To avoid the curse of dimensionality, text categorization （TC） algorithms based on machine learning （ML） have to use an feature selection （FS） method to reduce the dimensionality of feature space. Although havin...To avoid the curse of dimensionality, text categorization （TC） algorithms based on machine learning （ML） have to use an feature selection （FS） method to reduce the dimensionality of feature space. Although having been widely used, FS process will generally cause information losing and then have much side-effect on the whole performance of TC algorithms. On the basis of the sparsity characteristic of text vectors, a new TC algorithm based on lazy feature selection （LFS） is presented. As a new type of embedded feature selection approach, the LFS method can greatly reduce the dimension of features without any information losing, which can improve both efficiency and performance of algorithms greatly. The experiments show the new algorithm can simultaneously achieve much higher both performance and efficiency than some of other classical TC algorithms.展开更多
Objective:To identify the cerebral activation patterns associated with the processes that occur during viewing Chinese and English words in native Chinese English learners. Methods:12 right-handed Chinese English lear...Objective:To identify the cerebral activation patterns associated with the processes that occur during viewing Chinese and English words in native Chinese English learners. Methods:12 right-handed Chinese English learners were divided into two groups equally,namely English majors and non-English majors,and took semantic judgement tasks of both English and Chinese words, for whom the fMRI images were collected.Results:To various degrees, all subjects demonstrated activation of associated cerebral regions in both hemispheres and the left hemisphere activation was more significant for most subjects. Except for classical regions involved in language processing,such as Wernicke areas and Broca areas,there were other activated cerebral regions, including cerebellum, limbic system and basal ganglia nucleus, etc. To sum up,there were apparent overlap for cerebral activation distribution and no specific processing areas for both tasks. The analysis of ROI(region of interest)suggested that subjects in specialized group were more dependent on right hemisphere to perform English words task. Conclusion:Language cognition is dominated by left hemisphere,which is also shared by the right hemisphere to various degrees and thus two hemispheres work by ways of both dissociation and coordination. It is possible that working strategy of the right hemisphere in English task is related to proficiency of the second language. A variety of distinctions are shared by each subject for language cognitive patterns.展开更多
文摘To avoid the curse of dimensionality, text categorization （TC） algorithms based on machine learning （ML） have to use an feature selection （FS） method to reduce the dimensionality of feature space. Although having been widely used, FS process will generally cause information losing and then have much side-effect on the whole performance of TC algorithms. On the basis of the sparsity characteristic of text vectors, a new TC algorithm based on lazy feature selection （LFS） is presented. As a new type of embedded feature selection approach, the LFS method can greatly reduce the dimension of features without any information losing, which can improve both efficiency and performance of algorithms greatly. The experiments show the new algorithm can simultaneously achieve much higher both performance and efficiency than some of other classical TC algorithms.
文摘Objective:To identify the cerebral activation patterns associated with the processes that occur during viewing Chinese and English words in native Chinese English learners. Methods:12 right-handed Chinese English learners were divided into two groups equally,namely English majors and non-English majors,and took semantic judgement tasks of both English and Chinese words, for whom the fMRI images were collected.Results:To various degrees, all subjects demonstrated activation of associated cerebral regions in both hemispheres and the left hemisphere activation was more significant for most subjects. Except for classical regions involved in language processing,such as Wernicke areas and Broca areas,there were other activated cerebral regions, including cerebellum, limbic system and basal ganglia nucleus, etc. To sum up,there were apparent overlap for cerebral activation distribution and no specific processing areas for both tasks. The analysis of ROI(region of interest)suggested that subjects in specialized group were more dependent on right hemisphere to perform English words task. Conclusion:Language cognition is dominated by left hemisphere,which is also shared by the right hemisphere to various degrees and thus two hemispheres work by ways of both dissociation and coordination. It is possible that working strategy of the right hemisphere in English task is related to proficiency of the second language. A variety of distinctions are shared by each subject for language cognitive patterns.
