arrow

Reinforcement Learning 中以 Q learning 學習的倒單擺實驗。以x,x_dot,theta,theta_dot作為狀態參數 state，利用model模擬之結果做Q值更新，產生Q table，對學習平衡控制。結果以csv檔作為輸出，可以由使用者作圖觀察變化。(Reinforcement Learning , utilize Q learning for An inverted pendulum system control。x,x_dot,theta,theta_dot as state variable，use model result renew Q table，control learning of balance pole 。output csv file contain trail(times),balance time(sec).it s better observe the change if user plot it. )

利用最小方差方法估计复正弦加白噪声得平稳信号的功率谱(After using the method of minimum variance estimate sine smooth white noise to the signal power spectrum)

利用独立分量分析中的FastICA算法对盲信号源进行了分离。最终通过实验结果表明，独立分量分析可以有效地实现分离。(FastICA algorithm using independent component analysis and blind source separation. Eventually through the experimental results show that the independent component analysis can be effectively separated.)

prediction - neural network code

LDPC的TDMP译码算法的不同量化方案下，误码率的仿真程序，包含encoder,decoder.并附有仿真图(Under different quantization scheme TDMP LDPC decoding algorithm, BER simulation procedures, including encoder, decoder. Together with simulation diagram)

MATLAB希尔伯特Hilbert变换求包络谱 源程序代码(MATLAB Hilbert spectral envelope of the Hilbert transform)

对不同的查找精心效率的估计，其中采用了3中不同的查找 方式。(Search carefully for different efficiency estimates, which used 3 different search methods.)

图像灰度直方图统计，可以针对一幅已经存储的*.tif格式的图像(Image histogram statistics, can have been stored in a*. tif format images)

认知无线电中能量检测matlab源码，体是仿真误警概率下，不同信噪比下的检测概率的。(energy detection)

mfcc的matlab显示方法，可以直接运行(mfcc s showing by matlab)