Application of genetic algorithm in modeling university admission decision support system

Project Abstract

<p> </p><p>This thesis evaluates the impact of Universities’ entry qualification requirements and the<br>performance of students, in order to decide how these factors bring patterns that are best<br>for admission. The proposed model uses the defined University’s entry qualification as<br>input variables and the students’ first year performance to determine the best admission<br>requirements. Genetic algorithm was used as the searching technique to determine the<br>hidden relationship between the input and the associated performance. Students’<br>admission data and their corresponding first year results were obtained from the<br>department of Mathematics, Ahmadu Bello University, Zaria. The results indicated that<br>the observed performance of students whose admission into Mathematics Department<br>through the University Matriculation Examinations, Post University Tertiary<br>Matriculation Examinations and O’levels depends more on their respective mathematics<br>and physics average performance in all the three examinations than their entry scores in<br>the individual examination. A comparative study using a statistical model show that the<br>result obtained from the genetic algorithm approach were in line with the result of the<br>statistical model. The model was implemented using java programming language,<br>developed in Netbean environment.</p><p><strong>&nbsp;</strong></p> <br><p></p>

Project Overview

<p> NTRODUCTION<br>1.1 Introduction<br>University education in Nigeria has witnessed tremendous development since the<br>country’s independence in 1960 (Adeyemi, 2010). This is in recognition of the fact that<br>the national policy of education stipulates that university education in Nigeria shall<br>make optimum contribution to national development by intensifying and diversifying its<br>programmes for the development of high level manpower within the context of the<br>needs of the nation (FGN, 2004). One of the factors limiting the University in<br>performing its roles as it is required is the quality of students admitted into various<br>academic programmes (Adeyemo and Kuye, 2006). It is expected that an average<br>student admitted into the University should be able to face academic studies with ease<br>and pass his/her courses without engaging examination malpractice; because it is<br>assumed that such student would have had prior experience in public examination.<br>Students are expected to have sat for the Senior Secondary School Certificate<br>Examinations (SSCE) and passed the minimum requirement and presented themselves<br>for the Joint Admission and Matriculation Board (JAMB) Examination as a selection<br>test and pass at acceptable cut-off point before being offered admission into the<br>university (Salim, 2006). Despite these public examinations that the Nigerian<br>undergraduates had gone through, it has been observed that their performances in the<br>first two years of their undergraduate studies do not usually match that of the JAMB<br>which is used as the basis for their admission in the first place into the University<br>(Adeyemo and Kuye, 2006). Many students hardly pass all their first year courses and<br>2<br>majority of those who successfully do so usually have poor grades. A great percentage<br>of university graduates in Nigeria fall below second class upper division and the number<br>of spillover students in various departments are equally high. The situation gets worse<br>as those who manage to graduate are not productive in the labour market because they<br>are unable to meet the expectations of the employers (Ajala, 2010).<br>In 2005, Universities recommended that further screening be conducted on candidates<br>who sat scored between 180 and 200 marks in the university matriculations examination<br>depending on the university where admission is being sought. The recommendation was<br>made with the hope that the post- JAMB screening exercise would restore the past glory<br>of tertiary education in the country and make university education accessible only to<br>those who want and need it (Ande, 2006). Hence, these lead to multiple admissions<br>selection criteria.<br>The issue of whether or not the scores in O’levels, UME and PUTME correlate to the<br>candidate’s performance in the university, especially in the first year has begun to<br>attract researchers’ attention. Some researchers claimed that O’levels and UME have no<br>correlation. This needs further investigation and evaluation in order to arrive at a<br>reasonable conclusion. It is known that the selection of students is a complex decision<br>making process, in which multiple selection criteria often needs to be considered.<br>However, the selection criteria used in higher education admission processes varies<br>widely among programmes and no consistent conclusions can be reached on the<br>predictive values of these criteria (Wilson, 1999). Statistical procedures, such as<br>discriminant analysis and regression analysis are traditionally used for predicting the<br>potential academic success of the applicant (Graham, 1991). In the world of information<br>3<br>processing, there are lots of data with increasingly complex multi-domain problems<br>containing either real-world or computer-generated data, which the statistical data<br>processing tools may not be sufficient enough to handle, hence a more advanced<br>approach needs to be developed.<br>This thesis uses genetic algorithm to evaluate the admission requirement into various<br>university programmes using computer science of the department of mathematics,<br>Ahmadu Bello University Zaria as a case study. The system predicts the patterns that are<br>suitable for selection of students’ into the programme. Genetic algorithm has shown a<br>promising feature in the area of decision support system. The principle of survival of the<br>fittest in which genetic algorithm was modeled, could be of great benefit in the process<br>of random selection from the available data.<br>1.2 Background Information<br>Despite stringent measures and strategies employed by the Nigerian government to<br>ensure that educational standards are maintained at least at university level, students<br>who after passing through these vigorous examinations still perform far below<br>expectations. For instance, from the summary of Computer Science students’ data,<br>Mathematics department, Ahmadu Bello University, Zaira for 2009/2010 session, out of<br>173 students that were admitted into the programme none had CGPA above 4.5, 18 had<br>CGPA between 3.5 and 4.49, 35 had CGPA between 2.4 and 3.49, 10 had CGPA<br>between 1.5 and 2.39. At the end 97 student were recorded to have one or two carry<br>over and 2 were asked to withdraw (Departmental second semester summary,<br>2010). This implies that only 10.78% of the students actually had satisfactory results at<br>the end of their stay of first academic year. This also shows that 87.22% of the students<br>had academic challenges as undergraduate students. The high rate of poor academic<br>4<br>achievement among undergraduate is not unconnected with the channel through which<br>they gained entry into the University. Ebiri (2010), observed that using JAMB as a<br>yardstick for admission of students into Nigerian universities has led to the intake of<br>poor caliber of candidates, characterized by high failure rate, increase in examination<br>malpractice, high spillovers and the production of poor quality output that are neither<br>self-reliant nor able to contribute effectively in the employment world.<br>Ironically, the process of selecting candidates for admission into tertiary institutions has<br>largely depended on some fixed combinations of some subjects taken by applicants in<br>their lower level classes. However, this technique has never been proved efficient in<br>admitting candidates that may perform well in the chosen courses. The fast growing of<br>candidates seeking for admission into tertiary institutions, there is a need to use past<br>data for decision support in admitting suitable candidate for a course of study.<br>Universities are facing the immense and quick growth of the volume of educational data<br>(Schönbrunn and Hilbert, 2006). Intuitively, this large amount of raw stored data<br>contains valuable hidden knowledge, which could be used to improve the decisionmaking<br>process of universities (keshavamurthy et al., 2010). An analysis of the existing<br>transaction data provides the information on students that will allow the definition of the<br>key processes that have to be adapted in order to enhance the efficiency of studying<br>(Mario et al., 2010). It is tedious and difficult to analyze such large voluminous data<br>and establishing relationship between multiple features manually. Our proposed system<br>delves into the problem of finding data patterns in admission datasets and provides a<br>technique to predict the performance of students in the first year in the University based<br>on the admission combination.<br>5<br>1.3. Problem Definition and Motivation<br>Higher education systems all over the world nowadays are challenged by the new<br>information and communication technologies (Boufardea and Garofalakis, 2012).<br>Moreover, with the increase in competition among the prospective students into higher<br>institutions, most Universities are facing the daunting task of selecting the best students,<br>who have the ability and skills to pursue and succeed in their academic career in a<br>particular field of studies. This is because Universities are interested in increasing<br>performance. Performance is one of the means of measuring University’s quality and<br>reputation (Jusoff et al., 2008), thus higher institutions are becoming more interested in<br>predicting the paths of students, and identifying which students will require assistance<br>in order to graduate (Luan, 2004). In order to be able to achieve this objective, the<br>finding relationships and patterns that exist but are hidden among the vast amount of<br>educational data is needed. This knowledge will help in educational main processes<br>such as counseling, planning, registration, and evaluation in order to give suitable<br>recommendation of the students.<br>Predictions of qualities of entry result that should be used in admitting students into<br>respective programmes are published in Nigeria, mostly in medicine, education and<br>engineering and most of these are done using statistical approaches. The work of<br>Adewale et al (2007) and Luna (2004) show a great insight that the field of computer<br>science has a lot to offer in contributing to the knowledge evaluation and the<br>effectiveness of JAMB-UME Scores, post-UME scores and SSCE Scores.<br>The aim of this thesis is to determine how aggregation of UME, post-UME and SSCE<br>scores bring a pattern that is commonly attributed to the good performance of first year<br>students’ academic achievement at the university in the department of Mathematics,<br>Ahmadu Bello University, using the concept of Genetic Algorithm. The identification of<br>6<br>these patterns can help in the selection process for admitting students into the various<br>departments.<br>1.4. Objective of the Study<br>The main objective of this thesis is to design a model using genetic algorithm that can<br>be employed in searching trends or pattern in student’s previous admission records. This<br>is achieved by using the aggregation of UME, Post UME, O’level scores against their<br>corresponding CGPA at the end of their first academic year in the University. Realizing<br>this objective can help in candidates’ selection criteria for admission process into the<br>university. This main goal can be achieved by means of the following objectives which<br>are:<br>1. To determine the means by which data collected can be translated to meaningful<br>ones.<br>2. To develop a model for searching hidden pattern among the available data set<br>using genetic algorithm.<br>3. To implement model of genetic algorithm<br>4. To test and validate the model using real data of students’ records.<br>1.5 Research Methodology<br>In designing the system, the objectives stated in section 1.4 can be achieved by<br>considering the following steps:<br>1. Data collected are subjected to the process of feature extraction and<br>normalization. The data gathering process involves the collection of raw data<br>about students, which include the UTME score, PUTME score and O’level<br>results (which are the entry requirements into the University). Feature extraction<br>is carried out since the data collected can be inconsistence, incomplete or noisy.<br>7<br>This may be as a result of a number of factors ranging from data entry or<br>transmission problem, discrepancy in the naming convention, duplicated records<br>or incomplete data or removal of unwanted entries that are not required. All<br>these affect the analysis. The data used for the analysis was entered into an Excel<br>spreadsheet file. Each student was being identified using his/her JAMB number.<br>Also, normalization of data is carried out on each subject’s grade by using a<br>uniform data representation since each examination is being graded differently.<br>These datasets are stored and accessed using Mysql relational database.<br>2. The model of genetic algorithm of principle of survivor of the fittest is used in<br>searching through the formatted student academic performance. The different<br>operators of GA perform their own work by following the instruction for the<br>GA, till the best patterns are found.<br>3. The model is implemented using java with Mysql relational database which<br>provide the required functionalities in holding students’ academic data.<br>4. The performance of the model is then compared with the statistical approach<br>using SPSS software.<br>1.6 Contribution to Knowledge<br>Using decision support system for admission selection process by genetic algorithm, the<br>University admission requirement is validated against the performance at the end of<br>their first academic year, to detect hidden trends among the students’ performance. The<br>contributions of the study to knowledge are outlined below:<br>1. Government’s policy to promote higher education, learning and research will be<br>realized since the right candidates are selected and trained in the universities this<br>8<br>will bring about the production of the right human resources who are the major<br>factors of production.<br>2. An efficient, detailed and unbiased procedure of using average performance for<br>admission into universities is put in place as against using single subject<br>performance for selection processes.<br>3. Selection of best students for university education will also make teaching and<br>learning easier as the best student is usually an individual who is focused and<br>disciplined. This will go a long way in making the goal of education achieved<br>effectively for economic growth and development in to the various sectors of the<br>nation.<br>4. Since it provides better admission opportunity for qualified candidates, better<br>qualified graduates will now be turned out into the job market as opposed to the<br>output that comes from persons who struggle through the universities because<br>they were never qualified to be there in the first place.<br>1.7 Scope of the Study<br>This research work is a case study of Computer Science, Mathematics Department of<br>Ahmadu Bello University, Zaria, Kaduna State. The research aim to cover records of<br>students admitted in three years academic session into 100 level through O’level, JAMB<br>and Post-JAMB scores respectively. This study therefore grew out of curiosity to find<br>out how prediction helps to identify and to improve students’ performance.<br>To the best of my knowledge, no study in the literature at my disposal has been carried<br>out to compare the academic achievement between undergraduate students admitted<br>through their O’level, Post-JAMB and JAMB scores in Ahmadu Bello University,<br>Zaria. The statement of the problem therefore seeks to identify best patterns at which the<br>9<br>aggregation of the three examinations brings in the first year performance of the student.<br>This early prediction allows the instructor to provide appropriate advising or select<br>those with less risk for admission.<br>1.8 Significant of the Study<br>Precisely, the significance of this study is based on<br>1. Determining the extent to which scores in examinations conducted by the West<br>African Examination Council (WASSCE), National Examinations Council<br>(SSCE) and in conjunction with the Joint Admissions and Matriculation Board<br>(UME) and post-UTME to predict future academic achievement of students in<br>university degree examinations.<br>2. Develop structural models for predicting the academic achievement in<br>university degree examinations based on performance in public examinations.<br>1.9 Organization of the Thesis<br>The thesis is organized as follow: in the second chapter, review was made on the<br>predictive technique using Genetic Algorithm and literatures that were accomplished in<br>the area of University admission variables were reviewed. In the third chapter,<br>description was made on how to model finding patterns in admission combinations, by<br>first normalizing and later applying Genetic Algorithm. In the fourth chapter, a<br>proposed implementation of the decision support system is designed as followed from<br>chapter three, using java programming language and Msql relational database. The<br>thesis concludes in chapter five, with summary, conclusion and recommendation.<br>10 <br></p>