Learning classification algorithms in data mining
Institution: | California State University – Sacramento |
---|---|
Department: | Computer Science |
Degree: | MS |
Year: | 2015 |
Keywords: | Courseware; Data mining; Classification algorithms |
Record ID: | 2061341 |
Full text PDF: | http://hdl.handle.net/10211.3/139358 |
Classification algorithms are used in data mining to classify data based on class labels. It involves building a model using training data set, and then using the built model to assign given items to specific classes/categories. In the model building process, also called training process, a classification algorithm finds relationships between the attributes of the data and the target. Different classification algorithms use different techniques for finding relationships. These relationships are summarized in a model, which can then be applied to a new data set in which the class assignments are unknown. This project???s objective is to create a courseware that focuses on creating materials to achieve the goal of helping the students get deeper understanding of the most used classification algorithms in data mining. The existing materials on the classification algorithms are completely textual and students find it difficult to grasp. By using interactive examples and animated tutorials provided in the courseware, students should be able to intuitively learn these classification algorithms easily. With the help of this courseware, students will be able to learn the algorithms using flash animations and then visualize the steps with the help of interactive examples that can be modified in many ways by the student to get a complete understanding of the algorithms. There is also information provided on how to make practical use of these algorithms using data mining tools such as Weka and RapidMiner where students can apply the algorithms on real datasets available. Implementation of the courseware is done with technologies such as HTML, JavaScript, and Bootstrap CSS.