Search

Functional linear regression is one of the main modeling tools for working with functional data. Since functional data are usually stream data essentially and there are some noises in functional data. Many numerical research studies of machine learning indicate that the noise samples not only increase the amount of storage space, but also affect the performance of algorithm. Therefore, in this paper we consider a new learning strategy by introducing incremental learning, Markov sampling for functional linear regression and propose a novel functional incremental linear square regression algorithm based on Markov sampling (FILSR-MS). To have a better understanding of the proposed FILSR-MS, we not only estimate the generalization bound of the proposed algorithm and establish the fast learning rate, but also present some useful discussions. The performance of the proposed algorithm is validated by the numerical experiments for benchmark repository. [ABSTRACT FROM AUTHOR]

Objectives. We sought to determine whether disparities in health-related quality of life exist between veterans who live in rural settings and their suburban or urban counterparts. Methods. We determined health-related quality-of-life scores (physical and mental health component summaries) for 767 109 veterans who had used Veterans Health Administration services within the past 3 years. We used rural/urban commuting area codes to categorize veterans into rural, suburban, or urban residence. Results. Health-related quality-of-life scores were significantly lower for veterans who lived in rural settings than for those who lived in suburban or urban settings. Rural veterans had significantly more physical health comorbidities, but fewer mental health comorbidities, than their suburban and urban counterparts. Rural-urban disparities persisted in all survey subscales, across regional delivery networks, and after we controlled for sociodemographic factors. Conclusions. When compared with their urban and suburban counterparts, veterans who live in a rural setting have worse health-related quality-of-life scores. Policymakers, within and outside the Veterans Health Administration, should anticipate greater health care demands from rural populations.

Use of risk adjustment models to analyze managed care plans' selection of enrollees based on private information that is unavailable to regulators setting capitation rates is discussed. Additional information on the economic benefits offered by capitation payment systems to managed health plans is included.

A series of glasses with composition 60NaPO 3 -(40- x )CdF 2 - x YF 3 - y Er 2 O 3 were synthesized via melt-quenching methods and subsequently heat-treated to obtain upconversion luminescent glass ceramics containing NaYF 4 :Er crystals. Hexagonal and/or cubic NaYF 4 crystals were controlled to be bred in the glasses by changing the glass composition. The structure evolution driven by crystallization was characterized using advanced solid-state nuclear magnetic resonance (SSNMR) techniques. The SSNMR results reveal that the Y/Na ratio determines the crystalline phases of NaYF 4 precipitated in this glass system. Y 3+ attracts extra F - ions from P 5+ and Cd 2+ during crystallization because of its stronger ability to attract F - ions, leading to most Y 3+ ions being crystallized into the NaYF 4 crystals. The paramagnetic broadening effect of the Er 3+ ions on NMR signals as well as the upconversion luminescence results indicate that, before crystallization, most Er 3+ ions are surrounded by oxygen within the glasses; however, after crystallization, almost all of them enter the NaYF 4 crystals. On the basis of this local structure investigation, a composition design strategy is developed to obtain highly efficient upconversion luminescent glass ceramics.

Auscultation of heart sounds is an important method for the diagnosis of heart conditions. For most people, the audible component of heart sound are the first heart sound (S1) and the second heart sound (S2). Different diseases usually generate murmurs at different stages in a cardiac cycle. Segmenting the heart sounds precisely is the prerequisite for diagnosis. S1 and S2 emerges at the beginning of systole and diastole, respectively. Locating S1 and S2 accurately is beneficial for the segmentation of heart sounds. This paper proposed a method to classify the S1 and S2 based on their properties, and did not take use of the duration of systole and diastole. S1 and S2 in the training dataset were transformed to spectra by short-time Fourier transform and be feed to the two-stream convolutional neural network. The classification accuracy of the test dataset was as high as 91.135%. The highest sensitivity and specificity were 91.156% and 92.074%, respectively. Extracting the features of the input signals artificially can be avoid with the method proposed in this article. The calculation is not complicated, which makes this method effective for distinguishing S1 and S2 in real time.