Publication

Abstract : Due to rapidly increasing clinical data, clinics are increasingly outsourcing local data to to cloud servers online– this achieves convenience and also reduces data management expenditure. To ensure privacy, data of a sensitive nature needs encryption before outsourcing. This renders impossible usual data recovery methods such as keyword - based document recovery. We study Big Data Analytics in clinical data employing multi – keyword search, which also supports active update operations such as document removal and addition. To be more specific, we build an index tree that is founded on the sculpture of vector space to search multi - keywords; this supports flexible update operations. In addition, cosine similarity measures are used to support the precise ranking of results emerging from the search. We proceed to formulate a search algorithm – this relies on a Greedy Depth-first strategy -to improve search efficiency. Clinical data experiments demonstrate the efficacy of the proposed scheme