Survey
* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
Online Education Guidelines System for Students Hrishik Bhusari Mayuri More Neelam Bhatia Trushant Lohakare Prof. P. S. Hanvate Student, NBN Sinhgad School Of Engineering, Pune Student, NBN Sinhgad School Of Engineering, Pune Student, NBN Sinhgad School Of Engineering, Pune Student, NBN Sinhgad School Of Engineering, Pune Assistant Professor, NBN Sinhgad School Of Engineering, Pune hrishikbhusari@g mail.com mayurimore08@g mail.com neelam.bhatia101 @gmail.com lohakare.tushar@g mail.com poonamkumar.han [email protected] ABSTRACT E-learning is becoming a popular alternative to textbook learning. With a rapid development of Internet Technologies, the number of online book selling and educational guideline websites has increased, which enhanced the competition among them. It is not feasible for a user to go through each and every website and search most suitable data according to his requirement. This system proposes one platform for student’s education which will facilitate various reference books (arranged according to year, branch), question papers, exams, etc. It also helps user to have their useful information using recommendation system via ratings, which recommends the information/data that can be beneficial to the user. KEYWORDS recommendation, online education, data mining INTRODUCTION In 21st century, the information technology changes the whole world and thinking of human society. It provide powerful technological basis for the revolution and development conventional education system. Combination of internet and education would create the education system in the future which connects the teachers and students between thousand mails and realize the face-to-face communication. This changes education a lot so, the online education system becomes a popular theme which has been taken attention by varies of countries. Unfortunately data of existing online education system is very tangled up by education material without considering student’s demand and area of interest. Therefore major problem is inefficiency of systems [1]. The main objective of the system is providing educational information to students. This is a totally web-based search engine, its main aim is to provide education services in one place, user does not need to search different sites to get information about any subject or any educational material. RELATED WORK Significant amount of work has been dedicated to developing projects similar to the one being discussed in this paper. The existing system may not have the information which the user wants. For his information, the user needs to search for other systems also. Qingsong Tu presents a framework in [1] for the education system which helps students to find their educational material. DATA ANALYSIS The online education system can be divided into various stages such as intelligent studying, analysis and recommendation. First the system records all information of studying phase and test the result and so on to get the interest, ability technique of user. Then the system turns on analysis of this knowledge and makes the suitable study technique, respectively. Finally the online education system recommends the study content and resources according to intellective ability and intelligence level of the user. This process forms a circulation to renovate the system. When the user enters the system for the first time, a registration is required. This phase requires user’s username, password, mail id, name, branch, year, etc. In the next phase, the system will present the study related content dynamically, according to user’s information and related search history. During the studying process, user can choose various study techniques/facility which he likes. For example, if the user can’t get/like the content in reading, then see videos by video links. This is one of the most useful benefits of online educational system over traditional studying mode. The dynamic technique of the system helps the user to surf the newly related knowledge or further information of the subject. LOGICAL FRAMEWORK DESIGN OF ONLINE EDUCATIONAL SYSTEM (OES) The OES consists of resource database layer, extract module, data analysis layer i.e. mining/association rules and application layer. A student carries an activity in application layer. The data of browsing and downloading are collected to extract module. The user requirements are extracted in the extract module and proceeds with data mining of information and store in the user database layer. Meanwhile the data from the user database is analyzed in data analysis layer & data process layer takes part in scheduling and matching the study resource in database. Then the analysis center recommends the study material according to the user’s information and analyzed data. Confidence indicates the number of times the if/then statements have been found to be true. Result Generation This is where students can see the result which is nothing but the predicted and recommended books or any other study material like video links, question papers and so on. The student can also rate via up-like or down-like according to his interest. This likes will be saved in the database for further recommendations. Application Layer Fig 1. Logical Framework of the proposed model Application layer is the user friendly layer. It provides many system functions such as log-in, registration, studying, navigation, etc. Besides data analysis layer, it represents the list of recommendations for the user. Database Layer KEY TECHNOLOGIES The database Layer is an application programming interface which allows the communication between a computer and application. The database consists of study database and study material database. The user stores the user information like username, password, mail id, name, branch, year, etc. The study material database includes various kinds of informative books, video links, university question papers, Association rule learning is a popular and well researched method for discovering interesting relations between variables in large databases. It is intended to identify strong rules discovered in databases using different measures of interestingnes. The user characteristic modeling is the way of summing up the user model that can be read and calculated from the user information which can be collected from many aspects. For instance, the keywords input by the user for inquiring the information, the browsing history, system log and automatic records of the system server and so on. The data mining techniques like k-means is based on searching action of user always shows extract characteristic from the document content which the user has browsed according to the frequency characteristic of the entry. K-means clustering is a data mining/machine learning algorithm used to cluster observations into groups of related observations without any prior knowledge of those relationships. K-means clustering aims to partition n observations into k clusters in which each observation belongs to the cluster with the nearest mean, serving as a prototype of the cluster. K-means is one of the simple unsupervised learning algorithms that solve the wellknown clustering problem. The procedure follows a simple and easy way to classify a given data set through a certain number of clusters fixed a priori. Extract Module Extract module layer includes user information extraction and organization. The user information extraction extracts information from the study history records, visiting and downloading records, keyword inquiring records, etc. Function of organization center is to pre-process this information before retrieval and store the results into the database of metadata. Steps for K-means clustering:- Mining (Association Rules) This is where association rules are applied. By taking recommended values from database we are going to apply association rules. Association rules are if/then statements that help uncover relationships between seemingly unrelated data in a relational database or other information repository. An example of an association rule would be "If a customer buys a dozen eggs, he is 80% likely to also purchase milk." Association rules are created by analyzing data for frequent if/then patterns and using the criteria support and confidence to identify the most important relationships. Support is an indication of how frequently the items appear in the database. Assume X={x1,x2,x3,……..,xn}set of data points and V={v1,v2,…….,vc} be the set of centers. 1) Randomly select ‘c’ cluster centers. 2) Calculate the distance between each data point and cluster centers. 3) Assign the data points to the cluster center whose distance from the cluster center is minimum of all the cluster centers. 4) Again calculate the new cluster center using: REFERENCES [1] Quingsong Tu & Jian Liu. Research on Autonomous Online Education System based on Intelligent Recommendation [2] B. Lee (Volume 1) Introducing System Analysis and Design. Where ‘ci’ represents the number of data points in ith cluster. [3] James. A. Senn (Second Edition) Analysis and Design of Information Systems. 5) Again the distance between each data point and new obtained cluster centers are calculated. [4] Roger. S. Pressman Software Engineering 6) If no data point was reassigned then stop, else repeat from step 3. [5] http://www.hindustantimes.com/comment/india-seducation-system-needs-to-get-online-with-access-forall/article1-1385860.aspx The Advantage of k-means is, it is easy to understand, fast and robust. It also gives better result when data set are well separated from each other. Fig 1.Showing the result of k-means for ‘N’ = 60 and ‘c’=3 By analysis to many mark or position information existing in the information resource document, such as hypertext mark in HTML, subjects, keywords, abstracts of the scientific and technological literature resource, the weight and importance of the entry can be confirmed. CONCLUSION The OES provides a new relevant way to improve the current education system. It uses the recommendation technique which helps user to learn the thing better. By recording and analyzing various kinds of information during the study of the user, the OES provides interesting value. Then according to this value it recommends the study techniques, suggestions and resources intelligently. The application of the OES faces many technological difficulties. We proposed a logical framework of the system, and introduced the key technologies, and we should carry on further discussion on its application in our real education situation in our country.