Large-scale pinball twin support vector machines

Abstract

Twin support vector machines (TWSVMs) have been shown to be effective classifiers for a range of pattern classification tasks. However, the TWSVM formulation suffers from a range of shortcomings: (i) TWSVM uses hinge loss function which renders it sensitive to dataset outliers (noise sensitivity). (ii) It requires a matrix inversion calculation in the Wolfe-dual formulation which is intractable for datasets with large numbers of features/ samples. (iii) TWSVM minimizes the empirical risk instead of the structural risk in its formulation with the consequent risk of overfitting. This paper proposes a novel large scale pinball twin support vector machines (LPTWSVM) to address these shortcomings. The proposed LPTWSVM model firstly utilizes the pinball loss function to achieve a high level of noise insensitivity, especially in relation to data with substantial feature noise. Secondly, and most significantly, the proposed LPTWSVM formulation eliminates the need to calculate inverse matrices in the dual problem (which apart from being very computationally demanding may not be possible due to matrix singularity). Further, LPTWSVM does not employ kernel-generated surfaces for the non-linear case, instead using the kernel trick directly; this ensures that the proposed LPTWSVM is a fully modular kernel approach in contrast to the original TWSVM. Lastly, structural risk is explicitly minimized in LPT-WSVM with consequent improvement in classification accuracy (we explicitly analyze the properties of classification accuracy and noise insensitivity of the proposed LPTWSVM). Experiments on benchmark datasets show that the proposed LPTWSVM model may be effectively deployed on large datasets and that it exhibits similar or better performance on most datasets in comparison to relevant baseline methods.

GSA-KELM-KF: A Hybrid Model for Short-Term Traffic Flow Forecasting

“…where α = (γI + ϕ T ϕ) −1 Y is the coefficient matrix and k(x) = φ(x)ϕ T . The kernel trick [33] can be described by φ(x 1 )φ(x 2 ) T =κ(x 1 , x 2 ). Therefore, having…”

Estimation and Analysis of Building Costs Using Artificial Intelligence Support Vector Machine

“…An example of how neural network architectures may be utilised to get the best generalisation is the k-fold cross-validation approach. In the pertinent literature, 3 and ten-fold cross-validation approaches were advised to estimate practical applications [24].…”

Ecological Architectural Design in Nature Conservation Environment Relying on Support Vector Machines

“…. Some scholars analyzed the building energy-saving measures applicable to a certain region through field research and study in three major aspects: building planning and layout design, envelope heat insulation and sun-shading design and ventilation design, and the results showed that rural houses should be planned and designed as a whole, and the building body coefficient and orientation should be designed according to the actual local conditions; improvements in heat insulation and sun-shading of building exterior walls, roofs and exterior windows need to be strengthened to reduce the energy consumption of building operation; try to adopt the principle of natural ventilation to regulate the indoor temperature of buildings, thus reducing the energy consumption of indoor air conditioning [4,5]. Taking a village as an example, some scholars focused on the impact of the construction of a coastal wind farm on the economic development of the surrounding countryside, and found that the target requirements of economic efficiency, environmental sustainability, and security of supply can be achieved when the installation of wind and solar energy is configured in an optimal combination [6].…”