检测与识别

在gnuradio+usrp上实现OFDM协议，全双工的。(The OFDM agreement on the gnuradio+usrp, full-duplex.)

通过FFT算法来进行小波变换以及一些日常的统计分析，该包依赖于numpy，scipy等包的安装

说明：  tsne降维聚类，可视化，可画3D图，可运行，效果不错(TSNE dimensionality reduction clustering, visualization, can draw 3D map, can run, the effect is good)

K-means算法是最为经典的基于划分的聚类方法，是十大经典数据挖掘算法之一。K-means算法的基本思想是：以空间中k个点为形心进行聚类，对最靠近他们的对象归类。通过迭代的方法，逐次更新各簇的形心的值，直至得到最好的聚类结果。(K-means algorithm is the most classical partition-based clustering method and one of the ten classical data mining algorithms. The basic idea of K-means algorithm is to cluster k points in space and classify the objects closest to them. Iteratively, the values of centroid of clusters are updated one by one until the best clustering results are obtained.)

现在了faster rcnn

基于深度学习的人体姿态估计，主要是采用自下而上的方法，进行关节点的检测和聚类。进而对设计的模型做评估，检测关节点的准确率是否提升，是否达到了预想的效果。

keras模型转为其他模型格式，使用python接口实现

2010CB945500-组织干细胞识别、谱系重编程和示踪研究——相关学习资料，仅供个人学习参考，禁止用于商业目的(2010 CB945500 - Tissue Stem Cell Recognition, Genealogical Reprogramming and Tracer Research - Relevant Learning Materials for Individual Learning Reference only, Banned for Commercial Purpose)

回归预测 股票预测 用到支持向量机的相关预测项目(Regression forecast stock forecasting related forecasting project using support vector machine)

说明：  SCMA-ML-master code program(SCMA-ML-master code program)