期刊文献+
共找到2篇文章
< 1 >
每页显示 20 50 100
An Effective Concept Extraction Method for Improving Text Classification Performance
1
作者 ZHANGYuntao GONGLing +1 位作者 WANGYongcheng YINZhonghang 《Geo-Spatial Information Science》 2003年第4期66-72,共7页
This paper presents anew way to extract concept that can beused to improve text classification per-formance (precision and recall). Thecomputational measure will be dividedinto two layers. The bottom layercalled docum... This paper presents anew way to extract concept that can beused to improve text classification per-formance (precision and recall). Thecomputational measure will be dividedinto two layers. The bottom layercalled document layer is concernedwith extracting the concepts of parti-cular document and the upper layercalled category layer is with findingthe description and subject concepts ofparticular category. The relevant im-plementation algorithm that dramatic-ally decreases the search space is dis-cussed in detail. The experiment basedon real-world data collected from Info-Bank shows that the approach is supe-rior to the traditional ones. 展开更多
关键词 text classification concept extraction characteristic term associationrule ALGORITHM
下载PDF
Extraction of Basic Trends of Urban Expansion in China over Past 40 Years from Satellite Images 被引量:4
2
作者 WEN Qingke ZHANG Zengxiang +10 位作者 SHI Lifeng ZHAO Xiaoli LIU Fang XU Jinyong YI Ling LIU Bin WANG Xiao ZUO Lijun HU Shunguang LI Na LI Minmin 《Chinese Geographical Science》 SCIE CSCD 2016年第2期129-142,共14页
If urban sprawl is to be avoided in China in the next ten years, it is not only crucial to understand the overall history, current status, and future trends of urban expansion there, but also these differences, and th... If urban sprawl is to be avoided in China in the next ten years, it is not only crucial to understand the overall history, current status, and future trends of urban expansion there, but also these differences, and this is presently lacking. In this study, remotely sensed images with approximately 30 m spatial resolution were used to quantitatively assess the spatial and temporal patterns of urban expansion of 60 Chinese cities(1973–2013). Urban-expansion-process curves of the cities studied were drawn using annual expansion area as an indicator. Curve similarity analysis generated four basic process modes of urban expansion in China. These included cities that: 1) peaked around 2004 and then decelerated; 2) peaked around 2010 and then decelerated; 3) showed sustained acceleration, and 4) showed continued deceleration. Four basic process modes represented cities under different levels of development stage. Geographic location was found to be the most related characteristic to urban expansion process. Regional development policies at the national level in each region also showed highly temporal consistency with fluctuation characteristics of urban expansion process. Urban characteristic such as population size and administrative level were not found to be significantly related to urban expansion-process modes. Understanding the basic process-mode categories well is extremely important for future regional-balance planning and development of macroeconomic policies. 展开更多
关键词 urban expansion urbanization expansion-process mode long term urban development stage curve similarity urban characteristic
下载PDF
上一页 1 下一页 到第
使用帮助 返回顶部