施工组织设计是指导工程建设全过程活动的技术、经济和组织的综合性文件,随着自然语言处理(natural language processing,NLP)等人工智能技术的发展,针对施工组织设计文档智慧辅助审查中基础性工作:文本分类问题开展研究。为实现施工组...施工组织设计是指导工程建设全过程活动的技术、经济和组织的综合性文件,随着自然语言处理(natural language processing,NLP)等人工智能技术的发展,针对施工组织设计文档智慧辅助审查中基础性工作:文本分类问题开展研究。为实现施工组织设计文本的自动分类,运用Word2vec词嵌入技术对文本进行向量化表示,基于双向长短时记忆网络(bi-directional long short-term memory,Bi-LSTM)捕捉文本上下文序列信息,融入Attention机制,提取文本有效信息,采用softmax激活函数分类。结果表明:Attention Bi-LSTM在房建数据集上达到0.97的准确率、召回率以及F值,整体分类效果在正确率、宏平均、加权平均上均优于其他模型。融入Attention机制的Bi-LSTM文本分类模型通过双向捕获文本的特征并利用Attention机制提取有效信息,达到了联合优化的作用,提高了模型的分类性能。展开更多
Landsat Thematic Mapper （TM） and Enhanced Thematic Mapper Plus （ETM＋） images in 1985, 1986, 1993, 1994 and 2001 were used to quantify the land use and land cover changes （LUCC） in the Zhejiang coastal region wi...Landsat Thematic Mapper （TM） and Enhanced Thematic Mapper Plus （ETM＋） images in 1985, 1986, 1993, 1994 and 2001 were used to quantify the land use and land cover changes （LUCC） in the Zhejiang coastal region with a stratified unsupervised classification technique in conjunction with visual interpretation and to attempt an identification of the socioeconomic driving forces. In level I an overall accurate classification was achieved using a modified Anderson＇s Ⅰ/Ⅱ/Ⅲ-level classification scheme. The overall accuracy of the land use classification at Anderson level Ⅰ were 89.7% （1985）, 91.6% （1993）, and 90.4% （2001）. The most rapid land use change was a dramatic increase in urban or built-up areas, which quadrupled from 1985 to 2001. Over 90% of this newly expanded built-up area was originally paddy fields or other croplands. In different parts of the Zhejiang coastal region, urban land expansion was spatially uneven. Temporally, land use development did not stabilized, and the two study periods of time （1985-1993 and 1993-2001） had different transition styles. Socioeconomic factors, such as gross domestic product, total population, and financial expenditure, were all highly correlated with the expansion of urban or built-up areas. Based on the degree of urban sprawl and socioeconomic factors, cities and towns were further divided into six subgroups, which may help decision makers improve land use for the region.展开更多
Two field experiments were conducted in Jiashan and Yuhang towns of Zhejiang Province, China, to study the feasibility of predicting N status of rice using canopy spectral reflectance. The canopy spectral reflectance ...Two field experiments were conducted in Jiashan and Yuhang towns of Zhejiang Province, China, to study the feasibility of predicting N status of rice using canopy spectral reflectance. The canopy spectral reflectance of rice grown with different levels of N inputs was determined at several important growth stages. Statistical analyses showed that as a result of the different levels of N supply, there were significant differences in the N concentrations of canopy leaves at different growth stages. Since spectral reflectance measurements showed that the N status of rice was related to reflectance in the visible and NIR (near-infrared) ranges, observations for rice in 1 nm bandwidths were then converted to bandwidths in the visible and NIR spectral regions with IKONOS (space imaging) bandwidths and vegetation indices being used to predict the N status of rice. The results indicated that canopy reflectance measurements converted to ratio vegetation index (RVI) and normalized difference vegetation index (NDVI) for simulated IKONOS bands provided a better prediction of rice N status than the reflectance measurements in the simulated IKONOS bands themselves. The precision of the developed regression models using RVI and NDVI proved to be very high with R2 ranging from 0.82 to 0.94, and when validated with experimental data from a different site, the results were satisfactory with R2 ranging from 0.55 to 0.70. Thus, the results showed that theoretically it should be possible to monitor N status using remotely sensed data.展开更多
The radial basis function （RBF） emerged as a variant of artificial neural network. Generalized regression neural network （GRNN） is one type of RBF, and its principal advantages are that it can quickly learn and ra...The radial basis function （RBF） emerged as a variant of artificial neural network. Generalized regression neural network （GRNN） is one type of RBF, and its principal advantages are that it can quickly learn and rapidly converge to the optimal regression surface with large number of data sets. Hyperspectral reflectance （350 to 2500 nm） data were recorded at two different rice sites in two experiment fields with two cultivars, three nitrogen treatments and one plant density （45 plants m^-2）. Stepwise multivariable regression model （SMR） and RBF were used to compare their predictability for the leaf area index （LAI） and green leaf chlorophyll density （GLCD） of rice based on reflectance （R） and its three different transformations, the first derivative reflectance （D1）, the second derivative reflectance （D2） and the log-transformed reflectance （LOG）. GRNN based on D1 was the best model for the prediction of rice LAI and CLCD. The relationships between different transformations of reflectance and rice parameters could be further improved when RBF was employed. Owing to its strong capacity for nonlinear mapping and good robustness, GRNN could maximize the sensitivity to chlorophyll content using D1. It is concluded that RBF may provide a useful exploratory and predictive tool for the estimation of rice biophysical parameters.展开更多
When tunnels are constructed at shallow depths in areas with poor geological conditions,such as portal sections,valleys and hillsides in regions with granitic bedrock,considerable excavation-induced deformation of the...When tunnels are constructed at shallow depths in areas with poor geological conditions,such as portal sections,valleys and hillsides in regions with granitic bedrock,considerable excavation-induced deformation of the surrounding rock may occur,potentially resulting in tunnel collapses.The main reason for these problems is the lack of understanding of the deformation mechanism and evolution of the soft granitic rock surrounding the tunnel and the adoption of inappropriate construction technology and methods.This article analyzes the deformation mechanism of the rock surrounding a shallow tunnel based on in situ monitoring data as a case study and suggests that certain measures should be taken to effectively control the deformation of the surrounding rock and to minimize the potential for tunnel collapse.The results show that the deformation of the granitic soil surrounding the tunnel can be divided into three stages:the rapid deformation stage,the slow deformation stage and the stabilization stage.Appropriate construction methods should be carefully selected to ensure safety during tunnel excavation in the first stage.To avoid secondary disasters caused by tunnel collapses,three treatment measures may be implemented as part of safety management:enhancing the monitoring of the surrounding rock deformation,adjusting the construction methods and optimizing the support systems.In particular,accurate monitoring data and timely information feedback play a vital role in tunnel construction.Therefore,engineers with considerable engineering experience and professional knowledge are needed to analyze the monitoring data and make accurate predictions of tunnel deformation to ensure that reasonable measures are taken in the process of shallow tunnel excavation.展开更多
Mycoplasma ovipneumoniae, a kind of mycoplasma bacteria, commonly infects the respiratory tract causing respiratory disease in sheep and goats worldwide. Here, the complete genome sequence of M. ovipneumoniae strain N...Mycoplasma ovipneumoniae, a kind of mycoplasma bacteria, commonly infects the respiratory tract causing respiratory disease in sheep and goats worldwide. Here, the complete genome sequence of M. ovipneumoniae strain NM2010 isolated from a sheep in China was reported for the ifrst time.展开更多
文摘施工组织设计是指导工程建设全过程活动的技术、经济和组织的综合性文件,随着自然语言处理(natural language processing,NLP)等人工智能技术的发展,针对施工组织设计文档智慧辅助审查中基础性工作:文本分类问题开展研究。为实现施工组织设计文本的自动分类,运用Word2vec词嵌入技术对文本进行向量化表示,基于双向长短时记忆网络(bi-directional long short-term memory,Bi-LSTM)捕捉文本上下文序列信息,融入Attention机制,提取文本有效信息,采用softmax激活函数分类。结果表明:Attention Bi-LSTM在房建数据集上达到0.97的准确率、召回率以及F值,整体分类效果在正确率、宏平均、加权平均上均优于其他模型。融入Attention机制的Bi-LSTM文本分类模型通过双向捕获文本的特征并利用Attention机制提取有效信息,达到了联合优化的作用,提高了模型的分类性能。
文摘Landsat Thematic Mapper （TM） and Enhanced Thematic Mapper Plus （ETM＋） images in 1985, 1986, 1993, 1994 and 2001 were used to quantify the land use and land cover changes （LUCC） in the Zhejiang coastal region with a stratified unsupervised classification technique in conjunction with visual interpretation and to attempt an identification of the socioeconomic driving forces. In level I an overall accurate classification was achieved using a modified Anderson＇s Ⅰ/Ⅱ/Ⅲ-level classification scheme. The overall accuracy of the land use classification at Anderson level Ⅰ were 89.7% （1985）, 91.6% （1993）, and 90.4% （2001）. The most rapid land use change was a dramatic increase in urban or built-up areas, which quadrupled from 1985 to 2001. Over 90% of this newly expanded built-up area was originally paddy fields or other croplands. In different parts of the Zhejiang coastal region, urban land expansion was spatially uneven. Temporally, land use development did not stabilized, and the two study periods of time （1985-1993 and 1993-2001） had different transition styles. Socioeconomic factors, such as gross domestic product, total population, and financial expenditure, were all highly correlated with the expansion of urban or built-up areas. Based on the degree of urban sprawl and socioeconomic factors, cities and towns were further divided into six subgroups, which may help decision makers improve land use for the region.
基金Project supported by the National Natural Science Foundation of China (Nos. 30070444 and 40201021)the British Council (No. SHA/992/308)the Doctor Foundation of Qingdao University of Science and Technology.
文摘Two field experiments were conducted in Jiashan and Yuhang towns of Zhejiang Province, China, to study the feasibility of predicting N status of rice using canopy spectral reflectance. The canopy spectral reflectance of rice grown with different levels of N inputs was determined at several important growth stages. Statistical analyses showed that as a result of the different levels of N supply, there were significant differences in the N concentrations of canopy leaves at different growth stages. Since spectral reflectance measurements showed that the N status of rice was related to reflectance in the visible and NIR (near-infrared) ranges, observations for rice in 1 nm bandwidths were then converted to bandwidths in the visible and NIR spectral regions with IKONOS (space imaging) bandwidths and vegetation indices being used to predict the N status of rice. The results indicated that canopy reflectance measurements converted to ratio vegetation index (RVI) and normalized difference vegetation index (NDVI) for simulated IKONOS bands provided a better prediction of rice N status than the reflectance measurements in the simulated IKONOS bands themselves. The precision of the developed regression models using RVI and NDVI proved to be very high with R2 ranging from 0.82 to 0.94, and when validated with experimental data from a different site, the results were satisfactory with R2 ranging from 0.55 to 0.70. Thus, the results showed that theoretically it should be possible to monitor N status using remotely sensed data.
基金Project supported by the National Natural Science Foundation of China (No.40571115)the National High Tech-nology Research and Development Program (863 Program) of China (Nos.2006AA120101 and 2007AA10Z205)
文摘The radial basis function （RBF） emerged as a variant of artificial neural network. Generalized regression neural network （GRNN） is one type of RBF, and its principal advantages are that it can quickly learn and rapidly converge to the optimal regression surface with large number of data sets. Hyperspectral reflectance （350 to 2500 nm） data were recorded at two different rice sites in two experiment fields with two cultivars, three nitrogen treatments and one plant density （45 plants m^-2）. Stepwise multivariable regression model （SMR） and RBF were used to compare their predictability for the leaf area index （LAI） and green leaf chlorophyll density （GLCD） of rice based on reflectance （R） and its three different transformations, the first derivative reflectance （D1）, the second derivative reflectance （D2） and the log-transformed reflectance （LOG）. GRNN based on D1 was the best model for the prediction of rice LAI and CLCD. The relationships between different transformations of reflectance and rice parameters could be further improved when RBF was employed. Owing to its strong capacity for nonlinear mapping and good robustness, GRNN could maximize the sensitivity to chlorophyll content using D1. It is concluded that RBF may provide a useful exploratory and predictive tool for the estimation of rice biophysical parameters.
基金supported by the Project of Science and Technology Research and Development Plan of China Railway (Grant No. P2018G045)the Open Fund of Key Laboratory of Mountain Hazards and Earth Surface Processes, Chinese Academy of Sciencesthe Open Fund of Hunan International Scientific and Technological Innovation Cooperation Base of Advanced Construction and Maintenance Technology of Highway (Changsha University of Science & Technology) (Grant No. kfj190803)。
文摘When tunnels are constructed at shallow depths in areas with poor geological conditions,such as portal sections,valleys and hillsides in regions with granitic bedrock,considerable excavation-induced deformation of the surrounding rock may occur,potentially resulting in tunnel collapses.The main reason for these problems is the lack of understanding of the deformation mechanism and evolution of the soft granitic rock surrounding the tunnel and the adoption of inappropriate construction technology and methods.This article analyzes the deformation mechanism of the rock surrounding a shallow tunnel based on in situ monitoring data as a case study and suggests that certain measures should be taken to effectively control the deformation of the surrounding rock and to minimize the potential for tunnel collapse.The results show that the deformation of the granitic soil surrounding the tunnel can be divided into three stages:the rapid deformation stage,the slow deformation stage and the stabilization stage.Appropriate construction methods should be carefully selected to ensure safety during tunnel excavation in the first stage.To avoid secondary disasters caused by tunnel collapses,three treatment measures may be implemented as part of safety management:enhancing the monitoring of the surrounding rock deformation,adjusting the construction methods and optimizing the support systems.In particular,accurate monitoring data and timely information feedback play a vital role in tunnel construction.Therefore,engineers with considerable engineering experience and professional knowledge are needed to analyze the monitoring data and make accurate predictions of tunnel deformation to ensure that reasonable measures are taken in the process of shallow tunnel excavation.
基金supported by the Nationai Key Technology R&D Program of China (2011BAD18B01)
文摘Mycoplasma ovipneumoniae, a kind of mycoplasma bacteria, commonly infects the respiratory tract causing respiratory disease in sheep and goats worldwide. Here, the complete genome sequence of M. ovipneumoniae strain NM2010 isolated from a sheep in China was reported for the ifrst time.
