Vehicle data is one of the important sources of traffic accident digital forensics.We propose a novel method using long short-term memory-deep belief network by binary encoding(LSTM-BiDBN)controller area network ident...Vehicle data is one of the important sources of traffic accident digital forensics.We propose a novel method using long short-term memory-deep belief network by binary encoding(LSTM-BiDBN)controller area network identifier(CAN ID)to extract the event sequence of CAN IDs and the semantic of CAN IDs themselves.Instead of detecting attacks only aimed at a specific CAN ID,the proposed method fully considers the potential interaction between electronic control units.By this means,we can detect whether the vehicle has been invaded by the outside,to online determine the responsible party of the accident.We use our LSTM-BiDBN to distinguish attack-free and abnormal situations on CAN-intrusion-dataset.Experimental results show that our proposed method is more effective in identifying anomalies caused by denial of service attack,fuzzy attack and impersonation attack with an accuracy value of 97.02%,a false-positive rate of 6.09%,and a false-negative rate of 1.94%compared with traditional methods.展开更多
Tomographic particle image velocimetry(Tomo-PIV)has been successfully applied in measuring three-dimensional(3D)flow field in recent years.Such technology highly relies on the reconstruction technique which provides t...Tomographic particle image velocimetry(Tomo-PIV)has been successfully applied in measuring three-dimensional(3D)flow field in recent years.Such technology highly relies on the reconstruction technique which provides the spatial particle distribution by using images from multiple cameras at different viewing angles.As the most popular reconstruction method,the multiplicative algebraic reconstruction technique(MART)has advantages in high computational speed and high accuracy for low particle seeding reconstruction.However,the accuracy is not satisfactory in the case of dense particle distributions to be reconstructed.To overcome this problem,a symmetric encode-decoder fully convolutional network is proposed in this paper to improve the reconstruction quality of MART.The input of the neural network is the particle field reconstructed by the MART approach,while the output is the regenerated image with the same resolution.Numerical evaluations indicate that those blurred or irregular particles can be significantly refined by the trained neural network.Most of the ghost particles can also be removed by this filtering method.The reconstruction accuracy can be improved by more than 10%without increasing the computational cost.Experimental evaluations indicate that the trained neural network can also provide similar satisfactory reconstruction and improved velocity fields.展开更多
基金the National Key R&D Program of China(No.2017YFA60700602)。
文摘Vehicle data is one of the important sources of traffic accident digital forensics.We propose a novel method using long short-term memory-deep belief network by binary encoding(LSTM-BiDBN)controller area network identifier(CAN ID)to extract the event sequence of CAN IDs and the semantic of CAN IDs themselves.Instead of detecting attacks only aimed at a specific CAN ID,the proposed method fully considers the potential interaction between electronic control units.By this means,we can detect whether the vehicle has been invaded by the outside,to online determine the responsible party of the accident.We use our LSTM-BiDBN to distinguish attack-free and abnormal situations on CAN-intrusion-dataset.Experimental results show that our proposed method is more effective in identifying anomalies caused by denial of service attack,fuzzy attack and impersonation attack with an accuracy value of 97.02%,a false-positive rate of 6.09%,and a false-negative rate of 1.94%compared with traditional methods.
基金This work was supported in parts by the National Natural Science Foundation of China under grant no.61973270the Foundation for Innovative Research Groups of the National Natural Science Foundation of China under grant no.61621002the Fundamental Research Funds for Central Universities.
文摘Tomographic particle image velocimetry(Tomo-PIV)has been successfully applied in measuring three-dimensional(3D)flow field in recent years.Such technology highly relies on the reconstruction technique which provides the spatial particle distribution by using images from multiple cameras at different viewing angles.As the most popular reconstruction method,the multiplicative algebraic reconstruction technique(MART)has advantages in high computational speed and high accuracy for low particle seeding reconstruction.However,the accuracy is not satisfactory in the case of dense particle distributions to be reconstructed.To overcome this problem,a symmetric encode-decoder fully convolutional network is proposed in this paper to improve the reconstruction quality of MART.The input of the neural network is the particle field reconstructed by the MART approach,while the output is the regenerated image with the same resolution.Numerical evaluations indicate that those blurred or irregular particles can be significantly refined by the trained neural network.Most of the ghost particles can also be removed by this filtering method.The reconstruction accuracy can be improved by more than 10%without increasing the computational cost.Experimental evaluations indicate that the trained neural network can also provide similar satisfactory reconstruction and improved velocity fields.
