Reliability analysis is the key to evaluate software’s quality. Since the early 1970s, the Power Law Process, among others, has been used to assess the rate of change of software reliability as time-varying function ...Reliability analysis is the key to evaluate software’s quality. Since the early 1970s, the Power Law Process, among others, has been used to assess the rate of change of software reliability as time-varying function by using its intensity function. The Bayesian analysis applicability to the Power Law Process is justified using real software failure times. The choice of a loss function is an important entity of the Bayesian settings. The analytical estimate of likelihood-based Bayesian reliability estimates of the Power Law Process under the squared error and Higgins-Tsokos loss functions were obtained for different prior knowledge of its key parameter. As a result of a simulation analysis and using real data, the Bayesian reliability estimate under the Higgins-Tsokos loss function not only is robust as the Bayesian reliability estimate under the squared error loss function but also performed better, where both are superior to the maximum likelihood reliability estimate. A sensitivity analysis resulted in the Bayesian estimate of the reliability function being sensitive to the prior, whether parametric or non-parametric, and to the loss function. An interactive user interface application was additionally developed using Wolfram language to compute and visualize the Bayesian and maximum likelihood estimates of the intensity and reliability functions of the Power Law Process for a given data.展开更多
为更精确地预测航班过站时间,将全国机场按照规模差异及不同地理位置所导致的客流量差异和天气差异对航班过站时间造成的不同影响进行分类,基于各类机场航班数据,构建混合轻量级梯度提升机算法(LightGBM)模型对航班过站时间分类预测。...为更精确地预测航班过站时间,将全国机场按照规模差异及不同地理位置所导致的客流量差异和天气差异对航班过站时间造成的不同影响进行分类,基于各类机场航班数据,构建混合轻量级梯度提升机算法(LightGBM)模型对航班过站时间分类预测。引入自适应鲁棒损失函数(adaptive robust loss function,ARLF)改进LightGBM模型损失函数,降低航班数据中存在离群值的影响;通过改进的麻雀搜索算法对改进后的LightGBM模型进行参数寻优,形成混合LightGBM模型。采用全国2019年全年航班数据进行验证,实验结果验证了方法的可行性。展开更多
当前基于深度学习的地表覆盖分类方法依赖于大规模且标注精准的训练样本。但受限于成本和技术因素,训练样本不可避免地混入噪声标签,导致分类精度降低。因此,本文提出了融合协同学习和抗噪损失的含噪地表覆盖分类方法。该方法以协同学...当前基于深度学习的地表覆盖分类方法依赖于大规模且标注精准的训练样本。但受限于成本和技术因素,训练样本不可避免地混入噪声标签,导致分类精度降低。因此,本文提出了融合协同学习和抗噪损失的含噪地表覆盖分类方法。该方法以协同学习机制为主体架构,首先利用参数非共享的双支卷积网络分别提取影像初分类特征;然后,基于双支网络的影像分类概率建模干净数据和噪声数据,构建基于信息熵的噪声可信度评价指标;最后,以可信度评价指标代替人工设定权重的方式,提出基于噪声可信度的自适应主动被动损失函数,引导协同学习网络关注噪声样本。试验表明,该方法在公开数据集GID(模拟噪声)和众源数据OSM(实际噪声)上的平均交并比(mean intersection over union,mIOU)分别提升3.85%~23.3%和5.89%~6.73%,说明该方法具有更好的抗噪性能。展开更多
Increased market competition means that quality, cost and delivery time are crucial elements of modern production techniques. Taguchi’s robust design is the most powerful method available for reducing product cost, i...Increased market competition means that quality, cost and delivery time are crucial elements of modern production techniques. Taguchi’s robust design is the most powerful method available for reducing product cost, improving quality, and simultaneously reducing development time. Robust design aims to reduce the impact of noise on the product or process quality and leads to greater customer satisfaction and higher operational performance. The objective of robust design is to minimize the total quality loss in products or processes. The PQL model proposed by this paper simultaneously optimizes the static and dynamic problems by minimizing the total quality loss. Using the proposed PQL model and steps for optimization, the method addresses complex parameter design, which varies with the properties and objectives of the experimental data, to improve the product quality. The example of an electron beam surface hardening process is provided to demonstrate the implementation and usefulness of the proposed method.展开更多
本文提出了一种新型的自适应鲁棒损失函数,显著提高了同步定位与建图(Simultaneous Localization and Mapping,SLAM)算法在高噪声和异常值环境下的精度和稳定性。具体贡献如下:通过引入形状参数和尺度参数,实现了损失函数对不同数据分...本文提出了一种新型的自适应鲁棒损失函数,显著提高了同步定位与建图(Simultaneous Localization and Mapping,SLAM)算法在高噪声和异常值环境下的精度和稳定性。具体贡献如下:通过引入形状参数和尺度参数,实现了损失函数对不同数据分布的自适应,增强了对噪声和异常值的抵抗力;在多个公开数据集上进行的实验和仿真结果显示,本文方法与传统的平方损失函数和其他鲁棒损失函数(如Huber损失、Geman-McClure损失)相比,在精度和鲁棒性上均提高了15%~20%。这些结果突显了新方法在复杂环境下的应用潜力和优势。展开更多
文摘Reliability analysis is the key to evaluate software’s quality. Since the early 1970s, the Power Law Process, among others, has been used to assess the rate of change of software reliability as time-varying function by using its intensity function. The Bayesian analysis applicability to the Power Law Process is justified using real software failure times. The choice of a loss function is an important entity of the Bayesian settings. The analytical estimate of likelihood-based Bayesian reliability estimates of the Power Law Process under the squared error and Higgins-Tsokos loss functions were obtained for different prior knowledge of its key parameter. As a result of a simulation analysis and using real data, the Bayesian reliability estimate under the Higgins-Tsokos loss function not only is robust as the Bayesian reliability estimate under the squared error loss function but also performed better, where both are superior to the maximum likelihood reliability estimate. A sensitivity analysis resulted in the Bayesian estimate of the reliability function being sensitive to the prior, whether parametric or non-parametric, and to the loss function. An interactive user interface application was additionally developed using Wolfram language to compute and visualize the Bayesian and maximum likelihood estimates of the intensity and reliability functions of the Power Law Process for a given data.
文摘为更精确地预测航班过站时间,将全国机场按照规模差异及不同地理位置所导致的客流量差异和天气差异对航班过站时间造成的不同影响进行分类,基于各类机场航班数据,构建混合轻量级梯度提升机算法(LightGBM)模型对航班过站时间分类预测。引入自适应鲁棒损失函数(adaptive robust loss function,ARLF)改进LightGBM模型损失函数,降低航班数据中存在离群值的影响;通过改进的麻雀搜索算法对改进后的LightGBM模型进行参数寻优,形成混合LightGBM模型。采用全国2019年全年航班数据进行验证,实验结果验证了方法的可行性。
文摘当前基于深度学习的地表覆盖分类方法依赖于大规模且标注精准的训练样本。但受限于成本和技术因素,训练样本不可避免地混入噪声标签,导致分类精度降低。因此,本文提出了融合协同学习和抗噪损失的含噪地表覆盖分类方法。该方法以协同学习机制为主体架构,首先利用参数非共享的双支卷积网络分别提取影像初分类特征;然后,基于双支网络的影像分类概率建模干净数据和噪声数据,构建基于信息熵的噪声可信度评价指标;最后,以可信度评价指标代替人工设定权重的方式,提出基于噪声可信度的自适应主动被动损失函数,引导协同学习网络关注噪声样本。试验表明,该方法在公开数据集GID(模拟噪声)和众源数据OSM(实际噪声)上的平均交并比(mean intersection over union,mIOU)分别提升3.85%~23.3%和5.89%~6.73%,说明该方法具有更好的抗噪性能。
文摘Increased market competition means that quality, cost and delivery time are crucial elements of modern production techniques. Taguchi’s robust design is the most powerful method available for reducing product cost, improving quality, and simultaneously reducing development time. Robust design aims to reduce the impact of noise on the product or process quality and leads to greater customer satisfaction and higher operational performance. The objective of robust design is to minimize the total quality loss in products or processes. The PQL model proposed by this paper simultaneously optimizes the static and dynamic problems by minimizing the total quality loss. Using the proposed PQL model and steps for optimization, the method addresses complex parameter design, which varies with the properties and objectives of the experimental data, to improve the product quality. The example of an electron beam surface hardening process is provided to demonstrate the implementation and usefulness of the proposed method.
基金partially supported by NSFC(No.12171203)the Natural Science Foundation of Guangdong(No.2022A1515010045)+4 种基金the Fundamental Research Funds for the Central Universities(No.23JNQMX21)partially supported by NSFC(No.12171449)partially supported by NSFC(No.12271370)partially supported by NSFC(Nos.12231017,72171216,71921001,71991474)the National Key R&D Program of China(No.2022YFA1003803)。
文摘本文提出了一种新型的自适应鲁棒损失函数,显著提高了同步定位与建图(Simultaneous Localization and Mapping,SLAM)算法在高噪声和异常值环境下的精度和稳定性。具体贡献如下:通过引入形状参数和尺度参数,实现了损失函数对不同数据分布的自适应,增强了对噪声和异常值的抵抗力;在多个公开数据集上进行的实验和仿真结果显示,本文方法与传统的平方损失函数和其他鲁棒损失函数(如Huber损失、Geman-McClure损失)相比,在精度和鲁棒性上均提高了15%~20%。这些结果突显了新方法在复杂环境下的应用潜力和优势。
