基于马尔科夫随机场(Markov Random Field,MRF)模型下的遥感图像变化检测因固定组合能量函数导致的边缘分割模糊问题,提出了一种改进的变权重MRF遥感图像变化检测方法。该方法首先通过模糊C均值(Fuzzy C-means,FCM)算法对差值图像进行...基于马尔科夫随机场(Markov Random Field,MRF)模型下的遥感图像变化检测因固定组合能量函数导致的边缘分割模糊问题,提出了一种改进的变权重MRF遥感图像变化检测方法。该方法首先通过模糊C均值(Fuzzy C-means,FCM)算法对差值图像进行聚类分割,并依此分割结果作为变权重MRF的初始分割条件进行最终的分割;最后对分割结果进行掩膜处理,得到最终的变化检测结果。采用真实遥感影像进行对比实验,结果表明所提方法变化检测精度更高,边缘检测更加平滑,区域一致性更好。展开更多
The decomposition-based vector autoregressive model (DVAR) provides a new framework for scrutinizing the efficiency of technical analysis in forecasting stock returns. However, its relation- ships with other technic...The decomposition-based vector autoregressive model (DVAR) provides a new framework for scrutinizing the efficiency of technical analysis in forecasting stock returns. However, its relation- ships with other technical indicators still remain unknown. This paper investigates the relationships of DVAR model with the Japanese Candlestick indicators using simulations, theoretical explanations and empirical studies. The main finding of this paper is that both lower and upper shadows in Japanese Candlestick Granger contribute to the DVAR model explanation power, and thus, providing useful information for improving the DVAR forecasts. This finding makes sense as it means that the infor- mation contained in the lower and upper shadows should be used when modeling the stock returns with DVAR. Empirical studies performed on China SSEC stock index demonstrate that DVAR model with upper and lower shadows as exogenous variables does have informative and valuable out-of-sample forecasts.展开更多
文摘基于马尔科夫随机场(Markov Random Field,MRF)模型下的遥感图像变化检测因固定组合能量函数导致的边缘分割模糊问题,提出了一种改进的变权重MRF遥感图像变化检测方法。该方法首先通过模糊C均值(Fuzzy C-means,FCM)算法对差值图像进行聚类分割,并依此分割结果作为变权重MRF的初始分割条件进行最终的分割;最后对分割结果进行掩膜处理,得到最终的变化检测结果。采用真实遥感影像进行对比实验,结果表明所提方法变化检测精度更高,边缘检测更加平滑,区域一致性更好。
基金supported by the National Natural Science Foundation of China under Grant No.71401033
文摘The decomposition-based vector autoregressive model (DVAR) provides a new framework for scrutinizing the efficiency of technical analysis in forecasting stock returns. However, its relation- ships with other technical indicators still remain unknown. This paper investigates the relationships of DVAR model with the Japanese Candlestick indicators using simulations, theoretical explanations and empirical studies. The main finding of this paper is that both lower and upper shadows in Japanese Candlestick Granger contribute to the DVAR model explanation power, and thus, providing useful information for improving the DVAR forecasts. This finding makes sense as it means that the infor- mation contained in the lower and upper shadows should be used when modeling the stock returns with DVAR. Empirical studies performed on China SSEC stock index demonstrate that DVAR model with upper and lower shadows as exogenous variables does have informative and valuable out-of-sample forecasts.