Early intervention for depression is very important to ease the disease burden, but current diagnostic methods are still limited. This study investigated automatic depressed speech classification in a sample of 170 native Chinese subjects (85 healthy controls and 85 depressed patients). The classification performances of prosodic, spectral, and glottal speech features were analyzed in recognition of depression. We proposed an ensemble logistic regression model for detecting depression (ELRDD) in speech. The logistic regression, which was superior in recognition of depression, was selected as the base classifier. This ensemble model extracted many speech features from different aspects and ensured diversity of the base classifier. ELRDD provided better classification results than the other compared classifiers. A technique for identifying depression based on ELRDD, ELRDD-E, was here suggested and tested. It offered encouraging outcomes, revealing a high accuracy level of 75.00% for females and 81.82% for males, as well as an advantageous sensitivity/specificity ratio of 79.25%/70.59% for females and 78.13%/85.29% for males.
A new analytical method has been proposed by utilizing an electromagnetic induction principle with a short-circuited microstrip line jig and the complex permeability spectra can be calculated without a known reference sample. The new method using the short-circuited microstrip line can exhibit higher sensitivity and a wider frequency band than coplanar waveguide and pick-up coil. Two magnetic thin films having a good in-plane uniaxial anisotropy are measured by using the induction method. The results show typical complex permeability spectra in good agreement with the theoretical analytical results. The measured permeability values are verified by comparing with the initial susceptibility derived from the sweeping field results. The difference of measured permeability values is less than 5%.
Arid and semiarid ecosystems, or dryland, are important to global biogeochemical cycles. Dryland's community structure and vegetation dynamics as well as biogeochemical cycles are sensitive to changes in climate and atmospheric composition. Vegetation dynamic models has been applied in global change studies, but the complex interactions among the carbon (C), water, and nitrogen (N) cycles have not been adequately addressed in the current models. In this study, a process-based vegetation dynamic model was developed to study the responses of dryland ecosystems to environmental changes, emphasizing on the interactions among the C, water, and N processes. To address the interactions between the C and water processes, it not only considers the effects of annual precipitation on vegetation distribution and soil moisture on organic matter (SOM) decomposition, but also explicitly models root competition for water and the water compensation processes. To address the interactions between C and N processes, it models the soil inorganic mater processes, such as N mineralization/immobilization, denitrification/nitrification, and N leaching, as well as the root competition for soil N. The model was parameterized for major plant functional types and evaluated against field observations.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.