Visual communication design as a form of public pedagogy

This paper identifies visual communication design as a form of public pedagogy. Communication design practices aim to achieve the successful transmission of a message to a recipient in a visual mode. Understanding the theories and practices of visual communication design can assist in enhancing the reception of the communication, as these practices become a tool to increase the effectiveness of learning in a public space. To demonstrate this, I will use the example of museums as an informal place of public learning, and argue design, and in particular visual communication design strategies, are extremely important in the creation of successful learning. If participants are not engaged or entertained, their capacity for learning will diminish. Engagement depends on the representation of the information and the successful interpretation of that information by the visitor. Further, this paper will emphasize the vital role communication design plays in all forms of public pedagogy, not just within the museum context. However, non-designers create many public learning environments and although this paper argues the benefits of communication design to increasing the effectiveness of learning, it recognizes the narrow opportunities of applying this knowledge.

Learning vector representation of medical objects via EMR-driven nonnegative restricted Boltzmann machines (eNRBM)

Electronic medical record (EMR) offers promises for novel analytics. However, manual feature engineering from EMR is labor intensive because EMR is complex - it contains temporal, mixed-type and multimodal data packed in irregular episodes. We present a computational framework to harness EMR with minimal human supervision via restricted Boltzmann machine (RBM). The framework derives a new representation of medical objects by embedding them in a low-dimensional vector space. This new representation facilitates algebraic and statistical manipulations such as projection onto 2D plane (thereby offering intuitive visualization), object grouping (hence enabling automated phenotyping), and risk stratification. To enhance model interpretability, we introduced two constraints into model parameters: (a) nonnegative coefficients, and (b) structural smoothness. These result in a novel model called eNRBM (EMR-driven nonnegative RBM). We demonstrate the capability of the eNRBM on a cohort of 7578 mental health patients under suicide risk assessment. The derived representation not only shows clinically meaningful feature grouping but also facilitates short-term risk stratification. The F-scores, 0.21 for moderate-risk and 0.36 for high-risk, are significantly higher than those obtained by clinicians and competitive with the results obtained by support vector machines.

Redistribution, recognition and representation: working against pedagogies of indifference

This paper reports on an Australian government-commissioned research study that documented classroom pedagogies in 24 Queensland schools. The research created the model of ‘productive pedagogies’, which conjoined what Nancy Fraser calls a politics of redistribution, recognition and representation. In this model pedagogies are differentiated to support the role of schooling as a positional good, a good in itself, and a good towards the betterment of the broader social world. In contrast with the model’s intentions, the pedagogies mapped in the study’s classrooms lacked differentiation; indeed, they reflected ‘pedagogies of indifference’ and were seen as producing and legitimising social inequalities. The paper theorises the redistributive, recognitive and representative justice possibilities of ‘productive pedagogies’ towards more equitable outcomes for marginalised students. The paper justifies its reprising of this research in light of the contemporary policy emphasis on teaching quality, the reductive impact on pedagogies of high-stakes testing, and the context of growing inequality which limits the potential effects of schools and teacher pedagogies.