排序方式: 共有26条查询结果,搜索用时 5 毫秒
21.
22.
23.
24.
J. Goddard G. Schlotthauer M.E. Torres H.L. Rufiner 《Biomedical signal processing and control》2009,4(3):194-201
For an adequate analysis of pathological speech signals, a sizeable number of parameters is required, such as those related to jitter, shimmer and noise content. Often this kind of high-dimensional signal representation is difficult to understand, even for expert voice therapists and physicians. Data visualization of a high-dimensional dataset can provide a useful first step in its exploratory data analysis, facilitating an understanding about its underlying structure. In the present paper, eight dimensionality reduction techniques, both classical and recent, are compared on speech data containing normal and pathological speech. A qualitative analysis of their dimensionality reduction capabilities is presented. The transformed data are also quantitatively evaluated, using classifiers, and it is found that it may be advantageous to perform the classification process on the transformed data, rather than on the original. These qualitative and quantitative analyses allow us to conclude that a nonlinear, supervised method, called kernel local Fisher discriminant analysis is superior for dimensionality reduction in the actual context. 相似文献
25.
Self-organizing feature maps (SOFMs) represent a dimensionality-reduction algorithm that has been used to replicate feature
topographies observed experimentally in primary visual cortex (V1). We used the SOFM algorithm to model possible topographies
of generic sensory cortical areas containing up to five arbitrary physiological features. This study explored the conditions
under which these multi-feature SOFMs contained two features that were mapped monotonically and aligned orthogonally with
one another (i.e., “globally orthogonal”), as well as the conditions under which the map of one feature aligned with the longest
anatomical dimension of the modeled cortical area (i.e., “dominant”). In a single SOFM with more than two features, we never
observed more than one dominant feature, nor did we observe two globally orthogonal features in the same map in which a dominant
feature occurred. Whether dominance or global orthogonality occurred depended upon how heavily weighted the features were
relative to one another. The most heavily weighted features are likely to correspond to those physical stimulus properties
transduced directly by the sensory epithelium of a particular sensory modality. Our results imply, therefore, that in the
primary cortical area of sensory modalities with a two-dimensional sensory epithelium, these two features are likely to be
organized globally orthogonally to one another, and neither feature is likely to be dominant. In the primary cortical area
of sensory modalities with a one-dimensional sensory epithelium, however, this feature is likely to be dominant, and no two
features are likely to be organized globally orthogonally to one another. Because the auditory system transduces a single
stimulus feature (i.e., frequency) along the entire length of the cochlea, these findings may have particular relevance for
topographic maps of primary auditory cortex.
This research was supported by The McDonnell Center for Higher Brain Function, The Wallace H. Coulter Foundation and NIH grant
DC008880. 相似文献
26.
Estimation of additive regression models with known links 总被引:4,自引:0,他引:4