基于冠层光谱和BP神经网络的水稻叶片氮素浓度估算模型

[目的]快速、准确地诊断水稻叶片氮素营养状况,为水稻氮肥精准管理提供依据。[方法]以江西省农科院8种不同施肥处理的晚稻为研究对象,于主要生育期同步测定了水稻冠层光谱反射率及叶片全氮浓度(Leaf Nitrogen Concentration,LNC),系统分析了原始光谱反射率、一阶微分光谱、"三边"参数以及由350～1 350nm两两波段组合的差值(SD (Rλ1,Rλ2))、比值(SR (Rλ1,Rλ2))及归一化(ND(Rλ1,Rλ2))光谱指数与水稻LNC的相关关系,筛选出敏感参数,并以之为自变量构建了水稻LNC的传统预测模型,另外构建不同指标个数的多元线性与BP神经网络模型,并对模型进行验证。[结果](1)水稻LNC与一阶微分光谱在751nm处的相关性最高(r=0. 822);(2)"三边"参数中的红边面积SDr与LNC的相关性较高(r=0. 687);(3) 750nm附近的红边波段与近红外波段差值组合、550nm附近的绿光波段与近红外波段的比值及归一化差值组合与水稻LNC的相关性较高,以SD (R752,R751)、SR (R534,R1 350)和ND (R534,R1 349)表现最好,相关系数分别为0. 827、-0. 790和0. 788;(4)传统回归模型中以SD(R752,R751)构建的一元线性模型最佳(RC2=0. 665、RV2=0. 750、RMSEV=0. 4%、RPD=2. 034);(5)利用5个指标((R'751、SDr、SD (R752,R751)、SR (R534,R1 350)、ND (R534,R1 349))经逐步回归筛选出的2个指标SD ((R752,R751)和SR (R534,R1 350))构建预测水稻氮素的BP神经网络模型,预测效果最佳,其验证参数值分别为R2=0. 859、RMSEV=0. 302%和RPD=2. 669。[结论]基于单指标构建的传统线性模型计算过程简单但精度略低,而基于2个指标(SD (R752,R751)、SR (R534,R1 350))构建的BP神经网络模型预测精度高于该2指标构建的多元线性模型,表明在指标适合的情况下,BP神经网络对氮素具有较好的预测能力,是一种快速准确估算水稻叶片全氮浓度的方法。     

Opportunities to reduce road traffic injury: new insights from the study of urban areas

Abstract

Over the past four decades considerable efforts have been taken to mitigate the growing burden of road injury. With increasing urbanisation along with global mobility that demands not only safe but equitable, efficient and clean (reduced carbon footprint) transport, the responses to dealing with the burgeoning road traffic injury in low- and middle-income countries has become increasingly complex. In this paper, we apply unique methods to identify important strategies that could be implemented to reduce road traffic injury in the Asia-Pacific region; a region comprising large middle-income countries (China and India) that are currently in the throes of rapid motorisation. Using a convolutional neural network approach, we clustered countries containing a total of 1632 cities from around the world into groups based on urban characteristics related to road and public transport infrastructure. We then analysed 20 countries (containing 689 cities) from the Asia-Pacific region and assessed the global burden of disease attributed to road traffic injury and these various urban characteristics. This study demonstrates the utility of employing image recognition methods to discover new insights that afford urban and transport planning opportunities to mitigate road traffic injury at a regional and global scale.     

Network,knowledge and relationship impacts on innovation in tourism destinations

We combine network structure and firm-level relationship measures to explore the association between innovative behavior, firm position within the network of a destination, and the knowledge and relational trust characteristics of a firm's innovation-oriented relationships. We find current collaboration, shared knowledge and trust are associated with innovative behavior with partner firms, but that betweenness centrality indicates which partners are the most prominent innovators in a population. That is, relationship-level characteristics facilitate innovation partnerships, but network structure characteristics identify the most successful innovative partners. To theory, our findings contribute to efforts in the tourism, innovation and network literature to evaluate the differential effects of knowledge stocks and flows on innovation. For practice, our results suggest that promoters of innovation within a destination should leverage brokerage positions to improve the in-flow of ideas while encouraging the firms that share knowledge and trust to collaborate to apply those ideas.     

Efficiency,total factor productivity and returns to scale in a sustainable perspective: An analysis in the European Union at farm and regional level

For global sustainability it is imperative to find a balance across the three main components of sustainable development which are the economic, social and environmental aspects. However, it is not a simple task to make these contexts compatible, usually because of economic pressures which transform them into opposed objectives. This framework occurs across several dimensions within society and the economy, where the agricultural sector is not an exception. The objective of this study is to analyse the efficiency, total factor productivity and returns to scale in an economic, social and environmental perspective in farms of the European Union (EU) regions through Data Envelopment Analysis (DEA) approaches. The research concerning the returns to scale will be complemented by the Keynesian models. Data obtained from the European Union Farm Accountancy Data Network (FADN) was considered. The results show that in maintaining or improving the levels of production in farms, it is often possible to greatly reduce, in some cases, the consumption of fertilizers and crop protection products. On the other hand, from a social perspective, some European Union regions are more generous in the salaries paid to farming workers and absorb more labour, which in a European context of unemployment, may be an interesting way to realistically look at and be engaged in the agricultural planning in a sustainable way, founding a balanced trade-off among the economic, social and environmental dimensions.     

Evolution of the international air transportation country network from 2002 to 2013

In this research, we analyze the evolution of the international air transportation country network from 2002 to 2013 with two perspectives: The network’s physical topology and the functional network with traffic information. Our analysis shows that the network is scale-free and has the small-world property. The evolution of triadic properties suggests that the network gears towards symmetric, transitive closure. We find that United States, Great Britain, and France are critical from both perspectives; Surprisingly, South Africa is particularly critical from topological point of view. Furthermore, topological and functional criticality are highly correlated to the GDP of a country.     

平台企业主导的创新生态系统稳定性研究：基于企业间网络关系视角

平台企业主导的创新生态系统作为一种特殊类型生态系统，是由平台主导企业提供基本创新架构并与其它相关企业及关联机构组成的网络组织，企业间网络关系是创新生态系统的本质特征。基于企业间网络关系分析平台企业主导的创新生态系统网络的成员、联系、结构及功能特征,讨论网络结构变量对平台企业主导的创新生态系统稳定性的影响，以山东省30个平台企业主导的创新生态系统为调研样本，通过问卷调查方式，对所提出的假设进行检验。数据相关分析和回归分析结果表明：强有力的创新生态系统主导企业、系统内伙伴企业密度、企业本地化以及企业异质性4个因素对创新生态系统稳定性具有显著正向影响；系统内伙伴企业互惠性和居间性与创新生态系统稳定性之间关系不显著。最后，基于研究结论，提出保持平台企业主导的创新生态系统网络稳定性的政策建议。     

军民融合社会关系网络对军民融合新创企业成长的影响

军民融合新创企业是推动我国国防建设和社会经济融合发展的重要力量，军民融合社会关系网络具有丰富的异质性资源，可以有效促进军民融合新创企业成长。借鉴社会网络理论，构建以关系深度、关系广度、关系高度为代表的军民融合社会关系网络、耦合共生与军民融合新创企业成长理论模型，通过对收集的304份军民融合新创企业问卷数据进行实证分析，结果发现：军民融合社会关系网络对军民融合新创企业成长具有正向影响；耦合共生在军民融合社会关系网络与军民融合新创企业成长间发挥中介作用；创业导向显著调节耦合共生与军民融合新创企业成长的关系。     

A tourist kit ‘made in Italy’: An ‘intelligent’ system for implementing new generation destination cards

This study investigates the advantages and the potentiality of the ‘tourist kit’, an Italian solution based on the concept of a prepaid card that is issued by a large postal operator. The destination card can be reloaded by tourists according to their needs and its validity is not restricted to short periods. Thus, the kit provides tourists with an integrated, practical, and flexible tool capable of making their stay more enjoyable as it allows cardholders to choose and buy many products and services at discounted prices. The kit creates customer loyalty by utilising smart technology aimed at collecting accurate tourist information. This model deserves attention because it is probably the world's first case of a large postal operator entering the tourism sector with the proposal of an integrated and advanced destination card scheme. This research also discusses interesting opportunities and challenges related to the implementation of new generation tourist cards.     

网络组织流程协同效应的生成机理研究

文章主要对网络组织流程协同效应的生成机理进行深入研究。鉴于学术界对网络组织流程没有统一的认识，文章在文献分析和逻辑推理的基础上，首先明确界定了网络组织流程的内涵，进而构建了网络组织流程协同效应的概念模型，最后应用多层次回归分析对所采集的数据进行实证分析，验证网络组织流程协同效应的研究假设。结果表明，网络中结点企业间的关系强度正向影响流程协同效应，而网络组织的治理机制在关系强度与流程协同之间起着调节作用，跨组织信息系统起着部分调节作用。该结论对于网络组织的治理实践具有一定的理论和现实意义。     

技术创新网络多维邻近性演化研究

研究技术创新网络多维邻近性是否伴随创新网络生命周期不同发展阶段而呈现出不同演化特征，对创新网络内部伙伴选择、关系治理和创新绩效发展具有重要意义。基于IBM专利合作网络数据，运用Feature Selection方法，从地理邻近、社会邻近、技术邻近、组织邻近和制度邻近5个维度分析技术创新网络多维邻近性演化特征。结果表明：①生命周期视角下，在创新网络创生阶段，企业选择合作伙伴时主要考虑技术邻近性和组织邻近性，成长阶段主要考虑地理邻近性，成熟和衰退阶段主要考虑社会邻近性；②演化视角下，地理邻近性与技术邻近性曲线呈倒U型关系，地理邻近性在成长期达到最高点，技术邻近性在成熟期达到最高点；制度邻近性与组织邻近性呈U型关系，制度邻近性在成长期达到最低点，组织邻近性在成熟期达到最低点;社会邻近性则随着创新网络生命周期发展一直呈上升态势。