Reliability analysis and reliability-based optimization design require accurate measurement of failure probability under input uncertainties.A unified probabilistic reliability measure approach is proposed to calculat...Reliability analysis and reliability-based optimization design require accurate measurement of failure probability under input uncertainties.A unified probabilistic reliability measure approach is proposed to calculate the probability of failure and sensitivity indices considering a mixture of uncertainties under insufficient input data.The input uncertainty variables are classified into statistical variables,sparse variables,and interval variables.The conservativeness level of the failure probability is calculated through uncertainty propagation analysis of distribution parameters of sparse variables and auxiliary parameters of interval variables.The design sensitivity of the conservativeness level of the failure probability at design points is derived using a semi-analysis and sampling-based method.The proposed unified reliability measure method is extended to consider p-box variables,multi-domain variables,and evidence theory variables.Numerical and engineering examples demonstrate the effectiveness of the proposed method,which can obtain an accurate confidence level of reliability index and sensitivity indices with lower function evaluation number.展开更多
In recent years, deep networks has achieved outstanding performance in computer vision, especially in the field of face recognition. In terms of the performance for a face recognition model based on deep network, ther...In recent years, deep networks has achieved outstanding performance in computer vision, especially in the field of face recognition. In terms of the performance for a face recognition model based on deep network, there are two main closely related factors： 1） the structure of the deep neural network, and 2） the number and quality of training data. In real applications, illumination change is one of the most important factors that significantly affect the performance of face recognition algorithms. As for deep network models, only if there is sufficient training data that has various illumination intensity could they achieve expected performance. However, such kind of training data is hard to collect in the real world. In this paper, focusing on the illumination change challenge, we propose a deep network model which takes both visible light image and near-infrared image into account to perform face recognition. Near- infrared image, as we know, is much less sensitive to illuminations. Visible light face image contains abundant texture information which is very useful for face recognition. Thus, we design an adaptive score fusion strategy which hardly has information loss and the nearest neighbor algorithm to conduct the final classification. The experimental results demonstrate that the model is very effective in realworld scenarios and perform much better in terms of illumination change than other state-of-the-art models.展开更多
A Newton iteration-based interval uncertainty analysis method(NI-IUAM) is proposed to analyze the propagating effect of interval uncertainty in multidisciplinary systems. NI-IUAM decomposes one multidisciplinary syste...A Newton iteration-based interval uncertainty analysis method(NI-IUAM) is proposed to analyze the propagating effect of interval uncertainty in multidisciplinary systems. NI-IUAM decomposes one multidisciplinary system into single disciplines and utilizes a Newton iteration equation to obtain the upper and lower bounds of coupled state variables at each iterative step.NI-IUAM only needs to determine the bounds of uncertain parameters and does not require specific distribution formats. In this way, NI-IUAM may greatly reduce the necessity for raw data. In addition, NI-IUAM can accelerate the convergence process as a result of the super-linear convergence of Newton iteration. The applicability of the proposed method is discussed, in particular that solutions obtained in each discipline must be compatible in multidisciplinary systems. The validity and efficiency of NI-IUAM is demonstrated by both numerical and engineering examples.展开更多
基金supported by the Key Research and Development Program of Zhejiang Province(No.2021C01008)the National Natural Science Foundation of China(No.52105279)the Ningbo Natural Science Foundation of China(No.2021J163)。
文摘Reliability analysis and reliability-based optimization design require accurate measurement of failure probability under input uncertainties.A unified probabilistic reliability measure approach is proposed to calculate the probability of failure and sensitivity indices considering a mixture of uncertainties under insufficient input data.The input uncertainty variables are classified into statistical variables,sparse variables,and interval variables.The conservativeness level of the failure probability is calculated through uncertainty propagation analysis of distribution parameters of sparse variables and auxiliary parameters of interval variables.The design sensitivity of the conservativeness level of the failure probability at design points is derived using a semi-analysis and sampling-based method.The proposed unified reliability measure method is extended to consider p-box variables,multi-domain variables,and evidence theory variables.Numerical and engineering examples demonstrate the effectiveness of the proposed method,which can obtain an accurate confidence level of reliability index and sensitivity indices with lower function evaluation number.
文摘In recent years, deep networks has achieved outstanding performance in computer vision, especially in the field of face recognition. In terms of the performance for a face recognition model based on deep network, there are two main closely related factors： 1） the structure of the deep neural network, and 2） the number and quality of training data. In real applications, illumination change is one of the most important factors that significantly affect the performance of face recognition algorithms. As for deep network models, only if there is sufficient training data that has various illumination intensity could they achieve expected performance. However, such kind of training data is hard to collect in the real world. In this paper, focusing on the illumination change challenge, we propose a deep network model which takes both visible light image and near-infrared image into account to perform face recognition. Near- infrared image, as we know, is much less sensitive to illuminations. Visible light face image contains abundant texture information which is very useful for face recognition. Thus, we design an adaptive score fusion strategy which hardly has information loss and the nearest neighbor algorithm to conduct the final classification. The experimental results demonstrate that the model is very effective in realworld scenarios and perform much better in terms of illumination change than other state-of-the-art models.
基金supported by the National Natural Science Foundation of China(Grant No.11602012)the 111 Project(Grant No.B07009)+1 种基金the Defense Industrial Technology Development Program(Grant No.JCKY2016601B001)and the China Postdoctoral Science Foundation(Grant No.2016M591038)
文摘A Newton iteration-based interval uncertainty analysis method(NI-IUAM) is proposed to analyze the propagating effect of interval uncertainty in multidisciplinary systems. NI-IUAM decomposes one multidisciplinary system into single disciplines and utilizes a Newton iteration equation to obtain the upper and lower bounds of coupled state variables at each iterative step.NI-IUAM only needs to determine the bounds of uncertain parameters and does not require specific distribution formats. In this way, NI-IUAM may greatly reduce the necessity for raw data. In addition, NI-IUAM can accelerate the convergence process as a result of the super-linear convergence of Newton iteration. The applicability of the proposed method is discussed, in particular that solutions obtained in each discipline must be compatible in multidisciplinary systems. The validity and efficiency of NI-IUAM is demonstrated by both numerical and engineering examples.
