Small and medium-scale WSN information transmission link quality performance evaluation and experimental research
Xi-Liang Zha, Jin Yun Yuan, Feng Zhang, Pei-Yong Song · 2010 Sixth International Conference on Natural Computation · 2010
Considering the characteristics of the small scale, low-density node distribution, stable network topology of small and medium-scale wireless sensor networks and the factors of network operations performance be vulnerable to the effects of energy depletion and node failures, a small and medium-scale wireless sensor network performance evaluation method based on least squares support vector regression is proposed in this paper. Performance evaluation model is established using the n independent indicators transformed from n related data as the input of the support vector machines .Theoretical analysis shows that this approach can overcome the problem of neural network converges to local minimum value and has better recognition rate and generalization ability. Experimental results show that, compared with radial basis function (RBF) neural network, the relative error of the network performance evaluation cut back 86.7%.