Obtaining comprehensive and accurate information is very important in intelligent traffic system (ITS). In ITS, the GPS floating car system is an important approach for traffic data acquisition. However, in this syste...Obtaining comprehensive and accurate information is very important in intelligent traffic system (ITS). In ITS, the GPS floating car system is an important approach for traffic data acquisition. However, in this system, the GPS blind areas caused by tall buildings or tunnels could affect the acquisition of traffic information and depress the system performance. Aiming at this problem, a novel method employing a back propagation (BP) neural network is developed to estimate the traffic speed in the GPS blind areas. When the speed of one road section is lost, the speed of its related road sections can be used to estimate its speed. The complete historical data of these road sections are used to train the neural network, using Levenberg-Marquardt learning algorithm. Then, the current speed of the related roads is used by the trained neural network to get the speed of the road section without GPS signal. We compare the speed of the road section estimated by our method with the real speed of this road section, and the experimental results show that the proposed method of traffic speed estimation is very effective.展开更多
In this paper,we propose a dynamic multi-descriptor fusion(DMDF)approach to improving the retrieval accuracy of 3-dimensional(3D)model retrieval systems.First,an independent retrieval list is generated by using each i...In this paper,we propose a dynamic multi-descriptor fusion(DMDF)approach to improving the retrieval accuracy of 3-dimensional(3D)model retrieval systems.First,an independent retrieval list is generated by using each individual descriptor.Second,we propose an automatic relevant/irrelevant models selection(ARMS)approach to selecting the relevant and irrelevant 3D models automatically without any user interaction.A weighted distance,in which the weight associated with each individual descriptor is learnt by using the selected relevant and irrelevant models,is used to measure the similarity between two 3D models.Furthermore,a descriptor-dependent adaptive query point movement(AQPM)approach is employed to update every feature vector.This set of new feature vectors is used to index 3D models in the next search process.Four 3D model databases are used to compare the retrieval accuracy of our proposed DMDF approach with several descriptors as well as some well-known information fusion methods.Experimental results have shown that our proposed DMDF approach provides a promising retrieval result and always yields the best retrieval accuracy.展开更多
False monitoring information is a major problem in process production system and several ineffective methods have been proposed to identify false monitoring information in the production system. In this paper, a new m...False monitoring information is a major problem in process production system and several ineffective methods have been proposed to identify false monitoring information in the production system. In this paper, a new method is proposed to identify false monitoring information based on system coupling analysis and collision detection from the perspective of data analysis. Coupling multifractal features are extracted to reflect the changes in coupling relationship by utilizing the multifractal detrended cross-correlation analysis (MF-DXA). Each monitoring variable in process production system has more than one coupled variable, which can be regarded as multi-source. To achieve low redundancy in features and uniform description of coupling relationship, the feature level information fusion is studied based on modified Mahalanobis Taguchi system (MTS). False alarms are identified when the coupling relationships among the coupled monitoring variables collide. Analysis results of coupled R?ssler and Henon datasets indicate the feasibility of this method for selecting the effective coupling feature and uniform description of coupling relationship. The compressor system case of Coal Chemical Ltd. Group is studied and false monitoring information is identified.展开更多
基金funded by National Key Technology R&D Program of China (No.2006BAG01A03)
文摘Obtaining comprehensive and accurate information is very important in intelligent traffic system (ITS). In ITS, the GPS floating car system is an important approach for traffic data acquisition. However, in this system, the GPS blind areas caused by tall buildings or tunnels could affect the acquisition of traffic information and depress the system performance. Aiming at this problem, a novel method employing a back propagation (BP) neural network is developed to estimate the traffic speed in the GPS blind areas. When the speed of one road section is lost, the speed of its related road sections can be used to estimate its speed. The complete historical data of these road sections are used to train the neural network, using Levenberg-Marquardt learning algorithm. Then, the current speed of the related roads is used by the trained neural network to get the speed of the road section without GPS signal. We compare the speed of the road section estimated by our method with the real speed of this road section, and the experimental results show that the proposed method of traffic speed estimation is very effective.
基金supported in part by“MOST”under Grants No.102-2632-E-216-001-MY3 and No.104-2221-E-216-010-MY2
文摘In this paper,we propose a dynamic multi-descriptor fusion(DMDF)approach to improving the retrieval accuracy of 3-dimensional(3D)model retrieval systems.First,an independent retrieval list is generated by using each individual descriptor.Second,we propose an automatic relevant/irrelevant models selection(ARMS)approach to selecting the relevant and irrelevant 3D models automatically without any user interaction.A weighted distance,in which the weight associated with each individual descriptor is learnt by using the selected relevant and irrelevant models,is used to measure the similarity between two 3D models.Furthermore,a descriptor-dependent adaptive query point movement(AQPM)approach is employed to update every feature vector.This set of new feature vectors is used to index 3D models in the next search process.Four 3D model databases are used to compare the retrieval accuracy of our proposed DMDF approach with several descriptors as well as some well-known information fusion methods.Experimental results have shown that our proposed DMDF approach provides a promising retrieval result and always yields the best retrieval accuracy.
基金supported by the National Natural Science Foundation of China (Grant No. 51375375)
文摘False monitoring information is a major problem in process production system and several ineffective methods have been proposed to identify false monitoring information in the production system. In this paper, a new method is proposed to identify false monitoring information based on system coupling analysis and collision detection from the perspective of data analysis. Coupling multifractal features are extracted to reflect the changes in coupling relationship by utilizing the multifractal detrended cross-correlation analysis (MF-DXA). Each monitoring variable in process production system has more than one coupled variable, which can be regarded as multi-source. To achieve low redundancy in features and uniform description of coupling relationship, the feature level information fusion is studied based on modified Mahalanobis Taguchi system (MTS). False alarms are identified when the coupling relationships among the coupled monitoring variables collide. Analysis results of coupled R?ssler and Henon datasets indicate the feasibility of this method for selecting the effective coupling feature and uniform description of coupling relationship. The compressor system case of Coal Chemical Ltd. Group is studied and false monitoring information is identified.