Search

In this paper, support vector machines (SVMs), least squares SVMs (LSSVMs), relevance vector machines (RVMs), and probabilistic classification vector machines (PCVMs), are compared on sixteen binary and multiclass medical datasets. Particular emphasis is put on the comparison among the commonly used Gaussian radial basis function (GRBF) kernel, and the relatively new generalized min–max (GMM) kernel and exponentiated-GMM (eGMM) kernel. Since most medical decisions involve uncertainty, a postprocessing approach based on Platt’s method and pairwise coupling is employed to produce probabilistic outputs for prediction uncertainty assessment. The extensive empirical study illustrates that the SVM classifier using the tuning-free GMM kernel (SVM-GMM) shows good usability and broad applicability, and exhibits competitive performance against some state-of-the-art methods. These results indicate that SVM-GMM can be used as the first-choice method when selecting an appropriate kernel-based vector machine for medical diagnosis. As an illustration, SVM-GMM efficiently achieves a high accuracy of 98.92% on the thyroid disease dataset consisting of 7200 samples.

To make radial basis function (RBF) networks efficient for large-scale learning tasks, the parallel technique provides a promising way for the construction of multicolumn RBF network (MCRN), where the task to be tackled is decomposed into several subtasks and RBF networks designed for these subtasks are integrated as a parallel structure to obtain the final model. This paper focuses on presenting an efficient design method for MCRN based on improved generalized hybrid constructive (GHC) learning algorithm such that desired performance and high efficiency are guaranteed. Specifically, a minimum difference scheme is firstly introduced to divide a large-scale dataset into several parts with similar distribution. For each subtask, a compact RBF network is designed by improved GHC learning algorithm. By fully considering the inherent properties of RBF networks, a K-nearest potential centers based criterion is established to calculate the output of testing sample. Experiments on some benchmark classification problems are conducted to verify the advantages of the proposed method. In terms of training and testing efficiencies and classification accuracy, it is shown that our model is superior over some existing ones.

In order to study the influences of microstructures on corrosion behavior of double-side friction stir welded 6082Al thick plate. The corrosion behavior was firstly clarified by potentiodynamic pol...

The recognition of license plates is very important for intelligent transportation systems. Generally, the performance of an intelligent recognition algorithm is greatly affected by different shooting angles, illumination conditions and backgrounds of the license plate images. This paper presents a sequence recognition approach for intelligent recognition of Chinese license plates. Firstly, a spatial transformer network (STN) is employed to adjust the inclined and deformed license plates such that all the plates have a uniform orientation and thus are easier to be recognized. Then, an improved convolutional neural network (CNN) is designed to extract sequence features of the rectified license plates. The features of different convolutional layers are integrated as input to a bi-directional recurrent neural network (BRNN), where the character segmentation is not needed. Finally, the recognition is accomplished by the BRNN and connectionist temporal classification (CTC). Due to the lack of adequate Chinese license plates, an effective training method is presented in which the network is pre-trained by sufficiently enough synthetic license plates and is fine-tuned by our collected real Chinese license plates. The experimental results show that our model achieves better recognition accuracy and lower average edit distance than some existing methods.

To evaluate the efficiency of CT-based peritumoral radiomics signatures of clear cell renal cell carcinoma (ccRCC) for malignancy grading in preoperative prediction. 203 patients with pathologically confirmed as ccRCC were retrospectively enrolled in this study. All patients were categorized into training set (n = 122) and validation set (n = 81). For each patient, two types of volumes of interest (VOI) were masked on CT images. One type of VOIs was defined as the tumor mass volume (TMV), which was masked by radiologists delineating the outline of all contiguous slices of the entire tumor, while the other type defined as the peritumoral tumor volume (PTV), which was automatically created by an image morphological method. 1760 radiomics features were calculated from each VOI, and then the discriminative radiomics features were selected by Pearson correlation analysis for reproducibility and redundancy. These selected features were investigated their validity for building radiomics signatures by mRMR feature ranking method. Finally, the top ranked features, which were used as radiomics signatures, were input into a classifier for malignancy grading. The prediction performance was evaluated by receiver operating characteristic (ROC) curve in an independent validation cohort. The radiomics signatures of PTV showed a better performance on malignancy grade prediction of ccRCC with AUC of 0.807 (95% CI 0.800–0.834) in train data and 0.848 (95% CI 0.760–0.936) in validation data, while the radiomics signatures of TMV with AUC of 0.773 (95% CI 0.744–0.802) in train data and 0.810 (95% CI 0.706–0.914) in validation data. The CT-based peritumoral radiomics signature is a potential way to be used as a noninvasive tool to preoperatively predict the malignancy grades of ccRCC.

Accurate preoperative differential diagnosis of fat-poor angiomyolipoma (fp-AML) and clear cell renal cell carcinoma (ccRCC) is essential for proper treatment planning. In this paper, we develop an effective radiomics model for reliable noninvasive discrimination of fp-AML from ccRCC, which incorporates a sophisticated feature selection procedure and a sparse radial basis function neural network (sRBFNN). Specifically, 774 three-dimensional radiomics features are first extracted from contrast-enhanced computed tomography (CECT) images. Pearson’s correlation matrices and Welch’s t-test are used to remove the insignificant features, then sequential forward floating selection method is utilized to select the discriminative features. Finally, the sRBFNN is employed for classification. The radiomics model is examined by leave-one-out cross validation and yields the best performance of 90.00%, 66.67%, 100.0%, and 0.9173 in terms of prediction accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curves, respectively. Furthermore, the reliability of the predictions is verified by evaluating the probabilistic outputs of the sRBFNN. The experimental results demonstrate that the developed radiomics model has great potential in the noninvasive discrimination of fp-AML from ccRCC.

The probabilistic classification vector machine (PCVM) is an effective sparse learning approach for binary classification. This paper presents an extension of the PCVM to the multiclass case, which aims to provide reliable probabilistic outputs by taking advantage of the inherent probabilistic nature of the PCVM. The performance of the proposed multiclass PCVM is evaluated on several benchmark datasets. In particular, the probabilistic outputs are used to assess the confidence in the prediction. The experimental results demonstrate that multiclass PCVMs can make more confident correct predictions than probabilistic multiclass support vector machines and multiclass relevance vector machines.