Multi-scale cross-domain alignment for person image generation

Person image generation aims to generate images that maintain the original human appearance in different target poses.Recent works have revealed that the critical element in achieving this task is the alignment of appearance domain and pose domain.Previous alignment methods,such as appearance flow warping,correspondence learning and cross attention,often encounter challenges when it comes to producing fine texture details.These approaches suffer from limitations in accurately estimating appearance flows due to the lack of global receptive field.Alternatively,they can only perform cross-domain alignment on high-level feature maps with small spatial dimensions since the computational complexity increases quadratically with larger feature sizes.In this article,the significance of multi-scale alignment,in both low-level and high-level domains,for ensuring reliable cross-domain alignment of appearance and pose is demonstrated.To this end,a novel and effective method,named Multi-scale Crossdomain Alignment(MCA)is proposed.Firstly,MCA adopts global context aggregation transformer to model multi-scale interaction between pose and appearance inputs,which employs pair-wise window-based cross attention.Furthermore,leveraging the integrated global source information for each target position,MCA applies flexible flow prediction head and point correlation to effectively conduct warping and fusing for final transformed person image generation.Our proposed MCA achieves superior performance on two popular datasets than other methods,which verifies the effectiveness of our approach.

Detection of Oscillations in Process Control Loops From Visual Image Space Using Deep Convolutional Networks

Oscillation detection has been a hot research topic in industries due to the high incidence of oscillation loops and their negative impact on plant profitability.Although numerous automatic detection techniques have been proposed,most of them can only address part of the practical difficulties.An oscillation is heuristically defined as a visually apparent periodic variation.However,manual visual inspection is labor-intensive and prone to missed detection.Convolutional neural networks(CNNs),inspired by animal visual systems,have been raised with powerful feature extraction capabilities.In this work,an exploration of the typical CNN models for visual oscillation detection is performed.Specifically,we tested MobileNet-V1,ShuffleNet-V2,Efficient Net-B0,and GhostNet models,and found that such a visual framework is well-suited for oscillation detection.The feasibility and validity of this framework are verified utilizing extensive numerical and industrial cases.Compared with state-of-theart oscillation detectors,the suggested framework is more straightforward and more robust to noise and mean-nonstationarity.In addition,this framework generalizes well and is capable of handling features that are not present in the training data,such as multiple oscillations and outliers.

Acoustic radiation force impulse predicts long-term outcomes in a large-scale cohort:High liver cancer,low comorbidity in hepatitis B virus

BACKGROUND Acoustic radiation force impulse(ARFI)is used to measure liver fibrosis and predict outcomes.The performance of elastography in assessment of fibrosis is poorer in hepatitis B virus(HBV)than in other etiologies of chronic liver disease.AIM To evaluate the performance of ARFI in long-term outcome prediction among different etiologies of chronic liver disease.METHODS Consecutive patients who received an ARFI study between 2011 and 2018 were enrolled.After excluding dual infection,alcoholism,autoimmune hepatitis,and others with incomplete data,this retrospective cohort were divided into hepatitis B(HBV,n=1064),hepatitis C(HCV,n=507),and non-HBV,non-HCV(NBNC,n=391)groups.The indexed cases were linked to cancer registration(1987-2020)and national mortality databases.The differences in morbidity and mortality among the groups were analyzed.RESULTS At the enrollment,the HBV group showed more males(77.5%),a higher prevalence of prediagnosed hepatocellular carcinoma(HCC),and a lower prevalence of comorbidities than the other groups(P<0.001).The HCV group was older and had a lower platelet count and higher ARFI score than the other groups(P<0.001).The NBNC group showed a higher body mass index and platelet count,a higher prevalence of pre-diagnosed non-HCC cancers(P<0.001),especially breast cancer,and a lower prevalence of cirrhosis.Male gender,ARFI score,and HBV were independent predictors of HCC.The 5-year risk of HCC was 5.9%and 9.8%for those ARFI-graded with severe fibrosis and cirrhosis.ARFI alone had an area under the receiver operating characteristic curve(AUROC)of 0.742 for prediction of HCC in 5 years.AUROC increased to 0.828 after adding etiology,gender,age,and platelet score.No difference was found in mortality rate among the groups.CONCLUSION The HBV group showed a higher prevalence of HCC but lower comorbidity that made mortality similar among the groups.Those patients with ARFI-graded severe fibrosis or cirrhosis should receive regular surveillance.

Percolation transitions in edge-coupled interdependent networks with directed dependency links

We propose a model of edge-coupled interdependent networks with directed dependency links(EINDDLs)and develop the theoretical analysis framework of this model based on the self-consistent probabilities method.The phase transition behaviors and parameter thresholds of this model under random attacks are analyzed theoretically on both random regular(RR)networks and Erd¨os-Renyi(ER)networks,and computer simulations are performed to verify the results.In this EINDDL model,a fractionβof connectivity links within network B depends on network A and a fraction(1-β)of connectivity links within network A depends on network B.It is found that randomly removing a fraction(1-p)of connectivity links in network A at the initial state,network A exhibits different types of phase transitions(first order,second order and hybrid).Network B is rarely affected by cascading failure whenβis small,and network B will gradually converge from the first-order to the second-order phase transition asβincreases.We present the critical values ofβfor the phase change process of networks A and B,and give the critical values of p andβfor network B at the critical point of collapse.Furthermore,a cascading prevention strategy is proposed.The findings are of great significance for understanding the robustness of EINDDLs.

X-DB:软硬一体的新型数据库系统

数据库领域经历了3次发展时期:第1个时期起源于Codd提出的关系模型,奠定了数据库理论和系统的基础,并造就了早期的数据库商业巨头IBM DB2,Microsoft SQLServer和Oracle等;第2个时期由互联网的快速发展所推动,催生了NoSQL数据库系统,这一类数据库系统关注于系统可扩展性,但是牺牲了数据库的事务特性和SQL功能;第3个重要时期是以新硬件为基础的现代数据库时期,阿里巴巴数据库系统X-DB便属于这一时期的现代数据库.X-DB基于阿里巴巴大规模业务需求,充分利用新硬件的特性,围绕存储、网络、多核、并行和异构计算进行软硬一体协同设计,同时兼容MySQL生态,重塑关系型数据库体系结构.

计算机视觉技术应用研究综述

为了快速高效地处理图片,视频等信息。文章结合近年来国内外的一些参考文献和资料,选择了视频分析,安防监控和遥感影像等几个常见的应用场景,对当前的视觉技术应用情况进行详细的阐明,并对该领域今后的研究方向提出一些见解。希望此文所做的工作可以为读者带来一些收益和思考。

A parametric bootstrap approach for one-way classification model with skew-normal random effects

In this paper,several properties of one-way classification model with skew-normal random effects are obtained,such as moment generating function,density function and noncentral skew chi-square distribution,etc.Based on the EM algorithm,we discuss the maximum likelihood(ML)estimation of unknown parameters.For testing problem of fixed effect,a parametric bootstrap(PB)approach is developed.Finally,some simulation results on the Type I error rates and powers of the PB approach are obtained,which show that the PB approach provides satisfactory performances on the Type I error rates and powers,even for small samples.For illustration,our main results are applied to a real data problem.

Efficient Virtual Resource Allocation in Mobile Edge Networks Based on Machine Learning

The rapid growth of Internet content,applications and services require more computing and storage capacity and higher bandwidth.Traditionally,internet services are provided from the cloud(i.e.,from far away)and consumed on increasingly smart devices.Edge computing and caching provides these services from nearby smart devices.Blending both approaches should combine the power of cloud services and the responsiveness of edge networks.This paper investigates how to intelligently use the caching and computing capabilities of edge nodes/cloudlets through the use of artificial intelligence-based policies.We first analyze the scenarios of mobile edge networks with edge computing and caching abilities,then design a paradigm of virtualized edge network which includes an efficient way of isolating traffic flow in physical network layer.We develop the caching and communicating resource virtualization in virtual layer,and formulate the dynamic resource allocation problem into a reinforcement learning model,with the proposed self-adaptive and self-learning management,more flexible,better performance and more secure network services with lower cost will be obtained.Simulation results and analyzes show that addressing cached contents in proper edge nodes through a trained model is more efficient than requiring them from the cloud.

Advantage of populous countries in the trends of innovation efficiency

A flurry of studies indicates that population size has a positive effect on innovation,however,cross-country empirical evidence remains sparse.In this paper,we add to the literature by investigating the relationship between population size and innovation efficiency at the country level through constructing three relative indexes based on the datasets of patent applications and Research and Development(R&D)investment.Different from previous studies based on absolute innovation indicators,the relative indexes can reflect the core innovation efficiency of economies by excluding the impact from the difference of economic development level,with a view putting all economies into a comparable standard framework.For all of the three relative indexes,their long-term trends show significant correlations with population size,and the economy with a larger population usually has better and stable performance on the trends of innovation efficiency.In addition,we find that there is a critical population size,over which the economy would be more likely to have a spontaneous improvement on innovation efficiency.This study provides direct evidence in supporting the population size advantage on the trends of innovation efficiency at the economy level and provides new insight to understand the rapid development of innovation in a few populous countries.

Bootstrap inference of the skew-normal two-way classification random effects model with interaction

In this paper,we consider the statistical inference problems for the fixed effect and variance component functions in the two-way classification random effects model with skewnormal errors.Firstly,the exact test statistic for the fixed effect is constructed.Secondly,using the Bootstrap approach and generalized approach,the one-sided hypothesis testing and interval estimation problems for the single variance component,the sum and ratio of variance components are discussed respectively.Further,the Monte Carlo simulation results indicate that the exact test statistic performs well in the one-sided hypothesis testing problem for the fixed effect.And the Bootstrap approach is better than the generalized approach in the one-sided hypothesis testing problems for variance component functions in most cases.Finally,the above approaches are applied to the real data examples of the consumer price index and value-added index of three industries to verify their rationality and effectiveness.

Cloud-to-end rendering and storage management for virtual reality in experimental education

Background Real-time 3D rendering and interaction is important for virtual reality(VR)experimental education.Unfortunately,standard end-computing methods prohibitively escalate computational costs.Thus,reducing or distributing these requirements needs urgent attention,especially in light of the COVID-19 pandemic.Methods In this study,we design a cloud-to-end rendering and storage system for VR experimental education comprising two models:background and interactive.The cloud server renders items in the background and sends the results to an end terminal in a video stream.Interactive models are then lightweight-rendered and blended at the end terminal.An improved 3D warping and hole-filling algorithm is also proposed to improve image quality when the user's viewpoint changes.Results We build three scenes to test image quality and network latency.The results show that our system can render 3D experimental education scenes with higher image quality and lower latency than any other cloud rendering systems.Conclusions Our study is the first to use cloud and lightweight rendering for VR experimental education.The results demonstrate that our system provides good rendering experience without exceeding computation costs.

Cities Make Life Better:Hukou and Household Satisfaction about Life

This paper examines the relationship between a change of hukou and household satisfaction about life based on large-sample China Family Panel Studies(CFPS) data. As horizontally shown by cross-section data, significant hukou identity differences exist in the subjective happiness of households reflected in life satisfaction. However, the traditional view that "rural residents are subjectively happier than urban residents" is not verified in this study. From a vertical perspective of tracing data, the estimation results of the DID model and the PSM model indicate that a change of hukou identity for rural residents has a significantly positive effect on their subjective happiness, lending credence to the saying that "cities make life better".

Let Globalization Benefit 80% of SMEs

The world needs free trade,as we need more job positions.All issues brought by globalization are just our growing pains.In my opinion,globalization is not a threat to our economy and employment.On the contrary,it will create more job po-

Resource Allocation and Power Control Policy for Device-to-Device Communication Using Multi-Agent Reinforcement Learning

Device-to-Device(D2D)communication is a promising technology that can reduce the burden on cellular networks while increasing network capacity.In this paper,we focus on the channel resource allocation and power control to improve the system resource utilization and network throughput.Firstly,we treat each D2D pair as an independent agent.Each agent makes decisions based on the local channel states information observed by itself.The multi-agent Reinforcement Learning(RL)algorithm is proposed for our multi-user system.We assume that the D2D pair do not possess any information on the availability and quality of the resource block to be selected,so the problem is modeled as a stochastic non-cooperative game.Hence,each agent becomes a player and they make decisions together to achieve global optimization.Thereby,the multi-agent Q-learning algorithm based on game theory is established.Secondly,in order to accelerate the convergence rate of multi-agent Q-learning,we consider a power allocation strategy based on Fuzzy C-means(FCM)algorithm.The strategy firstly groups the D2D users by FCM,and treats each group as an agent,and then performs multi-agent Q-learning algorithm to determine the power for each group of D2D users.The simulation results show that the Q-learning algorithm based on multi-agent can improve the throughput of the system.In particular,FCM can greatly speed up the convergence of the multi-agent Q-learning algorithm while improving system throughput.

Cross-correlation matrix analysis of Chinese and American bank stocks in subprime crisis

In order to study the universality of the interactions among different markets, we analyze the cross-correlation matrix of the price of the Chinese and American bank stocks. We then find that the stock prices of the emerging market are more correlated than that of the developed market. Considering that the values of the components for the eigenvector may be positive or negative, we analyze the differences between two markets in combination with the endogenous and exogenous events which influence the financial markets. We find that the sparse pattern of components of eigenvectors out of the threshold value has no change in American bank stocks before and after the subprime crisis. However, it changes from sparse to dense for Chinese bank stocks. By using the threshold value to exclude the external factors, we simulate the interactions in financial markets.

Complex network perspective on modelling chaotic systems via machine learning

Recent advances have demonstrated that a machine learning technique known as "reservoir computing" is a significantly effective method for modelling chaotic systems. Going beyond short-term prediction, we show that long-term behaviors of an observed chaotic system are also preserved in the trained reservoir system by virtue of network measurements. Specifically, we find that a broad range of network statistics induced from the trained reservoir system is nearly identical with that of a learned chaotic system of interest. Moreover, we show that network measurements of the trained reservoir system are sensitive to distinct dynamics and can in turn detect the dynamical transitions in complex systems. Our findings further support that rather than dynamical equations, reservoir computing approach in fact provides an alternative way for modelling chaotic systems.

Recent Advances in Data-Driven Wireless Communication Using Gaussian Processes: A Comprehensive Survey

Data-driven paradigms are well-known and salient demands of future wireless communication. Empowered by big data and machine learning techniques,next-generation data-driven communication systems will be intelligent with unique characteristics of expressiveness, scalability, interpretability, and uncertainty awareness, which can confidently involve diversified latent demands and personalized services in the foreseeable future. In this paper, we review a promising family of nonparametric Bayesian machine learning models,i.e., Gaussian processes(GPs), and their applications in wireless communication. Since GP models demonstrate outstanding expressive and interpretable learning ability with uncertainty, they are particularly suitable for wireless communication. Moreover, they provide a natural framework for collaborating data and empirical models(DEM). Specifically, we first envision three-level motivations of data-driven wireless communication using GP models. Then, we present the background of the GPs in terms of covariance structure and model inference. The expressiveness of the GP model using various interpretable kernels, including stationary, non-stationary, deep and multi-task kernels,is showcased. Furthermore, we review the distributed GP models with promising scalability, which is suitable for applications in wireless networks with a large number of distributed edge devices. Finally, we list representative solutions and promising techniques that adopt GP models in various wireless communication applications.

Development status and trend of traditional Chinese medicine database

Following the trend of information technology,the development of traditional Chinese medicine(TCM)databases has led to great changes in terms of data.For example,the storage and dissemination medium of data has achieved a shift from paper books to the internet,and the content has expanded from basic information to comprehensive information such as targets and molecular structures of modern medicine.In recent years,the amount of information contained in the TCM databases has grown at an unparalleled rate.However,there are still challenges correlated with the database construction,including insufficient data volume,inconsistent construction standards,and a low level of platformization.Additionally,the prevalence of applications in the field of TCM like network pharmacology,bioinformatics,and artificial intelligence requires a large volume of high-quality data.Generally speaking,the advancements in life science and artificial intelligence technology have outpaced the development of TCM databases.Therefore,this paper compiled the current status of TCM databases,discussed the benefits and drawbacks of various databases,and concluded that the development trend should be comprehensive,platform-based,and tightly integrated with modern life science technology and artificial intelligence technology,so as to provide assistance to the modernization research of TCM.

A Deep Neural Collaborative Filtering Based Service Recommendation Method with Multi-Source Data for Smart Cloud-Edge Collaboration Applications

Service recommendation provides an effective solution to extract valuable information from the huge and ever-increasing volume of big data generated by the large cardinality of user devices.However,the distributed and rich multi-source big data resources raise challenges to the centralized cloud-based data storage and value mining approaches in terms of economic cost and effective service recommendation methods.In view of these challenges,we propose a deep neural collaborative filtering based service recommendation method with multi-source data(i.e.,NCF-MS)in this paper,which adopts the cloud-edge collaboration computing paradigm to build recommendation model.More specifically,the Stacked Denoising Auto Encoder(SDAE)module is adopted to extract user/service features from auxiliary user profiles and service attributes.The Multiple Layer Perceptron(MLP)module is adopted to integrate the auxiliary user/service features to train the recommendation model.Finally,we evaluate the effectiveness of the NCF-MS method on three public datasets.The experimental results show that our proposed method achieves better performance than existing methods.