软件学报写作格式.doc-资料库

5be55b81-cde6-4350-b0fa-82d7e592b818.doc.pdf-第1页.png

第1页 / 共11页

5be55b81-cde6-4350-b0fa-82d7e592b818.doc.pdf-第2页.png

第2页 / 共11页

5be55b81-cde6-4350-b0fa-82d7e592b818.doc.pdf-第3页.png

第3页 / 共11页

5be55b81-cde6-4350-b0fa-82d7e592b818.doc.pdf-第4页.png

第4页 / 共11页

5be55b81-cde6-4350-b0fa-82d7e592b818.doc.pdf-第5页.png

第5页 / 共11页

5be55b81-cde6-4350-b0fa-82d7e592b818.doc.pdf-第6页.png

第6页 / 共11页

5be55b81-cde6-4350-b0fa-82d7e592b818.doc.pdf-第7页.png

第7页 / 共11页

5be55b81-cde6-4350-b0fa-82d7e592b818.doc.pdf-第8页.png

第8页 / 共11页

Project 1  Task: Data Mining Applications Report  Worth: 15%  Deadline: 20:00, Sep. 26, 2012 Project Description: Click here   Received Submissions: Click here  Selected Works for Presentation: Click here The Task In this project, you are required to read some papers in one special issue of SIGKDD Explorations, and then write a report. There are four special issues which you can select: 1. Successful Real-World Data Mining Applications http://www.kdd.org/newsletter/explorations-june-2006-8-1 2. Web Content Data Mining http://www.kdd.org/newsletter/explorations-december-2004-6-2 3. Educational Data Mining http://www.kdd.org/newsletter/explorations-december-2011-13-2 4. Data Mining for Health Informatics http://www.kdd.org/newsletter/explorations-june-2007-9-1 Follow your interest, choose one from these special issues listed above, read some papers in your selected issue and write a report. The URLs of these special issues are also listed above, from which you can find the papers of each special issue directly. To wirte this report, you need to consider the following three aspects based on the papers your have read:  Motivation, i.e., why data mining is used in this application; Techniques, i.e., how data mining is used in this application;   Results, i.e., how well data mining performs in this application. NOTES: 1). Please use this MSWord template to write your report in Chinese with English abstract, the file for submission should be named with your ID number, e.g., "MG1233001.docx". 2). Do NOT plagiarize, plagiarism will be seriously penalized: You should

be careful on writing your report. Whenever you are using words and works of others, citations should be made clear such that one can tell which part is actually yours. Details about how to identify a plagiarism can be found in "Introduction to the Guidelines for Handling Plagiarism Complaints". Submission Name your report using your student ID, e.g., 'MG1233001.docx'. The file format should be doc/docx, no other format is acceptable. NO submission after the deadline is acceptable! NO email submission will be accepted! Upload your file to FTP: (please use FTP software to upload, do not use Windows Explorer or IE) ftp://lamda.nju.edu.cn/mg_DM_2012/assignment1/ username: mg_dm12 password: mg_dm12 Evaluation Your language: concise, precise, and logical. Your organization: good structure, clearly and properly separated sections and paragraphs. Citations: all works of non-yourself should have correct references. Insights: readers will have an idea on why and how data mining is useful in this application after reading your report. If plagiarism is identified, no scores will be given to this report. Presentation About 5 submissions will be selected and presented (by the author) in the class. Project 2  Task: A Classification Task  Worth: 10%

 Deadline: 20:00, Oct. 17, 2012 Project Description: Click here   Received Submissions: Click here  Selected Works for Presentation: Click here The Task In this project, you are required to do a classification task. In detail, your job includes: 1. Read the description of the task and download the data set; 2. Implement an algorithm and output the result; 3. Write a report; 4. Submit your work; 5. (optional) If selected, prepare your presentation Task Decription and Dataset Download Dataset: The dataset has in all 1100 instances. Each instance has 42 attributes. Download: training data[111 K]: each line is an instance, 700 instances in all. testing data[64 K]: each line is an instance, 400 instances in all. Task: Predict the label for each instance in testing data.. NOTES: I have maken some preprocessings for the original dataset. So, please do not make effort to find out the original dataset from website because it is useless. How to Write the Report Your report should includes:

1. Your understand and analysis of the problem; 2. The motivation of your algorithm and introduction of the background of your algorithm; 3. Full technical details of your algorithm, especially including pseudocode of your algorithm; 4. Description or analysis of the performance you got; 5. Conclusion and (optional) discussion. NOTES: 1. Please use this MSWord template to write your report in Chinese with English abstract, the file for submission should be named with your student ID, e.g., "MG1233001.docx". 2. Do NOT plagiarize, plagiarism will be seriously penalized: You should be careful on writing your report. Whenever you are using words and works of others, citations should be made clear such that one can tell which part is actually yours. Details about how to identify a plagiarism can be found in " Introduction to the Guidelines for Handling Plagiarism Complaints ". How to Submit Your submition should includes: 1. 'output.txt' file: containing the predicted labels of testing instances, each line corresponds to one instance like 'train label' file in training dataset; 2. 'report.pdf' file: your report; 3. source file of your algorithm Please carefully check out your submission: 1. Note that the name of the files should not be other names. 2. Pack all your files into a single compressed file (compress in zip, rar, or 7z formats). Name the compressed file using your student ID, e.g., 'MG1233001.rar'. Please delete the .bak, i.e., the backup files from your final .rar files.

Upload your file to FTP: (please use FTP software to upload, do not use Windows Explorer or IE) ftp://lamda.nju.edu.cn/mg_DM_2012/assignment2/ username: mg_dm12 password: mg_dm12 Evaluation We will evaluate your work in terms of: Your prediction: according to your "output.txt", we will use accuracy to evaluate your prediction. Your report: novel idea, sound techniques, and beautiful writing gain you high scores. Your source code: Fake and plagiarized source codes receives low scores. If plagiarism is identified, no scores will be given to this report. Presentation After all submissions being collected, about 5 assignments will be selected and presented (by the author) in the class. Project 3  Task: A Clustering Task  Worth: 10%  Deadline: 20:00, Nov. 7, 2012   Received Submissions: Click here  Project Description: Click here Selected Works for Presentation: Click here The Task In this project, you are required to do a clustering task. In detail, your job includes: 1. Read the description of the task and download the data set; 2. Implement an algorithm and output the result;

3. Write a report; 4. Submit your work; 5. (optional) If selected, prepare your presentation Task Decription and Dataset Download Dataset: The dataset has in all 1080 instances. Each instance has 856 attributes. Download: clustering data[1806 K]: each line is an instance, 1080 instances in all. Task: cluster the data and give the cluster id of each instance which it belongs to. NOTES: I have maken some preprocessings for the original dataset. So, please do not make effort to find out the original dataset from website because it is useless. How to Write the Report Your report should includes: 1. Your understand and analysis of the problem; 2. The motivation of your algorithm and introduction of the background of your algorithm; 3. Full technical details of your algorithm, especially including pseudocode of your algorithm; 4. Description or analysis of the performance you got; 5. Conclusion and (optional) discussion. NOTES:

1. Please use this MSWord template to write your report in Chinese with English abstract, the file for submission should be named with your student ID, e.g., "MG1233001.docx". 2. Do NOT plagiarize, plagiarism will be seriously penalized: You should be careful on writing your report. Whenever you are using words and works of others, citations should be made clear such that one can tell which part is actually yours. Details about how to identify a plagiarism can be found in " Introduction to the Guidelines for Handling Plagiarism Complaints ". How to Submit Your submition should includes: 1. 'output.txt' file : containing the clusters id of each examples, each line corresponds to one instance like the last task; 2. 'report.pdf' file : your report; 3. source file of your algorithm Please carefully check out your submission: 1. Note that the name of the files should not be other names. 2. Pack all your files into a single compressed file (compress in zip, rar, or 7z formats). Name the compressed file using your student ID, e.g., 'MG1233001.rar'. Please delete the .bak, i.e., the backup files from your final .rar files. Upload your file to FTP: (please use FTP software to upload, do not use Windows Explorer or IE) ftp://lamda.nju.edu.cn/mg_DM_2012/assignment3/ username: mg_dm12 password: mg_dm12 Evaluation We will evaluate your work in terms of: Your prediction: according to your "output.txt", we will use Rand measure to evaluate your clustering results. As for Rand measure, you may refer to http://en.wikipedia.org/wiki/Rand_measure.

Your report: novel idea, sound techniques, and beautiful writing gain you high scores. Your source code: Fake and plagiarized source codes receives low scores. If plagiarism is identified, no scores will be given to this report. Presentation After all submissions being collected, about 5 assignments will be selected and presented (by the author) in the class. Project 4  Task: Data Mining Practice on A Real-World Task  Worth: 15%  Deadline: 20:00, Dec. 19, 2012 Project Description: Click here   Received Submissions: Click here  Selected Works for Presentation: Click here The Task In this project, you are required to mine the PAKDD 2012 Data Mining Competition dataset. In detail, your job includes: 1. Read the description of the task and download the data set; 2. Implement an algorithm and output the prediction; 3. Write a report; 4. Submit your work; 5. (optional) If selected, prepare your presentation Task Decription and Dataset Download Background: Maintaining customers and ensuring customers are satisfied with the products offered have always been a major challenge for telcos. Companies

资料库

软件学报写作格式.doc

相关推荐

课程资源

热门标签

最新资料