Theoretical analysis of the electromagnetic field distribution in the focal region of a long metallic parabolic reflector that has its surface covered with a magnetized plasma layer is derived. The incident wave is co...Theoretical analysis of the electromagnetic field distribution in the focal region of a long metallic parabolic reflector that has its surface covered with a magnetized plasma layer is derived. The incident wave is considered to be with a general oblique incidence for both parallel and perpendicular polarizations. The electromagnetic field intensity expressions along the focal region are obtained accurately using Maslov＇s method. The effects of plasma thickness on the reflected and transmitted field distributions are investigated. The effects of other physi- cal parameters such as the angle of incidence and the plasma and cyclotron frequencies on the transmitted field- intensity distribution along the focal region are also studied. The results obtained by Maslov＇s method and Kirchhoff＇s approximation are found to be in a good agreement.展开更多
A very long wavelength infrared（VLWIR） focal plane array based on In As/Ga Sb type-Ⅱ super-lattices is demonstrated on a Ga Sb substrate. A hetero-structure photodiode was grown with a 50% cut-off wavelength of 15...A very long wavelength infrared（VLWIR） focal plane array based on In As/Ga Sb type-Ⅱ super-lattices is demonstrated on a Ga Sb substrate. A hetero-structure photodiode was grown with a 50% cut-off wavelength of 15.2 μm, at 77 K.A 320×256 VLWIR focal plane array with this design was fabricated and characterized. The peak quantum efficiency without an antireflective coating was 25.74% at the reverse bias voltage of-20 mV, yielding a peak specific detectivity of 5.89×10^10cm·Hz^1/2·W^-1. The operability and the uniformity of response were 89% and 83.17%. The noise-equivalent temperature difference at 65 K exhibited a minimum at 21.4 mK, corresponding to an average value of 56.3 mK.展开更多
为提高文本数据集的情感识别效率,采用深度学习方法,对互联网文本数据集进行情感分类,分别建立基于朴素贝叶斯(Naive Bayesian Classifier,NBC)、卷积神经网络(Convolutional Neural Network,CNN)和长短期记忆网络(Long Short Term Memo...为提高文本数据集的情感识别效率,采用深度学习方法,对互联网文本数据集进行情感分类,分别建立基于朴素贝叶斯(Naive Bayesian Classifier,NBC)、卷积神经网络(Convolutional Neural Network,CNN)和长短期记忆网络(Long Short Term Memory,LSTM)的情感识别模型。在二分类Focal损失函数的基础上,提出多分类Multi Focal损失函数MFL。基于搜狐新闻数据集和中美贸易战评论数据集的实验表明:使用多分类损失函数MFL的长短期记忆模型明显优于其它模型。展开更多
One hundred patients with focal epilepsy were recruited for the present study and their seizures controlled with antiepileptic drugs. The patients then orally received a capsule of tall gastrodis tuber powder, a tradi...One hundred patients with focal epilepsy were recruited for the present study and their seizures controlled with antiepileptic drugs. The patients then orally received a capsule of tall gastrodis tuber powder, a traditional Chinese drug, and underwent single photon emission computed tomography, long-term electroencephalogram, and CT/MRI. Blood drug levels were monitored throughout the study. Before treatment with tall gastrodis tuber, 35 of the 100 cases had abnormal CT/MRI scans; 79 cases had abnormal single photon emission computed tomography images; 86 cases had abnormal electroencephalogram; and a total of 146 abnormal perfusion foci were observed across the 100 subjects. After treatment, the number of patients with normal single photon emission computed tomography images increased by 12; normal electroencephalogram was observed in an additional 27 cases and the number of patients with epileptiform discharge decreased by 29 （34% of 86）; the total number of abnormal perfusion foci decreased by 52 （36%） and changes in abnormal loci were visible in 65 patients. These changes indicate that the administration of tall gastrodis tuber in combination with antiepileptic drugs repairs abnormal perfusion foci in patients with focal epilepsy Our results demonstrate that traditional Chinese drugs can repair abnormal perfusion foci and, as such, are a promising new pathway in the treatment of focal epilepsy.展开更多
基金the Deanship of Scientific Research at King Saud University for its funding of this work through the Research Group Project No. RG-1436-001
文摘Theoretical analysis of the electromagnetic field distribution in the focal region of a long metallic parabolic reflector that has its surface covered with a magnetized plasma layer is derived. The incident wave is considered to be with a general oblique incidence for both parallel and perpendicular polarizations. The electromagnetic field intensity expressions along the focal region are obtained accurately using Maslov＇s method. The effects of plasma thickness on the reflected and transmitted field distributions are investigated. The effects of other physi- cal parameters such as the angle of incidence and the plasma and cyclotron frequencies on the transmitted field- intensity distribution along the focal region are also studied. The results obtained by Maslov＇s method and Kirchhoff＇s approximation are found to be in a good agreement.
基金supported by the National Basic Research Program of China(Grant Nos.2013CB932904 and 2011CB922201)the National Special Funds for the Development of Major Research Equipment and Instruments,China(Grant No.2012YQ140005)the National Natural Science Foundation of China(Grant Nos.61274013,61290303,and 61306013)
文摘A very long wavelength infrared（VLWIR） focal plane array based on In As/Ga Sb type-Ⅱ super-lattices is demonstrated on a Ga Sb substrate. A hetero-structure photodiode was grown with a 50% cut-off wavelength of 15.2 μm, at 77 K.A 320×256 VLWIR focal plane array with this design was fabricated and characterized. The peak quantum efficiency without an antireflective coating was 25.74% at the reverse bias voltage of-20 mV, yielding a peak specific detectivity of 5.89×10^10cm·Hz^1/2·W^-1. The operability and the uniformity of response were 89% and 83.17%. The noise-equivalent temperature difference at 65 K exhibited a minimum at 21.4 mK, corresponding to an average value of 56.3 mK.
文摘为提高文本数据集的情感识别效率,采用深度学习方法,对互联网文本数据集进行情感分类,分别建立基于朴素贝叶斯(Naive Bayesian Classifier,NBC)、卷积神经网络(Convolutional Neural Network,CNN)和长短期记忆网络(Long Short Term Memory,LSTM)的情感识别模型。在二分类Focal损失函数的基础上,提出多分类Multi Focal损失函数MFL。基于搜狐新闻数据集和中美贸易战评论数据集的实验表明:使用多分类损失函数MFL的长短期记忆模型明显优于其它模型。
基金funded by the Key Project of Gansu Province, No.2GS054-A43-014-19
文摘One hundred patients with focal epilepsy were recruited for the present study and their seizures controlled with antiepileptic drugs. The patients then orally received a capsule of tall gastrodis tuber powder, a traditional Chinese drug, and underwent single photon emission computed tomography, long-term electroencephalogram, and CT/MRI. Blood drug levels were monitored throughout the study. Before treatment with tall gastrodis tuber, 35 of the 100 cases had abnormal CT/MRI scans; 79 cases had abnormal single photon emission computed tomography images; 86 cases had abnormal electroencephalogram; and a total of 146 abnormal perfusion foci were observed across the 100 subjects. After treatment, the number of patients with normal single photon emission computed tomography images increased by 12; normal electroencephalogram was observed in an additional 27 cases and the number of patients with epileptiform discharge decreased by 29 （34% of 86）; the total number of abnormal perfusion foci decreased by 52 （36%） and changes in abnormal loci were visible in 65 patients. These changes indicate that the administration of tall gastrodis tuber in combination with antiepileptic drugs repairs abnormal perfusion foci in patients with focal epilepsy Our results demonstrate that traditional Chinese drugs can repair abnormal perfusion foci and, as such, are a promising new pathway in the treatment of focal epilepsy.
