IDENTIFYING STUDENT CAPACITY TO IMPROVE ACADEMICS PERFOMANCE USING CLASSIFICATION ALGORITHM

Alagappa Institute of Skill Development & Computer Centre,Alagappa University, Karaikudi, India.15 -16 February 2017. IT Skills Show & International Conference on Advancements In Computing Resources (SSICACR-2017)

Format: Volume 5, Issue 1, No 17, 2017

Copyright: All Rights Reserved ©2017

Year of Publication: 2017

Author: NANDHINI.M,THENDRAL.T

Reference:IJCS-237

View PDF Format

Abstract

The main objective of the research is to improve Students performance in academic and classify the students as slow learner and fast learner according to their marks. The research problem is identifying slow learner and fast leaner from the given dataset using classification algorithms. Data mining is the process of extracting or mining hidden knowledge from huge amounts of data. The information and knowledge gained can be used for applications ranging from Financial Data Analysis, Retail Industry, Telecommunication Industry, Biological Data Analysis, Scientific Applications and Intrusion Detection [4]. Supervised learning is the machine learning task of inferring a function from labelled training data. Classification is the data mining technique. It is applied to our real time problems. Classification is the process of classify the data According to the features of the data with predefined set of classes [16]. It is difficult to analyse the large amount of data and make the decision based on that data. To solve this problem, data mining tools and techniques can be used. The weka tool is used for this research problem. Classification technique can be used for prediction of slow learners and fast learners for improving the performance. The student dataset can be used for classification process. The research takes three algorithms or classifiers to solve the research problem. The algorithms are Naïve bayes, Multilayer perceptron and J48. Each algorithm gives the best result for this research process. The J48 algorithm gives high accuracy compared to naïve bayes and multilayer perceptron. The accuracy of the J48 algorithm is 98%.

References

[1] AZWA ABDUL AZIZ, NUR HAFIEZA ISMAIL, FADHILAH AHMAD, “MINING STUDENTS’ ACADEMIC PERFORMANCE”, JOURNAL OF THEORETICAL AND APPLIED INFORMATION TECHNOLOGY, VOL. 53 NO.3,31 ST JULY 2013 , ISSN: 1992-8645 [2] CRISTÓBAL ROMERO, SEBASTIÁN VENTURA, PEDRO G. ESPEJO AND CÉSAR HERVÁS, “DATA MINING ALGORITHMS TO CLASSIFY STUDENTS” [3] A.A. AZIZ, N. H. ISMAIL, & F. AHMAD, “MINING STUDENTS’ ACADEMIC PERFORMANCE”, JOURNAL OF THEORETICAL AND APPLIED INFORMATION TECHNOLOGY, VOL. 53(2013), NO. 3, 485–495. [4] HAN, J. AND KAMBER, M., “DATA MINING: CONCEPTS AND TECHNIQUES”, 2ND EDITION. THE MORGAN KAUFMANN PUBLISHERS, 2006. [5] JIGNA ASHISH PATEL , “CLASSIFICATION ALGORITHMS AND COMPARISON IN DATA MINING” , INTERNATIONAL JOURNAL OF INNOVATIONS & ADVANCEMENT IN COMPUTER SCIENCE, IJIACS, VOLUME 4, MAY 2015, ISSN 2347 –8616 [6] MS. PRITI S. PATEL, DR.S.G.DESAI,”VARIOUS DATA MINING TECHNIQUES USED TO STUDY STUDENT’S ACADEMIC PERFORMANCE”, INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND MOBILE APPLICATIONS, VOL.3 ISSUE. 6, JUNE- 2015, PG. 55-58 ISSN: 2321-8363 [7] FADHILAH AHMAD, NUR HAFIEZA ISMAIL AND AZWA ABDUL AZIZ, “THE PREDICTION OF STUDENTS’ ACADEMIC PERFORMANCE USING CLASSIFICATION DATA MINING TECHNIQUES”, APPLIED MATHEMATICAL SCIENCES, VOL. 9, 2015, NO. 129, 6415-6426 [8] BRIJESH KUMAR BHARDWAJ AND SAURABH PAL , “DATA MINING : A PREDICTION FOR PERFORMANCE IMPROVEMENT USING CLASSIFICATION”, (IJCSIS) INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND INFORMATION SECURITY, VOL. 9 , NO. 4, APRIL 2011 [9] PIETER ADRIAANS AND DOLF ZANTINGE, DATA MINING, 1999, ISBN: 981-235-966-4. [10] POOJA THAKAR, ANIL MEHTA, MANISHA, “PERFORMANCE ANALYSIS AND PREDICTION IN EDUCATIONAL DATA MINING: A RESEARCH TRAVELOGUE”, INTERNATIONAL JOURNAL OF COMPUTER APPLICATIONS (097


Keywords

Slow learner, Fast learner, Classifiers, Student Performance, Accuracy, Classification, Naïve bayes, Multilayer Perceptron and J48.

This work is licensed under a Creative Commons Attribution 3.0 Unported License.   

TOP
Facebook IconYouTube IconTwitter IconVisit Our Blog