In the field of radiocommunication, modulation type identification is one of the most important characteristics in signal processing. This study aims to implement a modulation recognition system on two approaches to m...In the field of radiocommunication, modulation type identification is one of the most important characteristics in signal processing. This study aims to implement a modulation recognition system on two approaches to machine learning techniques, the K-Nearest Neighbors (KNN) and Artificial Neural Networks (ANN). From a statistical and spectral analysis of signals, nine key differentiation features are extracted and used as input vectors for each trained model. The feature extraction is performed by using the Hilbert transform, the forward and inverse Fourier transforms. The experiments with the AMC Master dataset classify ten (10) types of analog and digital modulations. AM_DSB_FC, AM_DSB_SC, AM_USB, AM_LSB, FM, MPSK, 2PSK, MASK, 2ASK, MQAM are put forward in this article. For the simulation of the chosen model, signals are polluted by the Additive White Gaussian Noise (AWGN). The simulation results show that the best identification rate is the MLP neuronal method with 90.5% of accuracy after 10 dB signal-to-noise ratio value, with a shift of more than 15% from the k-nearest neighbors’ algorithm.展开更多
Digital circuit and analog circuit courses are basic courses for students of science and engineering universities. Among them,the practical courses are of great significance for students to master the knowledge of ele...Digital circuit and analog circuit courses are basic courses for students of science and engineering universities. Among them,the practical courses are of great significance for students to master the knowledge of electronics. In order to make teachers teaching more efficiently and students studying more quickly,how to update the experimental course in teaching reform is the key point. This paper analyzing the present situation of teaching in the digital circuit and analog circuit courses,the teaching questions in universities. On the basis of it,the innovation measures of experimental teaching methods and contents are discussed. Our school tries to introduce the UltraLab network experiment platform,reform and optimize the teaching methods of related courses.And it’ s accelerating the construction and development of emerging engineering education’ s process,reducing effectively the teacher’s time for managing in equipment,improving the students’ ability to use instruments.展开更多
This study addresses the link between social media use and pro-environmental civic participation considering the moderating effect of social media affordances (public realm) on one hand, and lifestyle behaviors and cl...This study addresses the link between social media use and pro-environmental civic participation considering the moderating effect of social media affordances (public realm) on one hand, and lifestyle behaviors and climate change experiences (personal realm) on the other. We combine communication theory and behavioral models and using a sample of USA individuals (N = 7225) based on the American Trends Panel to predict variations in pro-environmental behavior. We show that social networks rather than information are more effective in predicting pro-environmental behavior. Moreover, a pro-environmental lifestyle as well as climate change experiences at the community level increase the likelihood for pro-environmental participation. However, affordances related to socioeconomic variations generate variations to pro-environmental civic participation. We conclude that in order to capture the depth of pro-environmental civic participation, it is necessary to theoretically and empirically bridge between private and public expressions of pro-environmental awareness.展开更多
通信信号调制识别技术可用于信号确认、干扰识别、电子战对抗以及星间链路通信等方面。针对低噪声下信号调制方式识别率低与识别种类少的问题,提出一种基于神经网络的数字模拟混合信号调制方式识别算法。简化并改进识别特征参数,降低参...通信信号调制识别技术可用于信号确认、干扰识别、电子战对抗以及星间链路通信等方面。针对低噪声下信号调制方式识别率低与识别种类少的问题,提出一种基于神经网络的数字模拟混合信号调制方式识别算法。简化并改进识别特征参数,降低参数对噪声干扰的敏感度,设计基于判决树的自动识别流程。通过自适应学习速率选取最优隐含层节点数,改进BP神经网络算法。结合判决树和改进的神经网络算法,给出基于神经网络的算法调制方式识别方案。仿真结果表明,在信噪比不低于0 d B时,该算法的平均识别成功率达到98%以上。展开更多
文摘In the field of radiocommunication, modulation type identification is one of the most important characteristics in signal processing. This study aims to implement a modulation recognition system on two approaches to machine learning techniques, the K-Nearest Neighbors (KNN) and Artificial Neural Networks (ANN). From a statistical and spectral analysis of signals, nine key differentiation features are extracted and used as input vectors for each trained model. The feature extraction is performed by using the Hilbert transform, the forward and inverse Fourier transforms. The experiments with the AMC Master dataset classify ten (10) types of analog and digital modulations. AM_DSB_FC, AM_DSB_SC, AM_USB, AM_LSB, FM, MPSK, 2PSK, MASK, 2ASK, MQAM are put forward in this article. For the simulation of the chosen model, signals are polluted by the Additive White Gaussian Noise (AWGN). The simulation results show that the best identification rate is the MLP neuronal method with 90.5% of accuracy after 10 dB signal-to-noise ratio value, with a shift of more than 15% from the k-nearest neighbors’ algorithm.
基金supported by University-level Teaching Reform Project of New Engineering,Beijing University of Chemical Technology(xgk2017040436)Teaching Reform Project of School of International Teaching,Beijing University of Chemical Technology(siejg201713)
文摘Digital circuit and analog circuit courses are basic courses for students of science and engineering universities. Among them,the practical courses are of great significance for students to master the knowledge of electronics. In order to make teachers teaching more efficiently and students studying more quickly,how to update the experimental course in teaching reform is the key point. This paper analyzing the present situation of teaching in the digital circuit and analog circuit courses,the teaching questions in universities. On the basis of it,the innovation measures of experimental teaching methods and contents are discussed. Our school tries to introduce the UltraLab network experiment platform,reform and optimize the teaching methods of related courses.And it’ s accelerating the construction and development of emerging engineering education’ s process,reducing effectively the teacher’s time for managing in equipment,improving the students’ ability to use instruments.
文摘This study addresses the link between social media use and pro-environmental civic participation considering the moderating effect of social media affordances (public realm) on one hand, and lifestyle behaviors and climate change experiences (personal realm) on the other. We combine communication theory and behavioral models and using a sample of USA individuals (N = 7225) based on the American Trends Panel to predict variations in pro-environmental behavior. We show that social networks rather than information are more effective in predicting pro-environmental behavior. Moreover, a pro-environmental lifestyle as well as climate change experiences at the community level increase the likelihood for pro-environmental participation. However, affordances related to socioeconomic variations generate variations to pro-environmental civic participation. We conclude that in order to capture the depth of pro-environmental civic participation, it is necessary to theoretically and empirically bridge between private and public expressions of pro-environmental awareness.
文摘通信信号调制识别技术可用于信号确认、干扰识别、电子战对抗以及星间链路通信等方面。针对低噪声下信号调制方式识别率低与识别种类少的问题,提出一种基于神经网络的数字模拟混合信号调制方式识别算法。简化并改进识别特征参数,降低参数对噪声干扰的敏感度,设计基于判决树的自动识别流程。通过自适应学习速率选取最优隐含层节点数,改进BP神经网络算法。结合判决树和改进的神经网络算法,给出基于神经网络的算法调制方式识别方案。仿真结果表明,在信噪比不低于0 d B时,该算法的平均识别成功率达到98%以上。
