tnn7_code_201212141110

Convolutional(2,1,6) Encoder and soft decision Viterbi Decoder

用最小二乘法反应雷达得到的图像，得到各种数据特征参数(Reaction of the least square method to obtain the radar image data to obtain various characteristic parameters)

matlab gui设计，包括gui界面设计，以及gui后台程序的设计(matlab gui design, including the gui interface design, and design gui daemon)

量子遗传算法的基本代码，较为简单，适合学习用(Codebase quantum genetic algorithm is simple, suitable for learning with)

说明：  语音信号的数字滤波处理 加入高斯噪声再滤除,信噪比小于20分贝(Voice signal digital filter handle add further filtered Gaussian noise, signal to noise ratio is less than 20 dB)

模拟人的步行，是一个很好的模拟程序！！！( WALKER Human gait. This model, developed by Nikolaus Troje, is a five-term Fourier series with vector-valued coefficients that are the principal components for data obtained in motion capture experiments involving subjects wearing reflective markers walking on a treadmill. The components, which are also known as "postures" or "eigenwalkers", correspond to the static position, forward motion, sideways sway, and two hopping/bouncing movements that differ in the phase relationship between the upper and lower portions of the body. The postures are also classified by gender. Sliders allow you to vary the amount that each component contributes to the overall motion. A slider setting greater than 1.0 overemphasizes the characteristic. Can you see whether positive values of the gender coefficient correspond to male or female subjects?)

矢量量化：基于分裂算法的LBG算法，用分裂质心的方法进行，直到达到码字数量为止(Vector quantization: based on splitting algorithm with LBG algorithm, and split centroid number code words until reaching so far )

MUSIC算法是基于天线阵列协方差矩阵的特征分解类DOA估计算法，这里给出的是基于解相干的MUSIC算法。(MUSIC algorithm is based on the antenna array covariance matrix eigen-decomposition DOA estimation algorithm presented here is based on the MUSIC algorithm decoherence.)

神经网络理论与MATLAB7实现，对一些算法进行了实现，(Neural Network Theory and MATLAB7 achieved, a number of algorithms to achieve,)

利用朴实贝叶斯方法求解有关肺炎的问题。肺炎对应有四个特征：发烧、疼痛、咳嗽和血细胞异常，当确定了患肺炎与否时，四个特征条件独立。假设患肺炎与否和四个特征都可表示为Ture和False。 根据pneumonia.tex文件中的数据（500行，每行前4个数对应4个特征变量，第5个数对应患肺炎是否为真，以0表示False，1表示Ture），编写Matlab 程序 maininference.m，从example.txt中读取病人的症状信息（0表示False，1表示True，-1表示not given），并计算对应的患肺炎的可能性。所给的信息按发烧、疼痛、咳嗽、血细胞异常的顺序排列。将计算结果保存在answer.txt中。(Simple Bayesian method to solve the question of pneumonia. Pneumonia corresponding four characteristics: fever, pain, cough and blood cell abnormalities, determine the risk of pneumonia or not, the four characteristics of conditional independence. Assumptions suffering from pneumonia or not and four features can be represented as Ture and False. According to the data pneumonia.tex file (500 lines, each line of the first four numbers corresponding to the four characteristic variables, number 5 corresponds to the risk of pneumonia is true, 0 represents False, said Ture), to write Matlab program maininference. m from example.txt read the information of the patient' s symptoms (0 = False, said True, the-1 indicates not given), and to calculate corresponding to the likelihood of suffering from pneumonia. The information given by the order of fever, pain, cough, blood cell abnormalities. The calculated results is be saved in answer.txt.)