Multitask networks version of the conventional Incremental Least Mean Square (ILMS) is developed and implemented over Wireless Sensor Networks (WSN). The concept of Code Division Multiple Access (CDMA) is adopted to extract a particular task or estimate solution successfully among different clusters. In addition, diffusion-based approaches of ILMS CDMA algorithm called the Combine-Then-Adapt (CTA) and the Adapt-Then-Combine (ATC) are developed which allow data exchanging among the neighbouring nodes to enhance the performance. As expected, the simulation results of ILMS CDMA topology consisting of 7 nodes that grouped in 3 clusters converged to -35 dB of Mean Square Error (MSE) and -47.75 dB of Mean Square Deviation (MSD), while the MSD performance of CTA and ATC approaches settled down to -50.32 dB and -51.52 dB, respectively, indicating performance enhancement of -2.6 dB and -3.8 dB.
更多
查看译文
关键词
incremental least mean square (ilms),multitask networks,code division multiple access (cdma),channel estimation,mean square error (mse),mean square deviation (msd)