2016/05/06(五) 14:20 - 張大中 教授(中央大學 通訊系) - Nonlinear Least Squares Methods for Target Localization in Wireless Sensor Networks
Topic：Nonlinear Least Squares Methods for Target Localization in Wireless Sensor Networks
Date&Time：2016/05/06 (五) 14:20
Speaker：張大中 教授(中央大學 通訊系)
Location：清華大學台達館 R216
Abstract：
Wireless sensor networks (WSNs) conventionally consist of a large number of low-cost, low-power, densely distributed, and mostly heterogeneous sensors. For the localization application, the target signal strength in a WSN is usually reported by sensors with quantized levels and all quantized data are collected in a fusion center to estimate the target location based on a nonlinear relationship between distance and signal strength. Instead of using the computation-intensive maximum likelihood (ML) method, we study the least squares method by which the least squares cost function is significantly deteriorated due to nonlinear parameter estimation. To solve this problem, the μ-law compression technique is considered for robust position estimation. Two nonlinear least squares estimation methods, Gauss-Newton and Nelder-Mead, are explored in our work. Numerical results show that the new robust localization method can achieve a good mean square error performance close to the ML method with lower computational loading.
Date&Time：2016/05/06 (五) 14:20
Speaker：張大中 教授(中央大學 通訊系)
Location：清華大學台達館 R216
Abstract：
Wireless sensor networks (WSNs) conventionally consist of a large number of low-cost, low-power, densely distributed, and mostly heterogeneous sensors. For the localization application, the target signal strength in a WSN is usually reported by sensors with quantized levels and all quantized data are collected in a fusion center to estimate the target location based on a nonlinear relationship between distance and signal strength. Instead of using the computation-intensive maximum likelihood (ML) method, we study the least squares method by which the least squares cost function is significantly deteriorated due to nonlinear parameter estimation. To solve this problem, the μ-law compression technique is considered for robust position estimation. Two nonlinear least squares estimation methods, Gauss-Newton and Nelder-Mead, are explored in our work. Numerical results show that the new robust localization method can achieve a good mean square error performance close to the ML method with lower computational loading.