kindly Read through abstracts,copy edith and give to your surpervisor....
PROJECT TOPIC: APPLICATION OF DATA MINING TECHNIQUES IN STUDENTS COURSE OF STUDY USING ARTIFICIAL NEURAL NETWORK TECHNIQUES
Department: Computer Science
FORMART: MS WORD
PAGES: 90 pages, abstract, chapter 1-5 , APENDIX A source code and APENDIX B output, well reserached and supervised
One of the major challenges encountered by schools in several countries, mainly
Within the academic sphere, is to handle the difficulties of students during the learning process, which in many cases might result in the lack of motivation and even university drop-out. Although there are other manual extraction of patterns from data such as Bayes’ theorem (1700s) and regression analysis (1800s), research conducted reveals that this manual extraction patterns can no more handle data extraction and retrieval without some limitations due to the fact that data sets have grown in size and complexity. In this project, we designed and implemented a system that uses the concept of neural network in the analysis of student course of study taking a case study of university of port harcourt polytechnique. The proposed system was designed using Adobe dream weaver cs4 and was implemented using Programming language. The methodology adopted in this research is Rapid Application Development Methodology (RAD), while carrying analysis for the design and implementation of the proposed system, the proposed system was implemented using java and mysql database. both primary and secondary method of data collection was used. This system so developed is able to predict student academic success by producing the student Grade Point Average (GPA) and Cumulative Grade Point Average (CGPA) based on his/her performance in both Class Assessment (CA) and Examination.
One of the major challenges encountered by schools in several countries, mainly within the academic sphere, is to handle the difficulties of students during the learning process, which in many cases might result in the lack of motivation and even university drop-out. In this sense, better understanding the students and their characteristics is crucial for the application of pedagogical techniques with a specific focus, aiming at reaching optimum productivity during the learning process. The manual extraction of patterns from data has occurred for centuries. Early methods of identifying patterns in data include Bayes’ theorem (1700s) and regression analysis (l800s). The proliferation, ubiquity and increasing power of Computer technology has dramatically increased data collection, storage, and manipulation ability. As data sets have grown in size and complexity, direct ‘’hands-on’’ data analysis has increasingly been augmented with indirect, automated data processing, aided by other discoveries in computer science, such as neural networking, cluster analysis, genetic algorithms (1950s), decision trees (1960s), and support vector machines (1990s). In this research work, we will introduce the concept of neural network to analyze student course of study, after the analysis stage, the system should be able to predict student academic success by producing the student the Grade Point Average (GPA) and Cumulative Grade Point Average (CGPA based on his/her performance in both Class Assessment (CA) and Examination taking a case study of Rivers State Polytechnic Bori.
In chapter two of this research work, we will look at what others have done in relation to this research work, in chapter three we are going to carry out proper analysis and design of both the existing and the proposed system and in chapter four we implement the proposed system based on the analysis and design done in chapter three. Then finally chapter five will contain the summary, conclusion and recommendation.
1.1 Background of the Study
Inspired by the structure of the brain, a neural network consists of a set of highly interconnected entities, called Processing Elements (PE) or units.
Each unit is designed to mimic its biological counterpart, the neuron. Each accepts weighted set of inputs and responds with an output. Neural networks address problems that are often difficult for traditional computers to solve, such as speech and pattern recognition, weather forecasts, sales forecasts, scheduling of buses, power loading forecasts, early cancer detection, etc. (Adefowoju and Osofisan, 2004; Emuoyibofarhe, 2003; Principe. 1999 Principe et al., 2000, Oladokun et al., 2006; and Adepoju, Ogunjuyigbe, and Alawode 2007).
The complexity and flexibility of the relationship that can be created is thus tremendous. Another desirable feature of network models is that they are readily updated as more historical data becomes available; that is, the models continue to learn and extend their knowledge base. Thus artificial neural network model are referred to as adaptive systems. This similarity to the human brain enables the neural network to simulate a wide range of functional forms which are either linear or non-linear. They also provide some insight into the way the human brain works. One of the most significant strengths of neural networks is their ability to learn from a limited set of examples (Principe et al., 2000; Anderson et al., 1994).
1.2 Statement of the Problem
The manual extraction of patterns from data such as Bayes’ theorem (1700s) and regression, analysis (1800s) has occurred for centuries. As data sets have grown in size and complexity, this manual extraction patterns can no more handle data extraction and retrieval without some limitations. This is because most of the databases are complex, large, and contain heterogeneous, imprecise, vague, uncertain and incomplete data.
Individual differences in academic performance have been linked to differences in intelligence and personality (Sophie. 201 1). Students with higher mental ability as demonstrated by IQ tests (quick learners) and those who are higher in conscientiousness (linked to effort and achievement motivation) tend to achieve highly in academic settings. But unfortunately in the educational system today student with low mental ability may lobby their way and find themselves performing higher than student with high mental ability. Therefore this research tends to tackle these problems by applying data mining techniques in the determination of student academic success.