Residual Analysis and Combination of Embedding Theorem and Artificial Intelligence in Chaotic Time Series Forecasting

Ardalani-Farsa, Muhammad; Zolfaghari, Saeed

doi:10.1080/08839514.2011.529263

Cited by 27 publications

(4 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hybrid Elman-NARX neural networks have been used for chaotic time-series prediction that produced exceptional results with the benchmark datasets [31]. Similar method was also used for backpropagation network with residual analysis that showed competitive results [32]. Type-2 fuzzy neural networks [33] have also been recently proposed for time-series prediction that employs weight update using backpropagation.…”

Section: A Computational Intelligence and Neuroevolution For Time-sementioning

confidence: 98%

Competition and Collaboration in Cooperative Coevolution of Elman Recurrent Neural Networks for Time-Series Prediction

Chandra

2015

IEEE Trans. Neural Netw. Learning Syst.

148

View full text Add to dashboard Cite

Collaboration enables weak species to survive in an environment where different species compete for limited resources. Cooperative coevolution (CC) is a nature-inspired optimization method that divides a problem into subcomponents and evolves them while genetically isolating them. Problem decomposition is an important aspect in using CC for neuroevolution. CC employs different problem decomposition methods to decompose the neural network training problem into subcomponents. Different problem decomposition methods have features that are helpful at different stages in the evolutionary process. Adaptation, collaboration, and competition are needed for CC, as multiple subpopulations are used to represent the problem. It is important to add collaboration and competition in CC. This paper presents a competitive CC method for training recurrent neural networks for chaotic time-series prediction. Two different instances of the competitive method are proposed that employs different problem decomposition methods to enforce island-based competition. The results show improvement in the performance of the proposed methods in most cases when compared with standalone CC and other methods from the literature.

show abstract

Section: A Computational Intelligence and Neuroevolution For Time-sementioning

confidence: 98%

Competition and Collaboration in Cooperative Coevolution of Elman Recurrent Neural Networks for Time-Series Prediction

Chandra

2015

IEEE Trans. Neural Netw. Learning Syst.

148

View full text Add to dashboard Cite

show abstract

“…In some events, the residuals show a high degree of correlation and demonstrate chaotic behaviour. Therefore, The content of the current chapter has been presented at the 29th International Symposium on Forecasting [199], submitted to Applied Artificial Intelligence Journal [200], and published in the Proceedings of the Industrial Engineering Research…”

Section: Chapter Chaotic Time Series Forecasting With Residual Analysis Using Ensemble Neural Networkmentioning

confidence: 99%

Chaotic time series forecasting with residual analysis using synergy of ensemble neural networks and Taguchi's design of experiments

Ardalani-Farsa¹

2021

Preprint

Self Cite

View full text Add to dashboard Cite

This dissertation aims to develop an effective and practical method to forecast chaotic time series. Chaotic behaviour has been observed in the areas of marketing, stock markets, supply chain management, foreign exchange rates, weather forecasting and many others. An effective forecasting model can reduce the potential risks and uncertainty and facilitate planning and decision making in chaotic systems. In this study, residual analysis using a combination of the embedding theorem and ensemble artificial neural networks is adopted to forecast chaotic time series. Based on the embedding theorem, the embedding parameters are determined and the time series is reconstructed into proper phase space points. The embedded phase space points are fed into the first neural network and trained. The weights and biases are kept to predict the future values of phase space points and accordingly to obtain future values of chaotic time series. The residual of the predicted time series is further analyzed; and, if a chaotic behaviour is observed, then the residuals are processed as a new chaotic time series and predicted. This iterative residual analysis can be repeated several times depending on the desired accuracy level and computational efficiency. Finally, the last neural network is trained using neural networks' result values of the time series and the residuals as input and the original time series as output. The initial weights and biases of the neural networks are improved using genetic algorithms. Taguchi's design of experiments is adopted to identify appropriate factor-level combinations to improve the result of the proposed forecasting method. A systematic approach is proposed to improve the combination of ensemble artificial neural networks and their parameters. The proposed methodology is applied to a number of benchmark and some real life chaotic time series. In addition, the proposed forecasting method has been applied to financial sector time series, namely, the stock markets and foreign exchange rates. The experimental results confirm that the proposed method can predict the chaotic time series more effectively in terms of error indices when compared with other forecasting methods in the literature.

show abstract

“…Artificial Intelligence within the supply chain context often serves to solve the industrial problems inherent within these systems, such as to do with operation synchronization, collaboration and distribution. Chaotic time series refers to deterministic systems with significant levels of complexity, with the prediction of these series applying to supply chain management practices [111].…”

Section: Artificial Intelligence-enabled Applicationsmentioning

confidence: 99%

Supply Chain 4.0: A Survey of Cyber Security Challenges, Solutions and Future Directions

2020

View full text Add to dashboard Cite

Supply chain 4.0 denotes the fourth revolution of supply chain management systems, integrating manufacturing operations with telecommunication and Information Technology processes. Although the overarching aim of supply chain 4.0 is the enhancement of production systems within supply chains, making use of global reach, increasing agility and emerging technology, with the ultimate goal of increasing efficiency, timeliness and profitability, Supply chain 4.0 suffers from unique and emerging operational and cyber risks. Supply chain 4.0 has a lack of semantic standards, poor interoperability, and a dearth of security in the operation of its manufacturing and Information Technology processes. The technologies that underpin supply chain 4.0 include blockchain, smart contracts, applications of Artificial Intelligence, cyber-physical systems, Internet of Things and Industrial Internet of Things. Each of these technologies, individually and combined, create cyber security issues that should be addressed. This paper explains the nature of the military supply chains 4.0 and how it uniquely differs from the commercial supply chain, revealing their strengths, weaknesses, dependencies and the fundamental technologies upon which they are built. This encompasses an assessment of the cyber risks and opportunities for research in the field, including consideration of connectivity, sensing and convergence of systems. Current and emerging semantic models related to the standardization, development and safety assurance considerations for implementing new technologies into military supply chains 4.0 are also discussed. This is examined from a holistic standpoint and through technology-specific lenses to determine current states and implications for future research directions.

show abstract

Residual Analysis and Combination of Embedding Theorem and Artificial Intelligence in Chaotic Time Series Forecasting

Cited by 27 publications

References 36 publications

Competition and Collaboration in Cooperative Coevolution of Elman Recurrent Neural Networks for Time-Series Prediction

Competition and Collaboration in Cooperative Coevolution of Elman Recurrent Neural Networks for Time-Series Prediction

Chaotic time series forecasting with residual analysis using synergy of ensemble neural networks and Taguchi's design of experiments

Supply Chain 4.0: A Survey of Cyber Security Challenges, Solutions and Future Directions

Contact Info

Product

Resources

About