Based on the maximum entropy principle, a probability density function (PDF) is derived for the distribution of wave heights in a random wave field, without any more hypothesis. The present PDF, being a non-Rayleigh f...Based on the maximum entropy principle, a probability density function (PDF) is derived for the distribution of wave heights in a random wave field, without any more hypothesis. The present PDF, being a non-Rayleigh form, involves two parameters: the average wave height H— and the state parameter γ. The role of γ in the distribution of wave heights is examined. It is found that γ may be a certain measure of sea state. A least square method for determining γ from measured data is proposed. In virtue of the method, the values of γ are determined for three sea states from the data measured in the East China Sea. The present PDF is compared with the well known Rayleigh PDF of wave height and it is shown that it much better fits the data than the Rayleigh PDF. It is expected that the present PDF would fit some other wave variables, since its derivation is not restricted only to the wave height.展开更多
Marine environmental design parameter extrapolation has important applications in marine engineering and coastal disaster prevention.The distribution models used for environmental design parameter usually pass the hyp...Marine environmental design parameter extrapolation has important applications in marine engineering and coastal disaster prevention.The distribution models used for environmental design parameter usually pass the hypothesis tests in statistical analysis,but the calculation results of different distribution models often vary largely.In this paper,based on the information entropy,the overall uncertainty test criteria were studied for commonly used distributions including Gumbel,Weibull,and Pearson-III distribution.An improved method for parameter estimation of the maximum entropy distribution model is proposed on the basis of moment estimation.The study in this paper shows that the number of sample data and the degree of dispersion are proportional to the information entropy,and the overall uncertainty of the maximum entropy distribution model is minimal compared with other models.展开更多
This paper applied Maximum Entropy (ME) model to Pinyin-To-Character (PTC) conversion in-stead of Hidden Markov Model (HMM) that could not include complicated and long-distance lexical informa-tion. Two ME models were...This paper applied Maximum Entropy (ME) model to Pinyin-To-Character (PTC) conversion in-stead of Hidden Markov Model (HMM) that could not include complicated and long-distance lexical informa-tion. Two ME models were built based on simple and complex templates respectively, and the complex one gave better conversion result. Furthermore, conversion trigger pair of y A → y B cBwas proposed to extract the long-distance constrain feature from the corpus; and then Average Mutual Information (AMI) was used to se-lect conversion trigger pair features which were added to the ME model. The experiment shows that conver-sion error of the ME with conversion trigger pairs is reduced by 4% on a small training corpus, comparing with HMM smoothed by absolute smoothing.展开更多
Complete prior statistical information is currently required in the majority of statistical evaluations of complex models. The principle of maximum entropy is often utilized in this context to fill in the missing piec...Complete prior statistical information is currently required in the majority of statistical evaluations of complex models. The principle of maximum entropy is often utilized in this context to fill in the missing pieces of available information and is normally claimed to be fair and objective. A rarely discussed aspect is that it relies upon testable information, which is never known but estimated, i.e. results from processing of raw data. The subjective choice of this processing strongly affects the result. Less conventional posterior completion of information is equally accurate but is computationally superior to prior, as much less information enters the analysis. Our recently proposed methods of lean deterministic sampling are examples of very few approaches that actively promote the use of minimal incomplete prior information. The inherited subjective character of maximum entropy distributions and the often critical implications of prior and posterior completion of information are here discussed and illustrated, from a novel perspective of consistency, rationality, computational efficiency and realism.展开更多
针对传统的ORB(Oriented fast and rotated brief)算法在运算速度以及精度方面有时难以满足某些应用场合实际要求,在特征点提取阶段,利用金字塔光流法提取特征点并划分有效及无效区域特征点,从而降低特征点匹配个数和提高后续运算特征...针对传统的ORB(Oriented fast and rotated brief)算法在运算速度以及精度方面有时难以满足某些应用场合实际要求,在特征点提取阶段,利用金字塔光流法提取特征点并划分有效及无效区域特征点,从而降低特征点匹配个数和提高后续运算特征点匹配速度;在特征点匹配阶段,将传统算法中的欧氏距离改为曼哈顿距离,再用MLESAC算法来剔除误匹配点。将SURF(Speeded up robust features)算法、SIFT(Scale-invariant feature transform)算法、ORB算法和改进后的ORB算法对光照条件不同、模糊度不同以及尺度大小不同的两张图像进行处理,改进后的ORB算法无论是在匹配速度还是匹配精度方面相比于传统ORB算法都有了明显改善。展开更多
为全面评价生态气候因子对湖北省烟叶生长发育的影响,利用2008—2020年中国气象局陆面数据同化系统(CMA land data assimilation system,CLDAS)数据集和其他环境因子,基于最大熵模型(MaxEnt),利用湖北省西部烟区实际种植点位模拟湖北省...为全面评价生态气候因子对湖北省烟叶生长发育的影响,利用2008—2020年中国气象局陆面数据同化系统(CMA land data assimilation system,CLDAS)数据集和其他环境因子,基于最大熵模型(MaxEnt),利用湖北省西部烟区实际种植点位模拟湖北省烟区的潜在适宜性分布,并评估影响适宜性分布的主导环境因子。结果显示:MaxEnt模型对烟草适宜性分布的模拟预测精度较高(AUC=0.854)。海拔(650~1750 m)、土壤类型(黄壤)、团棵期平均最低气温(8.9~15.0℃)、旺长期平均气温(16.0~22.9℃)、成熟期平均气温(18.8~25.6℃)是影响湖北烟草分布的主导环境因子。烟草的高适生区主要分布在恩施、十堰和襄阳南部及宜昌东南部,占湖北省总面积的18.2%,80%区域的海拔为700~1350 m、团棵期平均最低气温11.2~14.5℃、旺长期平均气温19.2~22.8℃、成熟期平均气温22.0~25.4℃。在所有环境因子中,海拔高度起决定性作用,温度则是影响烟草生长发育的重要气象因子。研究表明,本研究结果与湖北烟区实际空间分布基本相符。展开更多
In this study, by starting from Maximum entropy (MaxEnt) distribution of time series, we introduce a measure that quantifies information worth of a set of autocovariances. The information worth of autocovariences is m...In this study, by starting from Maximum entropy (MaxEnt) distribution of time series, we introduce a measure that quantifies information worth of a set of autocovariances. The information worth of autocovariences is measured in terms of entropy difference of MaxEnt distributions subject to different autocovariance sets due to the fact that the information discrepancy between two distributions is measured in terms of their entropy difference in MaxEnt modeling. However, MinMaxEnt distributions (models) are obtained on the basis of MaxEnt distributions dependent on parameters according to autocovariances for time series. This distribution is the one which has minimum entropy and maximum information out of all MaxEnt distributions for family of time series constructed by considering one or several values as parameters. Furthermore, it is shown that as the number of autocovariances increases, the entropy of approximating distribution goes on decreasing. In addition, it is proved that information worth of each model defined on the basis of MinMaxEnt modeling about stationary time series is equal to sum of all possible information increments corresponding to each model with respect to preceding model starting with first model in the sequence of models. The fulfillment of obtained results is demonstrated on an example by using a program written in Matlab.展开更多
Information based models for radiation emitted by a Black Body which passes through a scattering medium are analyzed. In the limit, when there is no scattering this model reverts to the Black Body Radiation Law. The a...Information based models for radiation emitted by a Black Body which passes through a scattering medium are analyzed. In the limit, when there is no scattering this model reverts to the Black Body Radiation Law. The advantage of this mathematical model is that it includes the effect of the scattering of the radiation between source and detector. In the case when the exact form of the scattering mechanism is not known a model using a single scattering parameter is derived. A simple version of this model is derived which is useful for analyzing large data.展开更多
近年来,深度强化学习在控制任务中取得了显著的效果.但受限于探索能力,难以快速且稳定地求解复杂任务.分层强化学习作为深度强化学习的重要分支,主要解决大规模问题.但是仍存在先验知识设定的不合理和无法有效平衡探索与利用等难题.针...近年来,深度强化学习在控制任务中取得了显著的效果.但受限于探索能力,难以快速且稳定地求解复杂任务.分层强化学习作为深度强化学习的重要分支,主要解决大规模问题.但是仍存在先验知识设定的不合理和无法有效平衡探索与利用等难题.针对以上问题,提出优势加权互信息最大化的最大熵分层强化学习(Maximum Entropy Hierarchical Reinforcement Learning with Advantage-weighted Mutual Information Maximization,HRLAMIM)算法.该算法通过优势函数加权重要性采样与互信息最大化,解决由策略引起的样本聚类问题,增加内部奖励来强调Option的多样性.同时,将奖励引入最大熵强化学习目标,使策略具有了更强的探索性和更好的稳定性.此外,采用Option数量退火方法,不仅减少了先验知识对性能的影响,还平衡了算法的探索与利用,并获得了更高的样本效率和更快的学习速度.将HRL-AMIM算法应用于Mujoco任务中,实验表明,与传统深度强化学习算法和同类型的分层强化学习算法相比,HRL-AMIM算法在性能和稳定性方面均具有较大的优势.进一步通过消融实验和超参数敏感性实验,验证了算法的鲁棒性和有效性.展开更多
文摘Based on the maximum entropy principle, a probability density function (PDF) is derived for the distribution of wave heights in a random wave field, without any more hypothesis. The present PDF, being a non-Rayleigh form, involves two parameters: the average wave height H— and the state parameter γ. The role of γ in the distribution of wave heights is examined. It is found that γ may be a certain measure of sea state. A least square method for determining γ from measured data is proposed. In virtue of the method, the values of γ are determined for three sea states from the data measured in the East China Sea. The present PDF is compared with the well known Rayleigh PDF of wave height and it is shown that it much better fits the data than the Rayleigh PDF. It is expected that the present PDF would fit some other wave variables, since its derivation is not restricted only to the wave height.
基金This research was financially supported by the National Natural Science Foundation of China(Grant Nos.52071306 and 51379195)the Natural Science Foundation of Shandong Province(Grant No.ZR2019MEE050).
文摘Marine environmental design parameter extrapolation has important applications in marine engineering and coastal disaster prevention.The distribution models used for environmental design parameter usually pass the hypothesis tests in statistical analysis,but the calculation results of different distribution models often vary largely.In this paper,based on the information entropy,the overall uncertainty test criteria were studied for commonly used distributions including Gumbel,Weibull,and Pearson-III distribution.An improved method for parameter estimation of the maximum entropy distribution model is proposed on the basis of moment estimation.The study in this paper shows that the number of sample data and the degree of dispersion are proportional to the information entropy,and the overall uncertainty of the maximum entropy distribution model is minimal compared with other models.
基金Supported by the National Natural Science Foundation of China as key program (No.60435020) and The HighTechnology Research and Development Programme of China (2002AA117010-09).
文摘This paper applied Maximum Entropy (ME) model to Pinyin-To-Character (PTC) conversion in-stead of Hidden Markov Model (HMM) that could not include complicated and long-distance lexical informa-tion. Two ME models were built based on simple and complex templates respectively, and the complex one gave better conversion result. Furthermore, conversion trigger pair of y A → y B cBwas proposed to extract the long-distance constrain feature from the corpus; and then Average Mutual Information (AMI) was used to se-lect conversion trigger pair features which were added to the ME model. The experiment shows that conver-sion error of the ME with conversion trigger pairs is reduced by 4% on a small training corpus, comparing with HMM smoothed by absolute smoothing.
文摘Complete prior statistical information is currently required in the majority of statistical evaluations of complex models. The principle of maximum entropy is often utilized in this context to fill in the missing pieces of available information and is normally claimed to be fair and objective. A rarely discussed aspect is that it relies upon testable information, which is never known but estimated, i.e. results from processing of raw data. The subjective choice of this processing strongly affects the result. Less conventional posterior completion of information is equally accurate but is computationally superior to prior, as much less information enters the analysis. Our recently proposed methods of lean deterministic sampling are examples of very few approaches that actively promote the use of minimal incomplete prior information. The inherited subjective character of maximum entropy distributions and the often critical implications of prior and posterior completion of information are here discussed and illustrated, from a novel perspective of consistency, rationality, computational efficiency and realism.
文摘针对传统的ORB(Oriented fast and rotated brief)算法在运算速度以及精度方面有时难以满足某些应用场合实际要求,在特征点提取阶段,利用金字塔光流法提取特征点并划分有效及无效区域特征点,从而降低特征点匹配个数和提高后续运算特征点匹配速度;在特征点匹配阶段,将传统算法中的欧氏距离改为曼哈顿距离,再用MLESAC算法来剔除误匹配点。将SURF(Speeded up robust features)算法、SIFT(Scale-invariant feature transform)算法、ORB算法和改进后的ORB算法对光照条件不同、模糊度不同以及尺度大小不同的两张图像进行处理,改进后的ORB算法无论是在匹配速度还是匹配精度方面相比于传统ORB算法都有了明显改善。
文摘为全面评价生态气候因子对湖北省烟叶生长发育的影响,利用2008—2020年中国气象局陆面数据同化系统(CMA land data assimilation system,CLDAS)数据集和其他环境因子,基于最大熵模型(MaxEnt),利用湖北省西部烟区实际种植点位模拟湖北省烟区的潜在适宜性分布,并评估影响适宜性分布的主导环境因子。结果显示:MaxEnt模型对烟草适宜性分布的模拟预测精度较高(AUC=0.854)。海拔(650~1750 m)、土壤类型(黄壤)、团棵期平均最低气温(8.9~15.0℃)、旺长期平均气温(16.0~22.9℃)、成熟期平均气温(18.8~25.6℃)是影响湖北烟草分布的主导环境因子。烟草的高适生区主要分布在恩施、十堰和襄阳南部及宜昌东南部,占湖北省总面积的18.2%,80%区域的海拔为700~1350 m、团棵期平均最低气温11.2~14.5℃、旺长期平均气温19.2~22.8℃、成熟期平均气温22.0~25.4℃。在所有环境因子中,海拔高度起决定性作用,温度则是影响烟草生长发育的重要气象因子。研究表明,本研究结果与湖北烟区实际空间分布基本相符。
文摘In this study, by starting from Maximum entropy (MaxEnt) distribution of time series, we introduce a measure that quantifies information worth of a set of autocovariances. The information worth of autocovariences is measured in terms of entropy difference of MaxEnt distributions subject to different autocovariance sets due to the fact that the information discrepancy between two distributions is measured in terms of their entropy difference in MaxEnt modeling. However, MinMaxEnt distributions (models) are obtained on the basis of MaxEnt distributions dependent on parameters according to autocovariances for time series. This distribution is the one which has minimum entropy and maximum information out of all MaxEnt distributions for family of time series constructed by considering one or several values as parameters. Furthermore, it is shown that as the number of autocovariances increases, the entropy of approximating distribution goes on decreasing. In addition, it is proved that information worth of each model defined on the basis of MinMaxEnt modeling about stationary time series is equal to sum of all possible information increments corresponding to each model with respect to preceding model starting with first model in the sequence of models. The fulfillment of obtained results is demonstrated on an example by using a program written in Matlab.
文摘Information based models for radiation emitted by a Black Body which passes through a scattering medium are analyzed. In the limit, when there is no scattering this model reverts to the Black Body Radiation Law. The advantage of this mathematical model is that it includes the effect of the scattering of the radiation between source and detector. In the case when the exact form of the scattering mechanism is not known a model using a single scattering parameter is derived. A simple version of this model is derived which is useful for analyzing large data.
文摘近年来,深度强化学习在控制任务中取得了显著的效果.但受限于探索能力,难以快速且稳定地求解复杂任务.分层强化学习作为深度强化学习的重要分支,主要解决大规模问题.但是仍存在先验知识设定的不合理和无法有效平衡探索与利用等难题.针对以上问题,提出优势加权互信息最大化的最大熵分层强化学习(Maximum Entropy Hierarchical Reinforcement Learning with Advantage-weighted Mutual Information Maximization,HRLAMIM)算法.该算法通过优势函数加权重要性采样与互信息最大化,解决由策略引起的样本聚类问题,增加内部奖励来强调Option的多样性.同时,将奖励引入最大熵强化学习目标,使策略具有了更强的探索性和更好的稳定性.此外,采用Option数量退火方法,不仅减少了先验知识对性能的影响,还平衡了算法的探索与利用,并获得了更高的样本效率和更快的学习速度.将HRL-AMIM算法应用于Mujoco任务中,实验表明,与传统深度强化学习算法和同类型的分层强化学习算法相比,HRL-AMIM算法在性能和稳定性方面均具有较大的优势.进一步通过消融实验和超参数敏感性实验,验证了算法的鲁棒性和有效性.