文本情感分类领域性强,传统情感分类方法在多领域混合数据上效果不佳。为了提升多领域混合情境下文本情感分类的准确率,使用双向编码器表征模型(bidirectional encoder representations from transformers,BERT)得到短文本的初级表征;...文本情感分类领域性强,传统情感分类方法在多领域混合数据上效果不佳。为了提升多领域混合情境下文本情感分类的准确率,使用双向编码器表征模型(bidirectional encoder representations from transformers,BERT)得到短文本的初级表征;利用对抗网络提取与领域无关的情感特征;利用双向长短期记忆网络(bidirectional long short-term memory,BiLSTM)提取上下文特征;将提取到的两种特征进行融合,构成基于对抗网络和BERT的情感分类模型,提升情感分类准确率。在公开数据集上进行的对比实验表明:基于对抗网络和BERT的情感分类模型相比于基线模型具有更高的准确率,准确率在两个数据集上分别达到了95.25%和93.61%,并且在领域差别较大的数据集上有着更好的表现,初步验证了多领域混合情景下情感分类模型的有效性。提出的模型适用于电商平台对商品进行实时监测之类涉及多领域的场景。展开更多
Abstract In this paper,the existence of periodic solution for the third order nonlinear ordinary differential equation of the form x…+f()+g()+h(x)=p(t) is considered,where f,g,h and p are the continuous f...Abstract In this paper,the existence of periodic solution for the third order nonlinear ordinary differential equation of the form x…+f()+g()+h(x)=p(t) is considered,where f,g,h and p are the continuous functions,and p(t+T)=p(t). By using the Leray Schauder degree method,some sufficient conditions to guarantee the existence of T periodic solution for the equation are obtained.Some previous results are extended and improved.展开更多
Beijing Municipal Administrative Center(Beijing MC)in Tongzhou District has inherited the non-capital core functions of Beijing’s central urban area,and its rapid construction and development urgently require a scien...Beijing Municipal Administrative Center(Beijing MC)in Tongzhou District has inherited the non-capital core functions of Beijing’s central urban area,and its rapid construction and development urgently require a scientific understanding of the pattern of land use evolution in the region.This paper analyzes the pattern of land use evolution in Tongzhou District over the past 40 years,from 1980 to 2020.According to the historical evolutionary characteristics of land use and urban development planning goals,combined with the driving factors of cultural tourism development,the Future Land-use Simulation(FLUS)model is used to simulate the spatial distribution of land use in Beijing MC(Tongzhou District)in 2035 under three scenarios of urbanization acceleration,deceleration and sustainable development.The results show three major trends.(1)Beijing MC(Tongzhou District)is dominated by urban development and construction.During the high-speed urbanization stage from 1980 to 2010,the urban expansion pattern of“along the Sixth Ring Road and along the Grand Canal”was formed.During the low-speed urbanization stage from 2010 to 2020,the land distribution was stable,and Tongzhou District formed a pattern of urban-rural differentiation and land intensification from northwest to southeast.As a typical area of Tongzhou District’s urbanization,Beijing MC has the same characteristics of the temporal and spatial evolution as Tongzhou as a whole.(2)By 2035,there are significant differences in land use among the three scenarios with respect to the magnitude of change and spatial distribution.The area and distribution of ecological land under the urban sustainable development scenario are optimal,which is conducive to the realization of sustainable urban development.In analyzing the degree of conformity with the three Beijing MC zoning plans,the prediction simulation under the sustainable development scenario is highly consistent with the land use of the“Beijing Municipal Administrative Center Regulatory Detailed Planning(Block Level)(2016–2035)”(hereinafter referred to as“Planning”)issued by the municipal government.However,there are certain deviations between the simulation predictions in the cultural tourism function area and the livable living scenery area and the corresponding“Planning”expectations.During the urban construction process,the internal ecological land area still needs to be increased.(3)Tongzhou District may lack a close connection between the urban and rural areas in the southeast.Potential risks such as the imbalance in the development of northern and southern townships require further attention in the development process.The prediction and simulation results of the model can provide certain data and methodological support for the construction of a harmonious and livable city in Beijing MC(Tongzhou District).展开更多
文摘文本情感分类领域性强,传统情感分类方法在多领域混合数据上效果不佳。为了提升多领域混合情境下文本情感分类的准确率,使用双向编码器表征模型(bidirectional encoder representations from transformers,BERT)得到短文本的初级表征;利用对抗网络提取与领域无关的情感特征;利用双向长短期记忆网络(bidirectional long short-term memory,BiLSTM)提取上下文特征;将提取到的两种特征进行融合,构成基于对抗网络和BERT的情感分类模型,提升情感分类准确率。在公开数据集上进行的对比实验表明:基于对抗网络和BERT的情感分类模型相比于基线模型具有更高的准确率,准确率在两个数据集上分别达到了95.25%和93.61%,并且在领域差别较大的数据集上有着更好的表现,初步验证了多领域混合情景下情感分类模型的有效性。提出的模型适用于电商平台对商品进行实时监测之类涉及多领域的场景。
文摘Abstract In this paper,the existence of periodic solution for the third order nonlinear ordinary differential equation of the form x…+f()+g()+h(x)=p(t) is considered,where f,g,h and p are the continuous functions,and p(t+T)=p(t). By using the Leray Schauder degree method,some sufficient conditions to guarantee the existence of T periodic solution for the equation are obtained.Some previous results are extended and improved.
基金The National Natural Science Foundation of China(31470518)The Project Supported by Institute of Culture and Tourism Development of Beijing Technology and Business University(202106104)。
文摘Beijing Municipal Administrative Center(Beijing MC)in Tongzhou District has inherited the non-capital core functions of Beijing’s central urban area,and its rapid construction and development urgently require a scientific understanding of the pattern of land use evolution in the region.This paper analyzes the pattern of land use evolution in Tongzhou District over the past 40 years,from 1980 to 2020.According to the historical evolutionary characteristics of land use and urban development planning goals,combined with the driving factors of cultural tourism development,the Future Land-use Simulation(FLUS)model is used to simulate the spatial distribution of land use in Beijing MC(Tongzhou District)in 2035 under three scenarios of urbanization acceleration,deceleration and sustainable development.The results show three major trends.(1)Beijing MC(Tongzhou District)is dominated by urban development and construction.During the high-speed urbanization stage from 1980 to 2010,the urban expansion pattern of“along the Sixth Ring Road and along the Grand Canal”was formed.During the low-speed urbanization stage from 2010 to 2020,the land distribution was stable,and Tongzhou District formed a pattern of urban-rural differentiation and land intensification from northwest to southeast.As a typical area of Tongzhou District’s urbanization,Beijing MC has the same characteristics of the temporal and spatial evolution as Tongzhou as a whole.(2)By 2035,there are significant differences in land use among the three scenarios with respect to the magnitude of change and spatial distribution.The area and distribution of ecological land under the urban sustainable development scenario are optimal,which is conducive to the realization of sustainable urban development.In analyzing the degree of conformity with the three Beijing MC zoning plans,the prediction simulation under the sustainable development scenario is highly consistent with the land use of the“Beijing Municipal Administrative Center Regulatory Detailed Planning(Block Level)(2016–2035)”(hereinafter referred to as“Planning”)issued by the municipal government.However,there are certain deviations between the simulation predictions in the cultural tourism function area and the livable living scenery area and the corresponding“Planning”expectations.During the urban construction process,the internal ecological land area still needs to be increased.(3)Tongzhou District may lack a close connection between the urban and rural areas in the southeast.Potential risks such as the imbalance in the development of northern and southern townships require further attention in the development process.The prediction and simulation results of the model can provide certain data and methodological support for the construction of a harmonious and livable city in Beijing MC(Tongzhou District).
