A real-time application for e-learning system using similarity measurement and visiting frequency

In the most educational environment, there are a large number of students with varying disabilities and the usage of technology within this environment is more dynamic. One of the most common techniques used for the particular category of people (is e-learning, which is the best option for those people. They have some difficulties such as, learning, communication, understanding, etc. for providing a better learning environment; many existing e-learning mechanisms provide the recommendation of subjects based on their personalization. However, it makes the whole learning process as complex, and there is a need to collect the request from them, which are the major drawbacks of the existing scheme. To overcome the issues, a new type of web-based e-learning system, namely, Most Similar Most Frequent Recommendation (MSMFR) is proposed in this paper with query analyzing option for people, who using e-learning. The proposed system is entirely based on the data structures such as stack, queue, linked list, etc in the distributed environment. Here, the physically challenged people can able to share their recommended content to others, who search the same one. Moreover, we provide a secure access and provisioning for them. The primary intention of this paper is to improve the learning capability of physically challenged people. Initially, the required information is collected from the data owner and, the meta-data is created from that data. Then, the query is obtained from the user, which is parsed into attributes. Hence, the semantic relationship between the attributes and meta-data and the visiting frequency are found out. Here, the rating ratio is calculated for the requested query by using a web history. Finally, the required information such as web or video is retrieved. This application is implemented in real-time and the results obtained are illustrated in the experimental section.