期刊文献+
共找到7篇文章
< 1 >
每页显示 20 50 100
协同稀疏低秩的高光谱图像解混 被引量:1
1
作者 韩红伟 冯向东 郭科 《现代电子技术》 2022年第5期67-73,共7页
稀疏解混能够有效地规避高光谱场景中缺少纯像元和估计端元数目的两个瓶颈问题,因而成为目前广泛研究的光谱解混技术。针对协同稀疏解混模型在边界上容易出现错误识别的问题,结合字典削减策略和低秩表示,提出一种协同稀疏低秩的解混模... 稀疏解混能够有效地规避高光谱场景中缺少纯像元和估计端元数目的两个瓶颈问题,因而成为目前广泛研究的光谱解混技术。针对协同稀疏解混模型在边界上容易出现错误识别的问题,结合字典削减策略和低秩表示,提出一种协同稀疏低秩的解混模型。该方法同时施加稀疏和低秩约束在丰度矩阵上,并对协同稀疏模型的?2,1混合范数采用加权策略,使得行稀疏性得到了增强,同时也使用非凸logdet(·)作为秩的光滑替代函数。由于提出方法充分利用了高光谱数据的空间信息和光谱信息,因此获得了比协同稀疏回归模型更准确的解混结果。最后利用著名的交替方向乘子方法(ADMM)对提出的非凸模型进行有效求解,实验结果验证了提出算法的有效性。 展开更多
关键词 协同稀疏回归 稀疏表示 高光谱解混 低秩表示 高光谱图像 解混模型 实验分析
下载PDF
Minimum distance constrained nonnegative matrix factorization for hyperspectral data unmixing 被引量:2
2
作者 于钺 SunWeidong 《High Technology Letters》 EI CAS 2012年第4期333-342,共10页
This paper considers a problem of unsupervised spectral unmixing of hyperspectral data. Based on the Linear Mixing Model ( LMM), a new method under the framework of nonnegative matrix fac- torization (NMF) is prop... This paper considers a problem of unsupervised spectral unmixing of hyperspectral data. Based on the Linear Mixing Model ( LMM), a new method under the framework of nonnegative matrix fac- torization (NMF) is proposed, namely minimum distance constrained nonnegative matrix factoriza- tion (MDC-NMF). In this paper, firstly, a new regularization term, called endmember distance (ED) is considered, which is defined as the sum of the squared Euclidean distances from each end- member to their geometric center. Compared with the simplex volume, ED has better optimization properties and is conceptually intuitive. Secondly, a projected gradient (PG) scheme is adopted, and by the virtue of ED, in this scheme the optimal step size along the feasible descent direction can be calculated easily at each iteration. Thirdly, a finite step ( no more than the number of endmem- bers) terminated algorithm is used to project a point on the canonical simplex, by which the abun- dance nonnegative constraint and abundance sum-to-one constraint can be accurately satisfied in a light amount of computation. The experimental results, based on a set of synthetic data and real da- ta, demonstrate that, in the same running time, MDC-NMF outperforms several other similar meth- ods proposed recently. 展开更多
关键词 hyperspectral data nonnegative matrix factorization (NMF) spectral unmixing convex function projected gradient (PG)
下载PDF
A hybrid decomposition-boosting model for short-term multi-step solar radiation forecasting with NARX neural network 被引量:3
3
作者 HUANG Jia-hao LIU Hui 《Journal of Central South University》 SCIE EI CAS CSCD 2021年第2期507-526,共20页
Due to global energy depletion,solar energy technology has been widely used in the world.The output power of the solar energy systems is affected by solar radiation.Accurate short-term forecasting of solar radiation c... Due to global energy depletion,solar energy technology has been widely used in the world.The output power of the solar energy systems is affected by solar radiation.Accurate short-term forecasting of solar radiation can ensure the safety of photovoltaic grids and improve the utilization efficiency of the solar energy systems.In the study,a new decomposition-boosting model using artificial intelligence is proposed to realize the solar radiation multi-step prediction.The proposed model includes four parts:signal decomposition(EWT),neural network(NARX),Adaboost and ARIMA.Three real solar radiation datasets from Changde,China were used to validate the efficiency of the proposed model.To verify the robustness of the multi-step prediction model,this experiment compared nine models and made 1,3,and 5 steps ahead predictions for the time series.It is verified that the proposed model has the best performance among all models. 展开更多
关键词 solar radiation forecasting multi-step forecasting smart hybrid model signal decomposition
下载PDF
Two Methods of AES Implementation Based on CPLD/FPGA
4
作者 刘常澍 彭艮鹏 王晓卓 《Transactions of Tianjin University》 EI CAS 2004年第4期285-290,共6页
This paper describes two single-chip——complex programmable logic devices/field programmable gate arrays(CPLD/FPGA)——implementations of the new advanced encryption standard (AES) algorithm based on the basic iterat... This paper describes two single-chip——complex programmable logic devices/field programmable gate arrays(CPLD/FPGA)——implementations of the new advanced encryption standard (AES) algorithm based on the basic iteration architecture (design [A]) and the hybrid pipelining architecture (design [B]). Design [A] is an encryption-and-decryption implementation based on the basic iteration architecture. This design not only supports 128-bit, 192-bit, 256-bit keys, but saves hardware resources because of the iteration architecture and sharing technology. Design [B] is a method of the 2×2 hybrid pipelining architecture. Based on the AES interleaved mode of operation, the design successfully accomplishes the algorithm, which operates in the feedback mode (cipher block chaining). It not only guarantees security of encryption/decryption, but obtains high data throughput of 1.05 Gb/s. The two designs have been realized on Aitera′s EP20k300EBC652-1 devices. 展开更多
关键词 advanced encryption standard (AES) ENCRYPTION DECRYPTION feedback mode hybrid pipelining hardware implementation
下载PDF
Analytical-Numerical Modeling Approach for Calculation of the Structural Distortions after Welding and Thermal Straightening
5
作者 Vesselin G. Michailov Nikolay Doynov 《Journal of Mechanics Engineering and Automation》 2016年第5期246-253,共8页
The analytic-numerical hybrid model for calculating welding distortions in large welded structures is presented. Objective of the analytical model is the calculation of the plastic strains and their distribution after... The analytic-numerical hybrid model for calculating welding distortions in large welded structures is presented. Objective of the analytical model is the calculation of the plastic strains and their distribution after welding and thermal straightening process. The consideration of the essential physical relations is put into discussion. Afterwards the obtained plastic strains by the analytical calculation are loaded on an elastic FE-model of the structure and the distortions of the whole structure are predicted. The consideration of welding and thermal straightening scenarios and the assembling stages is done by taking into account the intermediate variation of the strain state at every processing step. The model is intended to be used for solving industrial tasks, i.e. intending acceptable precision and calculation time as well as low simulation costs. The application of the model is demonstrated on structures with many welds and straightening spots. 展开更多
关键词 Computational welding mechanics welding distortions thermal straightening.
下载PDF
A scenario relaxation algorithm for finite scenario based robust assembly line balancing
6
作者 徐炜达 Xiao Tianyuan 《High Technology Letters》 EI CAS 2011年第1期1-6,共6页
A balancing problem for a mixed model assembly line with uncertain task processmg Ume anO daily model mixed changes is considered, and the objective is to minimize the work variances between stations in the line. For ... A balancing problem for a mixed model assembly line with uncertain task processmg Ume anO daily model mixed changes is considered, and the objective is to minimize the work variances between stations in the line. For the balancing problem for the scenario-based robust assembly line with a finitely large number of potential scenarios, the direct solution methodology considering all potential scenarios is quite time-consuming. A scenario relaxation algorithm that embeds genetic al- gorithm is developed. This new algorithm guarantees termination at an optimal robust solution with relatively short running time, and makes it possible to solve robust problems with large quantities of potential scenarios. Extensive computational results are reported to show the efficiency and effectiveness of the proposed algorithm. 展开更多
关键词 scenario-based decision making robust optimization assembly line balancing genetic algorithm
下载PDF
Stepwise decomposition and relative radiometric normalization for small footprint LiDAR waveform 被引量:4
7
作者 QIN YuChu LI Bin +2 位作者 NIU Zheng HUANG WenJiang WANG ChangYao 《Science China Earth Sciences》 SCIE EI CAS 2011年第4期625-630,共6页
As an advanced generation instrument of earth observation,small footprint full waveform light detection and ranging(LiDAR) technology has been widely used in the past few years.Decomposition and radiative correction i... As an advanced generation instrument of earth observation,small footprint full waveform light detection and ranging(LiDAR) technology has been widely used in the past few years.Decomposition and radiative correction is an important step in waveform data processing,it influences the accuracy of both information extraction and further applications.Based on a stepwise strategy,this study adopts Gaussian mixture model to approximate the LiDAR waveform.In addition to waveform decomposition,a relative correction model is proposed in this paper,the model considers the transmit pulses as well as the different of the travel path for implementing LiDAR waveform relative correction.Validation of the stepwise decomposition and relative correction model are carried out on LiDAR waveform acquired over Zhangye,China.The results indicate that stepwise decomposition identified the number of peaks in LiDAR waveforms,center position and width of each peak well.The relative radiometric correction also improves the similarity of waveforms which acquired at the same target. 展开更多
关键词 LiDAR waveform Gaussian mixture model stepwise decomposition relative radiometric correction
原文传递
上一页 1 下一页 到第
使用帮助 返回顶部