DB004107-模式分析与模式识别

研究生课程开设申请表

 开课院（系、所）：  信息科学与工程学院     

 课程申请开设类型： 新开√   重开□    更名□（请在□内打勾，下同）

一、课程介绍（含教学目标、教学要求等）（300字以内）

 本课程要求掌握模式识别与模式分析的基础、原理、方法和应用，以及该学科领域近年来取得的一些新的研究成果和技术，提高学生解决工程实际问题的能力。要求掌握的内容主要包括：1、模式识别概论；2、贝叶斯决策理论；3、线性判别函数；4、聚类分析；5、模糊模式识别；6、神经网络识别理论及模型；7、子空间法模式识别；8、特征的选择与提取。

二、教学大纲（含章节目录）：（可附页）

一、模式识别概论 

1. 模式识别的概念
2. 模式识别系统
3. 模式识别的应用   

二、贝叶斯决策理论

1. 基于最小错误率的贝叶斯决策
2. 基于最小风险的贝叶斯决策
3. 在限定一类错误率条件下使另一类错误率为最小的两类别决策
4. 最小最大决策
5. 序贯分类方法
6. 分类器设计  

三、 线性判别函数

1. 线形判别函数的基本概念

2. 感知器及其训练

3. 感知器准则函数及其梯度法

4. 最小平方和准则函数与H-K算法

5. Fisher线性判别式

6. 广义线性判决函数

7. 势函数法

四、 聚类分析
1. 相似性度量方法
2. 聚类准则
3. 两种简单的聚类算法（最近邻规则的聚类算法、最大最小距离聚类算法）
4. 快速动态聚类算法

五、模糊模式识别
1. 模糊信息处理基础
2. 模糊识别信息地获取
3. 模糊综合评判
4. 基于识别算法的模糊模式识别
5. 模糊聚类分析

六、神经网络识别理论及模型

1. 人工神经网络基本模型
2. 神经网络分类器
3. 模糊神经网络系统
4. 神经网络识别模型及相关技术

七、子空间法模式识别
1. 基本思想
2. K—L变换的数值计算
3. 子空间分类器
4. 学习子空间法

八、特征的选择与提取
1. 特征评判标准——类别可分性判据
2. 特征选择及搜索算法
3. 特征提取方法
4. 多层感知器用于特征压缩

三、教学周历

四、主讲教师简介：

 赵力，男，1958年出生。现工作于 ，教授。主要从事语音、声频和视频信号处理、情感信息处理等方面的研究工作。

五、任课教师信息（包括主讲教师）：

Application Form For Opening Graduate Courses

School (Department/Institute)：School of Information Science and Engineering

Course Type: New Open√    Reopen □    Rename □（Please tick in □, the same below）

1. Course Introduction (including teaching goals and requirements) within 300 words:

This course requires students master the foundation, principle, method, applications of pattern analysis and pattern recognition. The whole course can be divided into eight parts which include: introduction of pattern recognition;bayesian decision theory; linear discrimination function; clustering analyse; fuzzy pattern recognition; neutral network recognition theory and models; subspace pattern recognition; selection and acquisition of characteristics

2. Teaching Syllabus (including the content of chapters and sections. A sheet can be attached):

Ⅰ.Introduction of pattern recognition

1. definition of pattern recognition

2. pattern recognition system

3. application of pattern recognition

Ⅱ.Bayesian decision theory

1. bayesian decision based on minimum error probability

2. bayesian decision based on minimum harzard

3. two type bayesian decision

4. minimum maximum decision

5.sequence classify method

6. design of classification

Ⅲ. Linear discrimination function

1. basic definition of linear discrimination function

2. perceptron and its training

3. perceptron criterion function and gradient method

4. minimum square sum of criterion function and HK algorithm

5. Fisher linear discrimination function

6. generalized linear discrimination function

7. potential function

Ⅳ. Clustering analyse
1.similarity measurement  
2. clustering criterion

3. two kinds of simple clustering algorithms

4.fast dynamical clustering algorithms


Ⅴ. Fuzzy pattern recognition
1. fuzzy information processing fundamentations

2.fuzzy recognition information acquisition

3.fuzzy evaluation

4.fuzzy pattern recognition based on recognition algorithms

5.fuzzy cluster analysis

Ⅵ. Neutral network recognition theory and model

1. basic model of ANN

2. classifier of neutral network

3.fuzzy neutral network system

4.neutral network recognition model and related techniques

Ⅶ. Subspace pattern recognisiton
1. basic idea                  
2.numerical calculation of K-L transform
3. subspace classifier             
4. subspace learning method           

Ⅷ. Selection and acquisition of characteristics
1. criterion standard of characteristics

2.  selection and search algorithm of characteristics
3. acquisition of characteristics                      
4. multi-level perceptron applied to characteristics compress

3. Teaching Schedule:

Note: 1.Above one, two, and three items are used as teaching Syllabus in Chinese and announced on the Chinese website of Graduate School. The four and five items are preserved in Graduate School.

2. Course terms: Spring, Autumn , and Spring-Autumn term.  

3. The teaching languages for courses: Chinese, English or Chinese-English.

4. Applicable range of discipline: public, first-class discipline, second-class discipline, and third-class discipline.

5. Practice includes: experiment, investigation, research report, etc.

6. Teaching methods: lecture, seminar, practice, etc.

7. Examination for degree courses must be in paper.

8. Teaching material websites are those which have already been announced.

9. Brief introduction of chief lecturer should include: personal information (date of birth, gender, degree achieved, professional title), research direction, teaching and research achievements. (within 100-500 words)

4. Brief Introduction of Chief lecturer:

Zhao Li, male, born in 1958, work at school of information science and engineering, Southeast University, Professor, Research at speech, audio and video signal processing and emotional information processing.

5. Lecturer Information (include chief lecturer)