综合LDA与特征维度的丽江古城意象感知分析     

梁晨晨  李仁杰 《地理科学进展》2020,39(4):614-626

论文通过建立基于LDA(Latent Dirichlet Allocation)模型和包含两级特征维度的旅游地意象感知研究框架,将LDA主题模型用于旅游微博文本分析,以特征维度半定量刻画旅游地意象感知特征,减少LDA主题凝练的主观性,帮助研究者在特定维度框架约束下准确、客观地提取旅游地意象特征。丽江古城案例证明,一级特征维度可以完整勾勒出丽江古城意象感知的基本框架,包括以聚落形态、音乐意境、标志人物、休闲空间和纳西美食为核心的5组空间与景观元素,深度旅游者、城市居民、年轻人、女孩子4类人群的特殊感知体验,及旅游者与环境要素的不同互动特征;二级特征维度进一步精细解读丽江古城的意象感知特征,表现为丽江古城慢活性、夜生活和浪漫之都的文化意象、旅游者对地方文化与现代风情融合的凝视与体验等。结合特征维度的LDA模型,准确构建了意象基本框架,成功刻画了丽江古城的形象及精细特征,并能进一步解析意象的形成机制,为旅游地意象感知研究提供了新视角,有助于深度解读意象形成的地方意义,厘清认知、情感和行为意象间的关系。  相似文献   

基于AutoCAD的表格模板设计开发     

曾宪珪  徐昌荣 《海洋测绘》2004,24(5):58-61

采用图形模板和文本模板技术,设计开发了基于AutocAD环境的表格模板,利用表格模板可以自动绘制地籍、地形测量中的各种表格。同时还开发了一套表格绘制与表格编辑命令,扩大了AutoCAD的应用范围。  相似文献   

The persistence and role of basin structures on the 3D architecture of the Marañón Fold-Thrust Belt,Peru     

《Journal of South American Earth Sciences》2014

The 3D architecture of fold-thrust belts commonly involves thin-skinned and thick-skinned deformation. Both thick- and thin-skinned deformation styles have been suggested to occur in the Marañón Fold-Thrust Belt (MFTB) in Peru, but the relative timing and strain partitioning associated with them are not well understood. We demonstrate that inherited basement structures along the Peruvian convergent margin reactivated during the evolution of the MFTB. We present results from field mapping, interpretation of remote sensing imagery, and cross section construction and restoration. The results show that the Chonta Fault, a median pre-folding basin normal fault, was inverted and acted as a mechanical buttress during initial east-vergent contraction of the fold-thrust belt. This fault separates the belt into two domains of distinctly different structural styles. During the Eocene, units to the west of the Chonta Fault deformed by folding, using the fault as a buttress, and subsequently propagated eastward by thin-skinned thrusting. This was followed in the Miocene by west-vergent, basement-involved deformation, which overprinted the earlier east-vergent, thin-skinned structures. The proposed tectonic model of the MFTB highlights the role of basement-fault reactivation during orogenesis and the involvement of deep structures in partitioning deformation styles.  相似文献   

重大公共卫生事件中的舆情分析方法研究——以新冠肺炎疫情为例     

韩珂珂  邢子瑶  刘哲  刘峻明  张晓东 《地球信息科学学报》2021,23(2):331-340

2019年12月以来,新冠肺炎疫情迅速席卷全球,截至北京时间2020年5月10日16时40分,全球累计确诊病例4 115 662例,已成为全球聚焦的主要话题。微博等社交媒体平台成为此次疫情相关信息传播的重要渠道和公众情绪的有效传感器之一。对微博信息进行深入挖掘分析不但能研判舆情特点,更有助于政府对公众的情绪进行针对性疏导,合理管控舆情。因此,本文采集了2020年1月18日到2020年1月28日期间关于新冠肺炎的33万余条新浪微博数据,基于Louvain和Kmeans的空间聚类、改进的BTM主题词提取等算法,将用户关注热点信息和情感特征作为地域标签,构建了反映情感特征、地域关联与热点关注在内的舆情评价方法,实现了基于位置的信息融合,能够分析不同区域的舆情特点与关注主题差异。研究表明：基于BERT词向量的BTM主题词提取方法可以有效弥补传统主题词提取的计算量大、数据冗余等缺点,在热点挖掘时具有更强的表达能力;不同区域关注热点具有一定的差异性,结合省级、市级及基于Louvain-Kmeans的空间聚类的多尺度舆情分析方法,可以全方位展现不同区域舆情特点。本文提出的舆情分析方法可以有效反映不同区域的舆情特征,为重大公共卫生事件的舆情分析提供参考。  相似文献   

SVM在文本自动分类中的应用   总被引：3，自引：0，他引：3  

杨晓懿  刘嘉勇  陈淑敏 《成都信息工程学院学报》2005,20(2):121-124

支持向量机(S、M)是基于统计学习理论的一种新的模式识别技术。介绍了文本自动分类技术的主要研究概况，并进一步从支持向量机的原理及其在文本分类中的优点等方面阐述了支持向量机在文本分类中的应用。  相似文献   

中文文本中时间信息解析方法   总被引：1，自引：0，他引：1  

张春菊  张雪英  李明  王曙 《地理与地理信息科学》2014,30(6)

探讨了基于触发词汇和规则模型相结合的中文文本中时间信息解析方法。通过分析、归纳中文文本中时间信息描述特点,构建时间词汇词典和时间信息描述模式库,设计时间信息抽取、规范化表达和语义推理算法,实现了中文文本中时间信息的解析。实验结果表明,中文文本中时间信息抽取的准确率、召回率和F1值分别为75.00%、88.24%和40.54%,为泛在时空信息动态关联更新和实时挖掘分析提供数据源,且通过与空间维数据有机地、交互地组织,能够实时展现地理现象和事物的时空演化过程、时空分布特征,从而推动地理信息检索、LBS等地理信息服务向动态化、多维化方向发展。  相似文献   

Photosynthetic characteristics of sinking microalgae under the sea ice     

《Polar Science》2014,8(4):385-396

The photosynthetic characteristics of sinking a microalgal community were studied to compare with the ice algal community in the sea ice and the phytoplankton community in the water column under the sea ice at the beginning of the light season in the first-year sea ice ecosystem on the Mackenzie Shelf, in the western Canadian Arctic. The phytoplankton community was collected using a water bottle, whereas the sinking algal community was collected using particle collectors, and the ice algal community was obtained by using an ice-core sampler from the bottom portion of ice core. Photosynthesis versus irradiance (P-E) incubation experiments were conducted on deck to obtain the initial slope (α^B) and the maximum photosynthetic rate (P_m^B) of the three algal communities. The α^B and the P_m^B of the light saturation curve, and chlorophyll a (Chl a) specific absorption coefficient (ā_ph*) between the sinking microalgal community and the ice algal community were similar and were distinctly different from the phytoplankton community. The significant linear relationship between α^B and P_m^B, which was obtained among the three groups, may suggest that a photo-acclimation strategy is common for all algal communities under the low light regime of the early season. Although the sinking algal community could be held for the entire duration of deployment at maximum, this community remained photosynthetically active once exposed to light. This response suggests that sinking algal communities can be the seed population, which results in a subsequent phytoplankton bloom under the sea ice or in a surface layer, as well as representing food for the higher trophic level consumers in the Arctic Ocean even before the receding of the sea ice.  相似文献   

一种融合文本中地理位置和土地利用/覆被信息的野生动物活动细粒度定位方法     

尹文萍  高宸  樊辉  谢菲  张鑫 《地球信息科学学报》2022,24(7):1363-1374

文本蕴含大量地理位置描述信息,有效融合地理关联信息以实现文本的精细定位是地理信息服务的难点。本文提出一种融合土地利用/覆被信息的描述地理位置的细粒度定位方法：在文本描述地理关联信息（地理位置实体、土地利用/覆被实体与空间关系）抽取、土地利用/覆被精细分类与地理位置粗粒度匹配定位的基础上,使用自然语言空间关系近似转换模型,确定地理位置的细粒度定位范围;基于土地利用/覆被实体及其周边精细分类信息,在该范围内检索匹配,确定地理位置的细粒度定位坐标。本文以野生亚洲象活动/肇事监测文本为例开展实验,并用匹配率与位置精度评价定位质量,结果表明：本文方法显著提升了地理位置的细粒度定位质量,实验精确匹配率（81.51%）、位置误差距离的均值（65.97 m）及其≤50 m的比例（70.50%）均优于国内主流在线地理编码与地名检索服务结合空间关系或其单独使用结果。该方法有助于完善地理位置定位方法体系、提升地理信息空间化质量,并可服务于野生动物活动/肇事监测预警等精细定位任务。  相似文献   

实体数据模型在航行指南信息组织中的应用     

房宏图  丁金挺  张立华 《海洋测绘》2014,34(5):72-75

针对当前海图表达航行环境不完备、多种有效信息不能有效集成等不足,提出利用实体数据模型构建航行指南信息数据库的方法。文中介绍了实体数据模型,提出了航行指南信息数据集成的组织方法,构建了航行信息数据模型,并开发了航海图文信息系统,实现了航行指南信息的管理查询和应用。实验表明,基于实体数据模型的航行指南信息组织方法正确、有效。  相似文献   

A comparison of techniques for generating forest ownership spatial products     

《Applied geography (Sevenoaks, England)》2014

To fully understand forest resources, it is imperative to understand the social context in which the forests exist. A pivotal part of that context is the forest ownership. It is the owners, operating within biophysical and social constraints, who ultimately decide if the land will remain forested, how the resources will be used, and by whom. Forest ownership patterns vary substantially across the United States. These distributions are traditionally represented with tabular statistics that fail to capture the spatial patterns of ownership. Existing spatial products are not sufficient for many strategic-level planning needs because they are not electronically available for large areas (e.g., parcels maps) or do not provide detailed ownership categories (e.g., only depict private versus public ownership). Thiessen polygon, multinomial logit, and classification tree methods were tested for producing a forest ownership spatial dataset across four states with divergent ownership patterns: Alabama, Arizona, Michigan, and Oregon. Over 17,000 sample points with classified forest ownership, collected as part of the USDA Forest Service, Forest Inventory and Analysis (FIA) program, were divided into two datasets, one used as the dependent variable across all of the models and 10 percent of the points were retained for validation across the models. Additional model inputs included a polygon coverage of public lands from the Conservation Biology Institute’s Protected Areas Database (PAD) and data representing human population pressures, road densities, forest characteristics, land cover, and other attributes. The Thiessen polygon approach predicted ownership patterns based on proximity to the sample points in the model dataset and subsequent combining with the PAD ownership data layer. The multinomial logit and classification tree approaches predicted the ownership at the validation points based on the PAD ownership information and data representing human population, road, forest, land cover, and other attributes. The percentage of validation points across the four states correctly predicted ranged from 76.3 to 78.9 among the methods with corresponding weighted kappa values ranging from 0.73 to 0.76. Different methods performed slightly, but statistically significantly, better in different states Overall, the Thiessen polygon method was deemed preferable because: it has a lower bias towards dominant ownership categories; requires fewer inputs; and is simpler to implement.  相似文献