Local word vectors guiding keyphrase extraction     

Eirini Papagiannopoulou  Grigorios Tsoumakas 《Information processing & management》2018,54(6):888-902

Automated keyphrase extraction is a fundamental textual information processing task concerned with the selection of representative phrases from a document that summarize its content. This work presents a novel unsupervised method for keyphrase extraction, whose main innovation is the use of local word embeddings (in particular GloVe vectors), i.e., embeddings trained from the single document under consideration. We argue that such local representation of words and keyphrases are able to accurately capture their semantics in the context of the document they are part of, and therefore can help in improving keyphrase extraction quality. Empirical results offer evidence that indeed local representations lead to better keyphrase extraction results compared to both embeddings trained on very large third corpora or larger corpora consisting of several documents of the same scientific field and to other state-of-the-art unsupervised keyphrase extraction methods.  相似文献   

考虑充电和等待时间的集装箱码头AGV调度     

周小凡  苌道方  余芳  高银萍 《上海海事大学学报》2019,40(3):1-5

为提高自动化集装箱码头自动导引小车(automated guided vehicle,AGV)作业效率和利用率,考虑AGV的电量续航能力和重空载的耗电差异,在AGV任务选择时综合考虑任务距离和各任务紧急程度,并设置AGV充电结束条件以减少AGV排队等待的时间,建立以最小化完成任务总时间为目标的AGV调度模型。用Java进行实例求解。结果表明,对AGV采用多频次充电并将其允许工作电量百分比设定为71%时,完成任务总时间最短,耗电量最小,且AGV利用率较高。  相似文献   

Toward a moral economy of money? Money as a creature of democracy     

Jakob Feinig 《Journal of Cultural Economy》2020,13(5):531-547

ABSTRACT

This paper proposes a novel approach for understanding money users’ relation to monetary governance institutions. It first describes the stakes involved in monetary governance from a neo-chartalist/MMT perspective. In a second step, it discusses existing contributions on the relation between money issuer and money users, highlighting the literatures on central bank legitimacy and the social construction of money. It argues that neither allows for an analysis of the relation between monetary institutions and money users that takes the latter’s knowledge seriously. It then argues that the concept of moral economy can enrich scholarly analysis. Moral economies of money are defined as collective practices in which money users articulate demands as part of an understanding of money as a public good. Finally, the paper deploys the moral economy of money perspective to reconstruct the changing relation between institutions of monetary governance and money users since the Great Depression in the U.S. It shows how New Dealers silenced a moral economy of money, discusses fragmented moral economies after World War II, and the partial reemergence of such moral economies after the Great Financial Crisis. The paper concludes by discussing political implications and suggestions for further research.  相似文献   

Health-related fitness knowledge growth in middle school years: Individual- and school-level correlates     

Xihe Zhu  Justin A. Haegele  Haichun Sun 《运动与健康科学(英文)》2020,9(6):664-669

BackgroundHealth-related fitness knowledge (HRFK) has been an essential concept for many health and physical education programs. There has been limited understanding and longitudinal investigation on HRFK growth. This longitudinal study examined HRFK growth and its individual- and school-level correlates in middle school years under 1 curriculum condition: Five for Life.MethodsParticipants were 12,044 students from 47 middle schools. Data were collected at both individual/participant and school/institution levels. Individual-level variables included gender, grade, and HRFK test scores. School-level variables included percentage of students receiving free and reduced meals (FARM), student-to-faculty ratio for physical education, and school academic performance (SAP). We used hierarchical linear modeling to examine HRFK 3-year growth in relation to individual- and school-level correlates.ResultsThe average HRFK score at 6th grade for females was 42.81% ± 1.32%. The predicted HRFK growth was 17.06% ± 1.02% per year, holding other factors constant. A 1-standard deviation increase in FARM correlated with a 14.68%-point decrease in predicted test score (p = 0.02). A 1-standard deviation increase in SAP was associated with an 11.90%-point increase in HRFK score. Males had a significantly lower growth rate than females during the middle school years (0.78%/year, p = 0.02).ConclusionThe result showed that both individual- and school-level variables such as gender, FARM, and SAP influenced HRFK growth. Educators should heed gender differences in growth curves and recognize the correlates of school-level variables.  相似文献   

基于DE-SVM的船舶航迹预测模型     

刘娇  史国友  杨学钱  朱凯歌 《上海海事大学学报》2020,41(1):34-39

为提高船舶航迹预测精度,解决准确建模难度大和神经网络易陷入局部最优的问题,考虑实时获取目标船AIS数据较少的特点,提出一种基于支持向量机(support vector machine,SVM)的航迹预测模型。选择AIS数据中的航速、航向和船舶经纬度作为样本特征变量;采用小波阈值去噪的方法处理训练数据;采用差分进化(differential evolution,DE)算法对模型内部参数寻优以提高模型收敛速度和预测精度。选取天津港实船某段航迹的AIS数据,比较基于DE-SVM与基于BP神经网络的航迹预测模型的仿真结果。结果表明,基于DE-SVM的航迹预测模型具有更高的预测精度,简单、可行、高效,且耗时少。  相似文献   

基于NSGAⅡ的带时间窗生鲜品配送路径优化     

李善俊  陈淮莉 《上海海事大学学报》2020,41(2):58-64

考虑到生鲜品的易腐性、高时效性和对运输环境要求高的特点,为减少生鲜品配送企业的配送成本,提高客户满意度,在车辆载重、时间窗、生鲜品保质期等约束条件下,提出将配送总成本最小化和生鲜品新鲜度最大化的多目标车辆路径优化模型。利用改进的非支配排序遗传算法(non-dominated sorting genetic algorithmⅡ,NSGAⅡ)对模型进行求解。求出满足配送总成本最小和生鲜品新鲜度最大的相对较优解,证明模型的有效性。该模型在大规模配送和客户地理位置分布较为分散的情况下,对生鲜品新鲜度的优化较为明显。  相似文献   

集装化危险品物流作业风险因素识别与评价     

何景师  张智勇 《上海海事大学学报》2020,41(4):62-69

为识别与评价集装化危险品物流作业的风险因素，通过鱼骨图分析法构建风险因素评价指标体系。以风险发生的概率和后果为决策变量建立基于熵权 层次分析法（analytic hierarchy process, AHP）约束的数据包络分析(data envelopment analysis, DEA)法的风险评价模型。利用熵权 AHP解决传统DEA法的权重无限性问题，利用DEA法求解风险极大、极小值并对风险因素进行评价与排序。研究发现，人员风险、包装风险达到风险极大值，集装箱风险达到风险极小值。研究得到各风险因素决策单元的风险降低比例，并根据风险因素的特点提出集装化危险品物流作业风险管理的建议。结果表明了该评价模型的适用性和评价方法的科学性。  相似文献   

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   

大面积建成区建筑密度遥感制图产品的精度验证     

王帅  覃驭楚  杨富坤 《中国科学院大学学报》2020,37(1):83-92

大面积建成区建筑密度遥感制图产品能够提供土地开发强度与人类居住环境的基础信息，是支撑人居环境研究和土地利用规划的重要数据。全球人类居住区层（global human settlement layer，GHSL）是由欧盟联合研究中心负责的大面积人居环境制图项目，建成区建筑密度遥感制图产品是GHSL重要的组成部分。目前该产品在欧美地区已经完成了GHSL建成区建筑密度遥感制图产品的验证。然而以中国为代表的东亚区域的建筑物形态和城市布局与欧美等区域有较大的差别，有必要在亚洲地区对其进一步验证。以中国的5个典型城市（上海、西安、长春、昆明和乌鲁木齐）大面积单体建筑物分布图为基础，通过聚合分析和邻域关键点搜寻匹配等算法，生成中国建成区建筑密度栅格图像产品作为验证数据，然后通过回归分析等方法，在像元尺度上对GHSL建成区遥感制图产品进行评价验证。结果显示，GHSL建成区建筑密度产品在较低分辨率下可以反映中国地区建筑密度情况，但在较高分辨率下在高值区过高估计密度。本研究可以为中国地区研发建成区建筑面积密度产品提供依据。  相似文献   

基于MIP-SLA的叶片陶瓷型芯光固化成型技术     

王瑞昌  蒋睿嵩  明新国 《中国科学院大学学报》2020,37(2):162-168

为解决航空发动机空心涡轮叶片陶瓷型芯的3D打印难题，研究基于图像投影的复杂结构陶瓷型芯光固化成型（mask-image projection stereolithography，MIP-SLA）方法。搭建MIP-SLA工艺系统平台，对陶瓷浆料的制备和打印工艺参数的配置进行研究。分析利用球磨机将光敏树脂和陶瓷颗粒进行混合制备陶瓷浆料时，光敏树脂类型、固相含量、陶瓷颗粒粒径、分散剂含量和球磨时间对陶瓷浆料性能的影响。对不同配置参数下的打印效果进行对比分析，对确定的最佳打印工艺参数进行打印效果验证。  相似文献