Feature reduction is a key process in pattern recognition. This paper deals with the feature reduction methods for a time-shift invariant feature, power spectrum, in Radar Automatic Target Recognition (RATR) using Hig...Feature reduction is a key process in pattern recognition. This paper deals with the feature reduction methods for a time-shift invariant feature, power spectrum, in Radar Automatic Target Recognition (RATR) using High-Resolution Range Profiles (HRRPs). Several existing feature reduction methods in pattern recognition are analyzed, and a weighted feature reduction method based on Fisher's Discriminant Ratio (FDR) is proposed in this paper. According to the characteristics of radar HRRP target recognition, this proposed method searches the optimal weight vector for power spectra of HRRPs by means of an iterative algorithm, and thus reduces feature dimensionality. Compared with the method of using raw power spectra and some existing feature reduction methods, the weighted feature reduction method can not only reduce feature dimensionality, but also improve recognition performance with low computation complexity. In the recognition experiments based on measured data, the proposed method is robust to different test data and achieves good recognition results.展开更多
A thinner cortex has higher potential for binding GABA receptor A which is associated with larger amplitudes of intrinsic brain activity(i BA). However, the relationship between cortical thickness and i BA is unknown ...A thinner cortex has higher potential for binding GABA receptor A which is associated with larger amplitudes of intrinsic brain activity(i BA). However, the relationship between cortical thickness and i BA is unknown in intact and epileptic brains. To this end, we investigated the relationship between cortical thickness measured by highresolution MRI and surface-based i BA derived from resting-state functional MRI in normal controls(n = 82) andpatients with generalized tonic–clonic seizures(GTCS)only(n = 82). We demonstrated that the spatial distribution of cortical thickness negatively correlated with surface-based i BA amplitude at both whole-brain and within independent brain functional networks. In GTCS patients,spatial coupling between thickness and i BA amplitude decreased in the default mode, dorsal attention, and somatomotor networks. In addition, the vertex-wise acrosssubject thickness–i BA amplitude correspondence altered in the frontal and temporal lobes as well as in the precuneus in GTCS patients. The relationship between these two modalities can serve as a brain-based marker for detecting epileptogenic changes.展开更多
基金Partially supported by the National Natural Science Foundation of China (No.60302009)the National Defense Advanced Research Foundation of China (No.413070501).
文摘Feature reduction is a key process in pattern recognition. This paper deals with the feature reduction methods for a time-shift invariant feature, power spectrum, in Radar Automatic Target Recognition (RATR) using High-Resolution Range Profiles (HRRPs). Several existing feature reduction methods in pattern recognition are analyzed, and a weighted feature reduction method based on Fisher's Discriminant Ratio (FDR) is proposed in this paper. According to the characteristics of radar HRRP target recognition, this proposed method searches the optimal weight vector for power spectra of HRRPs by means of an iterative algorithm, and thus reduces feature dimensionality. Compared with the method of using raw power spectra and some existing feature reduction methods, the weighted feature reduction method can not only reduce feature dimensionality, but also improve recognition performance with low computation complexity. In the recognition experiments based on measured data, the proposed method is robust to different test data and achieves good recognition results.
基金supported by the National High Technology Research and Development Program of China(2015AA020505)the Natural Science Foundation of China(61533006,81201155,81301198,81471653,81401400,81271553,and 81422022)+1 种基金the Fundamental Research Funds for the Central Universities(ZYGX2013Z004)the China Postdoctoral Science Foundation(2013M532229)
文摘A thinner cortex has higher potential for binding GABA receptor A which is associated with larger amplitudes of intrinsic brain activity(i BA). However, the relationship between cortical thickness and i BA is unknown in intact and epileptic brains. To this end, we investigated the relationship between cortical thickness measured by highresolution MRI and surface-based i BA derived from resting-state functional MRI in normal controls(n = 82) andpatients with generalized tonic–clonic seizures(GTCS)only(n = 82). We demonstrated that the spatial distribution of cortical thickness negatively correlated with surface-based i BA amplitude at both whole-brain and within independent brain functional networks. In GTCS patients,spatial coupling between thickness and i BA amplitude decreased in the default mode, dorsal attention, and somatomotor networks. In addition, the vertex-wise acrosssubject thickness–i BA amplitude correspondence altered in the frontal and temporal lobes as well as in the precuneus in GTCS patients. The relationship between these two modalities can serve as a brain-based marker for detecting epileptogenic changes.
