Search

In this paper, motivate by quantile in the field statistics and bounded linex loss function a novel robust bounded quantile loss is proposed for improving the performance of support vector machine (SVM) and support vector regression (SVR). The bounded quantile loss has some important properties such as asymmetry, non-convexity, which make SVM and SVR based on bounded quantile (BQ-SVM and BQ-SVR) robust to noise. The Fisher consistency and generalization error bound of BQ-SVM guarantees the generalization capability of BQ-SVM. In addition, we derive the influence functions of BQ-SVM and BQ-SVR to show that they are less sensitive to outliers. However, the non-convexity of the proposed bounded quantile makes it difficult to optimize. We utilize the concave-convex procedure (CCCP) technique to solve the proposed models. A host of numerical studies on artificial and benchmark datasets are conducted, and various evaluation criteria were considered to demonstrate the effectiveness and the efficiency of the proposed method. Experimental results indicate that our proposed methods is more robust compare to classical and advanced methods when the dataset contains outliers in both classification and regression applications. • A novel bounded quantile loss (L b q loss) is proposed for robust learning problems. • The support vector machines based methods with L b q loss (BQ-SVM and BQ- SVR) are robust. • The designed ClipDCD-based CCCP algorithm is efficient to solve the BQ-SVM and BQ-SVR. • Numerical and theoretical results demonstrate the effectiveness of BQ-SVM and BQ-SVR. [ABSTRACT FROM AUTHOR]

Optical molecular tomography (OMT) is a potential pre-clinical molecular imaging technique with applications in a variety of biomedical areas, which can provide non-invasive quantitative three-dimensional (3D) information regarding tumor distribution in living animals. The construction of optical transmission models and the application of reconstruction algorithms in traditional model-based reconstruction processes have affected the reconstruction results, resulting in problems such as low accuracy, poor robustness, and long-time consumption. Here, a gates joint locally connected network (GLCN) method is proposed by establishing the mapping relationship between the inside source distribution and the photon density on surface directly, thus avoiding the extra time consumption caused by iteration and the reconstruction errors caused by model inaccuracy. Moreover, gates module was composed of the concatenation and multiplication operators of three different gates. It was embedded into the network aiming at remembering input surface photon density over a period and allowing the network to capture neurons connected to the true source selectively by controlling three different gates. To evaluate the performance of the proposed method, numerical simulations were conducted, whose results demonstrated good performance in terms of reconstruction positioning accuracy and robustness. [ABSTRACT FROM AUTHOR]