No abstract

Background: Cancer treatment is expensive and results in a lot of side effects, and thus survival prediction is necessary for the patients as well as the clinician. Data mining technology has been used in the medical domain to extract interesting information. Cancer prognosis is such an application in medicine. Objective: This study focuses on identifying the technologies used in the recent past for predicting the survival of cancer patients. Supervised, semi-supervised and unsupervised techniques have been used over the years successfully for the survival prediction of different types of cancer. Methods: A systematic literature review process has been followed in this study to discover the future directions of the research. This study focuses on uncovering the gaps in recent studies. Results and Conclusion: It has been found that the present system lacks structured information of the patients. Also, there are a lot of different cancer types that are still unexplored in terms of survival prediction, mainly due to the unavailability of sufficient data. Hence a lot can be improved if researchers may get their hands on required data for the research.

: Although there are many reciprocal recommenders based on different strategies which have found applications in different domains but in this paper we aim to design a common framework for both symmetric as well as asymmetric reciprocal recommendation systems (in Indian context), namely Job recommendation (asymmetric) and Online Indian matrimonial system (symmetric).The contributions of this paper is multifold: i) Iterative framework for Reciprocal Recommendation for symmetric as well as asymmetric systems. ii) Useful information extracted from explicit as well as implicit sources which were not explored in the existing system (Free-text mining in Indian Matchmaking System). iii) Considered job-seekers’ personal information like his marital status, kids, current location for suggesting recommendation. These parameters are very important from practical viewpoint of a user, how he perceives a job opening. iv) Proposed Privacy preservation in the proposed framework for Reciprocal Recommendation system. We have achieved improved efficiency through our framework as compared to the existing system.

: The immense growth of information has led to the wide usage of recommender systems for retrieving relevant information. One of the widely used methods for recommendation is collaborative filtering. However, such methods suffer from two problems, scalability and sparsity. In the proposed research, the two issues of collaborative filtering are addressed and a cluster-based recommender system is proposed. For the identification of potential clusters from the underlying network, Shapley value concept is used, which divides users into different clusters. After that, the recommendation algorithm is performed in every respective cluster. The proposed system recommends an item to a specific user based on the ratings of the item’s different attributes. Thus, it reduces the running time of the overall algorithm, since it avoids the overhead of computation involved when the algorithm is executed over the entire dataset. Besides, the security of the recommender system is one of the major concerns nowadays. Attackers can come in the form of ordinary users and introduce bias in the system to force the system function that is advantageous for them. In this paper, we identify different attack models that could hamper the security of the proposed cluster-based recommender system. The efficiency of the proposed research is validated by conducting experiments on student dataset.

No abstract