A novel WIFI indoor positioning method based on Genetic Algorithm and Twin Support Vector Regression

We propose a novel regression, which is called Twin Support Vector Regression (TSVR) to improve the precision of indoor positioning. Similar as Support Vector Regression (SVR), there are 6 parameters to be identified. However, compared with SVR, less computation time and approximate performance can be achieved with TSVR. Genetic Algorithm (GA) is used to avoid local optimum in indoor positioning to get proper parameters in TSVR. Experimental example is shown to illustrate the effectiveness of the proposed methods.