The basic idea of multi-class classification is a disassembly method,which is to decompose a multi-class classification task into several binary classification tasks.In order to improve the accuracy of multi-class cla...The basic idea of multi-class classification is a disassembly method,which is to decompose a multi-class classification task into several binary classification tasks.In order to improve the accuracy of multi-class classification in the case of insufficient samples,this paper proposes a multi-class classification method combining K-means and multi-task relationship learning(MTRL).The method first uses the split method of One vs.Rest to disassemble the multi-class classification task into binary classification tasks.K-means is used to down sample the dataset of each task,which can prevent over-fitting of the model while reducing training costs.Finally,the sampled dataset is applied to the MTRL,and multiple binary classifiers are trained together.With the help of MTRL,this method can utilize the inter-task association to train the model,and achieve the purpose of improving the classification accuracy of each binary classifier.The effectiveness of the proposed approach is demonstrated by experimental results on the Iris dataset,Wine dataset,Multiple Features dataset,Wireless Indoor Localization dataset and Avila dataset.展开更多
In order to eliminate the impact of the Doppler effects caused by the motion of the spacecraft on the X-ray pulsar-based navigation, an innovative navigation method using the pulse phase and Doppler frequency measurem...In order to eliminate the impact of the Doppler effects caused by the motion of the spacecraft on the X-ray pulsar-based navigation, an innovative navigation method using the pulse phase and Doppler frequency measurements of the X-ray pulsars is proposed. Given the initial estimate of the spacecraft's state,the real-time photon arrival model is established at the spacecraft with respect to the spacecraft's position and velocity predicted by the orbit dynamic model and their estimation errors. On this basis, a maximum likelihood estimation algorithm directly using the observed photon event timestamps is developed to extract a single pair of pulse phase and Doppler frequency measurements caused by the spacecraft's state estimation error. Since the phase estimation error increases as the observation time increases, we propose a new measurement updating scheme of referring the measurements to the middle time of an observation interval. By using the ground-based simulation system of X-ray pulsar signals, a series of photon-level simulations are performed. The results testify to the feasibility and real-timeliness of the proposed navigation method, and show that the incorporation of the Doppler measurement as well as the pulse phase into the navigation filter can improve the navigation accuracy.展开更多
X-ray pulsar-based navigation （XPNAV） is an attractive method for autonomous deep- space navigation in the future. The pulse phase estimation is a key task in XPNAV and its accuracy directly determines the navigatio...X-ray pulsar-based navigation （XPNAV） is an attractive method for autonomous deep- space navigation in the future. The pulse phase estimation is a key task in XPNAV and its accuracy directly determines the navigation accuracy. State-of-the-art pulse phase estimation techniques either suffer from poor estimation accuracy, or involve tile maximization of generally non- convex object function, thus resulting in a large computational cost. In this paper, a fasl pulse phase estimation method based on epoch folding is presented. The statistical properties of the observed profle obtained through epoch folding are developed. Based on this, we recognize the joint prob- ability distribution of the observed profile as the likelihood function and utilize a fast Fourier transform-based procedure to estimate the pulse phase. Computational complexity of the proposed estimator is analyzed as well. Experimental results show that the proposed estimator significantly outperforms the currently used cross-correlation （CC） and nonlinear least squares （NLS） estima- tors, while significantly reduces the computational complexity compared with NLS and maxinmm likelihood （ML） estimators.展开更多
基金supported by the National Natural Science Foundation of China(61703131 61703129+1 种基金 61701148 61703128)
文摘The basic idea of multi-class classification is a disassembly method,which is to decompose a multi-class classification task into several binary classification tasks.In order to improve the accuracy of multi-class classification in the case of insufficient samples,this paper proposes a multi-class classification method combining K-means and multi-task relationship learning(MTRL).The method first uses the split method of One vs.Rest to disassemble the multi-class classification task into binary classification tasks.K-means is used to down sample the dataset of each task,which can prevent over-fitting of the model while reducing training costs.Finally,the sampled dataset is applied to the MTRL,and multiple binary classifiers are trained together.With the help of MTRL,this method can utilize the inter-task association to train the model,and achieve the purpose of improving the classification accuracy of each binary classifier.The effectiveness of the proposed approach is demonstrated by experimental results on the Iris dataset,Wine dataset,Multiple Features dataset,Wireless Indoor Localization dataset and Avila dataset.
文摘In order to eliminate the impact of the Doppler effects caused by the motion of the spacecraft on the X-ray pulsar-based navigation, an innovative navigation method using the pulse phase and Doppler frequency measurements of the X-ray pulsars is proposed. Given the initial estimate of the spacecraft's state,the real-time photon arrival model is established at the spacecraft with respect to the spacecraft's position and velocity predicted by the orbit dynamic model and their estimation errors. On this basis, a maximum likelihood estimation algorithm directly using the observed photon event timestamps is developed to extract a single pair of pulse phase and Doppler frequency measurements caused by the spacecraft's state estimation error. Since the phase estimation error increases as the observation time increases, we propose a new measurement updating scheme of referring the measurements to the middle time of an observation interval. By using the ground-based simulation system of X-ray pulsar signals, a series of photon-level simulations are performed. The results testify to the feasibility and real-timeliness of the proposed navigation method, and show that the incorporation of the Doppler measurement as well as the pulse phase into the navigation filter can improve the navigation accuracy.
基金supported by the National Natural Science Foundation of China(No.61301173)
文摘X-ray pulsar-based navigation （XPNAV） is an attractive method for autonomous deep- space navigation in the future. The pulse phase estimation is a key task in XPNAV and its accuracy directly determines the navigation accuracy. State-of-the-art pulse phase estimation techniques either suffer from poor estimation accuracy, or involve tile maximization of generally non- convex object function, thus resulting in a large computational cost. In this paper, a fasl pulse phase estimation method based on epoch folding is presented. The statistical properties of the observed profle obtained through epoch folding are developed. Based on this, we recognize the joint prob- ability distribution of the observed profile as the likelihood function and utilize a fast Fourier transform-based procedure to estimate the pulse phase. Computational complexity of the proposed estimator is analyzed as well. Experimental results show that the proposed estimator significantly outperforms the currently used cross-correlation （CC） and nonlinear least squares （NLS） estima- tors, while significantly reduces the computational complexity compared with NLS and maxinmm likelihood （ML） estimators.
