As we knew that every individual is different than each other and their brain levels are also different, some students are very bright and some are not, so there is a need to develop such system which will teach them as per their thought process and learning habits. This research aims to develop a personalized virtual school environment for students which help them to learn the things same as they learn in school physically, but the thing here is each student will be treated differently as per his/her ability. Hence, this system would be a virtual school for any student, which resembles the CBSE school system in India. In this virtual school, all things are present such as teachers, homework, games, and exams which present in actual school except one which is the physical classroom because in virtual environment the course and things are personalized for each student as per his/her thoughts and brain level, so here the student can seat in his/her home and can learn at any time with help of computer. The system is a webbased environment and machine learning would be used for doing personalization on family and knowledge context of student. This web system contains four components: (1) Classification based on family context, (2) classification based on knowledge context, (3) learning material selection algorithm, (4) web-based learning system on top of above three, are discussed in this paper.

Dealing with the growing amount of user posted content like preferences, responses, comments, past experiences and beliefs spread through social media is a vital but challenging task. Being applied in several domains, recommender systems are used to find solutions and suggestions based on users interests including tourism-related opinion detection and tourist-attraction spot identification. Tourists can access and analyze this information for making decisions and predicting best tourist places. This study aims to predict tourist attraction spots and their related information by analyzing the data from social media (Facebook, Twitter etc.) which in turns help the tourist industry by deliberating what kind of attractions tourists can have and how to obtain their preferences. For this purpose four algorithms such as Kernel Density Estimation, K- Nearest Neighbor, Random forest and XG Boost have been used. The findings revealed that XG Boost yields better results in terms of accuracy than other three algorithms.

No abstract

A proper management of resources is very important when they are on public cloud to ensure security, cost optimization etc. Monitoring resources and sending notification to admin or authorized person for all monitored activities helps the corporate institute/organization who is using public cloud like AWS to manage the resources properly, as AWS in an organization is used by different users though they have roles associated with them but they can do any mistake which costs for an organization. Automated notifications can help on this issue when resources are monitored and notified to admin/authenticated person and they can take appropriate actions. This paper focuses on how to make an environment and hardware setup of instance in AWS using AMIs, user data and Terraform, securing and managing S3 from unwanted objects and automated deletion of unwanted resources. It is also important for an organization to verify that developers, tester etc. are working according to their provided environment standard so that they can guarantee that there is not be any problem after or during project development or delivery so, in context of that AMIs can be created and EC2 monitored for AMI.