基于广义回归神经网络的日总辐射曝辐量预估
采用广义回归神经网络(generalized regression neural network,GRNN)模型对山东烟台市福山气象站2000～2003年日总辐射曝辐量进行预估。模型通过交叉验证方法确定其关键参数(光滑因子),以日照时数、平均气压、平均气温、日最高气温、相对湿度、气溶胶光学厚度6个变量作为输入量。结果显示:GRNN15.9%,均方根误差为 …
Shupeng Zhuang
•
•
1 分钟阅读时长
A Perception-Inspired Deep Learning Framework for Predicting Perceptual Texture Similarity
Similarity learning plays a fundamental role in the fields of multimedia retrieval and pattern recognition. Prediction of perceptual similarity is a challenging task as in most …
剪切流作用下超大型浮体的非线性动力响应
本文研究了垂向速度呈指数形式分布的有旋剪切流作用下浮体的非线性动力特性。引入流函数构建控制方程和非线性边界条件。对于浮体为无限长板情形,运用同伦分析方法,得到收敛的近似解析解。结果表明,顺水剪切流使得波峰更尖锐、波谷更平坦,而顺水剪切流的作用则相反;同向的行进波和剪切流使得波速增加,而波流反向时波速减小。
Right Linear Map Preserving the Left Spectrum of 2x2 Quaternion Matrices; Pp. 378–386
In this paper, the form of a right linear map preserving the left spectrum of quaternion matrices of order 2 is characterized. The obtained conclusion is different from the …
Deyu Duan
Calibration Transfer of Soil Total Carbon and Total Nitrogen between Two Different Types of Soils Based on Visible-Near-Infrared Reflectance Spectroscopy
Although visible-near-infrared spectroscopy can rapidly and accurately determine soil nutrients without sample destruction,some problems remain unresolved, such as the mismatch of …
Xue-Ying Li
基于超混沌的RBF神经网络图像自适应水印算法
为了更好地保护图像版权信息,本工作结合超混沌系统和RBF神经网络,提出一种基于超混沌的RBF神经网络模型加密算法,根据JND(最小可视觉误差)模型实现水印的自适应嵌入,并应用RBF神经网络进行水印信息盲检测。实验研究表明:该算法复杂度较低、容易实现,并且具有良好的安全性、不可感知性和鲁棒性。
Linear Map Preserving the Right Spectrum of Quaternion Matrices
Let and be a right quaternion linear map from the set of matrices over the quaternion division ring into itself such that the set of matrices over the complex field is invariant …
Deyu Duan
Domain-Decomposition Generalized Finite Difference Method for Stress Analysis in Multi-Layered Elastic Materials
The generalized finite difference method (GFDM) is a relatively new meshless method for the numerical solution of certain boundary value problems. The method uses the Taylor series …
Robust and Effective Mesh Denoising Using Sparse Regularization
Mesh denoising is of great practical importance in geometric analysis and processing. In this paper we develop a novel L0sparse regularization method to robustly and reliably …
Yong Zhao