CSE301 – Bio-Computation
CSE301 – Bio-Computation Assessment 3
Contribution to overall module assessment 10%
Submission deadline 18:00, Friday, Dec 20 2019
1. Assessment Task
In this assessment, you are to implement MLP with back-propagation training algorithm, and RBF
network with the RBF centers initialized from k-means clustering, using MATLAB for vehicle logo
classification. Please use sigmoid activation functions where necessary.
In the dataset (logo.mat), 117 samples of 5 different types of vehicle logo images as shown in Fig. 1
are provided, with corresponding class labels (1-5) and 80 features in each sample using appropriate
feature extraction algorithm.
Fig.1 Examples of vehicle logo images
For both MLP and RBF design, divide the dataset into a training set (80%) and a testing set (20%) and
show the convergence performance using MSE for each epoch in the training process.
Based on your algorithms designed, discuss the following in the report:
(1) for MLP: the effect of different number of hidden units;
(2) for MLP: the effect of different learning rate and momentum;
(3) for RBF: the effect of different number of RBF centres;
(4) compare the best MLP model and the best RBF model using confusion matrix.
Note:
(1) it is acceptable to follow references (or using code fragments) from textbooks or internet
resources, but you must cite them clearly in your report;
(2) it is acceptable to apply Matlab toolboxes and Matlab functions.
2. Report
Each student must write an individual report in English. The report must be a single file in .pdf format
including all the plots, figures, tables and appendixes (failure to comply with this requirement will be
marked as Fail according 5. Marking Criteria).
The format of the report is: single-column A4 size, Times New Roman 12pt, single line spacing, page
numbered, 0.75-inch margin on top/bottom/left/right, and with maximum 10 pages including cover
page, reference (and appendixes if any).
The structure of the report is:
(1) introduction: task description and background;
(2) methodology: introduction of the methods and models;
(3) experimental results and analysis: experiment procedures, results discussion and analysis,
performance comparison etc.;
(4) conclusion;
(5) references.
3. Submission
You are required to:
(1) compress your written report and source code into one single .ZIP file (other format such as .rar
or .7z will be marked as Fail according to 5. Marking Criteria);
(2) name the zip file as: StudentID_GivenName_Surname (e.g. 1601234_Rui_Yang);
(3) upload to the submission folder in ICE by 18:00, Friday, Dec 20 2019.
Late submission will receive penalty in the marking in accordance with the University Code of Practice
on Assessment. For each working day after the deadline, 5 marks (out of 100) will be deducted for up
CSE301留学生作业代写、MATLAB程序语言作业调试
to 5 working days. However, the mark will not be reduced below the pass mark for the assessment.
Work assessed below the pass mark will not be penalised for late submission of up to 5 days. Work
received more than 5 working days after the deadline will receive a mark of 0.
4. Plagiarism
This assessment is an individual work. Plagiarism (e.g. copying materials from other sources without
proper acknowledgement) is a serious academic offence. Plagiarism will not be tolerated and will be
dealt with in accordance with the University Code of Practice on Assessment.
5. Marking Criteria
Category Requirement
First Class
(≥70%)
Overall outstanding work. All of the requirements have been implemented in the
program and report. Highly qualified report that closes to professional level. The
report is well-structured and organized, with all of required information included,
with very few English problems.
Second Upper
(60 to 69%)
Most of the requirements have been implemented in the program and report.
Good report which is clearly structured with most of the required information but
with few English problems.
Second Lower
(50 to 59%)
Substantial working program implementing a good range of the requirements.
Acceptable written report for Year 4 level, which contains sufficient information
but some English problems.
Third
(40 to 49%)
Executable program that generates recognizable results, which however are
incomplete. The written report is readable with insufficient information covered.
Problems may appear in the structure and organization, with many English
problems.
Fail
(0 to 39%)
Wrong format in submission. Program is not working; or most of the required
results are not produced; or without acknowledging properly sources used if any.
Poor report which covers very limited number of items required.
No submission A mark of 0 will be awarded.
END OF DOCUMENT
因为专业,所以值得信赖。如有需要,请加QQ:99515681 或 微信:codehelp
CSE301 – Bio-Computation的更多相关文章
- BIO\NIO\AIO记录
IO操作可以分为3类:同步阻塞(BIO).同步非阻塞(NIO).异步(AIO). 同步阻塞(BIO):在此种方式下,用户线程发起一个IO操作以后,必须等待IO操作的完成,只有当真正完成了IO操作以后, ...
- (转)也谈BIO | NIO | AIO (Java版)
原文地址: https://my.oschina.net/bluesky0leon/blog/132361 关于BIO | NIO | AIO的讨论一直存在,有时候也很容易让人混淆,就我的理解,给出一 ...
- socket Bio demo
最近在做socket通信,最开始是基于Bio开发(其实开发的时候也不知道这种是基于BIO).但是问题来了,客户端发的报文,服务端接收会少,为了解决问题,只能恶补一下相关知识. 服务端: import ...
- 网络通信简单实例BIO,NIO,AIO
这里,我将做一个简单的通信程序,分别使用三种原始的通信工具:BIO,NIO,AIO. 功能就是一个服务器,一个客户端.服务器就是处理请求,返回响应.而客户端就是连接服务器,发送请求,接收响应. 第一步 ...
- VECTOR COMPUTATION
COMPUTER OR GANIZATION AND ARCHITECTURE DESIGNING FOR PERFORMANCE NINTH EDITION Although the perform ...
- 【转】Tomcat 的三种(bio,nio.apr) 高级 Connector 运行模式
转载地址:http://www.oschina.net/question/54100_16195 tomcat的运行模式有3种.修改他们的运行模式.3种模式的运行是否成功,可以看他的启动控制台,或 ...
- REDIS fdatasync技术问题和BIO技术的引入
http://oldblog.antirez.com/post/fsync-different-thread-useless.html 这是原文作者的博客 把他翻译下 带上自己的一些理解 看看作者引入 ...
- Java BIO、NIO、AIO 学习(转)
转自 http://stevex.blog.51cto.com/4300375/1284437 先来个例子理解一下概念,以银行取款为例: 同步 : 自己亲自出马持银行卡到银行取钱(使用同步IO时,Ja ...
- Tomcat Connector三种运行模式(BIO, NIO, APR)的比较和优化
Tomcat Connector的三种不同的运行模式性能相差很大,有人测试过的结果如下: 这三种模式的不同之处如下: BIO: 一个线程处理一个请求.缺点:并发量高时,线程数较多,浪费资源. Tomc ...
- BIO,NIO,AIO
同步阻塞IO(JAVA BIO): 同步并阻塞,服务器实现模式为一个连接一个线程,即客户端有连接请求时服务器端就需要启动一个线程进行处理,如果这个连接不做任何事情会造成不必要的线程开销,当然可 ...
随机推荐
- eclipse项目有红色感叹号
1.依赖有问题 找到build path 点击configure build path 点击libraries 找到有红叉的包,然后选中移除 2.引用的包有问题 利用maven引用的包出现问题,有的包 ...
- kafka删除topic及其相关数据
1.删除kafka存储目录(server.properties文件log.dirs配置,默认为"/tmp/kafka-logs")相关topic目录 2.Kafka 删除topic ...
- PHP设计模式 - 命令模式
命令模式:在软件系统中,“行为请求者”与“行为实现者”通常呈现一种“紧耦合”.但在某些场合,比如要对行为进行“记录.撤销/重做.事务”等处理,这种无法抵御变化的紧耦合是不合适的.在这种情况下,如何将“ ...
- Python实现树
树 (tree) 是一种非常高效的非线性存储结构.树,可以很形象的理解,有根,有叶子,对应在数据结构中就是根节点.叶子节点,同一层的叶子叫兄弟节点,邻近不同层的叫父子节点,非常好理解. 注:定义来自百 ...
- SQLite接口函数 - C核心api实践与总结
SQLite核心源代码由C语言写就,同时提供了很多的扩展包可应用于其他编程语言和类库,如Python.Ruby.Java.Perl..Net/C#.Qt和ODBC.在很多情况下,针对一种语言有很多扩展 ...
- 【题解】Luogu P5324 [BJOI2019]删数
原题传送门 易知这个数列的顺序是不用考虑的 我们看两个数列 \(1,2,3\)和\(3,3,3\)都能删完,再看两个数列\(1,2,3,4\)和\(2,2,4,4\),也都能删完 不难发现,我们珂以把 ...
- InheritedWidget and screen
self: import 'package:flutter/material.dart'; class GrantScreen { static double _width, _height; sta ...
- vue-cli3使用svg
(根据网上教程实操,仅作个记录) 执行命令安装插件 npm install svg-sprite-loader --save-dev 在vue.config.js中,添加配置 module.expor ...
- Flink入门 - 窗口函数
/* * ProcessWinFunOnWindow */ final StreamExecutionEnvironment streamExecutionEnvironment = StreamEx ...
- 关于ABViewer的疑问解答
很多 CAD小伙伴都对 ABViewer 这款软件不陌生吧.ABViewer 是用来处理图纸和工程文档管理的一款通用软件.可以用它来查看,编辑,转换,测量和打印DWG和其他CAD文件,以及3D模型和光 ...