ID 原文 译文
24745 针对非协作通信下多径信道直接序列扩频信号伪随机（PN，Pseudorandom）码的估计难题，本文在分析信号二阶统计特性的基础上，提出了一种基于最大似然（ML，Maximum Likelihood）的 PN 码和多径信道联合盲估计的方法。 To solve the problem of pseudorandom (PN) codes estimation for direct sequence spread spectrum (DSSS) signals over multipath channels in non-cooperative communication, based on analyzing the second-order statistics of the signals, a method for joint blind estimation of PN codes and channels with maximum likelihood (ML) is proposed.
24746 该方法首先建立 PN 码和信道序列的最大似然数学模型，然后通过交替转换数学模型和使用迭代最小二乘投影（ILSP，Iterative Least Square Projection）算法实现 PN 码和多径信道的联合估计。 First, we establish a ML mathematical model of PN codes and multipath channels. Then, we iteratively transform the mathematical model and use the iterative least square projection (ILSP) algorithm to estimate the PN code and channel.
24747 为了进一步降低算法复杂度和避免矩阵求逆，本文给出了算法的自适应求解方式。 Furthermore, to reduce the complexity of the algorithm and avoid the matrix inversion, we present an adaptive rule of our algorithm.
24748 此外，针对低信噪比下信道估计误差引起 PN 码的估计精度下降的问题，本文提出了一种基于迭代总体最小二乘投影的改进算法。 Finally, to avoid the decrease of PN code estimation accuracy caused by the channel estimation error, especially under low signal-to-noise ratio, an improved algorithm based on the iterative total least squares projection (ITLSP) is presented.
24749 所提算法不受 PN 码码型限制，并通过仿真实验验证了算法的有效性。 The proposed methods are applicable to all types of PN codes and the simulation results are presented to demonstrate the effectiveness of the algorithms.
24750 为解决工业网络安全防护中工艺数据异常检测误报率较高的问题，本文提出一种基于时间序列的异常检测方法。 In order to solve the problem of high false alarm rate of abnormal detection of process data in industrial network security protection, this paper proposes an anomaly detection method based on time series.
24751 该方法对工艺数据进行相关性分析、向量映射等处理，再采用堆叠自编码神经网络（SAE）对工艺数据特征进行降维，根据工艺数据在传输序列间的相互关联性，设计基于长短期记忆神经网络（LSTM）的异常检测模型，最后进行工艺数据异常检测仿真实验验证分析。 In this method, the process data is analyzed by association analysis and vector mapping, and the stacked auto-encoder neural network (SAE) is used to reduce the dimension of process data features. According to the correlation of process data in the transmission sequence, an anomaly detection model based on long and short term memory neural network (LSTM) is designed. Finally, the simulation analysis of abnormal detection of process data is carried out.
24752 实验结果表明，基于时间序列的异常检测模型能有效提高工艺数据异常检测准确率，并且误报率要低于传统隐马尔可夫异常检测模型，同时获得较好的异常检测实时性。 The experimental results show that the anomaly detection model based on time series can greatly improve the accuracy of process data anomaly detection, and the false positive rate is lower than the traditional hidden Markov anomaly detection model, and at the same time get better real-time performance of anomaly detection.
24753 硅基光电晶体管在高频通信、自动控制、电力系统领域具有广泛的应用前景。 Silicon-based phototransistors have broad application prospects in the fields of high-frequency communication, automatic control, and power systems.
24754 从系统验证和仿真的角度，迫切需要建立光电晶体管的等效电路模型，该模型需要包含电学特性和光学特性。 From the perspective of system verification and simulation, there is an urgent need to establish an equivalent circuit model of phototransistors, which needs to include electrical and optical characteristics.