本文创新性地对艺术投资品进行重新分类,编制了新艺术品指数,通过建立混合自回归滑动平均模型(Mixture Autoregressive Moving Average Model简记MARMA)的方法对艺术投资品与其他因素的联动性进行分析,分别得出两类艺术品与股票市场、...本文创新性地对艺术投资品进行重新分类,编制了新艺术品指数,通过建立混合自回归滑动平均模型(Mixture Autoregressive Moving Average Model简记MARMA)的方法对艺术投资品与其他因素的联动性进行分析,分别得出两类艺术品与股票市场、宏观经济之间的关系并应用该模型进行预测。主要结论是:第一类艺术品可以使用股票指数来描述,第二类艺术品可以通过宏观经济变量来研究;与相似的投资品相比,在通胀环境下艺术品具有更高的投资价值。展开更多
模拟人类视觉感知机制,提出了一种基于多尺度自回归滑动平均(MARMA,multiscale autoregressive and moving average model)模型和Markov随机场(MRF,markov random field)的合成孔径雷达(SAR)图像分割新方法。首先,分析人类视觉感知系统...模拟人类视觉感知机制,提出了一种基于多尺度自回归滑动平均(MARMA,multiscale autoregressive and moving average model)模型和Markov随机场(MRF,markov random field)的合成孔径雷达(SAR)图像分割新方法。首先,分析人类视觉感知系统的工作机制和特点,利用SAR的成像机理,构建了SAR图像的金字塔结构和MARMA模型,以此模拟视觉过程中的空间尺度和朝向感知机制;然后,通过不同尺度上的MRF模型和改进的模拟退火(SA)算法实现更有效的多尺度分割策略。实验结果表明,本文提出的方法在SAR图像分割任务中有非常良好的表现。展开更多
An absolute gravimeter is a precision instrument for measuring gravitational acceleration, which plays an important role in earthquake monitoring, crustal deformation, national defense construction, etc. The frequency...An absolute gravimeter is a precision instrument for measuring gravitational acceleration, which plays an important role in earthquake monitoring, crustal deformation, national defense construction, etc. The frequency of laser interference fringes of an absolute gravimeter gradually increases with the fall time. Data are sparse in the early stage and dense in the late stage. The fitting accuracy of gravitational acceleration will be affected by least-squares fitting according to the fixed number of zero-crossing groups. In response to this problem, a method based on Fourier series fitting is proposed in this paper to calculate the zero-crossing point. The whole falling process is divided into five frequency bands using the Hilbert transformation. The multiplicative auto-regressive moving average model is then trained according to the number of optimal zero-crossing groups obtained by the honey badger algorithm. Through this model, the number of optimal zero-crossing groups determined in each segment is predicted by the least-squares fitting. The mean value of gravitational acceleration in each segment is then obtained. The method can improve the accuracy of gravitational measurement by more than 25% compared to the fixed zero-crossing groups method. It provides a new way to improve the measuring accuracy of an absolute gravimeter.展开更多
提出了一类用于非线性时间序列建模的混合自回归滑动平均模型(MARMA).该模型是由K个平稳或非平稳的ARMA分量经过混合得到的.讨论了MARMA模型的平稳性条件和自相关函数.给出了MARMA模型参数估计的期望极大化(expectation maximization)算...提出了一类用于非线性时间序列建模的混合自回归滑动平均模型(MARMA).该模型是由K个平稳或非平稳的ARMA分量经过混合得到的.讨论了MARMA模型的平稳性条件和自相关函数.给出了MARMA模型参数估计的期望极大化(expectation maximization)算法.运用贝叶斯信息准则(Bayes information criterion)来选择该模型.MARMA模型分布形式富于变化的特征使得它能够对具有多峰分布以及条件异方差的序列进行建模.通过两个实例验证了该模型,并和其他模型进行比较,结果表明MARMA模型能够更好地描述这些数据的特征.展开更多
文摘本文创新性地对艺术投资品进行重新分类,编制了新艺术品指数,通过建立混合自回归滑动平均模型(Mixture Autoregressive Moving Average Model简记MARMA)的方法对艺术投资品与其他因素的联动性进行分析,分别得出两类艺术品与股票市场、宏观经济之间的关系并应用该模型进行预测。主要结论是:第一类艺术品可以使用股票指数来描述,第二类艺术品可以通过宏观经济变量来研究;与相似的投资品相比,在通胀环境下艺术品具有更高的投资价值。
文摘模拟人类视觉感知机制,提出了一种基于多尺度自回归滑动平均(MARMA,multiscale autoregressive and moving average model)模型和Markov随机场(MRF,markov random field)的合成孔径雷达(SAR)图像分割新方法。首先,分析人类视觉感知系统的工作机制和特点,利用SAR的成像机理,构建了SAR图像的金字塔结构和MARMA模型,以此模拟视觉过程中的空间尺度和朝向感知机制;然后,通过不同尺度上的MRF模型和改进的模拟退火(SA)算法实现更有效的多尺度分割策略。实验结果表明,本文提出的方法在SAR图像分割任务中有非常良好的表现。
基金Project supported by the National Key R&D Program of China (Grant No. 2022YFF0607504)。
文摘An absolute gravimeter is a precision instrument for measuring gravitational acceleration, which plays an important role in earthquake monitoring, crustal deformation, national defense construction, etc. The frequency of laser interference fringes of an absolute gravimeter gradually increases with the fall time. Data are sparse in the early stage and dense in the late stage. The fitting accuracy of gravitational acceleration will be affected by least-squares fitting according to the fixed number of zero-crossing groups. In response to this problem, a method based on Fourier series fitting is proposed in this paper to calculate the zero-crossing point. The whole falling process is divided into five frequency bands using the Hilbert transformation. The multiplicative auto-regressive moving average model is then trained according to the number of optimal zero-crossing groups obtained by the honey badger algorithm. Through this model, the number of optimal zero-crossing groups determined in each segment is predicted by the least-squares fitting. The mean value of gravitational acceleration in each segment is then obtained. The method can improve the accuracy of gravitational measurement by more than 25% compared to the fixed zero-crossing groups method. It provides a new way to improve the measuring accuracy of an absolute gravimeter.
文摘提出了一类用于非线性时间序列建模的混合自回归滑动平均模型(MARMA).该模型是由K个平稳或非平稳的ARMA分量经过混合得到的.讨论了MARMA模型的平稳性条件和自相关函数.给出了MARMA模型参数估计的期望极大化(expectation maximization)算法.运用贝叶斯信息准则(Bayes information criterion)来选择该模型.MARMA模型分布形式富于变化的特征使得它能够对具有多峰分布以及条件异方差的序列进行建模.通过两个实例验证了该模型,并和其他模型进行比较,结果表明MARMA模型能够更好地描述这些数据的特征.
