ID 原文 译文
39076 针对S模式1090 MHz扩展电文(1090ES)的报头检测在低信噪比下虚警概率高的问题，提出基于报头多脉冲匹配滤波的恒虚警率报头检测方法。 To solve the problem of high false alarm rate for the preamble detection of Mode S 1090 MHz Extended Squitter(1090 ES) with low signal to noise ratio(SNR), a Constant False Alarm Rate(CFAR) preamble detection method based on multi-pulse matching filtering is proposed.
39077 由于检测门限是利用报头低电平期间的样本确定的，所以该方法对1090ES的数据块中的伪报头的误检具有一定的抑制能力。 Because the detection threshold is determined with the samples received during the low level of preamble, the proposed method has a certain suppression ability against false preamble in 1090 ES data block.
39078 仿真结果表明，在低信噪比环境下，该文方法相对于传统1090ES报头检测方法具备较好的检测性能，且较好实现1090ES数据块中伪报头的抑制，减轻了后续设备的数据处理负荷。 Simulation results show that, under lower SNR, the method proposed in this paper has better detection performance than the classification methods for detecting the 1090 ES preamble, and can suppress the false preamble in data block of 1090 ES well. Furthermore, the data processing load of subsequent equipment is reduced.
39079 为提高复杂网络环境中入侵检测模型的准确性和实时性，提出一种基于随机森林和极端梯度提升树(XGBoost)的网络入侵检测模型RF-XGB。 To improve the accuracy and real-time performance of intrusion detection models in complex network environments, a network intrusion detection model based on random forest and eXtreme Gradient Boosting(XGBoost) is proposed.
39080 首先针对随机森林算法计算特征重要性的特点，设计混合特征选择方法高效筛选出最有价值的特征子集; First, the feature importance is calculated based on the random forest algorithm. A hybrid feature selection method combining filtering and embedded is used to reduce the feature dimension of the dataset.
39081 在XGBoost算法中引入代价敏感函数来提高对少样本类别的检测率，使用网格法调参降低模型复杂度。 When detecting the sample category, the XGBoost algorithm based on cost-sensitive function and grid method tuning is used to improve Model accuracy.
39082 实验仿真结果表明，与其他机器学习算法相比，所提出的模型在具备更高检测精度的情况下减少了50%以上的处理时间，并在噪声影响下具有较好的鲁棒性和自适应性。 Experimental simulation results show that compared with other machine learning algorithms, the proposed model greatly reduces processing time by more than 50% with higher detection accuracy, and has better robustness and adaptability.
39083 传统频谱感知算法性能在低信噪比下不够理想，在高信噪比下较好，算法性能随信噪比降低逐渐变差。 The performance of traditional spectrum sensing is not ideal at low signal to noise ratio(SNR) and good at high SNR. As the SNR decreases, the performance of algorithms gradually deteriorates.
39084 本文提出了基于信号能量分布拟合优度的长短时记忆网络频谱感知算法，利用授权用户信号存在时的接收信号为基础，计算接收信号的能量分布，并将通过拟合优度算法得到的距离值作为特征构造特征向量， This paper proposes a spectrum sensing algorithm based on long short-term memory(LSTM) network and the goodness of fit of the distribution of signal energy. This method calculates the distance value form the energy distribution of the received signal when primary user signals exist.
39085 然后将特征向量输入长短时记忆网络训练得到模型， Then the feature vector consists of the distance value is input into a LSTM network training to obtain a model.