Spectral and spatial features in remotely sensed data play an irreplaceable role in classifying crop types for precision agriculture. Despite the thriving establishment of the handcrafted features, designing or select...Spectral and spatial features in remotely sensed data play an irreplaceable role in classifying crop types for precision agriculture. Despite the thriving establishment of the handcrafted features, designing or selecting such features valid for specific crop types requires prior knowledge and thus remains an open challenge. Convolutional neural networks(CNNs) can effectively overcome this issue with their advanced ability to generate high-level features automatically but are still inadequate in mining spectral features compared to mining spatial features. This study proposed an enhanced spectral feature called Stacked Spectral Feature Space Patch(SSFSP) for CNN-based crop classification. SSFSP is a stack of twodimensional(2 D) gridded spectral feature images that record various crop types’ spatial and intensity distribution characteristics in a 2 D feature space consisting of two spectral bands. SSFSP can be input into2 D-CNNs to support the simultaneous mining of spectral and spatial features, as the spectral features are successfully converted to 2 D images that can be processed by CNN. We tested the performance of SSFSP by using it as the input to seven CNN models and one multilayer perceptron model for crop type classification compared to using conventional spectral features as input. Using high spatial resolution hyperspectral datasets at three sites, the comparative study demonstrated that SSFSP outperforms conventional spectral features regarding classification accuracy, robustness, and training efficiency. The theoretical analysis summarizes three reasons for its excellent performance. First, SSFSP mines the spectral interrelationship with feature generality, which reduces the required number of training samples.Second, the intra-class variance can be largely reduced by grid partitioning. Third, SSFSP is a highly sparse feature, which reduces the dependence on the CNN model structure and enables early and fast convergence in model training. In conclusion, SSFSP has great potential for practical crop cla展开更多
The design of a seven-band stacked patch antenna for the C, X and Ku band is presented. The antenna consists of an H-slot loaded fed patch, stacked with dual U-slot loaded rectangular patch to generate the seven frequ...The design of a seven-band stacked patch antenna for the C, X and Ku band is presented. The antenna consists of an H-slot loaded fed patch, stacked with dual U-slot loaded rectangular patch to generate the seven frequency bands. The total size of the antenna is 39.25 × 29.25 mm2. The multiband stacked patch antenna is studied and designed using IE3D simulator. For verification of simulation results, the antenna is analyzed by circuit theory concept. The simulated return loss, radiation pattern and gain are presented. Simulated results show that the antenna can be designed to cover the frequency bands from (4.24 GHz to 4.50 GHz, 5.02 GHz to 5.25 GHz) in C-band application, (7.84 GHz to 8.23 GHz) in X-band and (12.16 GHz to 12.35 GHz, 14.25 GHz to 14.76 GHz, 15.25 GHz to 15.51 GHz, 17.52 GHz to 17.86 GHz) in Ku band applications. The bandwidths of each band of the proposed antenna are 5.9%, 4.5%, 4.83%, 2.36%, 3.53%, 1.68% and 1.91%. Similarly the gains of the proposed band are 2.80 dBi, 4.39 dBi, 4.54 dBi, 10.26 dBi, 8.36 dBi and 9.91 dBi, respectively.展开更多
A dual-band characteristic of stacked rectangular microstrip antenna is experimentally studied. It is a probe fed antenna for impedance matching with 50Ω coaxial cable. This antenna works well in the frequency range ...A dual-band characteristic of stacked rectangular microstrip antenna is experimentally studied. It is a probe fed antenna for impedance matching with 50Ω coaxial cable. This antenna works well in the frequency range (2.86 to 4.63 GHz). It is basically a low cost, light weight medium gain antenna, which is used for mobile communication. The variations of the length and width (1mm) of the stacked rectangular patch antenna have been done. And it is found dual resonance with increasing lower resonance frequency and almost constant upper resonance frequency with increases of the length & width of rectangular microstrip antenna. The input impedance and VSWR, return loss have been measured with the help of Network analyzer.展开更多
设计了一款层叠微带多频天线,可同时覆盖在DSRC(专用短距离通信,Dedicated Short Range Communications)和5G毫米波频段。通过将工作于低频段的矩形贴片天线与工作于毫米波频段的四元阵列天线组合,实现天线的多频段工作。基于有限元法...设计了一款层叠微带多频天线,可同时覆盖在DSRC(专用短距离通信,Dedicated Short Range Communications)和5G毫米波频段。通过将工作于低频段的矩形贴片天线与工作于毫米波频段的四元阵列天线组合,实现天线的多频段工作。基于有限元法高频结构仿真(High Frequency Structure Simulator,HFSS)对多频天线的S参数及辐射性能进行仿真。仿真分析结果表明,该天线反射系数小于-10 dB的频段为5.8813~5.9283 GHz、28.1603~29.3476 GHz和30.3419~31.1353 GHz,并通过刻蚀缺陷接地结构(DGS)使得天线在高频段的端口隔离度平均提高了14 dB,且在高频段显示出良好的全向性。该多频天线具有剖面低、隔离度高等优点,可应用于未来车用无线通信系统。展开更多
基金supported by the National Natural Science Foundation of China (67441830108 and 41871224)。
文摘Spectral and spatial features in remotely sensed data play an irreplaceable role in classifying crop types for precision agriculture. Despite the thriving establishment of the handcrafted features, designing or selecting such features valid for specific crop types requires prior knowledge and thus remains an open challenge. Convolutional neural networks(CNNs) can effectively overcome this issue with their advanced ability to generate high-level features automatically but are still inadequate in mining spectral features compared to mining spatial features. This study proposed an enhanced spectral feature called Stacked Spectral Feature Space Patch(SSFSP) for CNN-based crop classification. SSFSP is a stack of twodimensional(2 D) gridded spectral feature images that record various crop types’ spatial and intensity distribution characteristics in a 2 D feature space consisting of two spectral bands. SSFSP can be input into2 D-CNNs to support the simultaneous mining of spectral and spatial features, as the spectral features are successfully converted to 2 D images that can be processed by CNN. We tested the performance of SSFSP by using it as the input to seven CNN models and one multilayer perceptron model for crop type classification compared to using conventional spectral features as input. Using high spatial resolution hyperspectral datasets at three sites, the comparative study demonstrated that SSFSP outperforms conventional spectral features regarding classification accuracy, robustness, and training efficiency. The theoretical analysis summarizes three reasons for its excellent performance. First, SSFSP mines the spectral interrelationship with feature generality, which reduces the required number of training samples.Second, the intra-class variance can be largely reduced by grid partitioning. Third, SSFSP is a highly sparse feature, which reduces the dependence on the CNN model structure and enables early and fast convergence in model training. In conclusion, SSFSP has great potential for practical crop cla
文摘The design of a seven-band stacked patch antenna for the C, X and Ku band is presented. The antenna consists of an H-slot loaded fed patch, stacked with dual U-slot loaded rectangular patch to generate the seven frequency bands. The total size of the antenna is 39.25 × 29.25 mm2. The multiband stacked patch antenna is studied and designed using IE3D simulator. For verification of simulation results, the antenna is analyzed by circuit theory concept. The simulated return loss, radiation pattern and gain are presented. Simulated results show that the antenna can be designed to cover the frequency bands from (4.24 GHz to 4.50 GHz, 5.02 GHz to 5.25 GHz) in C-band application, (7.84 GHz to 8.23 GHz) in X-band and (12.16 GHz to 12.35 GHz, 14.25 GHz to 14.76 GHz, 15.25 GHz to 15.51 GHz, 17.52 GHz to 17.86 GHz) in Ku band applications. The bandwidths of each band of the proposed antenna are 5.9%, 4.5%, 4.83%, 2.36%, 3.53%, 1.68% and 1.91%. Similarly the gains of the proposed band are 2.80 dBi, 4.39 dBi, 4.54 dBi, 10.26 dBi, 8.36 dBi and 9.91 dBi, respectively.
文摘A dual-band characteristic of stacked rectangular microstrip antenna is experimentally studied. It is a probe fed antenna for impedance matching with 50Ω coaxial cable. This antenna works well in the frequency range (2.86 to 4.63 GHz). It is basically a low cost, light weight medium gain antenna, which is used for mobile communication. The variations of the length and width (1mm) of the stacked rectangular patch antenna have been done. And it is found dual resonance with increasing lower resonance frequency and almost constant upper resonance frequency with increases of the length & width of rectangular microstrip antenna. The input impedance and VSWR, return loss have been measured with the help of Network analyzer.
文摘设计了一款层叠微带多频天线,可同时覆盖在DSRC(专用短距离通信,Dedicated Short Range Communications)和5G毫米波频段。通过将工作于低频段的矩形贴片天线与工作于毫米波频段的四元阵列天线组合,实现天线的多频段工作。基于有限元法高频结构仿真(High Frequency Structure Simulator,HFSS)对多频天线的S参数及辐射性能进行仿真。仿真分析结果表明,该天线反射系数小于-10 dB的频段为5.8813~5.9283 GHz、28.1603~29.3476 GHz和30.3419~31.1353 GHz,并通过刻蚀缺陷接地结构(DGS)使得天线在高频段的端口隔离度平均提高了14 dB,且在高频段显示出良好的全向性。该多频天线具有剖面低、隔离度高等优点,可应用于未来车用无线通信系统。
