Search

Deep networks are widely used in few-shot learning methods, but deep networks suffer from large-scale network parameters and computational effort. Aiming at the above problems, we present a novel few-shot learning method with deep balanced network and acceleration strategy. Firstly, a series of simple linear operations are applied to few original features to obtain the more features. More features are obtained with fewer parameters, thus reducing the network parameters and computational effort. Then the local cross-channel interaction mechanism without dimensionality reduction is used to further improve the performance with nearly no increase in parameters and computational effort, so as to obtain a deep balanced network to balance performance, parameters, and computational effort. Finally, an acceleration strategy is designed to solve the problem that the gradient update in the deep network takes a tremendous amount of time in new tasks, speeding up the adaptation process. The experimental results of traditional and fine-grained image classification show that the few-shot learning method with deep balanced network can achieve or even exceed the classification accuracy of some existing methods with fewer network parameters and computational effort. The cross-domain experiments further demonstrate the advantages of the method above the domain shift. Simultaneously, the time required for classification in new tasks can be significantly decreased by using the acceleration strategy.

Deep convolutional network is commonly stacked by vast number of nonlinear convolutional layers. Deep fused network can improve the training process of deep convolutional network due to its capability of learning multi-scale representations and of optimizing information flow. However, the depth in a deep fused network does not contribute to the overall performance significantly. Therefore, a deep ensemble network consisting of deep fused network and branch channel is proposed. First, two base networks are combined in a concatenation and fusion manner to generate a deep fused network architecture. Then, an ensemble block with embedded learning mechanisms is formed to improve feature representation power of the model. Finally, the computational efficiency is improved by introducing group convolution without loss of performance. Experimental results on the standard recognition tasks have shown that the proposed network achieves better classification performance and has superior generalization ability compared to the original residual networks.

Most of the existing convolutional neural networks (CNNs) ignore multi-scale features of input image to different extents. Thus they lack robustness to feature scale of the input image, which limits the generalization ability of the model. In addition, on the premise of large-scale data, in order to obtain higher image classification accuracy, CNNs generally require more layers and a huge amount of parameters, resulting in a higher cost of network training. To this end, a Weight-Sharing Multi-Stage Multi-Scale Ensemble Convolutional Neural Network (WSMSMSE-CNN) is proposed in this paper. The input image is pooled several times to obtain multi-scale images and sent to a multi-stage network. Each stage is a multi-layer multi-scale ensemble network consisting of Conv Block, Pooling layer and Dropout layer. Conv Blocks in the same stage are connected by pooling layers while those in different stage but at the same location share the same weights. In this way, multi-scale features of both the same image and scale features of multi-scale images are obtained. In addition, the large-sized convolutional kernel is replaced by a number of consecutive small-sized ones, which not only keep the receptive field unchanged, but also effectively control the number of parameters. Experimental results on CIFAR-10 and CIFAR-100 datasets verify that WSMSMSE-CNN not only has good robustness, but also requires fewer layers to obtain higher classification accuracy.

Domain adaptation learning aims to solve the classification problems of unlabeled target domain by using rich labeled samples in source domain, but there are three main problems: negative transfer, under adaptation and under fitting. Aiming at these problems, a domain adaptation network based on hypergraph regularized denoising autoencoder (DAHDA) is proposed in this paper. To better fit the data distribution, the network is built with denoising autoencoder which can extract more robust feature representation. In the last feature and classification layers, the marginal and conditional distribution matching terms between domains are obtained via maximum mean discrepancy measurement to solve the under adaptation problem. To avoid negative transfer, the hypergraph regularization term is introduced to explore the high-order relationships among data. The classification performance of the model can be improved by preserving the statistical property and geometric structure simultaneously. Experimental results of 16 cross-domain transfer tasks verify that DAHDA outperforms other state-of-the-art methods.

In this paper, a novel semi-supervised feature extraction algorithm, i.e., semi-supervised transfer discriminant analysis (STDA) with knowledge transfer capability is proposed, based on the traditional algorithm that cannot get adapted in the change of the learning environment. By using both the pseudo label information from target domain samples and the actual label information from source domain samples in the label iterative refinement process, not only the between-class scatter is maximized while that within-class scatter is minimized, but also the original space structure is maintained via Laplacian matrix, and the distribution difference is reduced by using maximum mean discrepancy as well. Moreover, semi-supervised transfer discriminant analysis based on cross-domain mean constraint (STDA-CMC) is proposed. In this algorithm, the cross-domain mean constraint term is incorporated into STDA, such that knowledge transfer between domains is facilitated by making source and target samples after being projected are located more closely in the low-dimensional feature subspace. The proposed algorithm is proved efficient and feasible from experiments on several datasets.

In this paper, a review of parameter optimization methods of pulse-coupled neural networks (PCNNs) is presented. Considering that PCNN has been used in image processing for many years, the aim of this paper was to provide an overview of the work that has been done and to serve as a useful reference for those who are looking for PCNN parameter optimization methods and those who are researching PCNN applications for a specific field. This paper first briefly reviews the PCNN model, including the standard PCNN and several variants of PCNN. Then, we emphasize the optimization methods for PCNN’s parameters, describing three types of parameter optimization methods in detail. Next, the paper summarizes the applications of the optimized models of PCNN with adaptive parameters in image segmentation, image fusion, image denoising and edge detection.

It is urgent to diagnose colorectal cancer in the early stage. Some feature genes which are important to colorectal cancer development have been identified. However, for the early stage of colorectal cancer, less is known about the identity of specific cancer genes that are associated with advanced clinical stage. In this paper, we conducted a feature extraction method named Optimal Mean based Block Robust Feature Extraction method (OMBRFE) to identify feature genes associated with advanced colorectal cancer in clinical stage by using the integrated colorectal cancer data. Firstly, based on the optimal mean and L2,1-norm, a novel feature extraction method called Optimal Mean based Robust Feature Extraction method (OMRFE) is proposed to identify feature genes. Then the OMBRFE method which introduces the block ideology into OMRFE method is put forward to process the colorectal cancer integrated data which includes multiple genomic data: copy number alterations, somatic mutations, methylation expression alteration, as well as gene expression changes. Experimental results demonstrate that the OMBRFE is more effective than previous methods in identifying the feature genes. Moreover, genes identified by OMBRFE are verified to be closely associated with advanced colorectal cancer in clinical stage.

The effect of the copper content on properties of electroless Ni-Cu-P coating on heat exchanger surface was investigated, such as adhesion strength and surface characteristic, and anti-fouling property, which were considered to mitigate the accumulation of mineral fouling in the heat exchangers. The electroless ternary Ni-Cu-P coatings with different copper content were prepared on mild steel (1015) substrate surfaces by adjusting process parameters. Surface morphologies of coating and adhesion strength were investigated by using scanning electron microscopy (SEM) and MFT-4000 multifunctional material surface performance instrument, respectively. The results showed that the adhesion strength was improved with the addition of copper in the coating. With the increase of copper content, the deposition rate of ternary Ni-Cu-P coatings was increased, and the boundary of nodular became obvious. Moreover, the surface free energy of ternary Ni-Cu-P coatings was increased with the increase of copper content in the coatings and then decreased when enhancing the copper content further. The further fouling experiments indicated that all the ternary Ni-Cu-P coating surfaces with different copper content inhibited the adhesion of fouling compared with the stainless steel surface. The adhesion weight of fouling was approximately in proportion with the copper addition of ternary Ni-Cu-P coatings, but not the value of surface free energy. The work provides evidence that both adhesion strength and anti-fouling ability should be combined to use when applying surface modification in the field of heat exchanger.

Given recent investigations of gene regulatory networks, an increasing amount of attention is focused on the nonlinearity and randomness in these networks. It has always been assumed that gene regulation is a random process with Gaussian white noise. However, in practice, there is no ideal white noise; therefore results obtained from a model with white noise are not always exactly correct. We constructed a dynamic model of gene regulatory networks based on a first-order stochastic differential equation, which is often used for quantitative analysis of gene regulatory networks. For biological realism, we added a colored noise item, based on a sliding autoregressive model. The abilities of regulatory genes and the intensities of the colored noise item were estimated using an extended recursive least-square algorithm. We applied the model to budding yeast data and reconstructed regulatory networks. Our experimental results showed that the proposed model is suitable for the description of real gene regulatory networks.

In this paper, a Barnes-Godunova-Levin type inequality for the Sugeno integral based on an $( {\alpha,m} )$ -concave function is proved. Some examples are given to illustrate the validity of these inequalities. Finally, several important results, as special cases of an $( {\alpha,m} )$ -concave function, are also obtained.