Efficiency is an important factor in quantitative and qualitative analysis of radionuclides, and the gamma point source efficiency is related to the radial angle,detection distance, and gamma-ray energy. In this work,...Efficiency is an important factor in quantitative and qualitative analysis of radionuclides, and the gamma point source efficiency is related to the radial angle,detection distance, and gamma-ray energy. In this work, on the basis of a back-propagation(BP) neural network model,a method to determine the gamma point source efficiency is developed and validated. The efficiency of the point sources ^(137)Cs and ^(60)Co at discrete radial angles, detection distances, and gamma-ray energies is measured, and the BP neural network prediction model is constructed using MATLAB. The gamma point source efficiencies at different radial angles, detection distances, and gamma-ray energies are predicted quickly and accurately using this nonlinear prediction model. The results show that the maximum error between the predicted and experimental values is 3.732% at 661.661 keV, 11π/24, and 35 cm, and those under other conditions are less than 3%. The gamma point source efficiencies obtained using the BP neural network model are in good agreement with experimental data.展开更多
A sequence detector based on Hopfield Neural network(HNN) is presented, which is used to estimate the transmitted sequences from the received signals in mobile communications. In order to avoid the convergence of HNN ...A sequence detector based on Hopfield Neural network(HNN) is presented, which is used to estimate the transmitted sequences from the received signals in mobile communications. In order to avoid the convergence of HNN in local minima, a decreasing step algorithm (DSA) is proposed to search the optimum sequence quickly on the basis of the traditional simulated annealing (SA) algorithm. Computer simulation results show that the new HNN detector provides almost the same performance as that of the Viterbi detector while needs less computations and memory capacity, thus it is more feasible in hardware implementation and long constraint convolutional decoding.展开更多
A laser collimating system based on 2-D position sensitive detector (PSD) is presented in this paper. The working principle of PSD is depicted in detail. A calibration device was developed to check the nonlinearity er...A laser collimating system based on 2-D position sensitive detector (PSD) is presented in this paper. The working principle of PSD is depicted in detail. A calibration device was developed to check the nonlinearity errors of PSD and a multilayer feedforward neural network based on error back-propagation algorithm was used to compensate errors. With the aid of computer-based data acquisition system, an automatic dynamic measuring process was realized. A series of experiments, including comparison tests with laser interferometer, were done to evaluate the performance of the measuring system. The experimental results show that the spatial straightness errors of guide rails can be measured with high accuracy. The maximum differences between the device and laser interferometer are 0.027 mm in Y direction, and 0.053 mm in X direction in the measuring distance of 6 m.展开更多
The unfolding of neutron spectra from the pulse height distribution measured by a BC501A scintillation detector is accomplished by the application of artificial neural networks (ANN). A simple linear neural network wi...The unfolding of neutron spectra from the pulse height distribution measured by a BC501A scintillation detector is accomplished by the application of artificial neural networks (ANN). A simple linear neural network without biases and hidden layers is adopted. A set of monoenergetic detector response functions in the energy range from 0.25 MeV to 16 MeV with an energy interval of 0.25 MeV are generated by the Monte Carlo code O5S in the training phase of the unfolding process. The capability of ANN was demonstrated successfully using the Monte Carlo data itself and experimental data obtained from the Am-Be neutron source and D-T neutron source.展开更多
Application of Neural Network to signal detection in CDMA multi-user communications Gaussian channel is investigated. This paper is motivated by the fact that, in a multi-user CDMA system. the conventional receiver su...Application of Neural Network to signal detection in CDMA multi-user communications Gaussian channel is investigated. This paper is motivated by the fact that, in a multi-user CDMA system. the conventional receiver suffers severe performance degradation as the relative powers of the interfering signals become large(i.e. 'near-far problem'). Furthermore, in many cases, the optimum receiver which alleviates the near-far problem, is too complex to be of practical use. And by viewing this optimum multi-user detector problem in CDMA channel as an optimum nonlinear classification decision problem. we apply the Probabilistic Neural Network algorithm, which has the capacity of arbitrary nonlinear transformation, adaptive learning and tracking to implement this classification decision optimally and adaptively The performance of the Proposes neural detector is evaluated via computer simulations in terms of probability of detection and it is compared with those of the existing neural and conventional detector schemes in a multi-user environment.展开更多
结合固定型交通检测器空间配置的4条原则和配置密度优化步骤,提出基于数据挖掘技术的固定型交通检测器配置优化方法。设计6种高速公路出口匝道的固定型交通检测器配置密度方案作为实例研究对象,运用数据挖掘技术的时间序列指数平滑方法...结合固定型交通检测器空间配置的4条原则和配置密度优化步骤,提出基于数据挖掘技术的固定型交通检测器配置优化方法。设计6种高速公路出口匝道的固定型交通检测器配置密度方案作为实例研究对象,运用数据挖掘技术的时间序列指数平滑方法、AR IM A方法和神经网络方法分别建立高速公路出口匝道小时交通量W in ters预测模型、AR IM A预测模型及神经网络预测模型。采用网格搜索技术确定W in ters模型参数,设计一种比传统AR IM A模型参数估计方法更精确的算法程序,来估计AR IM A模型参数,采用3项误差指标评价模型预测效果。根据预测结果及高速公路事件管理交通参数精度要求确定可行方案及最佳方案。实例研究表明,在保证满足ITS对交通参数精度要求的同时,通过数据挖掘技术降低了交通流信息采集固定型检测器的配置密度及成本。展开更多
基金supported by the National Natural Science Foundation of China(Nos.41374130 and 41604154)Science and Technology Program of Sichuan,China(No.2017GZ0359)+1 种基金Science and Technology Support Program of Sichuan,China(No.2015JY0007)Open Foundation for Artificial Intelligence Key Laboratory of Sichuan Province of China(No.2016RYJ08)
文摘Efficiency is an important factor in quantitative and qualitative analysis of radionuclides, and the gamma point source efficiency is related to the radial angle,detection distance, and gamma-ray energy. In this work, on the basis of a back-propagation(BP) neural network model,a method to determine the gamma point source efficiency is developed and validated. The efficiency of the point sources ^(137)Cs and ^(60)Co at discrete radial angles, detection distances, and gamma-ray energies is measured, and the BP neural network prediction model is constructed using MATLAB. The gamma point source efficiencies at different radial angles, detection distances, and gamma-ray energies are predicted quickly and accurately using this nonlinear prediction model. The results show that the maximum error between the predicted and experimental values is 3.732% at 661.661 keV, 11π/24, and 35 cm, and those under other conditions are less than 3%. The gamma point source efficiencies obtained using the BP neural network model are in good agreement with experimental data.
文摘A sequence detector based on Hopfield Neural network(HNN) is presented, which is used to estimate the transmitted sequences from the received signals in mobile communications. In order to avoid the convergence of HNN in local minima, a decreasing step algorithm (DSA) is proposed to search the optimum sequence quickly on the basis of the traditional simulated annealing (SA) algorithm. Computer simulation results show that the new HNN detector provides almost the same performance as that of the Viterbi detector while needs less computations and memory capacity, thus it is more feasible in hardware implementation and long constraint convolutional decoding.
文摘A laser collimating system based on 2-D position sensitive detector (PSD) is presented in this paper. The working principle of PSD is depicted in detail. A calibration device was developed to check the nonlinearity errors of PSD and a multilayer feedforward neural network based on error back-propagation algorithm was used to compensate errors. With the aid of computer-based data acquisition system, an automatic dynamic measuring process was realized. A series of experiments, including comparison tests with laser interferometer, were done to evaluate the performance of the measuring system. The experimental results show that the spatial straightness errors of guide rails can be measured with high accuracy. The maximum differences between the device and laser interferometer are 0.027 mm in Y direction, and 0.053 mm in X direction in the measuring distance of 6 m.
基金supported by the National Magnetic Confinement Fusion Science Program (Grant No. 2010GB111002)
文摘The unfolding of neutron spectra from the pulse height distribution measured by a BC501A scintillation detector is accomplished by the application of artificial neural networks (ANN). A simple linear neural network without biases and hidden layers is adopted. A set of monoenergetic detector response functions in the energy range from 0.25 MeV to 16 MeV with an energy interval of 0.25 MeV are generated by the Monte Carlo code O5S in the training phase of the unfolding process. The capability of ANN was demonstrated successfully using the Monte Carlo data itself and experimental data obtained from the Am-Be neutron source and D-T neutron source.
文摘Application of Neural Network to signal detection in CDMA multi-user communications Gaussian channel is investigated. This paper is motivated by the fact that, in a multi-user CDMA system. the conventional receiver suffers severe performance degradation as the relative powers of the interfering signals become large(i.e. 'near-far problem'). Furthermore, in many cases, the optimum receiver which alleviates the near-far problem, is too complex to be of practical use. And by viewing this optimum multi-user detector problem in CDMA channel as an optimum nonlinear classification decision problem. we apply the Probabilistic Neural Network algorithm, which has the capacity of arbitrary nonlinear transformation, adaptive learning and tracking to implement this classification decision optimally and adaptively The performance of the Proposes neural detector is evaluated via computer simulations in terms of probability of detection and it is compared with those of the existing neural and conventional detector schemes in a multi-user environment.
文摘结合固定型交通检测器空间配置的4条原则和配置密度优化步骤,提出基于数据挖掘技术的固定型交通检测器配置优化方法。设计6种高速公路出口匝道的固定型交通检测器配置密度方案作为实例研究对象,运用数据挖掘技术的时间序列指数平滑方法、AR IM A方法和神经网络方法分别建立高速公路出口匝道小时交通量W in ters预测模型、AR IM A预测模型及神经网络预测模型。采用网格搜索技术确定W in ters模型参数,设计一种比传统AR IM A模型参数估计方法更精确的算法程序,来估计AR IM A模型参数,采用3项误差指标评价模型预测效果。根据预测结果及高速公路事件管理交通参数精度要求确定可行方案及最佳方案。实例研究表明,在保证满足ITS对交通参数精度要求的同时,通过数据挖掘技术降低了交通流信息采集固定型检测器的配置密度及成本。
