Affiliation:
1. College of Mathematics and Systems Science, Xinjiang University, Urumqi, PR China
Abstract
In this study, an innovative approach that combines least square support vector regression (LSSVR) with uncertainty theory to enhance its performance in dealing with low-quality or imprecise data from real-world be proposed. The resulting model, called uncertain least square support vector regression (ULSSVR), incorporates chance constraints and simplified parameter selection, which are critical to handle imprecise observations. A numerical algorithm called the conjugate residual method (CR) is introduced to reduce the computational complexity of the model solution. The experimental results using both small and medium-sized datasets demonstrate the superior performance of ULSSVR in terms of prediction accuracy and generalization ability compared to other models such as uncertain support vector regression (USVR), uncertain linear lodel, uncertain polynomial model, and uncertain growth models. ULSSVR not only improves prediction accuracy by at least 28.49% but also demonstrates faster computational speed. Overall, ULSSVR presents a promising solution for data science and internet applications where dealing with imprecise and low-quality data is a common challenge.
Subject
Artificial Intelligence,General Engineering,Statistics and Probability
Reference18 articles.
1. Least squares support vector machineclassifiers;Suykens;Neural Processing Letters,1999
2. Support vector method forfunction approximation, regression estimation, and signalprocessing;Vapnik;Advances in Neural Information Processing Systems,1997
3. Methods of conjugate gradients forsolving linear systems;Hestenes;Journal of Research of the NationalBureau of Standards,1952
4. Recurrent least squares support vectormachines;Suykens;IEEE Transactions on Circuits And Systems Part IFundamental Theory And Applications,2000
5. Evolving least squares supportvector machines for stock market trend mining;Yu;IEEETransactions on Evolutionary Computation,2009