• Acta Physica Sinica
  • Vol. 68, Issue 17, 170503-1 (2019)
Lin Yuan, Xue-Song Yang*, and Bing-Zhong Wang
DOI: 10.7498/aps.68.20190327 Cite this Article
Lin Yuan, Xue-Song Yang, Bing-Zhong Wang. Prediction of time reversal channel with neural network optimized by empirical knowledge based genetic algorithm[J]. Acta Physica Sinica, 2019, 68(17): 170503-1 Copy Citation Text show less
Structure of the neural network model combined with PCA.结合PCA技术的神经网络模型结构
Fig. 1. Structure of the neural network model combined with PCA.结合PCA技术的神经网络模型结构
Flowchart of the GA-BP model development process.建立GA-BP模型的流程图
Fig. 2. Flowchart of the GA-BP model development process.建立GA-BP模型的流程图
Flowchart of the proposed model to obtain channel characteristic.信道特性获取流程图
Fig. 3. Flowchart of the proposed model to obtain channel characteristic.信道特性获取流程图
Top view of the simulation scene.仿真场景俯视图
Fig. 4. Top view of the simulation scene.仿真场景俯视图
Comparison of the results of 11th order polynomial fitting and simulation data.11阶多项式拟合结果与仿真数据的对比
Fig. 5. Comparison of the results of 11th order polynomial fitting and simulation data.11阶多项式拟合结果与仿真数据的对比
Comparison of the signals of the proposed model and simulation: (a) Test sample #1; (b) test sample #2利用本模型获得接收信号与仿真获得信号的对比 (a)测试样本1; (b)测试样本2
Fig. 6. Comparison of the signals of the proposed model and simulation: (a) Test sample #1; (b) test sample #2利用本模型获得接收信号与仿真获得信号的对比 (a)测试样本1; (b)测试样本2
Comparison of different modeling methods for the channel impulse response peaks.采用不同模型得到的信道冲激响应峰值对比
Fig. 7. Comparison of different modeling methods for the channel impulse response peaks.采用不同模型得到的信道冲激响应峰值对比
X/cm Y/cm Z/cm
TRM12.500
TRM2–2.500
TRM37.500
TRM4–7.500
Table 1. Location of the TRM antennas.
坐标最小值/cm坐标最大值/cm
X1030
Y1030
Z030
Table 2. Location of the terminal antenna.
本模型FDTD软件仿真CST仿真软件
CPU时间约2 min 11 s约23 h约25 h
计算平台Intel i5-4430 3.00 GHz 16 GB(台式机)E5-2690v3 2.60 GHz 128 GB(服务器)E5-2690v3 2.60 GHz 128GB(服务器)
Table 3. CPU time and computer performance.
Lin Yuan, Xue-Song Yang, Bing-Zhong Wang. Prediction of time reversal channel with neural network optimized by empirical knowledge based genetic algorithm[J]. Acta Physica Sinica, 2019, 68(17): 170503-1
Download Citation