Recruitment is the process of hiring the right person for the right job. In the current competitive world, recruiting the right person from thousands of applicants is a tedious work. In addition, analyzing these huge numbers of applications manually might result into biased and erroneous output which may eventually cause problems for the companies. If these pools of resumes can be analyzed automatically and presented to the employers in a systematic way for choosing the appropriate person for their company, it may help the applicants and the employers as well. So in order to solve this need, we have developed a framework that takes the resume of the candidates, pull out information from them by recognizing the named entities using machine learning and score the applicants according to some predefined rules and employer requirements. Furthermore, employers can select the best suited candidates for their jobs from these scores by using skyline filtering.

A skyline query finds objects that are not dominated by another object from a given set of objects. Skyline queries help us to filter unnecessary information efficiently and provide us clues for various decision making tasks. In this paper, we consider skyline queries for location-based services and proposed a framework that can efficiently compute all nondominated paths in road networks. A path p is said to dominate another path q if p is not worse than q in any of the k dimensions and p is better than q in at least one of the k dimensions. Our proposed skyline framework considers several features related to road networks and return all non-dominated paths from the road networks. In our work, we compute skylines considering two different perspectives: business perspective and individual user's perspective. We have conducted several experiments to show the effectiveness of our method. From the experimental results, we can say that our system can perform efficient computation of skyline paths from road networks.

Due to the rapid growth of internet technologies, at present online social networks have become a part of people's everyday life. People shares their thoughts, feelings, likings, disliking and many other issues at social networks by posting messages, videos, images and commenting on these. It is a great source of heterogeneous data. Heterogeneous data is a kind of unstructured data which comes in a variety of forms with an uncertain speed. In this paper, we develop a framework to collect and analyze a significant amount of heterogeneous data obtained from the social network to understand the behavioural patterns of the people at the social networks. In our framework, at first we crawl data from a well-known social network through Graph API that contains post, comments, images and videos. We compute keywords from the users' comments and posts and separate keywords as noun, verb, and adjective with the help of an XML based parts of speech tagger. We analyze images related to each user to find out how a user like to move. For this purpose, we count the number of users in an image using frontal face detection classifier. We also analyze video files of the users to find the categories of videos. For this purpose, we divide each video into frames and measure the RGB properties, speed, duration, frame's height and width. Finally, for each user we combine information from text, images and videos and based on the combined information we develop the profile of the user. Then, we generate recommendations for each user based on activities of the user and cosine similarity between users. We perform several experiments to show the effectiveness of our developed system. From the experimental evaluation, we can say that our framework can generate results up to a satisfactory level.