Identification Model of Poverty-prone Population and Analysis of Poverty-causing Factors

doi:10.1117/12.2652463

	Identification Model of Poverty-prone Population and Analysis of Poverty-causing Factors
	Wu, Yiwen; Duan, Huiyu; Wang, Jikui
	2022
会议名称	2022 International Conference on Intelligent Systems, Communications, and Computer Networks, ISCCN 2022
会议录名称	Proceedings of SPIE - The International Society for Optical Engineering
卷号	12332
会议日期	June 17, 2022 - June 19, 2022
会议地点	Chengdu, China
会议录编者/会议主办者	Academic Exchange Information Center (AEIC)
出版者	SPIE
摘要	At the present stage, China's poverty-returning population identification mainly adopts manual identification methods, and many off-target phenomena have occurred. This paper proposes a Fuzzy C-means clustering (FCM) and random forest model for identifying the poverty-prone population to address this problem. Firstly, a multidimensional poverty identification indicator is established based on the sustainable livelihood indicator system (SLIS). Secondly, the dataset was extracted from the 2018 China Family Panel Studies (CFPS) data based on the SLIS system, and FCM was used to cluster the dataset into poor and non-poor. The high confidence poverty data were extracted as the poverty dataset. The FCM was then used to classify the poverty data into those prone to return to poverty and those who are hard to return to poverty. At the same time, random forest is used to construct an accurate identification model for the easy-to-return population on the poverty dataset. The model was evaluated using evaluation indexes such as accuracy. The results showed that the identification results of the model were consistent with the clustering results of the FCM. Finally, the random forest model was used to analyze the poverty-causing factors of the poverty-prone population data, and the main factors that cause poverty were derived. © 2022 SPIE.
关键词	Classification (of information) Clustering algorithms Data mining Forestry Fuzzy systems Fuzzy C-Means clustering Identification modeling Indicators systems Manual identification Poverty-causing factor Poverty-prone population Precise identification Present stage Random forest modeling Sustainable livelihood
DOI	10.1117/12.2652463
收录类别	EI
语种	英语
EI入藏号	20232014084936
EI主题词	Population statistics
EI分类号	716.1 Information Theory and Signal Processing ; 723.2 Data Processing and Image Processing ; 821 Agricultural Equipment and Methods ; Vegetation and Pest Control ; 903.1 Information Sources and Analysis ; 961 Systems Science
原始文献类型	Conference article (CA)
文献类型	会议论文
条目标识符	http://ir.lzufe.edu.cn/handle/39EH0E1M/35661
专题	信息工程与人工智能学院
通讯作者	Wang, Jikui
作者单位	School of Information Engineering, Lanzhou University of Finance and Economics, Lanzhou; 730020, China
通讯作者单位	兰州财经大学
推荐引用方式 GB/T 7714	Wu, Yiwen,Duan, Huiyu,Wang, Jikui. Identification Model of Poverty-prone Population and Analysis of Poverty-causing Factors[C]//Academic Exchange Information Center (AEIC):SPIE,2022.