Evolutionary Neural Architecture Search and Its Applications in Healthcare

Most of the neural network architectures are based on human experience,which requires a long and tedious trial-and-error process.Neural architecture search(NAS)attempts to detect effective architectures without human intervention.Evolutionary algorithms(EAs)for NAS can find better solutions than human-designed architectures by exploring a large search space for possible architectures.Using multiobjective EAs for NAS,optimal neural architectures that meet various performance criteria can be explored and discovered efficiently.Furthermore,hardware-accelerated NAS methods can improve the efficiency of the NAS.While existing reviews have mainly focused on different strategies to complete NAS,a few studies have explored the use of EAs for NAS.In this paper,we summarize and explore the use of EAs for NAS,as well as large-scale multiobjective optimization strategies and hardware-accelerated NAS methods.NAS performs well in healthcare applications,such as medical image analysis,classification of disease diagnosis,and health monitoring.EAs for NAS can automate the search process and optimize multiple objectives simultaneously in a given healthcare task.Deep neural network has been successfully used in healthcare,but it lacks interpretability.Medical data is highly sensitive,and privacy leaks are frequently reported in the healthcare industry.To solve these problems,in healthcare,we propose an interpretable neuroevolution framework based on federated learning to address search efficiency and privacy protection.Moreover,we also point out future research directions for evolutionary NAS.Overall,for researchers who want to use EAs to optimize NNs in healthcare,we analyze the advantages and disadvantages of doing so to provide detailed guidance,and propose an interpretable privacy-preserving framework for healthcare applications.

Effective distributed convolutional neural network architecture for remote sensing images target classification with a pre-training approach

How to recognize targets with similar appearances from remote sensing images(RSIs) effectively and efficiently has become a big challenge. Recently, convolutional neural network(CNN) is preferred in the target classification due to the powerful feature representation ability and better performance. However,the training and testing of CNN mainly rely on single machine.Single machine has its natural limitation and bottleneck in processing RSIs due to limited hardware resources and huge time consuming. Besides, overfitting is a challenge for the CNN model due to the unbalance between RSIs data and the model structure.When a model is complex or the training data is relatively small,overfitting occurs and leads to a poor predictive performance. To address these problems, a distributed CNN architecture for RSIs target classification is proposed, which dramatically increases the training speed of CNN and system scalability. It improves the storage ability and processing efficiency of RSIs. Furthermore,Bayesian regularization approach is utilized in order to initialize the weights of the CNN extractor, which increases the robustness and flexibility of the CNN model. It helps prevent the overfitting and avoid the local optima caused by limited RSI training images or the inappropriate CNN structure. In addition, considering the efficiency of the Na¨?ve Bayes classifier, a distributed Na¨?ve Bayes classifier is designed to reduce the training cost. Compared with other algorithms, the proposed system and method perform the best and increase the recognition accuracy. The results show that the distributed system framework and the proposed algorithms are suitable for RSIs target classification tasks.

Architecture of HLA Based Distributed Virtual Geographic Environment

Integrating the theory of distributed virtual geographic environment (DVGE) and high level architecture(HLA), the architecture of DVGE based on HLA is designed. The data flow and the object models of the architecture are also discussed. The architecture basically meets the need of DVGE in real-time communication, distribution, collaboration, reusing and interoperation, expansion, and standard.

Generalized Distributed Multicell Architecture:Group Cell

In order to make full use of advanced technologies for future mobile communications systems such as Space Time Code (STC), Joint Transmission (JT) and Multiple Input Multiple Output (MIMO), and to meet the requirements of high-bit-rate multimedia services, new network topologies should be studied. Generalized distributed multicell architecture can take full advantage of multi-antenna technologies and solve the problem of frequent handover caused by higher carrier frequencies. Group handover, the handover policy based on the architecture, can eliminate the cell edge effect. Furthermore, by applying the concept of group handover to 3G mobile communication systems, the Fast Cell Group Selection (FCGS) scheme can effectively improve the data rate for cell edge users.

Distributed MPC for Reconfigurable Architecture Systems via Alternating Direction Method of Multipliers

This paper investigates the distributed model predictive control(MPC)problem of linear systems where the network topology is changeable by the way of inserting new subsystems,disconnecting existing subsystems,or merely modifying the couplings between different subsystems.To equip live systems with a quick response ability when modifying network topology,while keeping a satisfactory dynamic performance,a novel reconfiguration control scheme based on the alternating direction method of multipliers(ADMM)is presented.In this scheme,the local controllers directly influenced by the structure realignment are redesigned in the reconfiguration control.Meanwhile,by employing the powerful ADMM algorithm,the iterative formulas for solving the reconfigured optimization problem are obtained,which significantly accelerate the computation speed and ensure a timely output of the reconfigured optimal control response.Ultimately,the presented reconfiguration scheme is applied to the level control of a benchmark four-tank plant to illustrate its effectiveness and main characteristics.

A distributed software architecture design framework based on attributed grammar

Software architectures shift the focus of developers from lines-of-code to coarser-grained architectural elements and their overall interconnection structure. There are, however, many features of the distributed software that make the developing methods of distributed software quite different from the traditional ways. Furthermore, the traditional centralized ways with fixed interfaces cannot adapt to the flexible requirements of distributed software. In this paper, the attributed grammar (AG) is extended to refine the characters of distributed software, and a distributed software architecture description language (DSADL) based on attributed grammar is introduced, and then a model of integrated environment for software architecture design is proposed. It can be demonstrated by the practice that DSADL can help the programmers to analyze and design distributed software effectively, so the efficiency of the development can be improved greatly.

Distribution Patterns of Remaining Hydrocarbons Controlled by Reservoir Architecture of Distributary Channel with Different Channel Style: S2 Formation of Songliao Basin, China

1 Introduction Reservoir architecture analysis of distributary channel of Daqing oilfield has drawn consistent interest among development geologists and petroleum engineers over the last decade(Lv et al.,1999;Zhou et al.,2008;Zhang et

Building Distributed Web GIS: A Mobile Agent Based Approach

The diversity of GISs and the wide spread availability of WWW have led to an increasing amount of research on integrating a variety of heterogeneous and autonomous GISs in a cooperative environment to construct a new generation of GIS characterizing in open architecture, distributed computation, interoperability, and extensibility. Our on going research project MADGIS (Mobile Agent based Distributed Geographic Information System) is reported, in which we propose the architecture of MADGIS to meet the requirements of integrating distributed GIS applications under Internet environment. We first describe the architecture of MADGIS, and detailed discussions focusing on the structure of client site, server site and mobile agent in MADGIS. Then we explore key techniques for MADGIS implementation.

An architecture for mobile database management system

In order to design a new kind of mobile database management system (DBMS)more suitable for mobile computing than the existent DBMS, the essence of database systems in mobilecomputing is analyzed. An opinion is introduced that the mobile database is a kind of dynamicdistributed database, and the concept of virtual servers to translate the clients' mobility to theservers' mobility is proposed. Based on these opinions, a kind of architecture of mobile DBMS, whichis of versatility, is presented. The architecture is composed of a virtual server and a local DBMS,the virtual server is the kernel of the architecture and its functions are described. Eventually,the server kernel of a mobile DBMS prototype is illustrated.

Integration of naval distributed tactical training simulation system based on advanced message queuing protocol

Aiming at the problems of unreliable data transmission,poor steadiness,nonsupport of complex data types,direct couple between data transmission and exchange,a high-level method based on advanced message queuing protocol( AMQP) is proposed to integrate naval distributed tactical training simulation system after serious consideration with current information exchange features of military combat system. Transferring layer in traditional user datagram protocol is implemented by publishing and subscribing scheme of message middleware. By creating message model to standardize message structure,integration architecture is formulated to resolve potential information security risks from inconsistent data type and express data transmission. Meanwhile,a communication model is put forward based on AMQP,which is in the center position of the whole transmission framework and responsible for reliably transferring battlefield data among subsystems. Experiments show that the method can accurately post amounts of data to the subscriber without error and loss,and can get excellent real-time performance of data exchange.

Scalable Distributed File Sharing System: A Robust Strategy for a Reliable Networked Environment in Tertiary Institutions

The bane of achieving a scalable distributed file sharing system is the centralized data system and single server oriented file [sharing] system. In this paper, the solution to the problems in a distributed environment is presented. Thus, inability to upload sizeable files, slow transportation of files, weak security and lack of fault tolerance are the major problems in the existing system. Hence, the utmost need is to build a client-server network that runs on two or more server systems in order to implement scalability, such that when one server is down, the other(s) would still hold up the activities within the network. And to achieve this reliable network environment, LINUX network operating system is recommended among others as a preferred platform for the synchronization of the server systems, such that every user activity like sending of internal memos/mails, publication of academic articles, is replicated;thereby, achieving the proposed result. Hence, Scalable Distributed File Sharing System provides the robustness required to having a reliable intranet.

Design of a Developing Platform of Supervisor and Management System for Industrial Process in DCS Based on Client/Server Architecture

Build a general software development platform for industrial process supervisor and management system by combining the technology of industrial configuration and Client/Server model, and introduce the architecture and topological application of this platform. It puts forward a solution to the real time problem in the industrial distributed supervisor system.

Dynamic Multicast Grouping Approach in HLA-Based Distributed Interactive Simulation

In order to improve the efficiency of data distributed management service in distributed interactive simulation based on high level architecture (HLA) and to reduce the network traffic and save the system resource, the approaches of multicast grouping in HLA-based distributed interactive simulation are discussed. Then a new dynamic multicast grouping approach is proposed. This approach is based on the current publication and subscription region in the process of simulation. The results of simulation experiment show that this approach can significantly reduce the message overhead and use fewer multicast groups.

Distributed Technology of E-Business and Its Practice

With the evolution of application system, there are t wo different system architectures. One is the traditional application system suc h as MIS and Business Software. Along with its extension, the traditional applic ation system transforms from file-based structure to C/S and then CSS model. At the same time, following the prevalence of Internet/Intranet, Web application s ystem based on browser comes into being. In early time, Web application only pro vided functions of looking over or querying static data on browser. But with the development of Internet/Intranet widely, it’s expected that more and more trad itional applications can be performed on browser, or even E-Business trades and other complicated application systems such as MIS, ERP and CRM and so on. In or der to satisfy both traditional application and Web application, reduce the cost of developing system repeatedly, increase the repeated use of application syste m and take advantage of the functions of OOA/OOD sufficiently, a new distributed architecture structure (system solution based on repeated components) comes for th. In this article, this distributed architecture structure will be discuss ed in detail. Firstly, the evolution of traditional application system and Web application sys tem will be talked over, especially the advantages and disadvantages of these tw o architectures. Secondly, the distributed architecture (system solution based o n repeated components) will be described particular. Several prevalent technolog y of component, such as COM+, CORBA and EJB, will also be illustrate d in this part. Thirdly, the practice of the technology of repeated component wi ll be discussed by analysing and designing the management system of Science & Te chnology Articles. Lastly, the latest distributed techonlogy of E-business(Web service based on xml/soap) will be discussed. In the end, Based on summing-up o f the distributed technology of E-Business, the future distributed tenchnology of E-Business will be expected.

Parallel Extraction of Marine Targets Applying OIDA Architecture

Computing resources are one of the key factors restricting the extraction of marine targets by using deep learning.In order to increase computing speed and shorten the computing time,parallel distributed architecture is adopted to extract marine targets.The advantages of two distributed architectures,Parameter Server and Ring-allreduce architecture,are combined to design a parallel distributed architecture suitable for deep learning–Optimal Interleaved Distributed Architecture(OIDA).Three marine target extraction methods including OTD_StErf,OTD_Loglogistic and OTD_Sgmloglog are used to test OIDA,and a total of 18 experiments in 3categories are carried out.The results show that OIDA architecture can meet the timeliness requirements of marine target extraction.The average speed of target parallel extraction with single-machine 8-core CPU is 5.75 times faster than that of single-machine single-core CPU,and the average speed with 5-machine 40-core CPU is 20.75 times faster.

Strata Architectural Variability and Facies Distribution in a Structural Transfer Zone: A Case Study of Fushan Sag, Northern South China Sea

Structural transfer zones in a half-graben rift basin play a significant role in controlling sandy sediments and providing a target for hydrocarbon exploration. Previous studies have classified the transfer zone in lacustrine environments into two different patterns: synthetic approaching transfer zones and synthetic overlapping transfer zones. However, the evolution of the depositional pattern and the controlling factors of the above transfer zones are still unclear. In the Fushan Sag, the northern South China Sea, an overlapping transfer zone developed in the early Eocene Epoch, while a synthetic approaching transfer zone developed in the late Eocene, due to tectonic uplift. This evolutionary process provided an opportunity to study the stacking pattern of strata architectural variability and facies distribution in the structural transfer zone of the Eocene lacustrine basin. In this study, following the indications of the oriented sedimentary structures in core samples and heavy mineral assemblages of 18 wells, the evolution of the paleo-hydrodynamic distribution during the early and late Eocene has been reconstructed. The sequence-stratigraphy was then divided and the sand body parameters calculated, according to the seismic data and well log interpretations. During the early Eocene, the lake level was at a low stand, the faults broken displacement in the East block being over 50 m. The prograding delta and turbidites are oriented perpendicular to the structural transfer zone. According to the quantitative analysis of the flow rate and the depositional parameters, we speculate that gravity transportation of the sediment and the sediment-supply are the dominating factors during this period. Up to the late Eocene, the rising lake level and the decreased fault displacement leads the flow to divert to a NE-direction, resulting in it being parallel to the axis of the transfer zone. Thus, we speculate that the accommodation space is predominant in this period. In comparison with the above two periods, a braided river delta with an isolated sand body and turbidites developing in the deep area is prominent in the overlapping transfer zone, while a meandering river delta is characteristic of the synthetic approaching transfer zone.

Trend judgment of abandoned channels and fine architecture characterization in meandering river reservoirs: A case study of Neogene Minhuazhen Formation NmⅢ2 layer in Shijiutuo bulge, Chengning uplift, Bohai Bay Basin, East China

Based on well logging responses,sedimentary patterns and sandstone thickness,the distribution characteristics of meandering river sedimentary sand body of Neogene Minghuazhen Formation NmⅢ2 layer in the west of Shijiutuo Bulge,Chengning Uplift,Bohai Bay Basin were investigated.A new approach to calculate the occurrence of the sand-mudstone interfaces using resistivity log of horizontal well was advanced to solve the multiple solution problem of abandoned channel’s orientation.This method uses the trigonometric function relationship between radius,dip and length of the resistivity log to calculate the occurrence qualitatively-quantitatively to help determine the true direction of the abandoned channels.This method can supplement and improve the architecture dissection technique for meandering river sandbodies.This method was used to study the dip angle and scale of the lateral accretion layers in point bar quantitatively to help determine the spatial distribution of lateral accretion layers.The fine architecture model of underground meandering river reservoir in the study area has been established.Different from traditional grids,different grid densities for lateral accretion layers and bodies were used in this model by non-uniform upscaling to establish the inner architecture model of point-bars and realize industrial numerical simulation of the whole study area.The research results can help us predict the distribution of remaining oil,tap remaining oil,and optimize the waterflooding in oilfields.

Distributed Satellite Cluster Network:a Survey

The ability of the monolithic satellite,satellite orbit(especially GEO),and radio resource are very limited,so the development of distributed satellite cluster network(DSCN) receives more and more worldwide attention.In this paper,DSCN is surveyed and the study status of DSCN architecture design is summarized.The formation flying of spacecrafts,reconfiguration,networking,and applied research on distributed satellite spacecraft are described in detail.The DSCN will provide a great technology innovation for space information network,satellite communications,satellite navigation,deep space exploration,and space remote sensing.In addition,this paper points out future trends of the DSCN development.

A Data Mining Algorithm Based on Distributed Decision-Tree in Grid Computing Environments

Recently, researches on distributed data mining by making use of grid are in trend. This paper introduces a data mining algorithm by means of distributed decision-tree,which has taken the advantage of conveniences and services supplied by the computing platform-grid,and can perform a data mining of distributed classification on grid.