An Electronic Registration for Undergraduate Students with Department Selection Based on Artificial Neural Network

The objective of the present research is to facilitate the administrative procedures associated with student registration process, and to ensure equal opportunities for all applicants in college. It aims to assist students in identifying appropriate alternatives available to the departments electronically anytime and anywhere saving time and effort for the student. For this purpose, an intelligent e-government system named "An Electronic Intelligent Registration with Department Selection" (E-IRDS) is designed as one of the intelligent eservices in Iraqi e-governance by using many tools and programming languages which are (PHP, MYSQL, HTML, CSS, XML, NOTPAD++, C#). Artificial neural networks (ANNs) technology is applied, notably Kohonen's self-organizing map (SOM) as one of the important unsupervised classification algorithms of machine learning for classifying and distributing the students automatically into the college academic departments based on their desires, their total degrees, and according to scientific plan for each department, in addition to the specific and personal student information. The applied results based on international standards demonstrated the accuracy of Kohonen's SOM algorithm in classification and distribution methods at least time and possible learning ratio. The system test and assessment results confirmed that it is characterized with a very high security and reliability and accuracy. It is also distinguished with very high efficiency and transparency as well as flexibility and high performance speed. The results also emphasized the ease and availability of the system to all students, besides the possibility of troubleshot and correct errors easily .


Introduction
In the latest decades, the use of Information and Communication Technologies (ICT) has actually obtained the increasing attentiveness in the public sector represented by e-governance services, especially within latest years when the developing countries have improved access to the provided services by the government for the purpose of reducing the costs as well as increasing the effectiveness of an organization [1].
Currently, the higher education sector in Iraq is playing an important role in the society improvement and development. The e-services implementation had really become the critical goal in universities context in worldwide [1]. E-Governance indicates to the public sector's use of ICT by government agencies to transmit information and deliver services to the citizens anytime and anywhere [2, 3]. E-government provides opportunities for citizens to participate in the decision-making process in democratic life that lead to increase transparency and efficiency making government more accountability [2,4]. For more than 15 years, the European Union built infrastructure of e-government, and supported research to how delivering e-government's services efficiently and effectively [4].
The Iraqi government began to use e-government technology in 2004 when the Iraqi Ministry of Science and Technology afforded the contract for the building up of an Iraqi egovernment project to an Italian company [5]. Iraqi e-government systems have been defined as the use of websites, e-mail, or any interaction method via the internet for the delivery of government services to citizens, the business sector, and civil society organizations [5]. Thus, most Iraqi universities (public or private) actually strived to exploit the modernistic technologies like (web 2.0, mobile applications) in improving the students-universities interaction [1]. It can be also benefit from modern machine learning technologies in egovernment systems for predict new knowledge from huge amounts of distributed data depending on the hidden relationships and patterns of events that cannot be directly Learning methods are classified into supervised, unsupervised, reinforcement learning.
Unsupervised learning method finds the correlations and relations among the input features to discover the subtle structure of unlabeled data such as the SOM model that utilizes unsupervised learning algorithms [7]. Among different present neural network architectures and learning algorithms, Kohonen's SOM is one of the most common neural network models It is a spontaneous classification method which is the origin of SOM. Actually, SOM is an unsupervised learning algorithm with a simple structure and computational form which projects high-dimensional data onto a low-dimensional grid which called a topological map [8,9].
In this paper, due to the difficulty of administrative procedures associated with Undergraduate students' registration process that requires manual recording and which often lead to loss of time and effort in Kirkuk University's colleges, Kohonen's SOM is applied as one of the important ANN algorithms in supplying e-government service.
The purpose of this study is to assist students to identify appropriate alternatives available for academic departments electronically anytime and anywhere saving student time and effort. It aims to supply automatic classification by applying Kohonen's algorithm for distributing students to desired departments relying on scientific plan of each department and students' total degrees as well as recording choices of students.

System Analysis
The analytical study about registry mechanism in Kirkuk University's colleges has proved the existence of several disadvantages and obstacles that restrict the registry process which are including : 1-Busyness of large number of staffs for a long time by routine students' registration and distribution them to college's academic departments 2-Students waiting and their families in long queues for the registration process completion.

3-Unreliable Registration and distribution processes.
4-Frequent questions of students as well as the overwork of registration staff . service (face-to-face) to e-service, as everybody may not prefer to utilize e-service and most of them are already familiar with the traditional service that is by dealing with people and not ICT. It has been also emphasized that the system is very high efficient (92.4%) by decreasing the time and effort. It is also enough flexible (91.1%) to control the DB design and modify its fields, in addition to the ability of update system structure with its interfaces and webpages such as adding or deleting further options of academic departments according to the college.
It has been proved the availability (87.6%) of the system by activating its website during registry period and possibility of using its pages anytime and anywhere. Eventually, the results have proved that the system is moderate maintainability (76.7%) for the capability of troubleshot by professionals. It also improves data access across system website and encourages students to participate in decision making process in e-registration that lead to increase transparency (80.1%).

Conclusions
In this paper, it is concluded that the E-IRDS is an integrated electronic system. It can be connected and merged with other electronic systems in Iraqi e-governance to reduce the boring routine of a series of reviews in scientific and civilian institutions. This system is enough flexible to be used in other universities and institutes. The registration process by using the designed system as an e-government application is done smoothly and lightness making it easier for the competent committees to register students with sorting and distributing them to the college departments. The system includes a good mechanism for users' accounts to control the adding and deleting of users, which increases the system control capability and efficiency. It is inferred the accuracy of Kohonen's SOM algorithm in classification and distribution to clusters with minimum learning rate and without error rate. It was found that the system is very high security and reliability. It is distinct with high transparency and high performance speed, in addition to students and employees well satisfaction to the system.