基于模糊神经网络的不同资源禀赋类型连片特困地区减贫绩效评价

Performance evaluation of poverty reduction by connecting different resource endowment types in difficult areas with difficulties based on fuzzy neural network

基于资源性贫困这一原始性贫困视角,结合各连片特困地区的资源禀赋特征,将14个连片特困地区划分为资源禀赋丰富区、资源禀赋中度区、资源禀赋匮乏区3个类别区域。通过构建以农村贫困发生率、农村常住居民基本经济状况、贫困居民居住卫生教育相关指标为输入层,以农村减贫人口为输出层的模糊神经网络,对2014—2016年3类型资源禀赋连片特困地区的减贫绩效进行评价分析。研究发现:各类型资源禀赋连片特困地区减贫绩效呈现逐年上升趋势,但仍有较大提升空间;不同类型片区内部减贫绩效区域差异性较大;连片特困地区资源禀赋越丰富的地区减贫绩效越显著。

Based on the original poverty perspective of resource-based poverty, the paper combines the characteristics of resource endowment in contiguous destitute areas and divides14 contiguous destitute areas into three categories: resource-rich areas, resource- moderate areas, and resource-poor areas. By constructing a fuzzy neural network which takes the occurring ratio of rural poverty, the basic economic status of rural residents, and the related indicators of poor residents’ health education as the input layer, the poverty reduction population in rural areas as the output layer, the poverty reduction performance of three types of resource endowment contiguous poverty-stricken areas from2014 to2016 are evaluated and analyzed. The study found: first, the poverty reduction performance of all types of resource endowment contiguous poverty-stricken areas shows an upward trend year by year, but there is still much room for improvement;second, there are significant regional differences in poverty reduction performance within different types of districts;third, the difficult areas which have the much richer resource endowment, the poverty reduction performance much better.