A hybrid robot selection model for efficient decisive support system using fuzzy logic and genetic algorithm

The growth of robotics solutions on cloud systems has encouraged researchers in finding solutions for efficient decisive support. In this way, several approaches are available in literature like TOPSIS which uses fuzzy logic and distance metrics in the selection of robots. Similarly, several other approaches use various features like rapidness, cost, networking, and so on. However, the methods suffer to achieve a higher result on various factors like data support, decision accuracy, and so on. By considering all these, a hybrid robot selection model with fuzzy logic and genetic model (HRS-FLGA) is designed. The method applies fuzzy logic in the selection of robots at good communication quality where the GA has been used in finding solutions at bad communication quality. The proposed model combines both Fuzzy logic and genetic algorithm in finding an optimal solution. The method computes various support measures like Data Fetch Quality Support (DFQS), Decision Quality Support (DQS), and Rapidness Support (RS) on a decisive system and based on the fuzzy parameters to measure Robot Selection Weight (RSW). Similarly, the genetic algorithm has been used in measuring the Robot Fitness Measure (RFS) to measure the fitness of the robot to achieve the expected result and its quality. The proposed model computes multi-Feature selection weight (MFSW) for the system and based on that the method selects the cloud robot to support the service access. The proposed model improves the performance of cloud robot selection with less false ratio.