Bandwidth-A ware Medical Image Retrieval in Mobile Cloud Computing Network

摘要

This paper proposes a bandwidth-aware content-based Medical Image retrieval method in Mobile Cloud computing environment, called the MiMiC. The whole query process of the MiMiC is composed of three steps. First when a doctor submits a query image I_q, a parallel image set reduction process is first conducted at a master node level. Then the candidate images are transferred to the slave nodes for a refinement process to obtain the answer set. Finally, the answer set is transferred to the query node. The proposed method including the adaptive load balancing scheme is specifically designed for solving the heterogeneity of the mobile cloud and an index-support image set reduction algorithm for reducing the data transfer cost in cloud environment. Additionally, we propose a bandwidth-conscious multi-resolution-based data transfer technique to further improve the query performance. The experimental results show that the performance of the algorithm is efficient and effective in minimizing the response time by decreasing the network transfer cost while increasing the parallelism of I/O and CPU.