log Soft Comput 17 2–3 255 287 https://doi.org/10.1016/j.jlap.2009.12.002

Asuncion A, Newman D (2007) UCI machine learning repository Irvine. Retrieved from http://www.ics.uci.edu/~mlearn/MLRepository.html. Accessed 01 Jan 2013

V Balasubramanian S-S Ho V Vovk 2014 Conformal prediction for reliable machine learning: theory, adaptations and applications Morgan Kaufmann Publishers Inc. Newnes

Boström H, Linusson H, Löfström T et al (2016) Evaluation of a variance-based nonconformity measure for regression forests. Paper presented at the 5th International Symposium on Conformal and Probabilistic Prediction with Applications, COPA 2016, Madrid, Spain, 9653, pp 75–89

O Bousquet A Elisseeff 2002 Stability and generalization J Mach Learn Res 2 3 499 526 https://doi.org/10.1162/153244302760200704

F Cucker DX Zhou 2007 Learning theory: an approximation theory viewpoint Cambridge monographs on applied and computational mathematics Cambridge University Press

J Derrac S García D Molina 2011 A practical tutorial on the use of nonparametric statistical tests as a methodology for comparing evolutionary and swarm intelligence algorithms Swarm Evol Comput 1 1 3 18 https://doi.org/10.1016/j.swevo.2011.02.002

T Gneiting M Katzfuss 2014 Probabilistic forecasting Ann Rev Stat Appl 1 1 125 151 https://doi.org/10.1146/annurev-statistics-062713-085831

G Huang H Zhou X Ding 2012 Extreme learning machine for regression and multiclass classification IEEE Trans Syst Man Cybernetics Part B (Cybernetics) 42 2 513 529 https://doi.org/10.1109/TSMCB.2011.2168604

Y LeCun Y Bengio G Hinton 2015 Deep learning Nature 521 7553 436 444 https://doi.org/10.1038/nature14539

J Lei M G’Sell A Rinaldo 2018 Distribution-free predictive inference for regression J Am Stat Assoc 113 523 1094 1111 https://doi.org/10.1080/01621459.2017.1307116

Z Li F Liu W Yang 2022 A survey of convolutional neural networks: analysis, applications, and prospects IEEE Trans Neural Netw Learn Syst 33 12 6999 7019 https://doi.org/10.1109/TNNLS.2021.3084827

BB Maaroof TA Rashid JM Abdulla 2022 Current studies and applications of shuffled frog leaping algorithm: a review Arch Computat Methods Eng 29 5 3459 3474 https://doi.org/10.1007/s11831-021-09707-2

A Mahmoodzadeh HR Nejati M Mohammadi 2022 Forecasting tunnel boring machine penetration rate using LSTM deep neural network optimized by grey wolf optimization algorithm Expert Syst Appl 209 118303 https://doi.org/10.1016/j.eswa.2022.118303

Melluish T, Saunders C, Nouretdinov I et al (2001) Comparing the Bayes and typicalness frameworks. Paper presented at the 12th European Conference on Machine Learning, ECML 2001, Freiburg, Germany, 2167, pp 360–371

MR Mohebbian HR Marateb KA Wahid 2023 Semi-supervised active transfer learning for fetal ECG arrhythmia detection Comput Methods Programs Biomed Update 3 100096 https://doi.org/10.1016/j.cmpbup.2023.100096

H Papadopoulos 2008 Inductive conformal prediction: theory and application to neural networks P Fritzsche Eds Tools in artificial intelligence IntechOpen London https://doi.org/10.5772/6078

Rahimi A, Recht B (2007) Random features for large-scale kernel machines. Paper presented at the Advances in Neural Information Processing Systems 20 (NIPS 2007), Vancouver, British Columbia, Canada, 3 (4): 1177–1184

Rasmussen CE, Neal RM, Hinton G et al. Delve data for evaluating learning in valid experiments, 1995–1996. Retrieved from: https://www.cs.toronto.edu/~delve/. Accessed 01 Mar 2003

A Sayeed Y Choi J Jung 2023 A deep convolutional neural network model for improving WRF simulations IEEE Trans Neural Netw Learn Syst 34 2 750 760 https://doi.org/10.1109/TNNLS.2021.3100902

J Schmidhuber 2015 Deep learning in neural networks: an overview Neural Netw 61 85 117 https://doi.org/10.1016/j.neunet.2014.09.003

T Schweder NL Hjort 2016 Confidence, likelihood, probability 41 Cambridge University Press Cambridge

J Shao 2003 Mathematical statistics Springer Science and Business Media New York

J Shen RY Liu M-g Xie 2018 Prediction with confidence—a general framework for predictive inference J Statist Plan Inference 195 126 140 https://doi.org/10.1016/j.jspi.2017.09.012

Steinberger L, Leeb H (2016) Leave-one-out prediction intervals in linear regression models with many variables. arXiv e-prints, arXiv:1602.05801. https://doi.org/10.48550/arXiv.1602.05801

AW Vaart van der 2000 Asymptotic statistics 3 Cambridge University Press Cambridge

V Vovk 2015 Cross-conformal predictors Ann Math Artif Intell 74 1 9 28 https://doi.org/10.1007/s10472-013-9368-4

Vovk V (2019) Universally consistent conformal predictive distributions. Paper presented at the Proceedings of the Eighth Symposium on Conformal and Probabilistic Prediction and Applications, 105, pp 105-122

V Vovk A Gammerman G Shafer 2005 Algorithmic learning in a random world Springer Science and Business Media New York

Vovk V, Nouretdinov I, Manokhin V et al (2018) Conformal Predictive Distributions with Kernels. Paper presented at the International Conference Commemorating the 40th Anniversary of Emmanuil Braverman's Decease, Boston, MA, USA, 11100, pp 103–121

Vovk V, Nouretdinov I, Manokhin V et al (2018) Cross-conformal predictive distributions. Paper presented at the Proceedings of the Seventh Workshop on Conformal and Probabilistic Prediction and Applications, 91, pp 37–51

Vovk V, Petej I, Toccaceli P et al (2020) Conformal calibrators. Paper presented at the Proceedings of the Ninth Symposium on Conformal and Probabilistic Prediction and Applications, Proceedings of Machine Learning Research, 128, pp 84–99

D Wang P Wang J Shi 2018 A fast and efficient conformal regressor with regularized extreme learning machine Neurocomputing 304 1 11 https://doi.org/10.1016/j.neucom.2018.04.012

D Wang P Wang Y Yuan 2020 A fast conformal predictive system with regularized extreme learning machine Neural Netw 126 347 361 https://doi.org/10.1016/j.neunet.2020.03.022

D Wang P Wang S Zhuang 2020 Asymptotic analysis of locally weighted jackknife prediction Neurocomputing 417 10 22 https://doi.org/10.1016/j.neucom.2020.07.074

L Wasserman 2006 All of nonparametric statistics Springer Science and Business Media New York

Werner H, Carlsson L, Ahlberg E et al (2020) Evaluating different approaches to calibrating conformal predictive systems. Paper presented at the Proceedings of the Ninth Symposium on Conformal and Probabilistic Prediction and Applications, 128, pp 134–150

Thông tin
Thông tin xuất bản

Complex & Intelligent Systems

Tập 9

5761-5778

Thông tin tác giả