Aiming at the problem of poor tracking robustness caused by severe occlusion,deformation,and object rotation of deep learning object tracking algorithm in complex scenes,an improved deep reinforcement learning object ...Aiming at the problem of poor tracking robustness caused by severe occlusion,deformation,and object rotation of deep learning object tracking algorithm in complex scenes,an improved deep reinforcement learning object tracking algorithm based on actor-double critic network is proposed.In offline training phase,the actor network moves the rectangular box representing the object location according to the input sequence image to obtain the action value,that is,the horizontal,vertical,and scale transformation of the object.Then,the designed double critic network is used to evaluate the action value,and the output double Q value is averaged to guide the actor network to optimize the tracking strategy.The design of double critic network effectively improves the stability and convergence,especially in challenging scenes such as object occlusion,and the tracking performance is significantly improved.In online tracking phase,the well-trained actor network is used to infer the changing action of the bounding box,directly causing the tracker to move the box to the object position in the current frame.Several comparative tracking experiments were conducted on the OTB100 visual tracker benchmark and the experimental results show that more intensive reward settings significantly increase the actor network’s output probability of positive actions.This makes the tracking algorithm proposed in this paper outperforms the mainstream deep reinforcement learning tracking algorithms and deep learning tracking algorithms under the challenging attributes such as occlusion,deformation,and rotation.展开更多
Without considering security, existing message scheduling mechanisms may expose critical messages to malicious threats like confidentiality attacks. Incorporating confidentiality improvement into message scheduling, t...Without considering security, existing message scheduling mechanisms may expose critical messages to malicious threats like confidentiality attacks. Incorporating confidentiality improvement into message scheduling, this paper investigates the problem of scheduling aperiodc messages with time-critical and security-critical requirements. A risk-based security profit model is built to quantify the security quality of messages; and a dynamic programming based approximation algorithm is proposed to schedule aperiodic messages with guaranteed security performance. Experimental results illustrate the efficiency and effectiveness of the proposed algorithm.展开更多
The paper describes modern technologies of Computer Network Reliability. Software tool is developed to estimate of the CCN critical failure probability (construction of a criticality matrix) by results of the FME(C)A-...The paper describes modern technologies of Computer Network Reliability. Software tool is developed to estimate of the CCN critical failure probability (construction of a criticality matrix) by results of the FME(C)A-technique. The internal information factors, such as collisions and congestion of switchboards, routers and servers, influence on a network reliability and safety (besides of hardware and software reliability and external extreme factors). The means and features of Failures Modes and Effects (Critical) Analysis (FME(C)A) for reliability and criticality analysis of corporate computer networks (CCN) are considered. The examples of FME(C)A-Technique for structured cable system (SCS) is given. We also discuss measures that can be used for criticality analysis and possible means of criticality reduction. Finally, we describe a technique and basic principles of dependable development and deployment of computer networks that are based on results of FMECA analysis and procedures of optimization choice of means for fault-tolerance ensuring.展开更多
The research is focused on the development of automatic detection method of abnormal features, that occur in recorded time series of ionosphere critical frequency fOF2 during periods of high solar or seismic activity....The research is focused on the development of automatic detection method of abnormal features, that occur in recorded time series of ionosphere critical frequency fOF2 during periods of high solar or seismic activity. The method is based on joint application of wavelet-transformation and neural networks. On the basis of wavelet transformation algorithms for the detection of features and estimation of their parameters were developed. Detection and analysis of characteristic components of time series are performed on the basis of joint application of wavelet transformation and neural networks. Method's approbation is performed on fOF2 data obtained at the observatory “Paratunka” (Paratunka settlement, Kamchatskiy Kray).展开更多
基金supported in part by the National Key R&D Program of China(No.2022YFB2602203)in part by the National Natural Science Foundation of China(Nos.U20A20225 and 61873200)Shaanxi Provincial Key Research and Development Program(No.2022-GY111).
文摘Aiming at the problem of poor tracking robustness caused by severe occlusion,deformation,and object rotation of deep learning object tracking algorithm in complex scenes,an improved deep reinforcement learning object tracking algorithm based on actor-double critic network is proposed.In offline training phase,the actor network moves the rectangular box representing the object location according to the input sequence image to obtain the action value,that is,the horizontal,vertical,and scale transformation of the object.Then,the designed double critic network is used to evaluate the action value,and the output double Q value is averaged to guide the actor network to optimize the tracking strategy.The design of double critic network effectively improves the stability and convergence,especially in challenging scenes such as object occlusion,and the tracking performance is significantly improved.In online tracking phase,the well-trained actor network is used to infer the changing action of the bounding box,directly causing the tracker to move the box to the object position in the current frame.Several comparative tracking experiments were conducted on the OTB100 visual tracker benchmark and the experimental results show that more intensive reward settings significantly increase the actor network’s output probability of positive actions.This makes the tracking algorithm proposed in this paper outperforms the mainstream deep reinforcement learning tracking algorithms and deep learning tracking algorithms under the challenging attributes such as occlusion,deformation,and rotation.
基金supported by the National Natural Science Foundation of China (60673142)the National High Technology Research and Development Progrm of China (863 Program) (2006AA01Z1732007AA01Z131)
文摘Without considering security, existing message scheduling mechanisms may expose critical messages to malicious threats like confidentiality attacks. Incorporating confidentiality improvement into message scheduling, this paper investigates the problem of scheduling aperiodc messages with time-critical and security-critical requirements. A risk-based security profit model is built to quantify the security quality of messages; and a dynamic programming based approximation algorithm is proposed to schedule aperiodic messages with guaranteed security performance. Experimental results illustrate the efficiency and effectiveness of the proposed algorithm.
文摘The paper describes modern technologies of Computer Network Reliability. Software tool is developed to estimate of the CCN critical failure probability (construction of a criticality matrix) by results of the FME(C)A-technique. The internal information factors, such as collisions and congestion of switchboards, routers and servers, influence on a network reliability and safety (besides of hardware and software reliability and external extreme factors). The means and features of Failures Modes and Effects (Critical) Analysis (FME(C)A) for reliability and criticality analysis of corporate computer networks (CCN) are considered. The examples of FME(C)A-Technique for structured cable system (SCS) is given. We also discuss measures that can be used for criticality analysis and possible means of criticality reduction. Finally, we describe a technique and basic principles of dependable development and deployment of computer networks that are based on results of FMECA analysis and procedures of optimization choice of means for fault-tolerance ensuring.
文摘The research is focused on the development of automatic detection method of abnormal features, that occur in recorded time series of ionosphere critical frequency fOF2 during periods of high solar or seismic activity. The method is based on joint application of wavelet-transformation and neural networks. On the basis of wavelet transformation algorithms for the detection of features and estimation of their parameters were developed. Detection and analysis of characteristic components of time series are performed on the basis of joint application of wavelet transformation and neural networks. Method's approbation is performed on fOF2 data obtained at the observatory “Paratunka” (Paratunka settlement, Kamchatskiy Kray).
