Protein-Protein Interaction Network Constructing Based on Text Mining and Reinforcement Learning with Application to Prostate Cancer

Fei Zhu, Quan Liu, Xiaofang Zhang, Bairong Shen

Abstract: In wireless sensor networks, since the energy and computing capacity of sensor nodes are limited, routing algorithm has become one of the most important area on which researchers focus. As most general routing algorithms cannot efficiently solve the minimal energy consumption and load-balancing problem, we propose a Dyna-Q based energy-efficient load-balancing multi-path routing algorithm, which fully considers the number of hops, the residual energy of sensor nodes and the energy consumption of nodes, reduces the network energy consumption and hence improves the network lifetime. The experiment showed that the survival number of nodes, the residual energy distribution of nodes and transmission success rate surpassed those of GT algorithm, indicating that the proposed algorithm could effectively reduce energy consumption and prolong the network lifetime.