With the development of intelligent and netw orking technology in automobile,the malicious attacks against in-vehicle CAN netw orks are increasing day by day,and the problem of information safety in automobile is aggr...With the development of intelligent and netw orking technology in automobile,the malicious attacks against in-vehicle CAN netw orks are increasing day by day,and the problem of information safety in automobile is aggravated. In this regard,this paper analyzes the security loopholes and threats w hich the CAN bus faced,put forw ard a kind of anomaly detection algorithm for vehicle CAN bus. The method uses support vector machine algorithm to distinguish betw een normal message and abnormal message,so as to realize the CAN bus anomaly detection. Theoretical and experimental studies show that this method can effectively detect abnormal packets in the CAN bus w ith a detection rate of over 90%,w hich can effectively resist malicious attacks such as tampering and cheating on the vehicle CAN bus.展开更多
This paper examines whether index inclusion has information content and the downward-sloping demand curve hypothesis in China. We investigate the stock price and volume effects when stocks are included in two major st...This paper examines whether index inclusion has information content and the downward-sloping demand curve hypothesis in China. We investigate the stock price and volume effects when stocks are included in two major stock indexes, the Shanghai Stock Exchange 30 Index （SH30） and the Shenzhen Component 40 Index （SZ40）. Furthermore, we also study the performance changes after index inclusion. We find significant price and volume increases for the stocks selected by the SH30 when the index was created and announced. Thus, the original inclusion may not be an information-free event. For subsequent index inclusions, we observe significant abnormal returns but not abnormal trade volume around the announcement date. However, the stock returns quickly reversed at the post-announcement period. Moreover, the financial performance of index included firms does not improve. The evidence does not support the price pressure hypothesis in China.展开更多
为保障医院信息网络的安全管理,避免医疗信息泄露,提出了基于深度生成模型的医院网络异常信息入侵检测算法。采用二进制小波变换方法,多尺度分解医院网络运行数据,结合自适应软门限去噪系数提取有效数据。运用最优运输理论中的Wasserst...为保障医院信息网络的安全管理,避免医疗信息泄露,提出了基于深度生成模型的医院网络异常信息入侵检测算法。采用二进制小波变换方法,多尺度分解医院网络运行数据,结合自适应软门限去噪系数提取有效数据。运用最优运输理论中的Wasserstein距离算法与MMD(Maximun Mean Discrepancy)距离算法,在深度生成模型中,对医院网络数据展开降维处理。向异常检测模型中输入降维后网络正常运行数据样本,并提取样本特征。利用深度学习策略中的Adam算法,生成异常信息判别函数,通过待测网络运行数据与正常网络运行数据的特征对比,实现医院网络异常信息入侵检测。实验结果表明,算法能实现对医院网络异常信息入侵的高效检测,精准检测多类型网络入侵行为,为医疗机构网络运行提供安全保障。展开更多
为准确识别乘客搭乘自动扶梯时的异常行为,避免安全事故的发生,提出了一种基于人体骨架的扶梯乘客异常行为识别方法。首先使用YOLOX-Tiny对视频中乘客位置进行检测,通过Alphapose算法提取骨骼关键点坐标,降低复杂背景的干扰;再使用多流...为准确识别乘客搭乘自动扶梯时的异常行为,避免安全事故的发生,提出了一种基于人体骨架的扶梯乘客异常行为识别方法。首先使用YOLOX-Tiny对视频中乘客位置进行检测,通过Alphapose算法提取骨骼关键点坐标,降低复杂背景的干扰;再使用多流膨胀3D卷积模块增强时空特征提取能力,聚合乘客骨架的全局特征;然后将其输入改进后的时空图卷积网络中提取乘客骨架信息,通过MS-TCN模块扩大接受域以增强时间特征的提取,联合人体关键点注意力模块(Key Point Attention Module,KPAM)提升网络对相似动作的关键骨架的关注度;最后通过Softmax对异常动作进行分类。采集扶梯运行现场视频制作数据集,试验结果表明,本文算法对乘客异常行为的识别精度达到96.1%,可应用于扶梯现场的视频监控系统,提高安全管理信息化水平。展开更多
针对传统异常用电检测在面临高维数据中的维数诅咒,以及不相关特征对异常检测的影响,造成检测精度低等问题,提出了一种基于无监督密度子空间选择的孤立森林检测算法。首先,提出了一种有效的基于密度的紧凑数据表示方法,提高了子空间选...针对传统异常用电检测在面临高维数据中的维数诅咒,以及不相关特征对异常检测的影响,造成检测精度低等问题,提出了一种基于无监督密度子空间选择的孤立森林检测算法。首先,提出了一种有效的基于密度的紧凑数据表示方法,提高了子空间选择策略的效率。然后,应用最小冗余-最大相关-密度准则(min-redundancy-maximum-relevance-to-density,mRMRD),用于选择基于互信息的相关子空间。最后,在相关子空间中构建隔离树并集成孤立森林,实现对异常用电数据的检测。通过实验分析,与传统检测算法相比,所提方法在准确率、ROC曲线下面积(area under curve,AUC)、F 1指标上均有提升,提高了异常用电检测的效果。同时,灵敏性分析也验证了无监督密度子空间孤立森林检测算法的有效性。展开更多
The high-frequency(HF)modeling of induction motors plays a key role in predicting the motor terminal overvoltage and conducted emissions in a motor drive system.In this study,a physics informed neural network-based HF...The high-frequency(HF)modeling of induction motors plays a key role in predicting the motor terminal overvoltage and conducted emissions in a motor drive system.In this study,a physics informed neural network-based HF modeling method,which has the merits of high accuracy,good versatility,and simple parameterization,is proposed.The proposed model of the induction motor consists of a three-phase equivalent circuit with eighteen circuit elements per phase to ensure model accuracy.The per phase circuit structure is symmetric concerning its phase-start and phase-end points.This symmetry enables the proposed model to be applicable for both star-and delta-connected induction motors without having to recalculate the circuit element values when changing the motor connection from star to delta and vice versa.Motor physics knowledge,namely per-phase impedances,are used in the artificial neural network to obtain the values of the circuit elements.The parameterization can be easily implemented within a few minutes using a common personal computer(PC).Case studies verify the effectiveness of the proposed HF modeling method.展开更多
文摘With the development of intelligent and netw orking technology in automobile,the malicious attacks against in-vehicle CAN netw orks are increasing day by day,and the problem of information safety in automobile is aggravated. In this regard,this paper analyzes the security loopholes and threats w hich the CAN bus faced,put forw ard a kind of anomaly detection algorithm for vehicle CAN bus. The method uses support vector machine algorithm to distinguish betw een normal message and abnormal message,so as to realize the CAN bus anomaly detection. Theoretical and experimental studies show that this method can effectively detect abnormal packets in the CAN bus w ith a detection rate of over 90%,w hich can effectively resist malicious attacks such as tampering and cheating on the vehicle CAN bus.
文摘This paper examines whether index inclusion has information content and the downward-sloping demand curve hypothesis in China. We investigate the stock price and volume effects when stocks are included in two major stock indexes, the Shanghai Stock Exchange 30 Index （SH30） and the Shenzhen Component 40 Index （SZ40）. Furthermore, we also study the performance changes after index inclusion. We find significant price and volume increases for the stocks selected by the SH30 when the index was created and announced. Thus, the original inclusion may not be an information-free event. For subsequent index inclusions, we observe significant abnormal returns but not abnormal trade volume around the announcement date. However, the stock returns quickly reversed at the post-announcement period. Moreover, the financial performance of index included firms does not improve. The evidence does not support the price pressure hypothesis in China.
文摘为保障医院信息网络的安全管理,避免医疗信息泄露,提出了基于深度生成模型的医院网络异常信息入侵检测算法。采用二进制小波变换方法,多尺度分解医院网络运行数据,结合自适应软门限去噪系数提取有效数据。运用最优运输理论中的Wasserstein距离算法与MMD(Maximun Mean Discrepancy)距离算法,在深度生成模型中,对医院网络数据展开降维处理。向异常检测模型中输入降维后网络正常运行数据样本,并提取样本特征。利用深度学习策略中的Adam算法,生成异常信息判别函数,通过待测网络运行数据与正常网络运行数据的特征对比,实现医院网络异常信息入侵检测。实验结果表明,算法能实现对医院网络异常信息入侵的高效检测,精准检测多类型网络入侵行为,为医疗机构网络运行提供安全保障。
文摘为准确识别乘客搭乘自动扶梯时的异常行为,避免安全事故的发生,提出了一种基于人体骨架的扶梯乘客异常行为识别方法。首先使用YOLOX-Tiny对视频中乘客位置进行检测,通过Alphapose算法提取骨骼关键点坐标,降低复杂背景的干扰;再使用多流膨胀3D卷积模块增强时空特征提取能力,聚合乘客骨架的全局特征;然后将其输入改进后的时空图卷积网络中提取乘客骨架信息,通过MS-TCN模块扩大接受域以增强时间特征的提取,联合人体关键点注意力模块(Key Point Attention Module,KPAM)提升网络对相似动作的关键骨架的关注度;最后通过Softmax对异常动作进行分类。采集扶梯运行现场视频制作数据集,试验结果表明,本文算法对乘客异常行为的识别精度达到96.1%,可应用于扶梯现场的视频监控系统,提高安全管理信息化水平。
文摘针对传统异常用电检测在面临高维数据中的维数诅咒,以及不相关特征对异常检测的影响,造成检测精度低等问题,提出了一种基于无监督密度子空间选择的孤立森林检测算法。首先,提出了一种有效的基于密度的紧凑数据表示方法,提高了子空间选择策略的效率。然后,应用最小冗余-最大相关-密度准则(min-redundancy-maximum-relevance-to-density,mRMRD),用于选择基于互信息的相关子空间。最后,在相关子空间中构建隔离树并集成孤立森林,实现对异常用电数据的检测。通过实验分析,与传统检测算法相比,所提方法在准确率、ROC曲线下面积(area under curve,AUC)、F 1指标上均有提升,提高了异常用电检测的效果。同时,灵敏性分析也验证了无监督密度子空间孤立森林检测算法的有效性。
文摘The high-frequency(HF)modeling of induction motors plays a key role in predicting the motor terminal overvoltage and conducted emissions in a motor drive system.In this study,a physics informed neural network-based HF modeling method,which has the merits of high accuracy,good versatility,and simple parameterization,is proposed.The proposed model of the induction motor consists of a three-phase equivalent circuit with eighteen circuit elements per phase to ensure model accuracy.The per phase circuit structure is symmetric concerning its phase-start and phase-end points.This symmetry enables the proposed model to be applicable for both star-and delta-connected induction motors without having to recalculate the circuit element values when changing the motor connection from star to delta and vice versa.Motor physics knowledge,namely per-phase impedances,are used in the artificial neural network to obtain the values of the circuit elements.The parameterization can be easily implemented within a few minutes using a common personal computer(PC).Case studies verify the effectiveness of the proposed HF modeling method.
