-
图 1 I/Q正交调制发射机
Figure 1.
-
图 2 I/Q调制器畸变的视觉表现
Figure 2.
-
图 3 滤波器畸变的视觉表现
Figure 3.
-
图 4 振荡器畸变的视觉表现
Figure 4.
-
图 5 功率放大畸变的视觉表现
Figure 5.
-
图 6 矢量图灰度图像
Figure 6.
-
图 7 深度残差网络的网络结构
Figure 7.
-
图 8 残差单元个数对识别性能的影响
Figure 8.
-
图 9 符号个数对识别性能的影响
Figure 9.
-
图 10 过采倍数对识别性能的影响
Figure 10.
-
图 11 不同算法的识别性能
Figure 11.
-
算法 文献[6]算法 文献[8]算法 文献[9]算法 文献[10]算法 文献[14]算法 本文算法 复杂度 $O\left( {ML\lg \left( {ML} \right)} \right) + O\left( S \right)$ $O\left( {ML} \right) + O\left( L \right)$ $O\left( {ML} \right) + O\left( L \right)$ $O\left( {ML} \right) + O\left( L \right)$ $O\left( {PQ\lg Q} \right) + O\left( S \right)$ $O\left( {ML} \right) + O\left( S \right)$ 表 1 不同算法的复杂度对比
-
辐射源 1 2 3 4 5 6 7 $g$ 0.0299 0.0188 0.0081 –0.0025 –0.0128 –0.0230 –0.0329 $\phi $ 0.0137 0.0093 0.0050 0.0006 –0.0038 –0.0081 –0.0125 ${c_{\rm I}}$ 0.0142 0.0097 0.0052 0.0007 –0.0038 –0.0083 –0.0128 ${c_{\rm Q}}$ 0.0147 0.0102 0.0057 0.0012 –0.0033 –0.0078 –0.0123 ${a_n}$ –0.0640 –0.0429 –0.0218 –0.0007 0.0204 0.0415 0.0627 ${b_n}$ –0.0740 –0.0498 –0.0256 –0.0014 0.0228 0.0470 0.0713 ${c_{\rm o}}$ 0.0002 0.0010 0.0018 0.0026 0.0034 0.0042 0.0050 ${\lambda _3}$ –0.2915–0.0079i –0.0003–0.0004i –0.4371–0.0092i –0.1459–0.0066i –0.5827–0.0096i –0.0731–0.0042i –0.3643–0.0085i ${\lambda _5}$ 0.0295+0.0005i 0.0001+0.0004i 0.0821+0.0048i 0.0338+0.0014i 0.0537+0.0029i 0.0571+0.0035i 0.0484+0.0022i 表 2 不同辐射源的畸变参数
-
RN 2 4 6 8 10 conv1 7×7, 32, stride2 max pool 3×3, stride 2 conv2_x $\left[ \begin{array}{l} 3 \times 3,32 \\ 3 \times 3,32 \\ \end{array} \right] \times 2$ $\left[ \begin{array}{l} 3 \times 3,32 \\ 3 \times 3,32 \\ \end{array} \right] \times 2$ $\left[ \begin{array}{l} 3 \times 3,32 \\ 3 \times 3,32 \\ \end{array} \right] \times 2$ $\left[ \begin{array}{l} 3 \times 3,32 \\ 3 \times 3,32 \\ \end{array} \right] \times 2$ $\left[ \begin{array}{l} 3 \times 3,32 \\ 3 \times 3,32 \\ \end{array} \right] \times 2$ conv3_x — $\left[ \begin{array}{l} 3 \times 3,64 \\ 3 \times 3,64 \\ \end{array} \right] \times 2$ $\left[ \begin{array}{l} 3 \times 3,64 \\ 3 \times 3,64 \\ \end{array} \right] \times 2$ $\left[ \begin{array}{l} 3 \times 3,64 \\ 3 \times 3,64 \\ \end{array} \right] \times 2$ $\left[ \begin{array}{l} 3 \times 3,64 \\ 3 \times 3,64 \\ \end{array} \right] \times 2$ conv4_x — — $\left[ \begin{array}{l} 3 \times 3,128 \\ 3 \times 3,128 \\ \end{array} \right] \times 2$ $\left[ \begin{array}{l} 3 \times 3,128 \\ 3 \times 3,128 \\ \end{array} \right] \times 2$ $\left[ \begin{array}{l} 3 \times 3,128 \\ 3 \times 3,128 \\ \end{array} \right] \times 2$ conv5_x — — — $\left[ \begin{array}{l} 3 \times 3,256 \\ 3 \times 3,256 \\ \end{array} \right] \times 2$ $\left[ \begin{array}{l} 3 \times 3,256 \\ 3 \times 3,256 \\ \end{array} \right] \times 2$ conv6_x — — — — $\left[ \begin{array}{l} 3 \times 3,512 \\ 3 \times 3,512 \\ \end{array} \right] \times 2$ avg pool 5-d fc, softmax 参数量 3.9×104 1.7×105 6.8×105 2.7×106 1.1×107 训练时间 (s) 0.3516 0.3858 0.4019 0.4262 0.4584 表 3 网络结构及其参数量和单批次训练时间
图共
11 个 表共
3 个
