Social media and other online websites have rich traffic information. How to extract and mine useful traffic information from online web data to address transportation problems has become a valuable and interesting research topic in current data-explosive era. In this chapter, we introduce a traffic analytic system with online web data. The proposed system can collect online data, use machine learning and natural language processing methods to extract traffic events, analyze traffic sentiment, and reason traffic scenarios. We also present some results based on the proposed system and techniques in practice.

We present a bibliographic and coauthorship-based collaboration analysis of papers published in the IEEE Transactions on Intelligent Transportation Systems (T-ITS) between 2014 and 2016 from the aspects of productivity, topics, citations, usage, and coauthorship networks. The most productive authors, institutions, countries/regions, and the most cited papers, most popular papers, as well as the most frequent topics and their trends are identified and analyzed. Social network methods are employed for revealing collaboration patterns among contributors through author- and institution-level coauthorship. The results show that China is playing a critical role in ITS research during this period but the interinstitution collaborations are less prevalent than it used to be. Overall data have indicated that IEEE T-ITS has made tremendous progress and contributed significantly to the accelerated growth of ITS fields over the last three years.

针对航母作战平台与体系的复杂性,将平行理论应用到航母的运维及作战与训练中,提出平行航母概念,定义平行航母的数字四胞胎（Digital quadruplet）:物理航母（Physical carrier）、描述航母（Descriptive carrier）、预测航母（Predictive carrier）和引导航母（Prescriptive carrier）.建立平行航母从物理航母到描述航母的描述智能、从描述航母到预测航母的预测智能、从预测航母到引导航母的引导智能框架体系.基于这一框架体系,提出平行航母的平行指挥与控制理念,以及平行指挥与控制体系框架结构,在运维、编队、战术群至作战平台等各方面,实现从传统的层级指挥控制向平行指挥控制的转型.

A quantitative and qualitative study on research developments in automation field is conducted based on the papers published in Acta Automatica Sinica during 2011 to 2016 from the aspects of productivity, citations, topics, usage, and coauthorship networks. The most productive authors, institutions, and the most cited papers, most popular papers, as well as the most frequent topics and their trends are identified and analyzed. Social network methods are employed for revealing collaboration patterns among contributors through author-level coauthorship. It is indicated that the automation field has made tremendous progress and Acta Automatica Sinica has contributed significantly to accelerate the growth over that period. The findings can help scientists in automation field to understand research developments, enhance academic exchanges,and promote collaborations as well.

针对我军武器装备研发、应用领域存在的问题,提出面向平行化技术的武器装备体系、理论、方法和技术.在虚实互动的平行思想指导下,将ACP方法应用于武器装备的设计研发、试验测试、生产制造、维护保养、毁伤评估等方面,构成平行武器的全生命周期.目标是实现武器装备、指挥系统、作战部队、军工企业、民用单位的紧密融合.对我军未来“察-打-评”一体化的武器装备发展有较好的指导意义.

深度学习在特征提取与模型拟合方面显示了其潜力和优势.对于存在高维数据的控制系统,引入深度学习具有一定的意义.近年来,已有一些研究关注深度学习在控制领域的应用.本文介绍了深度学习在控制领域的研究方向和现状,包括控制目标识别、状态特征提取、系统参数辨识和控制策略计算.并对相关的深度控制以及自适应动态规划与平行控制的方法和思想进行了描述.总结了深度学习在控制领域研究中的主要作用和存在的问题,展望了未来值得研究的方向.

针对海量开源情报的有效利用问题,提出了一种基于ASKE（Application Specific Knowledge Engine）的开源情报获取与分析框架,并以近5年来国内情报领域19种核心期刊所发表的学术论文为研究对象,从知识获取到情报处理分析,并结合主流分析方法与可视化工具,构建了国内情报学领域关键词、人物与机构知识图谱,对我国近期情报学的研究热点、关键人物与学术机构及其合作网络进行了归纳与分析,得到了诸多重要结论,这些结论能够帮助我们了解当前我国情报领域相关研究热点、关键人物与机构及其相关合作网络,明确我国情报学研究现状.

Nowadays, automation science and technology based on automatic control and information processing has be-come an essential impetus to productive forces and human life. So a comprehensive understanding of the latest research progress in this discipline is essential for its significant reference value to scholars and research institutions. In this paper, the automa-tion science and technology discipline is divided into five re-search fields, which are specifically defined as control theory and engineering, pattern recognition and intelligent systems, mea-surement technology and automatic equipment, navigation and guidance, and systems engineering. Each field is depicted by analyzing and mapping the data from 46 242 academic articles published on 88 journals during 2011～2013. The results show that the research interests are different between domestic and abroad, and that the domestic institutions and ethnic Chinese scholars have played an important role in promoting the devel-opment of automation science and technology.

As a new research field in wireless sensor network (WSN), wireless video sensor network (WVSN) makes surveillance multifunctional and intelligent, with rich and intuitive sensing information. It attracts more and more researchers' attention. We design and implement a wireless video sensor network prototype system, using WIFI as the wireless communication solution and CMOS video camera as the front-end sensor. The wireless video node adopts ARM11 based embedded platform. As back-end processing algorithm, the node realizes moving object detection. Finally, we verify the sensor network system. WIFI network can transmit video sequences smoothly. The moving object detection algorithm performs well.

To solve the communication problem between ARM and DSP in dual-CPU system,a design method of communication interface based on host port interface(HPI) is proposed.Firstly,two processers employed in the design are introduced briefly,which are S3C6410 and TMS320DM642.Then,the features,internal structure and working principle are analyzed.Furthermore,detailed interface hardware circuit and driver program under Linux design process are presented.Finally,the accuracy and efficiency of the design is validated by long run tests.It will have important practical value in embedded system development.