Aiming at the problem of low accuracy of traditional target detection methods for target detection in endoscopes in substation environments, a CNN-based real-time detection method for masked targets is proposed. The m...Aiming at the problem of low accuracy of traditional target detection methods for target detection in endoscopes in substation environments, a CNN-based real-time detection method for masked targets is proposed. The method adopts the overall design of backbone network, detection network and algorithmic parameter optimisation method, completes the model training on the self-constructed occlusion target dataset, and adopts the multi-scale perception method for target detection. The HNM algorithm is used to screen positive and negative samples during the training process, and the NMS algorithm is used to post-process the prediction results during the detection process to improve the detection efficiency. After experimental validation, the obtained model has the multi-class average predicted value (mAP) of the dataset. It has general advantages over traditional target detection methods. The detection time of a single target on FDDB dataset is 39 ms, which can meet the need of real-time target detection. In addition, the project team has successfully deployed the method into substations and put it into use in many places in Beijing, which is important for achieving the anomaly of occlusion target detection.展开更多
According to the characteristics of single-phase circuits and demand of using active filter for real-time detecting harmonic and reactive currents, a detecting method based on Fryze＇s power definition is proposed. Th...According to the characteristics of single-phase circuits and demand of using active filter for real-time detecting harmonic and reactive currents, a detecting method based on Fryze＇s power definition is proposed. The results of theoretical analysis and simula- tion show that the proposed method is effective in realtime detecting of instantaneous harmonic and reactive currents in single-phase circuits. When only detecting the total reactive currents, this method does not need a phase-locked loop circuit, and it also can be used in some special applications to provide different compensations on the ground of different requirements of electric network. Compared with the other methods based on the theory of instantaneous reactive power, this method is simple and easy to realize.展开更多
This paper examines how cybersecurity is developing and how it relates to more conventional information security. Although information security and cyber security are sometimes used synonymously, this study contends t...This paper examines how cybersecurity is developing and how it relates to more conventional information security. Although information security and cyber security are sometimes used synonymously, this study contends that they are not the same. The concept of cyber security is explored, which goes beyond protecting information resources to include a wider variety of assets, including people [1]. Protecting information assets is the main goal of traditional information security, with consideration to the human element and how people fit into the security process. On the other hand, cyber security adds a new level of complexity, as people might unintentionally contribute to or become targets of cyberattacks. This aspect presents moral questions since it is becoming more widely accepted that society has a duty to protect weaker members of society, including children [1]. The study emphasizes how important cyber security is on a larger scale, with many countries creating plans and laws to counteract cyberattacks. Nevertheless, a lot of these sources frequently neglect to define the differences or the relationship between information security and cyber security [1]. The paper focus on differentiating between cybersecurity and information security on a larger scale. The study also highlights other areas of cybersecurity which includes defending people, social norms, and vital infrastructure from threats that arise from online in addition to information and technology protection. It contends that ethical issues and the human factor are becoming more and more important in protecting assets in the digital age, and that cyber security is a paradigm shift in this regard [1].展开更多
In this paper, we introduce a system architecture for a patient centered mobile health monitoring (PCMHM) system that deploys different sensors to determine patients’ activities, medical conditions, and the cause of ...In this paper, we introduce a system architecture for a patient centered mobile health monitoring (PCMHM) system that deploys different sensors to determine patients’ activities, medical conditions, and the cause of an emergency event. This system combines and analyzes sensor data to produce the patients’ detailed health information in real-time. A central computational node with data analyzing capability is used for sensor data integration and analysis. In addition to medical sensors, surrounding environmental sensors are also utilized to enhance the interpretation of the data and to improve medical diagnosis. The PCMHM system has the ability to provide on-demand health information of patients via the Internet, track real-time daily activities and patients’ health condition. This system also includes the capability for assessing patients’ posture and fall detection.展开更多
随着交通愈加发达,道路愈加拥堵,如何实时准确地获取车辆基本信息以便交通部门及时管理特定路段和路口的车辆显得日益重要.对交通视频中车辆的检测和识别,不仅需要实时检测,还要保证其准确性.针对实际情况中车辆之间的遮挡、光照的变化...随着交通愈加发达,道路愈加拥堵,如何实时准确地获取车辆基本信息以便交通部门及时管理特定路段和路口的车辆显得日益重要.对交通视频中车辆的检测和识别,不仅需要实时检测,还要保证其准确性.针对实际情况中车辆之间的遮挡、光照的变化、阴影、道路旁树枝的晃动、背景中固定对象的移动等因素严重影响检测与识别的精度的问题,提出基于Faster-RCNN(Faster-Regions with CNN features)的车辆实时检测改进算法.首先采用k-means算法对KITTI数据集的目标框进行聚类,得到合适的长宽比,并增加一组尺度(64~2)以适应差异较大的车辆尺寸;然后改进区域提案网络,降低计算量,优化网络结构;最后在训练阶段采用多尺度策略,降低漏检率,提高精确率.实验结果表明:改进后的车辆检测算法的mAP(mean Average Precision)达到了82.20%,检测速率为每张照片耗时0.03875 s,基本能够满足车辆实时检测的需求.展开更多
针对深度学习方法运用于入侵检测时需要大量标注数据集和难以实时检测的缺陷,利用网络流量中正常数据多于异常数据的一般规律,提出一种结合集成K-means聚类和自编码器的EKM-AE(ensemble K-means and autoencoder)入侵检测方法.首先通过...针对深度学习方法运用于入侵检测时需要大量标注数据集和难以实时检测的缺陷,利用网络流量中正常数据多于异常数据的一般规律,提出一种结合集成K-means聚类和自编码器的EKM-AE(ensemble K-means and autoencoder)入侵检测方法.首先通过集成K-means聚类从实时抓取的网络流量中得出正常样例,用于训练自编码器,然后由完成训练的自编码器执行入侵检测.在虚拟局域网主机环境下进行了入侵检测实验,结果表明,在绝大多数实际应用场景(正常流量多于异常流量)下该方法具有良好的检测性能,且具有全过程无监督、可实时在线检测的优点,对主机网络安全有良好的提升作用.展开更多
针对现有人脸检测深度学习算法计算量大,难以移植到嵌入式平台,无法满足移动设备实时性和便捷性需求的问题,提出一种基于YOLO(You Only Look Once)算法的适用于嵌入式平台的小型人脸检测网络E-YOLO(Enhance-YOLO)。借鉴YOLO算法的思想,...针对现有人脸检测深度学习算法计算量大,难以移植到嵌入式平台,无法满足移动设备实时性和便捷性需求的问题,提出一种基于YOLO(You Only Look Once)算法的适用于嵌入式平台的小型人脸检测网络E-YOLO(Enhance-YOLO)。借鉴YOLO算法的思想,将人脸检测问题转换为回归问题,将待检测的图像均分为S×S个单元格,每个单元格检测落在单元格内的目标。通过修改YOLO网络模型中的卷积神经网络结构,提高其检测的准确性,同时减少网络结构中卷积核的数目,降低模型的大小。实验结果表明,E-YOLO模型大小为43MB,视频的检测帧率为26FPS,在WIDERFACE和FDDB数据集上均有较高的准确率和检测速度,可以实现在嵌入式平台下的实时人脸检测。展开更多
Over recent years, Convolutional Neural Networks (CNN) has improved performance on practically every image-based task, including Content-Based Image Retrieval (CBIR). Nevertheless, since features of CNN have altered o...Over recent years, Convolutional Neural Networks (CNN) has improved performance on practically every image-based task, including Content-Based Image Retrieval (CBIR). Nevertheless, since features of CNN have altered orientation, training a CBIR system to detect and correct the angle is complex. While it is possible to construct rotation-invariant features by hand, retrieval accuracy will be low because hand engineering only creates low-level features, while deep learning methods build high-level and low-level features simultaneously. This paper presents a novel approach that combines a deep learning orientation angle detection model with the CBIR feature extraction model to correct the rotation angle of any image. This offers a unique construction of a rotation-invariant CBIR system that handles the CNN features that are not rotation invariant. This research also proposes a further study on how a rotation-invariant deep CBIR can recover images from the dataset in real-time. The final results of this system show significant improvement as compared to a default CNN feature extraction model without the OAD.展开更多
文摘Aiming at the problem of low accuracy of traditional target detection methods for target detection in endoscopes in substation environments, a CNN-based real-time detection method for masked targets is proposed. The method adopts the overall design of backbone network, detection network and algorithmic parameter optimisation method, completes the model training on the self-constructed occlusion target dataset, and adopts the multi-scale perception method for target detection. The HNM algorithm is used to screen positive and negative samples during the training process, and the NMS algorithm is used to post-process the prediction results during the detection process to improve the detection efficiency. After experimental validation, the obtained model has the multi-class average predicted value (mAP) of the dataset. It has general advantages over traditional target detection methods. The detection time of a single target on FDDB dataset is 39 ms, which can meet the need of real-time target detection. In addition, the project team has successfully deployed the method into substations and put it into use in many places in Beijing, which is important for achieving the anomaly of occlusion target detection.
文摘According to the characteristics of single-phase circuits and demand of using active filter for real-time detecting harmonic and reactive currents, a detecting method based on Fryze＇s power definition is proposed. The results of theoretical analysis and simula- tion show that the proposed method is effective in realtime detecting of instantaneous harmonic and reactive currents in single-phase circuits. When only detecting the total reactive currents, this method does not need a phase-locked loop circuit, and it also can be used in some special applications to provide different compensations on the ground of different requirements of electric network. Compared with the other methods based on the theory of instantaneous reactive power, this method is simple and easy to realize.
文摘This paper examines how cybersecurity is developing and how it relates to more conventional information security. Although information security and cyber security are sometimes used synonymously, this study contends that they are not the same. The concept of cyber security is explored, which goes beyond protecting information resources to include a wider variety of assets, including people [1]. Protecting information assets is the main goal of traditional information security, with consideration to the human element and how people fit into the security process. On the other hand, cyber security adds a new level of complexity, as people might unintentionally contribute to or become targets of cyberattacks. This aspect presents moral questions since it is becoming more widely accepted that society has a duty to protect weaker members of society, including children [1]. The study emphasizes how important cyber security is on a larger scale, with many countries creating plans and laws to counteract cyberattacks. Nevertheless, a lot of these sources frequently neglect to define the differences or the relationship between information security and cyber security [1]. The paper focus on differentiating between cybersecurity and information security on a larger scale. The study also highlights other areas of cybersecurity which includes defending people, social norms, and vital infrastructure from threats that arise from online in addition to information and technology protection. It contends that ethical issues and the human factor are becoming more and more important in protecting assets in the digital age, and that cyber security is a paradigm shift in this regard [1].
文摘In this paper, we introduce a system architecture for a patient centered mobile health monitoring (PCMHM) system that deploys different sensors to determine patients’ activities, medical conditions, and the cause of an emergency event. This system combines and analyzes sensor data to produce the patients’ detailed health information in real-time. A central computational node with data analyzing capability is used for sensor data integration and analysis. In addition to medical sensors, surrounding environmental sensors are also utilized to enhance the interpretation of the data and to improve medical diagnosis. The PCMHM system has the ability to provide on-demand health information of patients via the Internet, track real-time daily activities and patients’ health condition. This system also includes the capability for assessing patients’ posture and fall detection.
文摘随着交通愈加发达,道路愈加拥堵,如何实时准确地获取车辆基本信息以便交通部门及时管理特定路段和路口的车辆显得日益重要.对交通视频中车辆的检测和识别,不仅需要实时检测,还要保证其准确性.针对实际情况中车辆之间的遮挡、光照的变化、阴影、道路旁树枝的晃动、背景中固定对象的移动等因素严重影响检测与识别的精度的问题,提出基于Faster-RCNN(Faster-Regions with CNN features)的车辆实时检测改进算法.首先采用k-means算法对KITTI数据集的目标框进行聚类,得到合适的长宽比,并增加一组尺度(64~2)以适应差异较大的车辆尺寸;然后改进区域提案网络,降低计算量,优化网络结构;最后在训练阶段采用多尺度策略,降低漏检率,提高精确率.实验结果表明:改进后的车辆检测算法的mAP(mean Average Precision)达到了82.20%,检测速率为每张照片耗时0.03875 s,基本能够满足车辆实时检测的需求.
文摘针对深度学习方法运用于入侵检测时需要大量标注数据集和难以实时检测的缺陷,利用网络流量中正常数据多于异常数据的一般规律,提出一种结合集成K-means聚类和自编码器的EKM-AE(ensemble K-means and autoencoder)入侵检测方法.首先通过集成K-means聚类从实时抓取的网络流量中得出正常样例,用于训练自编码器,然后由完成训练的自编码器执行入侵检测.在虚拟局域网主机环境下进行了入侵检测实验,结果表明,在绝大多数实际应用场景(正常流量多于异常流量)下该方法具有良好的检测性能,且具有全过程无监督、可实时在线检测的优点,对主机网络安全有良好的提升作用.
文摘针对现有人脸检测深度学习算法计算量大,难以移植到嵌入式平台,无法满足移动设备实时性和便捷性需求的问题,提出一种基于YOLO(You Only Look Once)算法的适用于嵌入式平台的小型人脸检测网络E-YOLO(Enhance-YOLO)。借鉴YOLO算法的思想,将人脸检测问题转换为回归问题,将待检测的图像均分为S×S个单元格,每个单元格检测落在单元格内的目标。通过修改YOLO网络模型中的卷积神经网络结构,提高其检测的准确性,同时减少网络结构中卷积核的数目,降低模型的大小。实验结果表明,E-YOLO模型大小为43MB,视频的检测帧率为26FPS,在WIDERFACE和FDDB数据集上均有较高的准确率和检测速度,可以实现在嵌入式平台下的实时人脸检测。
文摘Over recent years, Convolutional Neural Networks (CNN) has improved performance on practically every image-based task, including Content-Based Image Retrieval (CBIR). Nevertheless, since features of CNN have altered orientation, training a CBIR system to detect and correct the angle is complex. While it is possible to construct rotation-invariant features by hand, retrieval accuracy will be low because hand engineering only creates low-level features, while deep learning methods build high-level and low-level features simultaneously. This paper presents a novel approach that combines a deep learning orientation angle detection model with the CBIR feature extraction model to correct the rotation angle of any image. This offers a unique construction of a rotation-invariant CBIR system that handles the CNN features that are not rotation invariant. This research also proposes a further study on how a rotation-invariant deep CBIR can recover images from the dataset in real-time. The final results of this system show significant improvement as compared to a default CNN feature extraction model without the OAD.
