作者机构：
[Li, Huiqin; Tang, Yajiao; Zhu, Yulin; Song, Mengjia] Cent South Univ Forestry & Technol, Coll Econ, Changsha 410004, Peoples R China.;[Zhu, Yulin] Hunan Res Ctr High Qual Dev Ind Econ, Changsha 410004, Peoples R China.
通讯机构：
[Zhu, YL ] C;Cent South Univ Forestry & Technol, Coll Econ, Changsha 410004, Peoples R China.;Hunan Res Ctr High Qual Dev Ind Econ, Changsha 410004, Peoples R China.
关键词：
ecological zoning;zoning management policies;ecosystem service value;ecological risk;the Wuling Mountains area of Hunan Province
摘要：
Based on land use data from the Wuling Mountains area of Hunan Province for 2000, 2010, and 2020, we used tools such as frastats4.8 and ArcGIS10.8 to construct a model for assessing ecosystem service value and the ecological risk index. We divided the area into four regions based on ecosystem service value and ecological risk indicators, which served as the foundation for ecological zoning and a proposed strategy for an ecological security pattern that suits the ecology of the region. The results showed a general increase in both ecosystem service value and ecological risk in the study area from 2000 to 2020. The annual ecosystem service value exceeded CNY 300 x 109, with forests providing more than 77% of this value, and the regulating services value accounted for 68% of the total value. The mean ecological risk indexes for the periods of 2000, 2010, and 2020 were 0.0384, 0.0383, and 0.0395, respectively. The sizes of the four zones within the study area remained relatively stable: the ecological barrier zone accounted for more than 53% over three years; the ecological improvement zone, approximately 32%; the ecological control zone comprised 8.62% of the total area in 2000, and this proportion rose to 9.56% in 2020. The ecological conservation zone had the smallest proportion of the total area among the four zones. Our research provides a comprehensive analytical framework for constructing ecological security patterns in other developing countries and offers a new perspective for regional ecological zoning management and conservation planning.
作者机构：
[Tang, Yajiao; Yuan, Huaiyu; Zhu, Yulin; Hou, Maozhang] Cent South Univ Forestry & Technol, Coll Econ, Changsha 410004, Peoples R China.;[Song, Zhenyu] Taizhou Univ, Coll Informat Engn, Taizhou 225300, Peoples R China.;[Ji, Junkai; Li, Jianqiang] Shenzhen Univ, Coll Comp Sci & Software Engn, Shenzhen 518060, Peoples R China.;[Tang, Cheng] Nagoya Inst Technol, Dept Elect & Mech Engn, Nagoya 4668555, Japan.;[Tang, Yajiao; Yuan, Huaiyu; Zhu, Yulin; Hou, Maozhang] Res Ctr High Qual Dev Ind Econ, Changsha 410004, Peoples R China.
通讯机构：
[Junkai Ji] C;[Cheng Tang] D;College of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, China<&wdkj&>Department of Electrical and Mechanical Engineering, Nagoya Institute of Technology, Nagoya 466-8555, Japan
关键词：
Financial Time Series;Forecasting;Machine learning;Hybrid method
摘要：
Financial time series (FTS) are nonlinear, dynamic and chaotic. The search for models to facilitate FTS forecasting has been highly pursued for decades. Despite major related challenges, there has been much interest in this topic, and many efforts to forecast financial market pricing and the average movement of various financial assets have been implemented. Researchers have applied different models based on computer science and economics to gain efficient information and earn money through financial market investment decisions. Machine learning (ML) methods are popular and successful algorithms applied in the FTS domain. This paper provides a timely review of ML's adoption in FTS forecasting. The progress of FTS forecasting models using ML methods is systematically summarized by searching articles published from 2011 to 2021. Focusing on the analysis of ML methods applied to the theoretical basis and empirical application of FTS data forecasting, this paper provides a relevant reference for FTS forecasting and inter-disciplinary fusion research against the background of computational intelligence and big data. The liter-ature survey reveals that the most commonly used models for prediction involve long short-term memory (LSTM) and hybrid methods. The main contribution of this paper is not only building a system-atic program to compare the merits and demerits of specific FTS forecasting models but also detecting the importance and differences of each model to help researchers and practitioners make good choices. In addition, the limitations to be addressed and future research directions of ML models' adoption in FTS forecasting are identified.(c) 2022 Elsevier B.V. All rights reserved.
期刊：
WSEAS Transactions on Business and Economics,2020年17:869-878 ISSN：1109-9526
作者机构：
Department of Economics and Finance, Huashang College Guangdong University of Finance & Economics, Guangzhou, Guangdong, China;School of economics, Central South University of Forestry and Technology, Changsha, Hunan, China;Institute of Resources, Environment and Sustainable Development Research, Jinan University, Guangzhou, Guangdong, China
