The student grouping system based on academic achievement using the developed k-means algorithm is linked to the division of the student group, which is a system that will produce groups based on subjects taken by students and the highest scores and indirectly qualify to produce the several groups of assignment at the university. The problem is that most lecturers are difficult to choose and compare students with the highest score and lowest score. The K-Means technique used is a non-irregular learning algorithm and attempts to be collected based on their equations. This system can help students and lecturers in managing the groups more systematically and get records of each group. The results of the similarities of the distribution of students according to this group can help the lecturers to produce the several groups of students in dividing assignments at the university.
Introduction
Student Selection Based On Academic Achievement System Using K-Means Clustering will be implemented to assist students and lecturers in addressing this problem.
In addition, K-Mean is a cluster method used to represent a group of students. In this system, the equations are based on the list of subjects as well as the number of students scores. K-Means is an algorithm of unorganized learning methods and attempts to be collected based on their equations.
Total irregular scores of students will be collected based on the equation. In this system, the equations are based on the list of subjects as well as the number of students scores.
Objective
To analyze the problem of selecting group students focusing on the subject list and the subject scores.
To design a proposed system of Student Selection Based On Academic Achievement System Using K-Means Clustering
To develop a Student Selection Based On Academic Achievement System Using K-Means Clustering
Methodology
Iterative Model
Framework
K-Mean Clustering Technique
K-Means Clustering is one of the methods that can be used to divide objects into partitions by categories by viewing the given midpoint.
The cluster of objects is viewed from the nearest object to the nearest midpoint. After finding out the nearest point, the object will be classified as a member of that category.
Next is to classify the objects into the existing categories randomly.
The next step is to compare objects with the entire centroid that exists. Each object searches the centroid closest to him.
After the whole object is compared, the object will be classified in a certain category based on the nearest centroid.
Result for Admin
Result for Lecturer
Result for Student
Conclusion
Most of the current research uses k-means in conducting their research work. However, there is lacking of research that cluster student’s skill achievement based on overall subject mark. Thus, my project will cover on skill achievement using K-Means Algorithm.
Student Profile
STUDENT ID: BTCL15039674 SUPERVISOR :DR. SUHAILAN BIN SAFEI COURSE : Bachelor of Computer Science Internet Computing (Hons) INSTITUTION : Universiti Sultan Zainal Abidin Terengganu (UniSZA) CONTACT NUMBER : +6017 2712 761 EMAIL :[email protected]