Moose （Alces alces cameloides） is typically representative of the fauna of the frigid temperate zone and has been put on the Chinese second priority list of protected animals. The moose of northeast China is on the ...Moose （Alces alces cameloides） is typically representative of the fauna of the frigid temperate zone and has been put on the Chinese second priority list of protected animals. The moose of northeast China is on the southern most edge of its distribution in Asia. To study resource selection characteristics of moose and their response to human distur- bances and forest resource variables, the field work was conducted in Heilongiiang Provincial Shengshan Forestry Farm, which is located in the northwestern slope of Lesser Khingan Mountains, northeastern China, from January to March in both 2006 and 2007. A total of 428 plots were examined within the study area. Signs of moose use were found in 19 plots. Based on the analysis of resource selection function, we found that moose selected areas with higher densities of mixed deciduous broadleaf patch and mixed coniferous and broad leaf patch, and a higher NDVI value. Moose avoided settlement 6 km away and remained low probability of occurrence within 3 km from roads,展开更多
工业电机轴承的故障诊断对设备性能和寿命至关重要。传统的诊断方法是将多个工厂的数据汇集在一起,这存在数据隐私和标注成本高的问题。为了解决这些问题,提出一种基于自适应本地融合(adaptive local collaboration,ALC)联邦学习的故障...工业电机轴承的故障诊断对设备性能和寿命至关重要。传统的诊断方法是将多个工厂的数据汇集在一起,这存在数据隐私和标注成本高的问题。为了解决这些问题,提出一种基于自适应本地融合(adaptive local collaboration,ALC)联邦学习的故障诊断策略。在该方法中,不同工况轴承数据将存储于多个客户端,中心服务端与各个客户端协同工作,以建立联邦学习诊断模型。采用改进的ResNet-18网络作为分类器,在个性化联邦学习框架下进行训练,ALC联邦学习方法使每个客户端能有效融合全局和局部模型,提取全局信息优化本地训练结果。实验证明,该方法在保护数据隐私的同时与其他方法相比较,提高了故障诊断准确性,特别在多工厂环境中表现出更高的故障分类精度。展开更多
基金financially supported by National Excellent Doctoral Dissertation of PR China-FANEDD(No.201069)""Program for New Century Excellent Talents in University–NCET(No.10-0310)""the Fundamental Research Funds for the Central Universities(No.DL12DA01)
文摘Moose （Alces alces cameloides） is typically representative of the fauna of the frigid temperate zone and has been put on the Chinese second priority list of protected animals. The moose of northeast China is on the southern most edge of its distribution in Asia. To study resource selection characteristics of moose and their response to human distur- bances and forest resource variables, the field work was conducted in Heilongiiang Provincial Shengshan Forestry Farm, which is located in the northwestern slope of Lesser Khingan Mountains, northeastern China, from January to March in both 2006 and 2007. A total of 428 plots were examined within the study area. Signs of moose use were found in 19 plots. Based on the analysis of resource selection function, we found that moose selected areas with higher densities of mixed deciduous broadleaf patch and mixed coniferous and broad leaf patch, and a higher NDVI value. Moose avoided settlement 6 km away and remained low probability of occurrence within 3 km from roads,
文摘工业电机轴承的故障诊断对设备性能和寿命至关重要。传统的诊断方法是将多个工厂的数据汇集在一起,这存在数据隐私和标注成本高的问题。为了解决这些问题,提出一种基于自适应本地融合(adaptive local collaboration,ALC)联邦学习的故障诊断策略。在该方法中,不同工况轴承数据将存储于多个客户端,中心服务端与各个客户端协同工作,以建立联邦学习诊断模型。采用改进的ResNet-18网络作为分类器,在个性化联邦学习框架下进行训练,ALC联邦学习方法使每个客户端能有效融合全局和局部模型,提取全局信息优化本地训练结果。实验证明,该方法在保护数据隐私的同时与其他方法相比较,提高了故障诊断准确性,特别在多工厂环境中表现出更高的故障分类精度。
