ID 原文 译文
44776 基于KDD CUP 99数据集的实验结果表明，相较遗传算子整合粒子群算法(CMPSO)、粒子群算法(PSO)和粒子群联合禁忌算法，IPSO-TS 减少了至少 29.2%的特征，缩短了至少 15%的平均检测时间，提高了至少 2.96%的平均分类准确率。 Compared with genetic algorithm integrated particle swarm optimization (CMPSO), particle swarm optimization (PSO)and PSO-TS algorithms, experimental results based on the KDD CUP 99 dataset show that the method reduces the features by about 29.2% , shortens about 15% of the average detection time, and increases about 2.96% of the average classification accuracy.
44777 高精度车内定位技术是提供车内智能服务、进行车内用户行为习惯分析等应用的基础，有重要实用价值。 High precision in-vehicle positioning is the basis of providing smart in-vehicle service, passengers' behavior analysis and other issues, and has important practical value.
44778 针对无线信号传输易受环境影响的问题， The RSSI (received signal strength indicator) values of BLE(Bluetooth low energy) can be used to do analysis and computation in location system.
44779 对车内定位提出了一种基于蓝牙多信道多RSSI 值（multi-channel multi-RSSIvalues）的车内定位方法 VehLoc。 To deal with the problem that RSSI is vulnerable to environmental issues, an in-vehicle location method called VehLoc based on BLE multi-channel multi-RSSI values was proposed.
44780 接收端在传统的采集蓝牙 RSSI 信号的基础上，同时记录信号的信道来源，通过使用 3 个蓝牙信标在其不同信道的 RSSI 值对使用者终端在车内的位置进行粗细粒度与分布相结合的区域分析和位置判断。 By using a plurality of Bluetooth transmitters, the location of the receiving terminals in the vehicle was analyzed by combining the coarse, fine classifier and distribution fitting of the user's RSSI values in different channels.
44781 实验结果表明，VehLoc 定位方法对车内 5 个主要位置的分类正确率均可达 90%。 The experimental results show that the average accuracy of VehLoc in the five main positions in-vehicle classification can reach 90%.
44782 针对目前纸币图像特征提取与分析方法缺少对相位结构信息有效描述的问题，提出一种基于四元共空间模式的特征提取算法。 New feature extraction algorithm was proposed based on quaternion common spatial pattern in order to solve the lack of effective description of phase information in the banknote feature extraction and analysis.
44783 该算法首先采用四元矩阵描述纸币图像的相位与幅值信息，并对四元复合厄米特协方差矩阵进行对角化； Firstly, the quarter-nion matrix was utilized to describe the phase information of the banknote image, and made diagonalization of quaternion composite Hermitian matrix.
44784 然后将样本向量输入到复合四元滤波器中， Secondly, the sample vector was input to the composite quaternion filter.
44785 并将分解得到的四元矩阵实部与虚部的方差作为纸币特征向量； The extracted feature vector was obtained by using the variance of the real part and imaginary part.