Deep Correlation Mining Based on Hierarchical Hybrid Networks for Heterogeneous BigData Recommendations

ABSTARCT :

The advancement of several significant technologies, such as artificial intelligence, cyber intelligence, and machine learning, has made big data penetrate not only into the industry and academic field but also our daily life along with a variety of cyber-enabled applications. In this article, we focus on a deep correlation mining method in heterogeneous big data environments. Experiments based on DBLP and Research Gate data show the practicability and usefulness of our model and method. A hierarchical hybrid network (HHN) model is constructed to describe multi type relationships among different entities, and a series of measures are defined to quantify the internal correlations within one specific layer or external correlations between different layers. An intelligent router based on deep reinforcement learning framework is designed to generate optimal actions to route across the HHN. An improved random walk with the restart-based algorithm is then developed with the intelligent router, based on the hierarchical influence across network associated with multiple correlations. An intelligent recommendation mechanism is finally designed and applied to support users’ collaboration works in scholarly big data environments.

EXISTING SYSTEM :

? Data integration tools are evolving towards the unification of structured and unstructured data and will begin to include semantic capabilities. ? Knowledge acquisition from autonomous, semantically heterogeneous and distributed data sources, query-centric, and federated approaches to data integration are of special interest ? Data confidentiality means certain data or the associations among data points are sensitive and cannot be released to others. ? Heterogeneity of big data also means that it is an obligation to acquire and deal with structured, semi-structured, and even entirely unstructured data.

DISADVANTAGE :

? The lack of data integrity usually relates to data tampering and incomplete data. ? Studies on social network and correlation analysis, issues of cyber intelligence mining with the RWR method, and researches on the intelligent recommendation in the cyber-social system are addressed, respectively, in this section. ? To cope with the cold start problem in event-based social networks, they built a primary graph according to entities and their relations from an event-based social network, and a feedback graph according to user feedback from event reservations.

PROPOSED SYSTEM :

? This paper introduces data processing methods for heterogeneous data and Big Data analytics, Big Data tools, some traditional data mining (DM) and machine learning (ML) methods. ? Deep learning and its potential in Big Data analytics are analysed. ? In this article, we designed and built a hierarchical hybrid network (HHN) model to describe multiple associations among different entities, in order to provide the intelligent recommendation in the context of heterogeneous big data integration from multiple data sources.

ADVANTAGE :

? To evaluate the efficiency of IR, we performed a test on how fast the proposed method can achieve the highest reward. ? Demonstrate the general performance of the four methods. It shows that the performances of all the methods decrease with the increasing length of recommendation list. ? The undirected links among different users within each layer can be used to describe the similarity-based correlations among them.