Saliency Detection by Multi-Context Deep Learning daima

说明：  使用ARIMA-SVR组合预测的方式对数据进行预测，ARIMA与SVR分别对线性与非线性有较好的预测效果，因此通过SVR来预测ARIMA的残差使得预测结果更为精确(Arima-svr combined forecasting method is used to forecast the data. ARIMA and SVR have better prediction effect on linear and nonlinear respectively. Therefore, the residual of ARIMA predicted by SVR makes the prediction result more accurate)

说明：  K均值聚类算法是先随机选取K个对象作为初始的聚类中心。然后计算每个对象与各个种子聚类中心之间的距离，把每个对象分配给距离它最近的聚类中心。聚类中心以及分配给它们的对象就代表一个聚类。一旦全部对象都被分配了，每个聚类的聚类中心会根据聚类中现有的对象被重新计算。这个过程将不断重复直到满足某个终止条件。终止条件可以是没有（或最小数目）对象被重新分配给不同的聚类，没有（或最小数目）聚类中心再发生变化，误差平方和局部最小。(K-means clustering is a method of vector quantization, originally from signal processing, that is popular for cluster analysis in data mining. k-means clustering aims to partition n observations into k clusters in which each observation belongs to the cluster with the nearest mean, serving as a prototype of the cluster. This results in a partitioning of the data space into Voronoi cells.)

利用Python爬去豆瓣电影信息，存入数据库并生成磁云。

决策树与集成算法，用来分类已知数据种类，希望对编程有帮助(Decision tree and ensemble algorithm are used to classify known data types.)

说明：  abaqus 读取最大主应力插件，用于abaqus，自己编写(Read the maximum principal stress plug-in)

py语言led控制操作代码,第三方工具。(Py language LED control operation code, third-party tools.)

用于abaqus周期性边界条件的建立，采用python参数化建模。(The periodic boundary conditions for ABAQUS,The parameterized modeling of Python is adopted.)

pot模型参数估计, 其中有个超额均值函数图, 以及超额数按gpd分布拟合后的残差与指数分布的q-q图(Extreme value theory ; POT model)

说明：  Python 分水岭算法 用于图像分割等图像处理(Python watershed algorithm)

说明：  LSTM 的例子 单向LSTM 双向LSTM 多层LSTM(LSTM long short term memory)