Академический Документы
Профессиональный Документы
Культура Документы
This section presents a discussion of the literature which further enriched the
conceptualization of the study and aided in describing the rational design that
guided the conduct of the researcher.
Related Studies
According to Wisconsin, (2011), “An Online Scholarship Application
System” for a foundation at University of Wisconsin-La Crosse. This deals with
a large number of scholarship applications as it uses paper-based processing.
This evolution focuses on replacement in which portions of the existing system
is substituted for re-engineered system portions. The system was developed
under java development platform using java in the business logic layer, JSP in
the presentation layer and Oracle 10g Express Edition in the database layer. It
was run under IIS application server.
In addition, Asia pacific issues. No. 48( 2001) sighted that some basic
applications areas like e-exams that are related to E -scholarship System were
also reviewed. In a paper titled "An Arabic Web- Based Exam Management
System" [M. Z. Rashad 2010) proposed a web based online examination.
Related Literatures
Research have focused on empathetic students retention, persistence
and degree attainment, national statistics remain objectively constant.
Modifications to Tinto’s Theory (1987, 1993) original theory of students’
departure have been proposed to take into account diverse populations
according to Hurtado & Carter, (1997)
College graduates are more likely satisfied with their jobs, and place a
better premium on the need to feel that their work is more important according
to Friedl, M. A (1997). They also make to engage civically, with higher rates
volunteering and voting as to Al-Radaideh (2006]. Better educational
accomplishment is connected with both advanced salaries and lower idleness
rates said Kuleswar (2010).
In the past few years, the use of decision trees (DTs) to classify remotely
sensed data has increased. Proponents of the method claim that it has some of
advantages over the ML and ANN algorithms. The DT is computationally fast,
make no statistical assumptions, and can handle data that is represented on
different measurement scales. Software to implement DTs is readily available
over the Internet. Pruning of DTs can make them smaller and more easily
interpretable, while the use of boosting techniques can improve performance
(Pal, M., & Mather, P. M. 2003).
Classification exactitudes produced by each of these decision tree
algorithms are associated with both maximum probability and linear
discriminant function classifiers. Outcomes from this study show that the
decision tree algorithms constantly outdo the maximum prospect and linear
discriminant function classifiers with respect to classification — cation
correctness Friedl, M. A., & Brodley, C. E. (1997)
The decision tree is a very good and practical method since it is relatively
fast, and can be easily converted to simple classification rules. The decision
tree method depends mainly on using the information gain metric which
determines the attribute that is most useful. Baradwaj,(2012)
Online application system has been spreading all throughout the globe; it
contracts with a large number of applications as the groundwork uses paper-
based processing. Through this, more transactions can take place at a time.
In the other hand, one of the mutual relations that have been computerized
online is the scholarship application. Research shows the numbers of
scholarship applications from students and to streamline the selection and
financial reconciliation processes at the research site. Moreover, to lessen the
work in online systems, a classification algorithm is used to assess different
kinds of entities. The most common classification algorithm is the Decision
Tree. A decision tree is a set of conditions organized in a hierarchical structure.