ABSTRACT
Nowadays, some students need an extra pocket money to support their life in university. One of the way to get an extra pocket money is to be a part time tutor either among their friends in university or among the school students outside the university. Being a part time tutor is so good for them to build their self-esteem and also to gain an experience for their future career. However, some of them are still confused to teach since they don’t really know how to assess their abilities in the specific subject. Moreover, they need to proof to their future client or students that they are capable to teach the subject. Therefore, this project was built to classify their abilities to teach a subject based on their achievement in the courses that they take in university. This project is important to convince another student who need a tutor in a specific subject. To realize this project, clustering technique will be apply using centroid based clustering algorithm, K-means. K-means is often called an unsupervised learning, as we don’t have prescribed labels in the data and no class values denoting a priori grouping of the data instances are given.
INTRODUCTION
My Part Time Tutor Selection System is a tutor selection system based on Student’s Academic Achievement using K-Means Algorithm and it is a web base application system. This system is to help students who want to be a part-timer teacher to teach subject that fit their skills in a particular subject. The problem is how to classify tutor teacher among students according to certain subject correctly. As example, if they wanted to be a tutor in Data Structure subject, they must have a good result in basic programming subject and object-oriented programming subject. The system will group the potential tutors that nearly matched to the subject requirement. To realize the system, K-Means Clustering Algorithm will be used. To apply a tutor jobs, they need to fill in subject grade and the grade will be calculated based on the centroids to determine they are in the right tutors group.
OBJECTIVES |
FRAMEWORK |
KMEANS CLUSTERING ALGORITHM
K-Means Clustering is the simplest unsupervised learning technique that can solve clustering problem. The step follows a simple and easy way to classify a given set of data set through a certain number of cluster (assume k clusters) fixed a prior.
¡Define k centroids, one for each cluster.
These centroids should be placed in a wily way because of different location cause different result. So, is better to place them as much as possible far away from each other.
¡Take each point belonging to a given data set and associated it to a nearest centroid.
When no point is pending the first step is done. At this point, recalculated k new centroids as center of the clusters resulting from the previous step is needed.
¡After this k new centroids, a new binding has to be done between the same data points and nearest new centroids.
A loop has been generated, until it notices that the k centroids change their location step by step until no more changes are done. In the simplest words, centroids do not move any more.
¡Define k centroids, one for each cluster.
These centroids should be placed in a wily way because of different location cause different result. So, is better to place them as much as possible far away from each other.
¡Take each point belonging to a given data set and associated it to a nearest centroid.
When no point is pending the first step is done. At this point, recalculated k new centroids as center of the clusters resulting from the previous step is needed.
¡After this k new centroids, a new binding has to be done between the same data points and nearest new centroids.
A loop has been generated, until it notices that the k centroids change their location step by step until no more changes are done. In the simplest words, centroids do not move any more.
results
ADMIN PAGES
user pages
CONCLUSION
In conclusion, this system is propose to group part time tutors based on similar course achievement and assign them with a suitable subject to teach that suit their skill. Finally, the tutors will be given a list of recommended subject that is suitable with their range group. This system also may help the admin to group the tutor automatically based on the criteria of subject that they key in for the group.