Regularizing topic discovery in emrs with side information by using hierarchical bayesian models

We propose a novel hierarchical Bayesian framework, word-distance-dependent Chinese restaurant franchise (wd-dCRF) for topic discovery from a document corpus regularized by side information in the form of word-to-word relations, with an application on Electronic Medical Records (EMRs). Typically, a EMRs dataset consists of several patients (documents) and each patient contains many diagnosis codes (words). We exploit the side information available in the form of a semantic tree structure among the diagnosis codes for semantically-coherent disease topic discovery. We introduce novel functions to compute word-to-word distances when side information is available in the form of tree structures. We derive an efficient inference method for the wddCRF using MCMC technique. We evaluate on a real world medical dataset consisting of about 1000 patients with PolyVascular disease. Compared with the popular topic analysis tool, hierarchical Dirichlet process (HDP), our model discovers topics which are superior in terms of both qualitative and quantitative measures.

Scalable hierarchical rings based routing to a mobile robot in wireless sensor networks

Location service provides location information of robots to sensors, to enable event reporting. Existing protocols apply partial flooding to trace robots, leading to poor scalability. We propose a novel scalable location service, which applies hierarchical rings to update robot location and guide routing toward it. Each mobile robot creates a set of hierarchical update rings of doubling radii. Whenever the robot leaves its k-th ring, it updates its new location to sensors along its newly defined k-th ring, and re-defines all smaller rings for future decisions. When a sensor needs to route to the mobile robot, it starts searching from its smallest ring and sends location query to the sensors along the ring. If the query fails, the search then extends to the next larger ring, until it intersects an existing update ring, from which the search can be directed towards reported center. The location of destination is updated whenever another more recent ring is intersected. Our scheme guarantees message delivery if robot remains connected to sensors during its move. The theoretical analysis and simulation results demonstrate better scalability than previous protocols for the similar goal. © 2014 IEEE.

The association between socio-economic position and diet quality in Australian adults

Objective: We aimed to investigate the association between multiple measures of socio-economic position (SEP) and diet quality, using a diet quality index representing current national dietary guidelines, in the Australian adult population. Design: Cross-sectional study. Linear regression analyses were used to estimate the association between indicators of SEP (educational attainment, level of income and area-level disadvantage) and diet quality (measured using the Dietary Guideline Index (DGI)) in the total sample and stratified by sex and age (≤55 years and >55 years). Setting: A large randomly selected sample of the Australian adult population. Subjects: Australian adults (n 9296; aged ≥25 years) from the Australian Diabetes, Obesity and Lifestyle Study. Results: A higher level of educational attainment and income and a lower level of area-level disadvantage were significantly associated with a higher DGI score, across the gradient of SEP. The association between indicators of SEP and DGI score was consistently stronger among those aged ≤55 years compared with their older counterparts. The most disadvantaged group had a DGI score between 2 and 5 units lower (depending on the marker of SEP) compared with the group with the least disadvantage. Conclusions: A higher level of SEP was consistently associated with a higher level of diet quality for all indicators of SEP examined. In order to reduce socio-economic inequalities in diet quality, healthy eating initiatives need to act across the gradient of socio-economic disadvantage with a proportionate focus on those with greater socio-economic disadvantage.

Hierarchical gene selection and genetic fuzzy system for cancer microarray data classification

This paper introduces a novel approach to gene selection based on a substantial modification of analytic hierarchy process (AHP). The modified AHP systematically integrates outcomes of individual filter methods to select the most informative genes for microarray classification. Five individual ranking methods including t-test, entropy, receiver operating characteristic (ROC) curve, Wilcoxon and signal to noise ratio are employed to rank genes. These ranked genes are then considered as inputs for the modified AHP. Additionally, a method that uses fuzzy standard additive model (FSAM) for cancer classification based on genes selected by AHP is also proposed in this paper. Traditional FSAM learning is a hybrid process comprising unsupervised structure learning and supervised parameter tuning. Genetic algorithm (GA) is incorporated in-between unsupervised and supervised training to optimize the number of fuzzy rules. The integration of GA enables FSAM to deal with the high-dimensional-low-sample nature of microarray data and thus enhance the efficiency of the classification. Experiments are carried out on numerous microarray datasets. Results demonstrate the performance dominance of the AHP-based gene selection against the single ranking methods. Furthermore, the combination of AHP-FSAM shows a great accuracy in microarray data classification compared to various competing classifiers. The proposed approach therefore is useful for medical practitioners and clinicians as a decision support system that can be implemented in the real medical practice.

Socioeconomic position in young adulthood is associated with BMI in Australian families

BACKGROUND: Low socioeconomic position (SEP) is associated with increased cardiovascular (CV) disease risk, but the relative importance of SEP in childhood and adulthood, and of changes in SEP between these two life stages, remains unclear. Studies of families may help clarify these issues. We aimed to assess whether SEP in young adulthood, or change in SEP from childhood to young adulthood, was associated with five continuously measured CV risk factors. METHODS: We used data from 286 adult Australian families from the Victorian Family Heart Study (VFHS), in which some offspring have left home (n = 364) and some remained at home (n = 199). SEP (defined as the Index of Relative Socioeconomic Disadvantage) was matched to addresses. We fitted variance components models to test whether young adult SEP and/or change in SEP was associated with systolic blood pressure, diastolic blood pressure, body mass index (BMI), total cholesterol or high-density lipoprotein cholesterol, after adjustment for parental SEP and within-family correlation. RESULTS: An increase in SEP of 100 SEIFA units from childhood to adulthood was associated with a lower BMI (β = -0.49 kg/m(2), P < 0.01) only. CONCLUSIONS: These results suggest that a change in SEP in young adulthood is an important predictor of BMI, independent of childhood SEP.

Bayesian hierarchical modeling of the temporal dynamics of subjective well-being: A 10 year longitudinal analysis

This study demonstrates, for the first time, how Bayesian hierarchical modeling can be applied to yield novel insights into the long-term temporal dynamics of subjective well-being (SWB). Several models were proposed and examined using Bayesian methods. The models were assessed using a sample of Australian adults (. n=. 1081) who provided annual SWB scores on between 5 and 10 occasions. The best fitting models involved a probit transformation, allowed error variance to vary across participants, and did not include a lag parameter. Including a random linear and quadratic effect resulted in only a small improvement over the intercept only model. Examination of individual-level fits suggested that most participants were stable with a small subset exhibiting patterns of systematic change.

A systematic review of the effectiveness of whole-of-community interventions by socioeconomic position

Whole-of-community (WOC) interventions have led to modest reductions in population weight gain. Whether they exhibit differential effectiveness by socioeconomic position (SEP) remains unknown. We aimed to summarize evidence of differential effectiveness of WOC interventions by SEP. Electronic databases and grey literature were searched to identify studies that evaluated the effectiveness of a WOC intervention on behavioural change measures, energy balance behaviours and/or anthropometric outcomes according to any measure of SEP. Interventions were assessed for the following characteristics: structural changes to the environment, number of settings the intervention acted in, presence of community engagement and whether equity was considered in its design. Ten studies were included. Nine reported a greater or equal effect among low SEP groups compared with high SEP groups. These studies commonly featured interventions that incorporated structural changes to the environment, acted across more than three settings and/or employed community engagement. Conclusions did not change when excluding low-quality studies (n = 4). WOC interventions represent an effective and equitable approach for the reduction of population weight. Structural components, a larger number of settings and community engagement were common in equitable WOC interventions and should be considered in the design of future WOC interventions.

Development of hierarchical porous NiO-YSZ with improved mechanical properties

 The thesis developed an hierarchical porous NiO/YSZ with high mechanical performance using a novel process. This process fabricates initial scaffolds with a controllable porosity by enhancing the surface energy of poly methyl methacrylate (PMMA) for the assembly of NiO-YSZ/PMMA. It maintains the hierarchical porous structure using two-step sintering (TSS) to restrict the growth of nanoparticles, and improves the mechanical properties in combination with a bimodal distribution of NiO/YSZ nano-particles.

Hierarchical analysis of avian re-nesting behavior: mean, across-individual, and intra-individual responses

© 2015, Springer-Verlag Berlin Heidelberg. Anti-predator behavior is a key aspect of life history evolution, usually studied at the population (mean), or across-individual levels. However individuals can also differ in their intra-individual (residual) variation, but to our knowledge, this has only been studied once before in free-living animals. Here we studied the distances moved and changes in nest height and concealment between successive nesting attempts of marked pairs of grey fantails (Rhipidura albiscapa) in relation to nest fate, across the breeding season. We predicted that females (gender that decides where the nest is placed) should on average show adaptive behavioral responses to the experience of prior predation risk such that after an unsuccessful nesting attempt, replacement nests should be further away, higher from the ground, and more concealed compared with replacement nests after successful nesting attempts. We found that, on average, females moved greater distances to re-nest after unsuccessful nesting attempts (abandoned or depredated) in contrast to after a successful attempt, suggesting that re-nesting decisions are sensitive to risk. We found no consistent across-individual differences in distances moved, heights, or concealment. However, females differed by 53-fold (or more) in their intra-individual variability (i.e., predictability) with respect to distances moved and changes in nest height between nesting attempts, indicating that either some systematic variation went unexplained and/or females have inherently different predictability. Ignoring these individual differences in residual variance in our models obscured the effect of nest fate on re-nesting decisions that were evident at the mean level.

A review of the relationship between socioeconomic position and the early-life predictors of obesity

A range of important early-life predictors of later obesity have been identified. Children of lower socioeconomic position (SEP) have a steeper weight gain trajectory from birth with a strong socioeconomic gradient in child and adult obesity prevalence. An assessment of the association between SEP and the early-life predictors of obesity has been lacking. The review involved a two-stage process: Part 1, using previously published systematic reviews, we developed a list of the potentially modifiable determinants of obesity observable in the pre-natal, peri-natal or post-natal (pre-school) periods; and part 2, conducting a literature review of evidence for socioeconomic patterning in the determinants identified in part 1. Strong evidence was found for an inverse relationship between SEP and (1) pre-natal risk factors (pre-pregnancy maternal body mass index (BMI), diabetes and pre-pregnancy diet), (2) antenatal/peri natal risk factors (smoking during pregnancy and low birth weight) and (3) early-life nutrition (including breastfeeding initiation and duration, early introduction of solids, maternal and infant diet quality, and some aspects of the home food environment), and television viewing in young children. Less strong evidence (because of a lack of studies for some factors) was found for paternal BMI, maternal weight gain during pregnancy, child sleep duration, high birth weight and lack of physical activity in young children. A strong socioeconomic gradient exists for the majority of the early-life predictors of obesity suggesting that the die is cast very early in life (even pre-conception). Lifestyle interventions targeting disadvantaged women at or before child-bearing age may therefore be particularly important in reducing inequality. Given the likely challenges of reaching this target population, it may be that during pregnancy and their child's early years are more feasible windows for engagement.

Trends in child and adolescent obesity prevalence in economically advanced countries according to socioeconomic position: a systematic review

Recent obesity trends in children and adolescents suggest a plateau. However, it is unclear whether such trends have been experienced across socioeconomic groups. We analysed whether recent trends in child and adolescent overweight and obesity differ by socioeconomic position (SEP) across economically advanced countries. Eligible studies reported overweight and obesity prevalence in children and/or adolescents (2-18 years), for at least two time points since 1990, stratified by SEP. Socioeconomic differences in trends in child and adolescent overweight and obesity over time were analysed. Differences in trends between SEP groups were observed across a majority of studies. Over half the studies indicated increasing prevalence among low SEP children and adolescents compared to a third of studies among children and adolescents with a high SEP. Around half the studies indicated widening socioeconomic inequalities in overweight and obesity. Since 2000 a majority of studies demonstrated no change or a decrease in prevalence among both high and low SEP groups. However around 40% of studies indicated widening of socioeconomic inequalities post-2000. While our study provides grounds for optimism, socioeconomic inequalities in overweight and obesity continue to widen. These findings highlight the need for greater consideration of different population groups when implementing obesity interventions. © 2015 World Obesity.