基于隐马尔科夫模型的VLCC目的港预测     

杨春  王一丹  徐晖  胡勤友  潘亚兰 《上海海事大学学报》2020,41(4):42-49

超大型油船(very large crude carrier，VLCC)目的港预测对海运原油流向预测以及货源地未来运力估计具有重要作用。针对VLCC的AIS目的港信息存在缺失、更新不及时、不准确等现象，提出一种基于隐马尔科夫模型的VLCC目的港预测方法。分析船舶AIS轨迹数据，得到油船历史停靠港口序列；根据VLCC轨迹提取习惯航路，以航路中的交叉点为依据设置观测线；利用船舶航行轨迹数据判断船舶是否经过观测线以及经过观测线的方向，对不同方向分别计算船舶在挂靠港间的转移概率矩阵和船舶挂靠港与观测线间的输出概率矩阵，建立VLCC目的港预测模型并进行预测。研究结果表明：在大多数情况下VLCC目的港预测的准确率可以达到70%以上；航线越固定、运行越规律的船舶，预测准确率越高；船舶越靠近目的港，预测越准确；重载状态下的船舶目的港预测更准确。  相似文献   

基于深度学习的SSD模型尾矿库自动提取     

闫凯  沈汀  陈正超  闫弘轩 《中国科学院大学学报》2020,37(3):360-367

针对华北地区尾矿库自动提取问题，将基于深度学习的SSD目标检测模型应用于遥感图像尾矿库提取。首先标记华北地区2 000个样本，随机挑选1 500个作为训练样本，剩余样本作为测试样本，验证模型的检测精度。分析卷积层对应感受野与图像中尾矿库尺寸关系，发现原始SSD模型漏检误检大型尾矿库。改进SSD模型结构，提出增加额外卷积层的策略，提高对大型尾矿库目标的检测精度。实验表明，在置信度阈值为0.3时，改进的SSD模型相比原始模型，检测精确率提高10.0%，召回率提高14.4%，提高了大型尾矿库检测精度。验证了基于深度学习的SSD目标检测模型自动提取尾矿库的可行性以及改进算法的有效性。  相似文献   

基于距离方程组的机载SAR图像立体定位方法     

潘志刚  王超  曹舸 《中国科学院大学学报》2020,37(6):798-804

提出一种基于距离方程组的机载SAR图像立体定位方法，该方法使用同一成像区域的3幅SAR图像进行无控制点定位，首先确定目标在3幅图像中对应的同名像点，解析该像点对应的雷达平台瞬时经纬度坐标、海拔高度以及目标到雷达平台的斜距值，在地心坐标系下建立3幅图像对应同名像点的距离方程组，对非线性方程组进行求解得到同名像点基于地心坐标系的坐标值，并通过坐标转换得到目标点的经纬度坐标及海拔高度，实现三维定位。对影响定位精度的系统误差因素进行仿真分析，利用实飞的机载SAR图像进行目标定位实验，结果验证了该方法的有效性。  相似文献   

An extension of the technology acceptance model in the big data analytics system implementation environment     

Surabhi Verma  Som Sekhar Bhattacharyya  Saurav Kumar 《Information processing & management》2018,54(5):791-806

Research on the adoption of systems for big data analytics has drawn enormous attention in Information Systems research. This study extends big data analytics adoption research by examining the effects of system characteristics on the attitude of managers towards the usage of big data analytics systems. A research model has been proposed in this study based on an extensive review of literature pertaining to the Technology Acceptance Model, with further validation by a survey of 150 big data analytics users. Results of this survey confirm that characteristics of the big data analytics system have significant direct and indirect effects on belief in the benefits of big data analytics systems and perceived usefulness, attitude and adoption. Moreover, there are mediation effects that exist among the system characteristics, benefits of big data analytics systems, perceived usefulness and the attitude towards using big data analytics system. This study expands the existing body of knowledge on the adoption of big data analytics systems, and benefits big data analytics providers and vendors while helping in the formulation of their business models.  相似文献   

Online social viewing: Cross-cultural adoption and uses of bullet-screen videos     

Anan Wan  Leigh Moscowitz  Linwan Wu 《Journal of International and Intercultural Communication》2020,13(3):197-215

ABSTRACT

Bullet-screen technology, an innovative way of interacting with online videos, allows viewers to contribute comments that simultaneously appear over videos. Popular in East Asia, the technology is making its way to American audiences. This study employed a comparative qualitative focus group approach to explore how American and Chinese viewers responded to and interacted with this new format of online videos. Three themes emerge from this investigation: (1) the unique affordances of this technology; (2) barriers to adoption and usage; and (3) cultural differences that impact the user experience. The theoretical and practical implications for bullet-screen technologies are discussed.  相似文献   

Limitations on the human capital transferability of adult migrants in Spain: Incentive or barrier for a new investment in education?     

Jacobo Muñoz-Comet  María Miyar-Busto 《European Journal of Education》2018,53(4):586-599

Many empirical studies on immigrant integration document the benefits of an education acquired in the country of destination. In this article; we study how the degree of human capital transferability affects an immigrant's chances of studying in Spain. We used data from the Spanish Labour Force Survey (2008–2015) for a sample of adults aged 18–55 who had left the educational system. The main findings show that natives are the ethnic group with the highest likelihood of re-enrolling in education. Amongst immigrants, those with fewer limitations on human capital transferability also invest more. These results question the predictions of the Immigrant Human Capital Investment model which expect that immigrants whose human capital depreciates upon arrival and those who can obtain a higher return on a new investment in education are therefore more likely to study. Moreover, the effect of skill transferability differs depending on the type of obstacle and the kind of education. Immigrants with less linguistic and cultural familiarity with the host country are less likely to undertake non-formal education than formal education. However, when the transferability obstacles are related to administrative requirements and legal restrictions, the probability of investing in non-formal education is higher. We conclude that immigrants with low skill transferability are not only less well integrated in the labour market upon arrival, but are also less able to redress that disadvantage through a new investment in education.  相似文献   

Location extraction from tweets     

Thi Bich Ngoc Hoang  Josiane Mothe 《Information processing & management》2018,54(2):129-144

Five hundred million tweets are posted daily, making Twitter a major social media platform from which topical information on events can be extracted. These events are represented by three main dimensions: time, location and entity-related information. The focus of this paper is location, which is an essential dimension for geo-spatial applications, either when helping rescue operations during a disaster or when used for contextual recommendations. While the first type of application needs high recall, the second is more precision-oriented. This paper studies the recall/precision trade-off, combining different methods to extract locations. In the context of short posts, applying tools that have been developed for natural language is not sufficient given the nature of tweets which are generally too short to be linguistically correct. Also bearing in mind the high number of posts that need to be handled, we hypothesize that predicting whether a post contains a location or not could make the location extractors more focused and thus more effective. We introduce a model to predict whether a tweet contains a location or not and show that location prediction is a useful pre-processing step for location extraction. We define a number of new tweet features and we conduct an intensive evaluation. Our findings are that (1) combining existing location extraction tools is effective for precision-oriented or recall-oriented results, (2) enriching tweet representation is effective for predicting whether a tweet contains a location or not, (3) words appearing in a geography gazetteer and the occurrence of a preposition just before a proper noun are the two most important features for predicting the occurrence of a location in tweets, and (4) the accuracy of location extraction improves when it is possible to predict that there is a location in a tweet.  相似文献   

基于短时交通流量预测对路网微观交通仿真的研究     

张虎 《苏州市职业大学学报》2021,(1)

针对早高峰短时交通流量预测数据少、波动大的特点,提出用灰色模型进行预测。将灰色GM(2,1)改进为灰色GM(2,1,λ,ρ)预测模型,以提高预测精度。针对粒子群算法(PSO)的早熟现象,将Logistic混沌搜索嵌入到PSO算法,应用混沌粒子群算法(CPSO)寻找灰色GM(2,1,λ,ρ)预测模型最优的参数λ和ρ。结合两者提出了基于CPSO–GM(2,1,λ,ρ)的早高峰短时交通流预测模型。利用VISSIM对研究路网进行微观交通仿真,通过VISSIM–Excel、VBA–Matlab平台实现了短时交通流量预测和路网微观交通仿真数据的交互,对集成交通控制系统的架构进行了方案设计。仿真结果表明,结合流量预测的路网优于固定信号配时下的路网仿真。  相似文献   

新媒体用户的内容消费特征与媒介使用模式——以百度百家号的调研分析结论为例(2)     

喻国明学术工作室  喻国明  刘淼  韩婷 《传媒观察》2020,(5):32-38

本文把视线聚焦在新媒体的媒体语境当中,以百度百家号为例,考察了新媒体用户在内容层面、认知层面和行为层面上的认知与使用模式。基于对百度百家号用户媒介认知与媒介使用情况的网络问卷调查数据,本研究从新媒体用户重点关注的文章类型、内容来源的关注度以及网络内容的信任度三个方面分析了新媒体用户的内容消费特征并提出了优化网络内容平台内容建设机制及信息扩散机制的策略与建议。在用户层面,需重点培养激活核心用户以提升内容生态的活跃度;在平台层面,需纳入优质内容资源,重视品牌建设。  相似文献   

基于RBV的企业信息化绩效评估层次模型     

张嵩  吴绪永 《科学学与科学技术管理》2007,28(6):129-133

以基于资源的企业理论(RBV)为基础,将企业IT资源分为IT基础设施资源、IT人力资源和互补性组织资源三类。指出IT资源对企业绩效影响的过程性,提出基于RBV的信息化绩效评估层次模型,并以实际企业为例,分析每一层次的评估范围和评估指标,帮助企业对信息技术商业价值进行有效的评估。  相似文献