This is a Final year project. A Web based system will be developed based on this following requirement
[read more=”Click here to Read More” less=”Read Less”]
The aim of this project is to develop an online system and database for helping the State Vocational and Technical Education Board to effectively and efficiently monitor State’s colleges towards sustained education quality. As such, the system will be designed to help the State Education Board run a database of the following major State colleges’ elements:
• Facilities (like lecture halls, hostels, and laboratories), facility capacity, and current states; funds disbursement and management; staff requirements, training equipment; existing university affiliations; and courses offered.
• Students – names and personal IDs, gender, disciplines/subjects/courses registered for, exam bookings, discipline records, performance records, admission and completion dates (or dropout), and attendance records among others.
• Alumni records.
• Extra-curricular activities.
Analyse, develop and implement a system that will ease schools monitoring in the state Board and replace the existing manual system.
Design and implement a database for the college monitoring system that will keep the college records operate by the Board and help in decision making using the specified techniques.
To develop the system that will trace and monitor student’s productivity in the state Board schools.
Predictive data mining techniques will be implemented to facilitate extraction of valuable patterns/ insights from the massive datasets gathered by the education board. Link analysis, clustering, and classification are examples data mining techniques that will be used to find relationships between datasets for predictive college monitoring and control as well as making new discoveries in a timely manner. This way, the State Education Board will be able to achieve a number of benefits, including but not limited to:
• Adequate collection, management, collation, publication, and storage of state colleges’ data and knowledge – under strong central coordination.
• Maintain seamless communications and collaboration with other stakeholders, including the State government, National Board of Technical Education (NBTE), National Universities Commission (NUC), National Commission for Colleges of Education (NCCE), and the Federal Ministry of Education (FME) among others.
• Proactively understand facility/equipment and human resource demands for rapid action.
• Track fund allocation and management.
• Correlate admission enquiries and actual admissions to predict future enrolment rates and plan for resources.
• Forecast student dropout and course request transfer rates.
• Predict curriculum success rates.
• Track alumni for targeted mailing on-need basis.
• Predict student performance throughout the college life and identify reasons for weak grades to make effective decisions related to appropriateness of teaching methods, policies, and learning resources towards achieving improved education quality and academic performance.
The following are the main objectives that will be pursued:
1. To critically review relevant and recent literature regarding data mining techniques, application of these techniques in monitoring colleges, and case studies of college monitoring systems.
2. Conduct a comprehensive requirements elicitation and specifications by administering face-to-face unstructured interviews involving the following major stakeholders: Education Board officials, state college administrators, and educators.
3. Plan, design, and develop the online monitoring system, including aspects of functional and non-functional requirements.
4. Develop appropriate test cases and assess the system for utility or reliability, compatibility, usability, mobile readiness, and security.
5. Link the system with relevant online educational systems (such as portals) and social media sites to optimise data collection potential.
6. Compile the documentation, including aspects of key code snippets and user manual.
A literature review will help gather relevant information related to the research area and the system being developed. A review of recent and relevant literature will elaborate terminologies, definitions, and trends regarding data mining techniques and their application in monitoring state colleges. Unstructured interviews will help gather the online system’s functional and non-functional requirements. Then, the system will be designed, developed, and tested based on the requirements.
1.3 Research question
How can we plan, design, and develop an online monitoring system that incorporates aspects of data mining techniques to facilitate monitoring of state colleges in the context of State?
State governments and college administrators are working towards having an understanding of what is going on in state colleges. For example, past records and current events may help predict potential class and course enrolment sizes as demonstrated by the board degree monitoring system. Tutors would like to have an idea of students’ performance in addition to ways through which they can approach future lessons to drive greater understanding. Stakeholders are looking for ways to stay adequately alert and prevent unwanted consequences due to inaction and flawed assumptions. State colleges are accountable to politicians, parents, and local authorities among other stakeholders about statistics such as school dropout and university qualification rates (Parry 2012). It will achieve this by developing online system integrated with predictive monitoring capabilities driven data mining techniques to help the State Education Board deliver quality education.
3.0 Justified methodology
Stratified random sampling will be used in this study with the target population being key stakeholders of state colleges. Stratification basically entails dividing the members of a population into mutually exclusive, collectively exhaustive, or consistent subpopulations prior to sampling. Then, systematic or simple random sampling is performed to draw respondents from each subpopulation (Hesse-Biber 2010). In the context of this study, simple random sampling will be applied as opposed to systematic sampling. Simple random sampling chooses each person randomly, thus all persons within a stratum have an equal chance of being selected. Consequently, the sample assures an unbiased survey method (Hesse-Biber 2010). This will ensure that each stratum contributes to the study findings. It is expected that the strata differ in population, thus the target sample size of 20 survey respondents across the entire population will be well balanced to avoid selection bias and estimation error. Therefore, the sample sizes per strata will be State Vocational and Technical Education Board officials (4), state college administrators (6), and teachers (10). Face-to-face or video interviews will be administered to these respondents.
My Hidden Paragraph Here [/read]