A novel automatic white-balance algorithm based on adaptive-luminance is proposed in this paper. This algorithm rede- fines the gray pixels region, which can filter the gray pixels accurately. Furthermore, with the re...A novel automatic white-balance algorithm based on adaptive-luminance is proposed in this paper. This algorithm rede- fines the gray pixels region, which can filter the gray pixels accurately. Furthermore, with the relations between gray pixels’ luminance with standard light source and their chroma Cb, Cr shifts with other color temperatures, the algorithm estab- lishes the equations between the captured pixels and the original ones, which can estimate the gains of RGB channels exactly. To evaluate the prop...展开更多
Filter bank multicarrier quadrature amplitude modulation(FBMC-QAM)will encounter inter-ference and noise during the process of channel transmission.In order to suppress the interference in the communication system,cha...Filter bank multicarrier quadrature amplitude modulation(FBMC-QAM)will encounter inter-ference and noise during the process of channel transmission.In order to suppress the interference in the communication system,channel equalization is carried out at the receiver.Given that the con-ventional least mean square(LMS)equilibrium algorithm usually suffer from drawbacks such as the inability to converge quickly in large step sizes and poor stability in small step sizes when searching for optimal weights,in this paper,a design scheme for adaptive equalization with dynamic step size LMS optimization is proposed,which can further improve the convergence and error stability of the algorithm by calling the Sigmoid function and introducing three new parameters to control the range of step size values,adjust the steepness of step size,and reduce steady-state errors in small step sta-ges.Theoretical analysis and simulation results demonstrate that compared with the conventional LMS algorithm and the neural network-based residual deep neural network(Res-DNN)algorithm,the adopted dynamic step size LMS optimization scheme can not only obtain faster convergence speed,but also get smaller error values in the signal recovery process,thereby achieving better bit error rate(BER)performance.展开更多
针对可见光通信信号在传输中易受信道环境和背景噪声干扰等因素影响调制格式识别精度的问题,提出一种用于可见光通信信号调制格式识别的改进YOLOv5s(You Only Look Once)算法。首先,通过YOLOv5s算法网络输入端引入Mixup数据增强方式,将...针对可见光通信信号在传输中易受信道环境和背景噪声干扰等因素影响调制格式识别精度的问题,提出一种用于可见光通信信号调制格式识别的改进YOLOv5s(You Only Look Once)算法。首先,通过YOLOv5s算法网络输入端引入Mixup数据增强方式,将其与原网络中的Mosaic数据增强方式相结合,提升网络的鲁棒性,并增强算法在不同调制格式信号间的泛化能力;其次,将自适应空间特征融合(ASFF)引入到Neck网络中,充分提取不同层次的特征,提高检测精度。实验结果表明,在混合信噪比条件下,所提改进算法的平均精度均值(mAP)达到了0.903,比原始YOLOv5s算法提升了0.7%,且在信噪比为20 dB时mAP高达0.993。展开更多
Connected and autonomous vehicle(CAV)vehicle to infrastructure(V2I)scenarios have more stringent requirements on the communication rate,delay,and reliability of the Internet of vehicles(Io V).New radio vehicle to ever...Connected and autonomous vehicle(CAV)vehicle to infrastructure(V2I)scenarios have more stringent requirements on the communication rate,delay,and reliability of the Internet of vehicles(Io V).New radio vehicle to everything(NR-V2X)adopts link adaptation(LA)to improve the efficiency and reliability of road safety information transmission.In order to solve the problem that the existing LA scheduling algorithms cannot adapt to the Doppler shift and complex fast time-varying channel in V2I scenario,resulting in low reliability of information transmission,this paper proposes a deep Q-learning(DQL)-based massive multiple-input multiple-output(MIMO)LA scheduling algorithm for autonomous driving V2I scenario.The algorithm combines deep neural network(DNN)with Q-learning(QL)algorithm,which is used for joint scheduling of modulation and coding scheme(MCS)and space division multiplexing(SDM).The system simulation results show that the algorithm proposed in this paper can fully adapt to the different channel environment in the V2I scenario,and select the optimal MCS and SDM for the transmission of road safety information,thereby the accuracy of road safety information transmission is improved,collision accidents can be avoided,and bring a good autonomous driving experience.展开更多
针对自动气象站数据采集器温度通道容易受到环境温度影响限制测量精度的问题,对数据采集器进行了温度漂移检测实验并对实验数据进行了误差分析,提出了基于改进自适应遗传算法优化的最小二乘支持向量机(improved adaptive geneticalgorit...针对自动气象站数据采集器温度通道容易受到环境温度影响限制测量精度的问题,对数据采集器进行了温度漂移检测实验并对实验数据进行了误差分析,提出了基于改进自适应遗传算法优化的最小二乘支持向量机(improved adaptive geneticalgorithm least squares support vector machine,IAGA-LSSVM)的温度补偿方法。改进的自适应遗传算法能够对最小二乘支持向量机拟合过程中的关键参数进行调整从而建立最优模型。与传统LS-SVM相比,IAGA-LSSVM对温度数据的建模均方根误差减小了0.007,有效提高了建模的精度。根据建立的最优函数模型对该数据采集器温度通道进行温度补偿结果表明,经该方法补偿后的数据采集器在任何温度环境下的温度测量误差均小于0.03℃,具有更高的测量精度和稳定性,有效提高了自动气象站的温度观测质量。同时,设计开发了温度补偿界面,为自动气象站观测数据校验和实际业务应用奠定了基础。展开更多
基金supported by the National Natural Science Fou-ndation of China (Grant No.60576025)the Special SubjectFoundation of Tianjin (Grant.05 FZZDGX00200).
文摘A novel automatic white-balance algorithm based on adaptive-luminance is proposed in this paper. This algorithm rede- fines the gray pixels region, which can filter the gray pixels accurately. Furthermore, with the relations between gray pixels’ luminance with standard light source and their chroma Cb, Cr shifts with other color temperatures, the algorithm estab- lishes the equations between the captured pixels and the original ones, which can estimate the gains of RGB channels exactly. To evaluate the prop...
基金the National Natural Science Foundation of China(No.61601296,61701295)the Science and Technology Innovation Action Plan Project of Shanghai Science and Technology Commission(No.20511103500)the Talent Program of Shanghai University of Engineering Science(No.2018RC43).
文摘Filter bank multicarrier quadrature amplitude modulation(FBMC-QAM)will encounter inter-ference and noise during the process of channel transmission.In order to suppress the interference in the communication system,channel equalization is carried out at the receiver.Given that the con-ventional least mean square(LMS)equilibrium algorithm usually suffer from drawbacks such as the inability to converge quickly in large step sizes and poor stability in small step sizes when searching for optimal weights,in this paper,a design scheme for adaptive equalization with dynamic step size LMS optimization is proposed,which can further improve the convergence and error stability of the algorithm by calling the Sigmoid function and introducing three new parameters to control the range of step size values,adjust the steepness of step size,and reduce steady-state errors in small step sta-ges.Theoretical analysis and simulation results demonstrate that compared with the conventional LMS algorithm and the neural network-based residual deep neural network(Res-DNN)algorithm,the adopted dynamic step size LMS optimization scheme can not only obtain faster convergence speed,but also get smaller error values in the signal recovery process,thereby achieving better bit error rate(BER)performance.
文摘针对可见光通信信号在传输中易受信道环境和背景噪声干扰等因素影响调制格式识别精度的问题,提出一种用于可见光通信信号调制格式识别的改进YOLOv5s(You Only Look Once)算法。首先,通过YOLOv5s算法网络输入端引入Mixup数据增强方式,将其与原网络中的Mosaic数据增强方式相结合,提升网络的鲁棒性,并增强算法在不同调制格式信号间的泛化能力;其次,将自适应空间特征融合(ASFF)引入到Neck网络中,充分提取不同层次的特征,提高检测精度。实验结果表明,在混合信噪比条件下,所提改进算法的平均精度均值(mAP)达到了0.903,比原始YOLOv5s算法提升了0.7%,且在信噪比为20 dB时mAP高达0.993。
基金supported by the Natural Science Foundation of Chongqing(No.cstc2019jcyjmsxmX0017)。
文摘Connected and autonomous vehicle(CAV)vehicle to infrastructure(V2I)scenarios have more stringent requirements on the communication rate,delay,and reliability of the Internet of vehicles(Io V).New radio vehicle to everything(NR-V2X)adopts link adaptation(LA)to improve the efficiency and reliability of road safety information transmission.In order to solve the problem that the existing LA scheduling algorithms cannot adapt to the Doppler shift and complex fast time-varying channel in V2I scenario,resulting in low reliability of information transmission,this paper proposes a deep Q-learning(DQL)-based massive multiple-input multiple-output(MIMO)LA scheduling algorithm for autonomous driving V2I scenario.The algorithm combines deep neural network(DNN)with Q-learning(QL)algorithm,which is used for joint scheduling of modulation and coding scheme(MCS)and space division multiplexing(SDM).The system simulation results show that the algorithm proposed in this paper can fully adapt to the different channel environment in the V2I scenario,and select the optimal MCS and SDM for the transmission of road safety information,thereby the accuracy of road safety information transmission is improved,collision accidents can be avoided,and bring a good autonomous driving experience.
文摘针对自动气象站数据采集器温度通道容易受到环境温度影响限制测量精度的问题,对数据采集器进行了温度漂移检测实验并对实验数据进行了误差分析,提出了基于改进自适应遗传算法优化的最小二乘支持向量机(improved adaptive geneticalgorithm least squares support vector machine,IAGA-LSSVM)的温度补偿方法。改进的自适应遗传算法能够对最小二乘支持向量机拟合过程中的关键参数进行调整从而建立最优模型。与传统LS-SVM相比,IAGA-LSSVM对温度数据的建模均方根误差减小了0.007,有效提高了建模的精度。根据建立的最优函数模型对该数据采集器温度通道进行温度补偿结果表明,经该方法补偿后的数据采集器在任何温度环境下的温度测量误差均小于0.03℃,具有更高的测量精度和稳定性,有效提高了自动气象站的温度观测质量。同时,设计开发了温度补偿界面,为自动气象站观测数据校验和实际业务应用奠定了基础。
