On some properties of weighted averaging with variable weights

Density-based means have been recently proposed as a method for dealing with outliers in the stream processing of data. Derived from a weighted arithmetic mean with variable weights that depend on the location of all data samples, these functions are not monotonic and hence cannot be classified as aggregation functions. In this article we establish the weak monotonicity of this class of averaging functions and use this to establish robust generalisations of these means. Specifically, we find that as proposed, the density based means are only robust to isolated outliers. However, by using penalty based formalisms of averaging functions and applying more sophisticated and robust density estimators, we are able to define a broader family of density based means that are more effective at filtering both isolated and clustered outliers. © 2014 Elsevier Inc. All rights reserved.

A framework for evaluating the impact of obesity prevention strategies on socioeconomic inequalities in weight.

We developed a theoretical framework to organize obesity prevention interventions by their likely impact on the socioeconomic gradient of weight. The degree to which an intervention involves individual agency versus structural change influences socioeconomic inequalities in weight. Agentic interventions, such as standalone social marketing, increase socioeconomic inequalities. Structural interventions, such as food procurement policies and restrictions on unhealthy foods in schools, show equal or greater benefit for lower socioeconomic groups. Many obesity prevention interventions belong to the agento-structural types of interventions, and account for the environment in which health behaviors occur, but they require a level of individual agency for behavioral change, including workplace design to encourage exercise and fiscal regulation of unhealthy foods or beverages. Obesity prevention interventions differ in their effectiveness across socioeconomic groups. Limiting further increases in socioeconomic inequalities in obesity requires implementation of structural interventions. Further empirical evaluation, especially of agento-structural type interventions, remains crucial.

A hybrid weighted aggregation method based on consistency and consensus in group decision making

A recent study in Science indicated that the confidence of a decision maker played an essential role in group decision making problems. In order to make use of the information of each individual's confidence of the current decision problem, a new hybrid weighted aggregation method to solve a group decision making peoblem is proposed in this paper. Specifically, the hybrid weight of each expert is generated by a convex combination of his/her subjective experience-based weight and objective problem-domain-based weight. The experience-based weight is derived from the expert's historical experiences and the problem-domain-based weight is characterized by the confidence degree and consensus degree of each expert's opinions in the current decision making process. Based on the hybrid weighted aggregation method, all the experts' opinions which are expressed in the form of fuzzy preference relations are consequently aggregated to obtain a collective group opinion. Some valuable properities of the proposed method are discussed. A nurse manager hiring problem in a hospital is employed to illustrate that the proposed method provides a rational and valid solution for the group decision making problem when the experts are not willing to change their initial preferences, or the cost of change is high due to time limitation.

New generalized Halanay inequalities with applications to stability of nonlinear non-autonomous time-delay systems

In this paper, a general class of Halanay-type non-autonomous functional differential inequalities is considered. A new concept of stability, namely global generalized exponential stability, is proposed. We first prove some new generalizations of the Halanay inequality. We then derive explicit criteria for global generalized exponential stability of nonlinear non-autonomous time-delay systems based on our new generalized Halanay inequalities. Numerical examples and simulations are provided to illustrate the effectiveness of the obtained results.

Mining allocating patterns in one-sum weighted items

An Association Rule (AR) is a common knowledge model in data mining that describes an implicative cooccurring relationship between two disjoint sets of binary-valued transaction database attributes (items), expressed in the form of an "antecedent⇒ consequent" rule. A variant of the AR is the Weighted Association Rule (WAR). With regard to a marketing context, this paper introduces a new knowledge model in data mining -ALlocating Pattern (ALP). An ALP is a special form of WAR, where each rule item is associated with a weighting score between 0 and 1, and the sum of all rule item scores is 1. It can not only indicate the implicative co-occurring relationship between two (disjoint) sets of items in a weighted setting, but also inform the "allocating" relationship among rule items. ALPs can be demonstrated to be applicable in marketing and possibly a surprising variety of other areas. We further propose an Apriori based algorithm to extract hidden and interesting ALPs from a "one-sum" weighted transaction database. The experimental results show the effectiveness of the proposed algorithm. © 2008 IEEE.

Institutional processes and the production of gender inequalities: the case of Australian child support research and administration

This article analyses the administrative and research capture of child support data as a case study of how institutional data collection processes are performative in perpetuating gendered inequalities. We compare interviews with 19 low-income single mothers and their longitudinal survey responses from the same research to reveal how low-income women strategically or inadvertently ‘smoothed’ their experiences when responding to data collection processes. This directly resulted in material and symbolic costs in the form of reduced welfare benefits and limited evidence with which to lobby for policy reform. These processes in turn provided benefits to fathers and the state in the form of reduced child support liabilities and enforcement action, and welfare outlays, respectively. We conclude that current administrative and research data collection practices provide a limited and gendered evidence base for administrative justice and policy reform.

Addressing migration-related social and health inequalities in Australia: call for research funding priorities to recognise the needs of migrant populations

Objective Migrants constitute 26% of the total Australian population and, although disproportionately affected by chronic diseases, they are under-represented in health research. The aim of the present study was to describe trends in Australian Research Council (ARC)- and National Health and Medical Research Council (NHMRC)-funded initiatives from 2002 to 2011 with a key focus on migration-related research funding.Methods Data on all NHMRC- and ARC-funded initiatives between 2002 and 2011 were collected from the research funding statistics and national competitive grants program data systems, respectively. The research funding expenditures within these two schemes were categorised into two major groups: (1) people focused (migrant-related and mainstream-related); and (2) basic science focused. Descriptive statistics were used to summarise the data and report the trends in NHMRC and ARC funding over the 10-year period.Results Over 10 years, the ARC funded 15 354 initiatives worth A$5.5 billion, with 897 (5.8%) people-focused projects funded, worth A$254.4 million. Migrant-related research constituted 7.8% of all people-focused research. The NHMRC funded 12 399 initiatives worth A$5.6 billion, with 447 (3.6%) people-focused projects funded, worth A$207.2 million. Migrant-related research accounted for 6.2% of all people-focused initiatives.Conclusions Although migrant groups are disproportionately affected by social and health inequalities, the findings of the present study show that migrant-related research is inadequately funded compared with mainstream-related research. Unless equitable research funding is achieved, it will be impossible to build a strong evidence base for planning effective measures to reduce these inequalities among migrants.What is known about the topic? Immigration is on the rise in most developing countries, including Australia, and most migrants come from low- and middle-income countries. In Australia, migrants constitute 26% of the total Australian population and include refugee and asylum seeker population groups. Migrants are disproportionately affected by disease, yet they have been found to be under-represented in health research and public health interventions.What does this paper add? This paper highlights the disproportions in research funding for research among migrants. Despite migrants being disproportionately affected by disease burden, research into their health conditions and risk factors is grossly underfunded compared with the mainstream population.What are the implications for practitioners? Migrants represent a significant proportion of the Australian population and hence are capable of incurring high costs to the Australian health system. There are two major implications for practitioners. First, the migrant population is constantly growing, therefore integrating the needs of migrants into the development of health policy is important in ensuring equity across health service delivery and utilisation in Australia. Second, the health needs of migrants will only be uncovered when a clear picture of their true health status and other determinants of health, such as psychological, economic, social and cultural, are identified through empirical research studies. Unless equitable research funding is achieved, it will be impossible to build a strong evidence base for planning effective measures to reduce health and social inequalities among migrant communities.

Thurstonian Boltzmann machines: learning from multiple inequalities

We introduce Thurstonian Boltzmann Machines (TBM), a unified architecture that can naturally incorporate a wide range of data inputs at the same time. Our motivation rests in the Thurstonian view that many discrete data types can be considered as being generated from a subset of underlying latent continuous variables, and in the observation that each realisation of a discrete type imposes certain inequalities on those variables. Thus learning and inference in TBM reduce to making sense of a set of inequalities. Our proposed TBM naturally supports the following types: Gaussian, intervals, censored, binary, categorical, muticategorical, ordinal, (in)-complete rank with and without ties. We demonstrate the versatility and capacity of the proposed model on three applications of very different natures; namely handwritten digit recognition, collaborative filtering and complex social survey analysis. Copyright 2013 by the author(s).

The mediating role of dietary factors and leisure time physical activity on socioeconomic inequalities in body mass index among Australian adults

BACKGROUND: The relationship between socioeconomic position and obesity has been clearly established, however, the extent to which specific behavioural factors mediate this relationship is less clear. This study aimed to ascertain the contribution of specific dietary elements and leisure-time physical activity (LTPA) to variations in obesity with education in the baseline (1990-1994) Melbourne Collaborative Cohort Study (MCCS).

METHODS: 18, 489 women and 12, 141 men were included in this cross-sectional analysis. A series of linear regression models were used in accordance with the products of coefficients method to examine the mediating role of alcohol, soft drink (regular and diet), snacks (healthy and sweet), savoury items (healthy and unhealthy), meeting fruit and vegetable guidelines and LTPA on the relationship between education and body mass index (BMI).

RESULTS: Compared to those with lowest educational attainment, those with the highest educational attainment had a 1 kg/m2 lower BMI. Among men and women, 27% and 48%, respectively, of this disparity was attributable to differences in LTPA and diet. Unhealthy savoury item consumption and LTPA contributed most to the mediated effects for men and women. Alcohol and diet soft drink were additionally important mediators for women.

CONCLUSIONS: Diet and LTPA are potentially modifiable behavioural risk factors for the development of obesity that contribute substantially to inequalities in BMI. Our findings highlight the importance of specific behaviours which may be useful to the implementation of effective, targeted public policy to reduce socioeconomic inequalities in obesity.

Extension of bivariate means to weighted means of several arguments by using binary trees

ABSTRACTAveraging aggregation functions are valuable in building decision making and fuzzy logic systems and in handling uncertainty. Some interesting classes of averages are bivariate and not easily extended to the multivariate case. We propose a generic method for extending bivariate symmetric means to n-variate weighted means by recursively applying the specified bivariate mean in a binary tree construction. We prove that the resulting extension inherits many desirable properties of the base mean and design an efficient numerical algorithm by pruning the binary tree. We show that the proposed method is numerically competitive to the explicit analytical formulas and hence can be used in various computational intelligence systems which rely on aggregation functions.

A distributed spatial-temporal weighted model on MapReduce for short-term traffic flow forecasting

Accurate and timely traffic flow prediction is crucial to proactive traffic management and control in data-driven intelligent transportation systems (D2ITS), which has attracted great research interest in the last few years. In this paper, we propose a Spatial-Temporal Weighted K-Nearest Neighbor model, named STW-KNN, in a general MapReduce framework of distributed modeling on a Hadoop platform, to enhance the accuracy and efficiency of short-term traffic flow forecasting. More specifically, STW-KNN considers the spatial-temporal correlation and weight of traffic flow with trend adjustment features, to optimize the search mechanisms containing state vector, proximity measure, prediction function, and K selection. urthermore, STW-KNN is implemented on a widely adopted Hadoop distributed computing platform with the MapReduce parallel processing paradigm, for parallel prediction of traffic flow in real time. inally, with extensive experiments on real-world big taxi trajectory data, STW-KNN is compared with the state-of-the-art prediction models including conventional K-Nearest Neighbor (KNN), Artificial Neural Networks (ANNs), Naïve Bayes (NB), Random orest (R), and C4.. The results demonstrate that the proposed model is superior to existing models on accuracy by decreasing the mean absolute percentage error (MAPE) value more than 11.9% only in time domain and even achieves 89.71% accuracy improvement with the MAPEs of between 4% and 6.% in both space and time domains, and also significantly improves the efficiency and scalability of short-term traffic flow forecasting over existing approaches.