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.

Efficient and High-quality Recommendations via Momentum-incorporated Parallel Stochastic Gradient Descent-Based Learning

A recommender system(RS)relying on latent factor analysis usually adopts stochastic gradient descent(SGD)as its learning algorithm.However,owing to its serial mechanism,an SGD algorithm suffers from low efficiency and scalability when handling large-scale industrial problems.Aiming at addressing this issue,this study proposes a momentum-incorporated parallel stochastic gradient descent(MPSGD)algorithm,whose main idea is two-fold:a)implementing parallelization via a novel datasplitting strategy,and b)accelerating convergence rate by integrating momentum effects into its training process.With it,an MPSGD-based latent factor(MLF)model is achieved,which is capable of performing efficient and high-quality recommendations.Experimental results on four high-dimensional and sparse matrices generated by industrial RS indicate that owing to an MPSGD algorithm,an MLF model outperforms the existing state-of-the-art ones in both computational efficiency and scalability.

Classification of Short Time Series in Early Parkinson’s Disease With Deep Learning of Fuzzy Recurrence Plots

There are many techniques using sensors and wearable devices for detecting and monitoring patients with Parkinson’s disease(PD).A recent development is the utilization of human interaction with computer keyboards for analyzing and identifying motor signs in the early stages of the disease.Current designs for classification of time series of computer-key hold durations recorded from healthy control and PD subjects require the time series of length to be considerably long.With an attempt to avoid discomfort to participants in performing long physical tasks for data recording,this paper introduces the use of fuzzy recurrence plots of very short time series as input data for the machine training and classification with long short-term memory(LSTM)neural networks.Being an original approach that is able to both significantly increase the feature dimensions and provides the property of deterministic dynamical systems of very short time series for information processing carried out by an LSTM layer architecture,fuzzy recurrence plots provide promising results and outperform the direct input of the time series for the classification of healthy control and early PD subjects.

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.

政策文本计量视角下的全民阅读政策扩散特征

加强全民阅读政策扩散研究,了解全民阅读政策扩散的特征及影响,有利于增强全民阅读政策制定和发布的科学性,提升全民阅读政策实施效果。文章以我国全民阅读政策文本为样本,运用时序分析法和社会网络分析法梳理政策参照关系,测量政策扩散的4个维度:扩散强度、扩散广度、扩散速度和扩散方向,分析政策扩散特征。研究发现:全民阅读政策扩散呈现时序性聚集分布特征,集中在2012-2017年;法律类全民阅读政策在扩散强度、扩散广度和扩散速度方面均处于领先地位,具有绝对的权威性和指导性,其次为规划类和决定类,最低的是意见类、通知类和方案类;全民阅读政策存在自上而下扩散和平行扩散两个扩散方向,中央政策以自上而下扩散为主,地方政策以平行扩散为主。文章从建立健全全民阅读政策发布和扩散体系、选择合适的政策类型和发布机构以及打通全民阅读政策的垂直扩散路径3个方面提出优化建议。

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.

A Survey of Game Theory as Applied to Social Networks

Social network services can not only help people form relationships and make new friends and partners,but also assist in processing personal information,sharing knowledge,and managing social relationships.Social networks achieve valuable communication and collaboration,bring additional business opportunities,and have great social value.Research on social network problems is effective by using assumption,definition,analysis,modeling,and optimization strategies.In this paper,we survey the existing problems of game theory applied to social networks and classify their application scenarios into four categories:information diffusion,behavior analysis,community detection,and information security.Readers can clearly master knowledge application in every category.Finally,we discuss certain limitations of game theory on the basis of research in recent years and propose future directions of social network research.

An Improved Algorithm for Optimizing MapReduce Based on Locality and Overlapping

MapReduce is currently the most popular programming model for big data processing, and Hadoop is a weU-known MapReduce implementation platform. However, Hadoop jobs suffer from imbalanced workloads during the reduce phase and inefficiently utilize the available computing and network resources. In some cases, these problems lead to serious performance degradation in MapReduce jobs. To resolve these problems, in this paper, we propose two algorithms, the Locality-Based Balanced Schedule （LBBS） and Overlapping-Based Resource Utilization （OBRU）, that optimize the Locality-Enhanced Load Balance （LELB） and the Map, Local reduce, Shuffle, and final Reduce （MLSR） phases. The LBBS collects partition information from input data during the map phase and generates balanced schedule plans for the reduce phase. OBRU is responsible for using computing and network resources efficiently by overlapping the local reduce, shuffle, and final reduce phases. Experimental results show that the LBBS and OBRU algorithms yield significant improvements in load balancing. When LBBS and OBRU are applied, job performance increases by 15% from that of models using LELB and MLSR.

Evolutionary Cryptography Theory-Based Generating Method for Secure ECs

Ant Colony Optimization （AGO） has the character of positive feedback, distributed searching, and greedy searching. It is applicable to optimization grouping problems. Traditional cryptographic research is mainly based on pure mathematical methods which have complicated theories and algorithm. It seems that there is no relationship between cryptography and ACO. Actually, some problems in cryptography are due to optimization grouping problems that could be improved using an evolutionary algorithm. Therefore, this paper presents a new method of solving secure curve selection problems using ACO. We improved Complex Multiplication （CM） by combining Evolutionary Cryptography Theory with Weber polynomial solutions. We found that ACO makes full use of valid information generated from factorization and allocates computing resource reasonably. It greatly increases the performance of Weber polynomial solutions. Compared with traditional CM, which can only search one root once time, our new method searches all roots of the polynomial once, and the average time needed to search for one root reduces rapidly. The more roots are searched, the more ECs are obtained.

Crystal-KMC： Parallel Software for Lattice Dynamics Monte Carlo Simulation of Metal Materials

Kinetic Monte Carlo （KMC） is a widely used method for studying the evolution of materials at the microcosmic level. At present, while there are many simulation software programs based on this algorithm, most focus on the verification of a certain phenomenon and have no analog-scale requirement, so many are serial in nature. The dynamic Monte Carlo algorithm is implemented using a parallel framework called SPPARKS, but Jt does not support the Embedded Atom Method （EAM） potential, which is commonly used in the dynamic simulation of metal materials. Metal material - the preferred material for most containers and components -- plays an important role in many fields, including construction engineering and transportation. In this paper, we propose and describe the development of a parallel software program called CrystaI-KMC, which is specifically used to simulate the lattice dynamics of metallic materials. This software uses MPI to achieve a parallel multiprocessing mode, which avoid the limitations of serial software in the analog scale. Finally, we describe the use of the paralleI-KMC simulation software CrystaI-KMC in simulating the diffusion of vacancies in iron, and analyze the experimental results. In addition, we tested the performance of CrystaI-KMC in ＂meta -Era＂ supercomputing clusters, and the results show the CrystaI-KMC parallel software to have good parallel speedup and scalability.

Simple Method for Realizing Weil Theorem in Secure ECC Generation

How to quickly compute the number of points on an Elliptic Curve （EC） has been a longstanding challenge. The computational complexity of the algorithm usually employed makes it highly inefficient. Unlike the general EC, a simple method called the Weil theorem can be used to compute the order of an EC characterized by a small prime number, such as the Kobltiz EC characterized by two. The fifteen secure ECs recommended by the National Institute of Standards and Technology （NIST） Digital Signature Standard contain five Koblitz ECs whose maximum base domain reaches 571 bits. Experimental results show that the computation speed decreases for base domains exceeding 600 bits. In this paper, we propose a simple method that combines the Weil theorem with Pascals triangle, which greatly reduces the computational complexity. We have validated the performance of this method for base fields ranging from 2l^100 to 2^1000. Furthermore, this new method can be generalized to any ECs characterized by any small prime number.

Challenges and Opportunities in Algorithmic Solutions for Re-Balancing in Bike Sharing Systems

In recent years,the booming of the Bike Sharing System(BSS)has played an important role in offering a convenient means of public transport.The BSS is also viewed as a solution to the first/last mile connection issue in urban cities.The BSS can be classified into dock and dock-less.However,due to imbalance in bike usage over spatial and temporal domains,stations in the BSS may exhibit overflow(full stations)or underflow(empty stations).In this paper,we will take a holistic view of the BSS design by examining the following four components:system design,system prediction,system balancing,and trip advisor.We will focus on system balancing,addressing the issue of overflow/underflow.We will look at two main methods of bike re-balancing:with trucks and with workers.Discussion on the other three components that are related to system balancing will also be given.Specifically,we will study various algorithmic solutions with the availability of data in spacial and temporal domains.Finally,we will discuss several key challenges and opportunities of the BSS design and applications as well as the future of dock and dock-less BSS in a bigger setting of the transportation system.

Approximating Special Social Influence Maximization Problems

Social Influence Maximization Problems(SIMPs)deal with selecting k seeds in a given Online Social Network(OSN)to maximize the number of eventually-influenced users.This is done by using these seeds based on a given set of influence probabilities among neighbors in the OSN.Although the SIMP has been proved to be NP-hard,it has both submodular(with a natural diminishing-return)and monotone(with an increasing influenced users through propagation)that make the problem suitable for approximation solutions.However,several special SIMPs cannot be modeled as submodular or monotone functions.In this paper,we look at several conditions under which non-submodular or non-monotone functions can be handled or approximated.One is a profit-maximization SIMP where seed selection cost is included in the overall utility function,breaking the monotone property.The other is a crowd-influence SIMP where crowd influence exists in addition to individual influence,breaking the submodular property.We then review several new techniques and notions,including double-greedy algorithms and the supermodular degree,that can be used to address special SIMPs.Our main results show that for a specific SIMP model,special network structures of OSNs can help reduce its time complexity of the SIMP.

Latent Co-interests' Relationship Prediction

With the development of the social media and Internet, discovering latent information from massive information is becoming particularly relevant to improving user experience. Research efforts based on preferences and relationships between users have attracted more and more attention. Predictive problems, such as inferring friend relationship and co-author relationship between users have been explored. However, many such methods are based on analyzing either node features or the network structures separately, few have tried to tackle both of them at the same time. In this paper, in order to discover latent co-interests＇ relationship, we not only consider users＇ attributes but network information as well. In addition, we propose an Interest-based Factor Graph Model （I-FGM） to incorporate these factors. Experiments on two data sets （bookmarking and music network） demonstrate that this predictive method can achieve better results than the other three methods （ANN, NB, and SVM）.