A deep convolutional neural network for diabetic retinopathy detection via mining local and long-range dependence

Diabetic retinopathy(DR),the main cause of irreversible blindness,is one of the most common complications of diabetes.At present,deep convolutional neural networks have achieved promising performance in automatic DR detection tasks.The convolution operation of methods is a local cross-correlation operation,whose receptive field de-termines the size of the local neighbourhood for processing.However,for retinal fundus photographs,there is not only the local information but also long-distance dependence between the lesion features(e.g.hemorrhages and exudates)scattered throughout the whole image.The proposed method incorporates correlations between long-range patches into the deep learning framework to improve DR detection.Patch-wise re-lationships are used to enhance the local patch features since lesions of DR usually appear as plaques.The Long-Range unit in the proposed network with a residual structure can be flexibly embedded into other trained networks.Extensive experimental results demon-strate that the proposed approach can achieve higher accuracy than existing state-of-the-art models on Messidor and EyePACS datasets.

A multi-feature-based intelligent redundancy elimination scheme for cloud-assisted health systems

Redundancy elimination techniques are extensively investigated to reduce storage overheads for cloud-assisted health systems.Deduplication eliminates the redundancy of duplicate blocks by storing one physical instance referenced by multiple duplicates.Delta compression is usually regarded as a complementary technique to deduplication to further remove the redundancy of similar blocks,but our observations indicate that this is disobedient when data have sparse duplicate blocks.In addition,there are many overlapped deltas in the resemblance detection process of post-deduplication delta compression,which hinders the efficiency of delta compression and the index phase of resemblance detection inquires abundant non-similar blocks,resulting in inefficient system throughput.Therefore,a multi-feature-based redundancy elimination scheme,called MFRE,is proposed to solve these problems.The similarity feature and temporal locality feature are excavated to assist redundancy elimination where the similarity feature well expresses the duplicate attribute.Then,similarity-based dynamic post-deduplication delta compression and temporal locality-based dynamic delta compression discover more similar base blocks to minimise overlapped deltas and improve compression ratios.Moreover,the clustering method based on block-relationship and the feature index strategy based on bloom filters reduce IO overheads and improve system throughput.Experiments demonstrate that the proposed method,compared to the state-of-the-art method,improves the compression ratio and system throughput by 9.68%and 50%,respectively.

An Enhanced GAN for Image Generation

Generative adversarial networks(GANs)with gaming abilities have been widely applied in image generation.However,gamistic generators and discriminators may reduce the robustness of the obtained GANs in image generation under varying scenes.Enhancing the relation of hierarchical information in a generation network and enlarging differences of different network architectures can facilitate more structural information to improve the generation effect for image generation.In this paper,we propose an enhanced GAN via improving a generator for image generation(EIGGAN).EIGGAN applies a spatial attention to a generator to extract salient information to enhance the truthfulness of the generated images.Taking into relation the context account,parallel residual operations are fused into a generation network to extract more structural information from the different layers.Finally,a mixed loss function in a GAN is exploited to make a tradeoff between speed and accuracy to generate more realistic images.Experimental results show that the proposed method is superior to popular methods,i.e.,Wasserstein GAN with gradient penalty(WGAN-GP)in terms of many indexes,i.e.,Frechet Inception Distance,Learned Perceptual Image Patch Similarity,Multi-Scale Structural Similarity Index Measure,Kernel Inception Distance,Number of Statistically-Different Bins,Inception Score and some visual images for image generation.

Sparse representation scheme with enhanced medium pixel intensity for face recognition

Sparse representation is an effective data classification algorithm that depends on the known training samples to categorise the test sample.It has been widely used in various image classification tasks.Sparseness in sparse representation means that only a few of instances selected from all training samples can effectively convey the essential class-specific information of the test sample,which is very important for classification.For deformable images such as human faces,pixels at the same location of different images of the same subject usually have different intensities.Therefore,extracting features and correctly classifying such deformable objects is very hard.Moreover,the lighting,attitude and occlusion cause more difficulty.Considering the problems and challenges listed above,a novel image representation and classification algorithm is proposed.First,the authors’algorithm generates virtual samples by a non-linear variation method.This method can effectively extract the low-frequency information of space-domain features of the original image,which is very useful for representing deformable objects.The combination of the original and virtual samples is more beneficial to improve the clas-sification performance and robustness of the algorithm.Thereby,the authors’algorithm calculates the expression coefficients of the original and virtual samples separately using the sparse representation principle and obtains the final score by a designed efficient score fusion scheme.The weighting coefficients in the score fusion scheme are set entirely automatically.Finally,the algorithm classifies the samples based on the final scores.The experimental results show that our method performs better classification than conventional sparse representation algorithms.

Two-view attention-guided convolutional neural network for mammographic image classification

Deep learning has been widely used in the field of mammographic image classification owing to its superiority in automatic feature extraction.However,general deep learning models cannot achieve very satisfactory classification results on mammographic images because these models are not specifically designed for mammographic images and do not take the specific traits of these images into account.To exploit the essential discriminant information of mammographic images,we propose a novel classification method based on a convolutional neural network.Specifically,the proposed method designs two branches to extract the discriminative features from mammographic images from the mediolateral oblique and craniocaudal(CC)mammographic views.The features extracted from the two-view mammographic images contain complementary information that enables breast cancer to be more easily distinguished.Moreover,the attention block is introduced to capture the channel-wise information by adjusting the weight of each feature map,which is beneficial to emphasising the important features of mammographic images.Furthermore,we add a penalty term based on the fuzzy cluster algorithm to the cross-entropy function,which improves the generalisation ability of the classification model by maximising the interclass distance and minimising the intraclass distance of the samples.The experimental results on The Digital database for Screening Mammography INbreast and MIAS mammography databases illustrate that the proposed method achieves the best classification performance and is more robust than the compared state-ofthe-art classification methods.

Application of improved virtual sample and sparse representation in face recognition

Sparse representation plays an important role in the research of face recognition.As a deformable sample classification task,face recognition is often used to test the performance of classification algorithms.In face recognition,differences in expression,angle,posture,and lighting conditions have become key factors that affect recognition accuracy.Essentially,there may be significant differences between different image samples of the same face,which makes image classification very difficult.Therefore,how to build a robust virtual image representation becomes a vital issue.To solve the above problems,this paper proposes a novel image classification algorithm.First,to better retain the global features and contour information of the original sample,the algorithm uses an improved non‐linear image representation method to highlight the low‐intensity and high‐intensity pixels of the original training sample,thus generating a virtual sample.Second,by the principle of sparse representation,the linear expression coefficients of the original sample and the virtual sample can be calculated,respectively.After obtaining these two types of coefficients,calculate the distances between the original sample and the test sample and the distance between the virtual sample and the test sample.These two distances are converted into distance scores.Finally,a simple and effective weight fusion scheme is adopted to fuse the classification scores of the original image and the virtual image.The fused score will determine the final classification result.The experimental results show that the proposed method outperforms other typical sparse representation classification methods.

An Isomerism Learning Model to Solve Time-Varying Problems Through Intelligent Collaboration

Dear Editor,This letter deals with a solution for time-varying problems using an intelligent computational(IC)algorithm driven by a novel decentralized machine learning approach called isomerism learning.In order to meet the challenges of the model’s privacy and security brought by traditional centralized learning models,a private permissioned blockchain is utilized to decentralize the model in order to achieve an effective coordination,thereby ensuring the credibility of the overall model without exposing the specific parameters and solution process.

An activated variable parameter gradient‐based neural network for time‐variant constrained quadratic programming and its applications

This study proposes a novel gradient‐based neural network model with an activated variable parameter,named as the activated variable parameter gradient‐based neural network(AVPGNN)model,to solve time‐varying constrained quadratic programming(TVCQP)problems.Compared with the existing models,the AVPGNN model has the following advantages:(1)avoids the matrix inverse,which can significantly reduce the computing complexity;(2)introduces the time‐derivative of the time‐varying param-eters in the TVCQP problem by adding an activated variable parameter,enabling the AVPGNN model to achieve a predictive calculation that achieves zero residual error in theory;(3)adopts the activation function to accelerate the convergence rate.To solve the TVCQP problem with the AVPGNN model,the TVCQP problem is transformed into a non‐linear equation with a non‐linear compensation problem function based on the Karush Kuhn Tucker conditions.Then,a variable parameter with an activation function is employed to design the AVPGNN model.The accuracy and convergence rate of the AVPGNN model are rigorously analysed in theory.Furthermore,numerical experiments are also executed to demonstrate the effectiveness and superiority of the proposed model.Moreover,to explore the feasibility of the AVPGNN model,appli-cations to the motion planning of a robotic manipulator and the portfolio selection of marketed securities are illustrated.

Background modeling methods in video analysis： A review and comparative evaluation

Foreground detection methods can be applied to efficiently distinguish foreground objects including moving or static objects from back- ground which is very important in the application of video analysis, especially video surveillance. An excellent background model can obtain a good foreground detection results. A lot of background modeling methods had been proposed, but few comprehensive evaluations of them are available. These methods suffer from various challenges such as illumination changes and dynamic background. This paper first analyzed advantages and disadvantages of various background modeling methods in video analysis applications and then compared their performance in terms of quality and the computational cost. The Change detection.Net （CDnet2014） dataset and another video dataset with different envi- ronmental conditions （indoor, outdoor, snow） were used to test each method. The experimental results sufficiently demonstrated the strengths and drawbacks of traditional and recently proposed state-of-the-art background modeling methods. This work is helpful for both researchers and engineering practitioners. Codes of background modeling methods evaluated in this paper are available atwww.yongxu.org/lunwen.html.

Geometric-Spectral Reconstruction Learning for Multi-Source Open-Set Classification With Hyperspectral and LiDAR Data

Dear editor,This letter presents an open-set classification method of remote sensing images(RSIs)based on geometric-spectral reconstruction learning.More specifically,in order to improve the ability of RSI classification model to adapt to the open-set environment,an openset classification method based on geometric and spectral feature fusion is proposed.