Semi-supervised dimensionality reduction based on partial least squares for visual analysis of high dimensional data

Dimensionality reduction is employed for visual data analysis as a way to obtaining reduced spaces for high dimensional data or to mapping data directly into 2D or 3D spaces. Although techniques have evolved to improve data segregation on reduced or visual spaces, they have limited capabilities for adjusting the results according to user's knowledge. In this paper, we propose a novel approach to handling both dimensionality reduction and visualization of high dimensional data, taking into account user's input. It employs Partial Least Squares (PLS), a statistical tool to perform retrieval of latent spaces focusing on the discriminability of the data. The method employs a training set for building a highly precise model that can then be applied to a much larger data set very effectively. The reduced data set can be exhibited using various existing visualization techniques. The training data is important to code user's knowledge into the loop. However, this work also devises a strategy for calculating PLS reduced spaces when no training data is available. The approach produces increasingly precise visual mappings as the user feeds back his or her knowledge and is capable of working with small and unbalanced training sets.

Three-dimensional Doppler evaluation of single spherical samples from the placenta: intra- and interobserver reliability

Objective To evaluate the intra- and interobserver reliability of assessment of three-dimensional power Doppler (3D-PD) indices from single spherical samples of the placenta. Methods Women with singleton pregnancies at 2440 weeks' gestation were included. Three scans were independently performed by two observers; Observer 1 performed the first and third scan, intercalated by the scan of Observer 2. The observers independently analyzed the 3D-PD datasets that they had previously acquired using four different methods, each using a spherical sample: random sample extending from basal to chorionic plate; random sample with 2 cm3 of volume; directed sample to the region subjectively determined as containing more color Doppler signals extending from basal to chorionic plate; or directed sample with 2 cm3 of volume. The vascularization index (VI), flow index (FI) and vascularization flow index (VFI) were evaluated in each case. The observers were blinded to their own and each other's results. Additional evaluation was performed according to placental location: anterior, posterior and fundal or lateral. Intra- and interobserver reliability was assessed by intraclass correlation coefficients (ICC). Results Ninety-five pregnancies were included in the analysis. All three placental 3D-PD indices showed only weak to moderate reliability (ICC < 0.66 and ICC < 0.48, intra- and interobserver, respectively). The highest values of ICC were observed when using directed spherical samples from basal to chorionic plate. When analyzed by placental location, we found lower ICCs for lateral and fundal placentae compared to anterior and posterior ones. Conclusion Intra- and interobserver reliability of assessment of placental 3D-PD indices from single spherical samples in pregnant women greater than 24 weeks' gestation is poor to moderate, and clinical usefulness of these indices is likely to be limited. Copyright (c) 2012 ISUOG. Published by John Wiley & Sons, Ltd.

Stability analysis and area spectrum of three-dimensional Lifshitz black holes

In this work, we probe the stability of a z = 3 three-dimensional Lifshitz black hole by using scalar and spinorial perturbations. We found an analytical expression for the quasinormal frequencies of the scalar probe field, which perfectly agree with the behavior of the quasinormal modes obtained numerically. The results for the numerical analysis of the spinorial perturbations reinforce the conclusion of the scalar analysis, i.e., the model is stable under scalar and spinor perturbations. As an application we found the area spectrum of the Lifshitz black hole, which turns out to be equally spaced.

Obese elderly women exhibit low postural stability: a novel three-dimensional evaluation system

OBJECTIVE: The aim of this study was to evaluate the multisegmental static postural balance of active eutrophic and obese elderly women using a three-dimensional system under different sensory conditions. METHODS: A cross-sectional study was conducted on 31 elderly women (16 eutrophic and 15 obese) aged 65 to 75 years. The following anthropometric measurements were obtained: weight, height, waist and hip circumference, and handgrip strength. The physical activity level was evaluated using the International Physical Activity Questionnaire. Body composition was measured using the deuterium oxide dilution technique. The Polhemus (R) Patriot (three-dimensional) equipment was used to measure the parameters of postural balance along the anteroposterior and laterolateral axes. The data acquisition involved one trial of 60 s to test the limit of stability and four trials of 90 s each under the following conditions: (1) eyes open, stable surface; (2) eyes closed, stable surface; (3) eyes open, unstable surface; and (4) eyes closed, unstable surface. RESULTS: For the limit of stability, significant differences were observed in the maximum anteroposterior and laterolateral displacement (p<0.01) and in the parameter maximum anteroposterior displacement in the eyes closed stable surface condition (p<0.01) and maximum anteroposterior and laterolateral displacement in the eyes open unstable surface (p<0.01 and p = 0.03) and eyes closed unstable surface (p<0.01 and p<0.01) conditions. CONCLUSIONS: Obese elderly women exhibited a lower stability limit (lower sway area) compared with eutrophic women, leaving them more vulnerable to falls.