In this paper,an approach is developed to optimize the quality of the training samples in the conventional Artificial Neural Network(ANN)by incorporating expert knowledge in the means of constructing expert-rule sampl...In this paper,an approach is developed to optimize the quality of the training samples in the conventional Artificial Neural Network(ANN)by incorporating expert knowledge in the means of constructing expert-rule samples from rules in an expert system,and through training by using these samples,an ANN based on expert-knowledge is further developed.The method is introduced into the field of quantitative identification of potential seismic sources on the basis of the rules in an expert system.Then it is applied to the quantitative identification of the potential seismic sources in Beijing and its adjacent area.The result indicates that the expert rule based on ANN method can well incorporate and represent the expert knowledge in the rules in an expert system,and the quality of the samples and the efficiency of training and the accuracy of the result are optimized.展开更多
Urban environmental quality research is crucial,as cities become competitive centers concentrating human talent,industrial activity,and financial resources,contributing significantly to national economies.Municipal an...Urban environmental quality research is crucial,as cities become competitive centers concentrating human talent,industrial activity,and financial resources,contributing significantly to national economies.Municipal and government priorities include retaining residents,preventing skilled worker outflow,and meeting the evolving needs of urban populations.The study presents the development and application of a scenario-based spatial analysis tool for assessing urban environmental quality at a detailed spatial scale within the city of Novosibirsk.Using advanced geoinformatics,GIS techniques,and an expert knowledge base,the tool integrates diverse thematic data layers with user-defined scenarios to compute and visualize the Scenario-based Urban Environment Quality Index across 87,905 standardized unit areas.The methodology incorporates comprehensive criteria aligned with existing urban planning frameworks and includes demographic targeting to address the city’s heterogeneous population.Validation against expert evaluations demonstrates high accuracy and consistency,while dynamicmodeling capabilities facilitate monitoring the effects of planned urban development initiatives.This approach bridges a critical gap in urban planning by providing granular,data-driven insights that reflect residents’real needs and spatial inequalities.The tool greatly benefits municipal authorities by enabling evidence-based prioritization of interventions,fostering inclusive and sustainable urban growth,and enhancing transparency and participatory governance.Its implementation as a no-code/low-code QGIS plugin ensures wide accessibility and practical application in strategic urban development,marking a significant advancement in urban environment quality assessment science and practice.展开更多
文摘In this paper,an approach is developed to optimize the quality of the training samples in the conventional Artificial Neural Network(ANN)by incorporating expert knowledge in the means of constructing expert-rule samples from rules in an expert system,and through training by using these samples,an ANN based on expert-knowledge is further developed.The method is introduced into the field of quantitative identification of potential seismic sources on the basis of the rules in an expert system.Then it is applied to the quantitative identification of the potential seismic sources in Beijing and its adjacent area.The result indicates that the expert rule based on ANN method can well incorporate and represent the expert knowledge in the rules in an expert system,and the quality of the samples and the efficiency of training and the accuracy of the result are optimized.
基金funded by theMinistry of Science and Higher Education of Russia,R&D project number FEFS-2026-0003.
文摘Urban environmental quality research is crucial,as cities become competitive centers concentrating human talent,industrial activity,and financial resources,contributing significantly to national economies.Municipal and government priorities include retaining residents,preventing skilled worker outflow,and meeting the evolving needs of urban populations.The study presents the development and application of a scenario-based spatial analysis tool for assessing urban environmental quality at a detailed spatial scale within the city of Novosibirsk.Using advanced geoinformatics,GIS techniques,and an expert knowledge base,the tool integrates diverse thematic data layers with user-defined scenarios to compute and visualize the Scenario-based Urban Environment Quality Index across 87,905 standardized unit areas.The methodology incorporates comprehensive criteria aligned with existing urban planning frameworks and includes demographic targeting to address the city’s heterogeneous population.Validation against expert evaluations demonstrates high accuracy and consistency,while dynamicmodeling capabilities facilitate monitoring the effects of planned urban development initiatives.This approach bridges a critical gap in urban planning by providing granular,data-driven insights that reflect residents’real needs and spatial inequalities.The tool greatly benefits municipal authorities by enabling evidence-based prioritization of interventions,fostering inclusive and sustainable urban growth,and enhancing transparency and participatory governance.Its implementation as a no-code/low-code QGIS plugin ensures wide accessibility and practical application in strategic urban development,marking a significant advancement in urban environment quality assessment science and practice.
