Abstract
This paper presents the design of an efficient soft computing technique for increasing the accuracy of the Infrared Sensor, by using the Support Vector Machines (SVM) and Neural Networks (NN). The analysis for SVM was done with different functions available and the results are presented. For Neural Networks, the analysis was done with different member functions and different number of. To determine the appropriate model, the model with minimum Root Mean square Error (RMSE) and Mean Absolute Percentage Error (MAPE) when compared with the sensor's measurements were selected. The results indicate that the Neural Network model could reduce the relative RMSE by a factor of 0.58 and MAPE by a factor of 0.76 which is much greater than the results obtained from Support Vector Machine.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have