State Prediction of Poverty Alleviation Objects Based on HMM and Multidimensional Data

doi:10.16182/j.issn1004731x.joss.20-1006

Abstract

Abstract:

In order to solve the problems of inaccurate prediction of poverty, poverty reduction and poverty returen, and the difficulty in identifying the key factors affecting the state transition, 8 key features and 22 observed states are extracted from the poverty reduction basic data and multi-industry data. The relationship between observed state and implied state is constructed, and the hidden markov model (HMM) of poverty alleviation is established. Data of a deep poverty county for three consecutive years are used as samples for parameter training, test experiment and result verification. The results show that the method has a strong prediction ability for back poverty, poverty and poverty alleviation with low error rate, and can accurately identify the key elements affecting poverty return. The method is of great practical significance for guiding the precise poverty alleviation work.

Key words: hidden markov model(HMM), precise poverty alleviation, data analysis, prediction method, return to poverty

CLC Number:

Jun He, Sunyan Hong, Yifang Zhou, Shikai Shen, Muquan Zou. State Prediction of Poverty Alleviation Objects Based on HMM and Multidimensional Data[J]. Journal of System Simulation, 2022, 34(5): 1118-1126.

Figures/Tables 7

Fig. 1

Fig. 2

Table 1

Table 2

Fig. 3

Fig. 4

Fig. 5

References 23

[1]	聂燕敏. 用大数据提升深度贫困地区脱贫成效[J]. 人民论坛, 2019(15): 50-51.
	Nie Yanmin. Using Big Data to Improve Poverty Alleviation in Deep Poverty-Stricken Areas[J]. People Forum, 2019(15): 50-51.
[2]	何俊, 张德海. 云南少数民族地区精准扶贫大数据智能分析模型[J]. 云南民族大学学报(自然科学版), 2018, 27(3): 249-254.
	He Jun, Zhang Dehai. Intelligent Analysis Model of Big Data for Targeted Poverty Alleviation in Yunnan Minority Areas[J]. Journal of Yunnan University for Nationalities (Natural Science Edition), 2018, 27(3): 249-254.
[3]	刘星辰. 我国精准扶贫面临的深度困境及策略[J]. 合作经济与科技, 2019(20): 28-29.
	Liu Xingchen. The Deep Dilemma and Strategy of Targeted Poverty Alleviation in China[J]. Cooperative Economy and Technology, 2019(20): 28-29.
[4]	王娇. 大数据与精准扶贫研究[J]. 广西质量监督导报, 2019(7): 31-32.
	Wang Jiao. Research on Big Data and Targeted Poverty Alleviation[J]. Guangxi Quality Supervision Guide, 2019(7): 31-32.
[5]	何华征. 论大数据时代精准扶贫的数据伦理问题[J]. 现代经济探讨, 2019(7): 1-9.
	He Huazheng. On the Data Ethics of Targeted Poverty Alleviation in the Era of big Data[J]. Discussion on Modern Economy, 2019(7): 1-9.
[6]	Al-Sayed Mustafa, Khattab Sherif, Omara Fatma Abd El-Sattar. Prediction Mechanisms for Monitoring State of Cloud Resources Using Markov Chain Model[J]. Journal of Parallel and Distributed Computing (S0743-7315), 2016, 96: 163-171.
[7]	Zheng R J, Liu K, Zhu J L, et al. Stochastic Resource Scheduling via Bilayer Dynamic Markov Decision Process in Mobile Cloud Networks[J]. Computer Communications (S0140-3664), 2019, 145: 234-242.
[8]	Zhang X, Li Y X, Wang S Z, et al. Enhancing Stock Market Prediction with Extended Coupled Hidden Markov Model Over Multi-Sourced Data[J]. Knowledge and Information Systems (S0219-1377), 2019, 61(2): 1071-1090.
[9]	Abdelaziz A H, Zeiler S, Kolossa D. Learning Dynamic Stream Weights for Coupled-Hmm-Based Audio-Visual Speech Recognition[J]. IEEE/ACM TASLP (S1063-6692), 2015, 23(5): 863-876.
[10]	吴争, 李瑶虹, 杨晓梅, 等. 基于HMM的无线充电系统PFC装置故障检测[J]. 电力工程技术, 2020, 39(6): 166-171.
	Wu Zheng, Li Yaohong, Yang Xiaomei, et al. Fault Detection of PFC Device in Wireless Charging System based on HMM[J]. Power Engineering Technology, 2020, 39(6): 166-171.
[11]	吴佳, 曾惟如, 陈瀚霖, 等. 基于隐马尔可夫模型的软件状态评估预测方法[J]. 软件学报, 2016, 27(12): 3208-3222.
	Wu Jia, Zeng Weiru, Chen Hanlin, et al. Software State Evaluation and Prediction Method Based on Hidden Markov Model[J]. Acta Software Sinica, 2016, 27(12): 3208-3222.
[12]	Rabiner L R, Juang B H. An Introduction to Hidden Markov Models[J]. IEEE ASSP Magazine (S1556-6072), 1986, 3(1): 4-16.
[13]	Tobias Z, Philipp B, Martin V. Predicting Enhancers in Mammalian Genomes Using Supervised Hidden Markov Models[J]. BMC Bioinformatics (S1471-2105), 2019, 20(1): 157-168.
[14]	Timothy C, Konstantinos G K, Sangarapillai L. Analysis of Hidden Markov Model Learning Algorithms for the Detection and Prediction of Multi-Stage Network Attacks[J]. Future Generation Computer Systems (S0167-739X), 2020, 108: 636-649.
[15]	Charles V, Aparicio J, Zhu J. The Curse of Dimensionality of Decision-Making Units: A Simple Approach to Increase the Discriminatory Power of Data Envelopment Analysis[J]. European Journal of Operational Research (S0377-2217), 2019, 279(3): 929-940.
[16]	Zhao F N, Hung D L S, Wu S Q. K-means Clustering-Driven Detection of Time-Resolved Vortex Patterns and Cyclic Variations Inside a Direct Injection Engine[J]. Applied Thermal Engineering (S1359-4311), 2020, 180(5): 115810.
[17]	Zhang J, Wang F, Zhong Z, et al. Continuous Phase Modulation Classification via Baum-Welch Algorithm[J]. IEEE Communications Letters (S1089-7798), 2018, 22(7): 1390-1393.
[18]	Duan H N, Abdullah R, Pascal P. Discriminative Training of Feed-Forward and Recurrent Sum-Product Networks by Extended Baum-Welch[J]. International Journal of Approximate Reasoning (S1873-4731), 2020, 124: 66-81.
[19]	Chung E J. Nanoparticle Strategies for Biomedical Applications: Reviews from the University of Southern California Viterbi School of Engineering[J]. SLAS Technology (S2472-6303), 2019, 24(2): 321-334.
[20]	刘云, 袁浩恒. 数据挖掘中并行离散化数据准备优化[J]. 四川大学学报(自然科学版), 2018, 55(5): 993-999.
	Liu Yun, Yuan Haoheng. Optimization of Parallel Discrete Data Preparation in Data Mining[J]. Journal of Sichuan University (Natural Science Edition), 2018, 55(5): 993-999.
[21]	刘天阳, 郭禾, 王宇新, 等. 海面图像单应的估算及数据归一化方法[J]. 计算机工程与应用, 2011, 47(13): 181-185, 222.
	Liu Tianyang, Guo He, Wang Yuxin, et al. Estimation of Sea Surface Image Homography and Data Normalization Method[J]. Computer Engineering and Application, 2011, 47(13): 181-185, 222.
[22]	武琰, 樊海红. 移动终端冗余运营数据迭代消除仿真研究[J]. 计算机仿真, 2019, 36(7): 445-448, 458.
	Wu Yan, Fan Haihong. Simulation Study on Iterative Elimination of Redundant Operation Data of Mobile Terminals[J]. Computer Simulation, 2019, 36(7): 445-448, 458.
[23]	刘彦随, 周扬, 刘继来. 中国农村贫困化地域分异特征及其精准扶贫策略[J]. 中国科学院院刊, 2016, 31(3): 269-278.
	Liu Yansui, Zhou Yang, Liu Jilai. Regional Differentiation Characteristics of Poverty Alleviation in Rural China and Its Targeted Poverty Alleviation Strategy[J]. Journal of Chinese Academy of Ciences, 2016, 31(3): 269-278.

序号	关键特征(观察状态)
1	家庭特征(6人及以下)
2	家庭特征(6人以上)
3	收入特征(2500元以下)
4	收入特征(2 500~5 000元)
5	收入特征(5 000元以上)
6	教育特征(文化程度中学及以下)
7	教育特征(文化程度中学以上)
8	教育特征(在校生3人及以下)
9	教育特征(在校生3人以上)
10	生产特征(占家庭人口50%及以下)
11	生产特征(占家庭人口50%以上)
12	主观特征(平均务工时间6个月及以下)
13	主观特征(平均务工时间6个月以上)
14	主观特征(务工月收入3 000元及以下)
15	主观特征(务工月收入3 000元以上)
16	客观特征(因负担致贫5种)
17	客观特征(因发展条件致贫5种)
18	政策特征(享受民政兜底)
19	政策特征(危房改造或异地搬迁)
20	政策特征(享受生态补偿)
21	政策特征(有护林员收入)
22	其它特征(家庭有残疾人)

多维数据集	2016年	2017年	2018年
基础数据集	23 556	25 030	22 584
林草数据集	8 613	9 061	6 365
残联数据集	1 136	1 520	1 722
人社数据集	220	346	376
教体数据集	5 165	5 182	4 937
住建数据集	1 072	1 246	938
民政数据集	7 415	6 822	5 194
合计	47 177	49 207	42 116