Wang Feiyue

Traffic incident detection algorithm based on non-parameter regression

We first describe the traffic congestion problem that many countries are facing with in the world. Then we propose a traffic incident detection algorithm based on non-parametric regression to solve the congestion problem. Finally, we compare the algorithm with other incident detection algorithms on the detection rate, false alarm rate and mean detection time. A simulation result shows the algorithm proposed has higher detection rate, lower false alarm rate and longer mean time detection. Furthermore, we state the direction of our next study.

Study of city area traffic coordination control on the basis of agent

On the basis of agent technology, this paper focuses on a study of area traffic flow coordination control. The composition and structure of agents for area traffic flow control is discussed and the coordination strategy of the intersection agent is described. On the basis of this study, some simulations on a sample road net are preformed by analyzing the simulation results. The feasibility of using agent technology to study area traffic coordination control is asserted.

Chemical composition of river particulates in eastern China

A total of 42 aquatic particulate sample:, (suspended matter and < 63 μm surficial sediments) was collected from 11 large rivers in eastern China. Contents of both major elements (Al, Si, Ca, Mg, K, Na, Ti, Fe, Mn) and trace elements (Cu, Pb, Zn, Cd, Cr, Co, Ni, V) in the particulate samples were analyzed. The geographic variations of river particulate compositions were studied. The results showed that the Yellow River particulates contained a notably high content of Ca and a low content of Al. Except for the Yellow River, A1 contents in particulates increased from the northern rivers to the southern rivers, while K and Na decreased. Trace elements were relatively enriched in the southern river particulates. The geographic variations seemed to be related to the weathering types and geological background within the river basins. The average composition of river particulates in China was then estimated. Based on the Chinese river data from this paper, as well as on the literature data for other main world rivers, a new estimation of the global average particulate composition was reported. Since the earlier estimations in the literature were not concerned with or at best concerned only with few of the Chinese rivers which contribute a major proportion to the global load of river particulates, this new estimation may be more reasonable.

Social computing and computational societies: The foundation and consequence of smart societies

Social computing, as the technical foundation of future computational smart societies, has potential to improve the effectiveness of using dynamic and open-source big data, systematically integrate various factors including people, positions, events, objects and organizations, and establish a novel social structure with symmetric information, equal rights and a flat configuration. As such, social computing can facilitate the evolution of social administration from traditional paradigms to an intensive, informational, intelligent and innovative model with real-time and complete responses. To this end, we should take full advantage of such key technologies as social sensor networks, knowledge automation, high-performance distributed computing, and cyber/artificial-physical-coupled parallel systems to enhance overall capabilities in perception, modeling, analysis, decision-making and implementation, and thus improve societal functions and services. The ultimate goal is to create a novel and configurable social management mode with closed-loop feedback from public opinion, parallel management, and mobile command and control.

A framework for social signal processing and analysis：from social sensing networks to computational dialectical analytics

The availability of real-time and reliable social signals is a necessity for implementing closed-loop and feedback based dynamic social management. However, the concepts and methods for social signals are far behind those for physical signal processing and analysis, and need to be developed in a systematic approach. As social and new media and social networking reach to all corners of societies rapidly, the problem of social signal processing and analysis becomes significant and the demand for effective solutions is great and urgent. This paper investigates issues related to the modeling and management of social systems, characterization of social signals and channels, social sensors and construction of social sensing networks, artificial societies, computational experiments, and parallel execution (the ACP approach) for reasoning and synthesis in computational social systems, computational dialectics, and computational analytics. Our objective is to establish a framework and methodology for acquisition, processing, analysis, analytics, and application of social signals.

Component-based constructing approach for application specific embedded operating systems

Rapid advances in the real-time embedded operating systems necessitate the development of Internet oriented application specific embedded operating systems. The ASOS (application specific embedded operating systems) has now become a promising research direction of the embedded operating system. The paper clarifies the concept of the ASOS, and takes the embedded operating system applied in the traffic signal controller we are now developing to illustrate the main characteristics of the ASOS. Benefits from the CBSE (component-based software engineering) include system quality improvement, shorter time to market, integration of complex systems, etc. However, as for the embedded system, the component-based technology and theories still in an exploration period, though many projects are carried on. In this paper, we present the process of our approach to construct the ASOS based on the component technology.

Heuristic algorithm for the container loading problem with multiple constraints

This paper addresses the container loading problem with multiple constraints that occur at many manufacturing sites, such as furniture factories, appliances factories, and kitchenware factories. These factories receive daily orders with expiration dates, and each order consists of one or more items. On a particular day, certain orders expire, and the expiring orders must be handled (shipped) prior to the non-expiring ones. All of the items in an order must be placed in one container, and the volume of the container should be maximally utilized. A heuristic algorithm is proposed to standardize the packing of (order) items into a container. The algorithm chooses the expiring orders first before handling the non-expiring orders. In both steps, the algorithm first selects a collection of orders by considering a simulated annealing strategy and subsequently packs the collection of orders into the container via a treegraph search procedure. The validity of the algorithm is examined through experimental results using BR instances. 2017 Elsevier Ltd. All rights reserved.

核能5.0:智能时代的核电工业新形态与体系架构

本文旨在讨论核能5.0（Nuclear Energy 5.0）的基本概念、体系架构和关键平台技术等问题.首先讨论了核能5.0出现的新智能时代基础，阐述了虚拟数字工业崛起的技术背景.详细叙述了核电工业新形态与体系结构，即平行核能的定义、意义、研究内容、体系架构以及应用领域.接下来讨论了核能5.0中新一代核心技术，包括核能物联网、知识自动化、发展性人工智能、大规模协同演进技术、核能区块链等.最后讨论了核能5.0中在核电系统的具体应用场景与案例，重点是核电工控系统安全评估与核电站数字化仪控系统.

Parallel networks and network softwarization: a novel network architecture

The coexistence of various protocols for current networks leads to extremely complex network systems, which not only limits the development of network technologies, but also cannot meet the growing demands for cloud computing, big data, service visualization applications, etc. With the development of information telecommunication technology, decreasing hardware costs, and the rise of open source packages, network systems have become more dynamic and flexible, and network service providers expect easier access to the information technology market. A new business model and collaborative competition must be formed.However, current network systems are becoming increasingly complex, which also increases project and societal complexity. The attributes of multi-field, dynamicity, and unpredictability lead network systems to be massively complex, making it difficult to comprehensively evaluate and accurately amend their schema. Therefore, as a new network architecture, parallel network is expected to revolutionize the current network situation and meet the evolving demand for network services. The core idea of parallel networking is to construct artificial networks and effectively optimize the network system operations via the interactions between real networks and artificial networks. Through computational experiments and analysis of the artificial networks, a control strategy based on network traffic flow can be continuously tracked and updated in real-time. Meanwhile, the collected operating status of the real network can also be used to optimize the model of the artificial network. These strategies can be applied to all types of network equipment to control network operations. Therefore, it is possible to allocate network resources more effectively, to improve the management and utilization of resources, and to provide new network solutions to address changing network demands more effectively.

平行机器人与平行无人系统:框架、结构、过程、平台及其应用

本文将基于ACP（Artificial societies，computational experiments，parallel execution）的平行系统思想与机器人领域相结合，形成一种软硬件相结合的框架，为无人机、无人车、无人船在复杂环境中实验、学习与实际工作提供便捷、安全的平台，即平行无人系统.本文从平行机器人的基本概念出发，提出平行无人系统的基本框架，并介绍了各模块的基本功能与实现方法，探讨了其中的关键技术.然后本文围绕无人机、无人车、无人船三个方面展望了无人平行系统在实际中的应用和所面临的挑战，提出了平行无人系统的未来发展方向.