Nonnegative blind source separation by sparse component analysis based on determinant measure

The problem of nonnegative blind source separation (NBSS) is addressed in this paper, where both the sources and the mixing matrix are nonnegative. Because many real-world signals are sparse, we deal with NBSS by sparse component analysis. First, a determinant-based sparseness measure, named D-measure, is introduced to gauge the temporal and spatial sparseness of signals. Based on this measure, a new NBSS model is derived, and an iterative sparseness maximization (ISM) approach is proposed to solve this model. In the ISM approach, the NBSS problem can be cast into row-to-row optimizations with respect to the unmixing matrix, and then the quadratic programming (QP) technique is used to optimize each row. Furthermore, we analyze the source identifiability and the computational complexity of the proposed ISM-QP method. The new method requires relatively weak conditions on the sources and the mixing matrix, has high computational efficiency, and is easy to implement. Simulation results demonstrate the effectiveness of our method.

An improved physarum centrality measure for weighted networks

Identification of the most central node within a network is one of the primary problems in network analysis. Among various centrality measures for weighted networks, most are based on the assumption that information only spreads through the shortest paths. Then, a mathematical model of an amoeboid organism has been used by Physarum centrality to relax the assumption. However, its computational complexity is relatively high by finding competing paths between all pairs of nodes in networks. In this paper, with the idea of a ground node, an improved Physarum centrality is proposed by maintaining the feature of original measure with the performance is greatly enhanced. Examples and applications are given to show the efficiency and effectiveness of our proposed measure in weighted networks.

Utilising self-report data to measure racial discrimination in the labour market

Although economists have developed a series of approaches to modelling the existence of labour market discrimination, rarely is this topic examined by analysing self-report survey data. After reviewing theories and empirical models of labour market discrimination, we examine self-reported experience of discrimination at different stages in the labour market, among three racial groups utilising U.S. data from the 2001-2003 National Survey of American Life. Our findings indicate that African Americans and Caribbean blacks consistently report more experience of discrimination in the labour market than their non-Hispanic white counterparts. At different stages of the labour market, including hiring, termination and promotion, these groups are more likely to report discrimination than non-Hispanic whites. After controlling for social desirability bias and several human capital and socio-demographic covariates, the results remain robust for African Americans. However, the findings for Caribbean blacks were no longer significant after adjusting for social desirability bias. Although self-report data is rarely utilised to assess racial discrimination in labour economics, our study confirms the utility of this approach as demonstrated in similar research from other disciplines. Our results indicate that after adjusting for relevant confounders self-report survey data is a viable approach to estimating racial discrimination in the labour market. Implications of the study and directions for future research are provided.

Myopia and pensions in general equilibrium

The US social security tax rate has doubled in the last half century.

Does the degree of myopic behavior that we observe in the US justify the size of the social security program? To study this question we build a computable general equilibrium model that is composed of life-cycle permanent-income consumers who save optimally and “hand-to-mouth” consumers who just consume their disposable income. Our model is a continuous-time, general equilibrium extension of the model by Cremer et al. (Int Tax Public Financ 15(5):547–562, 2008), though we abstract from the redistributive function of social security to focus on myopia. Retirement is a choice variable in our model and the social security program is designed to mimic the US program in which the annuity value of benefits increases with the retirement age. Also, we allow for delayed claiming beyond the date of retirement. The model matches a variety of important data targets relating to saving and retirement. We find that small reductions in the social security tax rate provide significant welfare gains to both groups of consumers.

What features epitomize cohesion: development of a preliminary measure

Presently, no consensus has been reached with regards to measuring workplace cohesion. Cohesion measures often allude to abstract concepts rather than tangible features, therefore this study identified the tangible features and specific practices that epitomize cohesive workgroups. Specifically, 28 individuals were interviewed and asked to reflect upon two workgroups in which they had been employed before, only one of which was cohesive. Participants identified tangible features, practices, or characteristics that typified each of these workgroups. Content analysis uncovered 14 features of cohesion, such as shared emotional events in the past, friendly and welcoming greetings, and a feeling of pride when other people in the team excel on some task. A provisional measure of cohesion was then distilled from these items.

Aggregating fuzzy implications to measure group consensus

We approach the problem of measuring consensus for a set of real inputs by aggregating the fuzzy implication degrees between each pair of inputs. We compare our operator with existing consensus measures in terms of their satisfaction of desirable properties. The appeal of such an approach lies in the interpretability and flexibility that results from component-wise construction which we modeled on the Bonferroni mean. We also outline some intentions for future research.

Nonnegative Blind Source Separation by Sparse Component Analysis Based on Determinant Measure

The problem of nonnegative blind source separation (NBSS) is addressed in this paper, where both the sources and the mixing matrix are nonnegative. Because many real-world signals are sparse, we deal with NBSS by sparse component analysis. First, a determinant-based sparseness measure, named D-measure, is introduced to gauge the temporal and spatial sparseness of signals. Based on this measure, a new NBSS model is derived, and an iterative sparseness maximization (ISM) approach is proposed to solve this model. In the ISM approach, the NBSS problem can be cast into row-to-row optimizations with respect to the unmixing matrix, and then the quadratic programming (QP) technique is used to optimize each row. Furthermore, we analyze the source identifiability and the computational complexity of the proposed ISM-QP method. The new method requires relatively weak conditions on the sources and the mixing matrix, has high computational efficiency, and is easy to implement. Simulation results demonstrate the effectiveness of our method.

Having the courage to measure up for education

In this “age of measurement” it is increasing difficult for educators to educate (Biesta, 2010). The pressures to conform to the demands of bureaucratic authorities generally trump over educators and their aims to educate. One of the factors contributing to this is because as Dewey (1929a, p. 133) has argued, our aims and our desires to educate don’t have deep enough roots. He suggests that educators ought to have “cultivated” and “significant conscious desires” and a disposition to be “courageous” (1929a, p. 134; 1929b, p. 38) in order to attain the independence to ensure that our practices in education are indeed educational. Dewey (1934) called such a disposition a “religious attitude” because it engages with the ultimate concerns that people can aspire towards. In this paper I shall argue that this religious attitude of Dewey’s which can enable our roots to deepen, does not just pertain to our aims of education as an intellectual phenomenon. Rather it can be understood as existential (Webster, 2009) in the sense that aims of education are specific to individuals in situation – not to abstract or universal understandings of education. It shall also be argued that this existential aspect of our being is emotive, and deepening its roots might enable us to become more courageous and thus more able to challenge the barriers inherent in our current ‘age of measurement’ so that education may become more of a reality.

Aussie leads project to measure Iraq’s heritage destruction

A Melbourne academic is leading a very different battle in Iraq: an attempt to restore as much as possible of the country's ransacked cultural heritage.