Air pollution is one of the leading causes of mortality globally, resulting in millions of deaths each year. Efficient monitoring is important to measure exposure and enforce legal limits. New low-cost sensors can be deployed in greater numbers and in more varied locations, motivating the problem of efficient automated placement. Previous work suggests Bayesian optimisation is an appropriate method, but only considered a satellite data set, with data aggregated over all altitudes. It is ground-level pollution, that humans breathe, which matters most. We improve on those results using hierarchical models and evaluate our models on urban pollution data in London to show that Bayesian optimisation can be successfully applied to the problem.

Energy disaggregation (a.k.a nonintrusive load monitoring, NILM), a single-channel blind source separation problem, aims to decompose the mains which records the whole house electricity consumption into appliance-wise readings. This problem is difficult because it is inherently unidentifiable. Recent approaches have shown that the identifiability problem could be reduced by introducing domain knowledge into the model. Deep neural networks have been shown to be a promising approach for these problems, but sliding windows are necessary to handle the long sequences which arise in signal processing problems, which raises issues about how to combine predictions from different sliding windows. In this paper, we propose sequence-to-point learning, where the input is a window of the mains and the output is a single point of the target appliance. We use convolutional neural networks to train the model. Interestingly, we systematically show that the convolutional neural networks can inherently learn the signatures of the target appliances, which are automatically added into the model to reduce the identifiability problem. We applied the proposed neural network approaches to real-world household energy data, and show that the methods achieve state-of-the-art performance, improving two standard error measures by 84% and 92%.

Decreasing our demand for energy is an important component of the global effort to reduce carbon emissions. Energy consumption, both at home and in the workplace, is greatly influenced by human behaviour. Our research investigates how technological interventions could support behaviour-based energy reduction. This paper reports a Living Lab study on the co-design of a device for improving energy efficiency via behaviour change in a large public-sector organisation. We emphasise the importance of taking a broad view of organisational behaviour, highlighting the complex and indirect ways that it influences energy use. Methods and findings are reported from a series of insight and innovation workshops that we held with staff, and which led to the development of a prototype device - LILEE: The Little Interface for Lab Equipment Efficiency. We describe LILEE and discuss how it embodies wider lessons for the design of effective energy-related behaviour change interventions.

In many statistical problems, a more coarse-grained model may be suitable for population-level behaviour, whereas a more detailed model is appropriate for accurate modelling of individual behaviour. This raises the question of how to integrate both types of models. Methods such as posterior regularization follow the idea of generalized moment matching, in that they allow matchingexpectations between two models, but sometimes both models are most conveniently expressed as latent variable models. We propose latent Bayesian melding, which is motivated by averaging the distributions over populations statistics of both the individual-level and the population-level models under a logarithmic opinion pool framework. In a case study on electricity disaggregation, which is a type of single-channel blind source separation problem, we show that latent Bayesian melding leads to significantly more accurate predictions than an approach based solely on generalized moment matching.

Abstract The integrative ambitions of systems biology and neuroinformatics—to construct working models of the machinery of living cells and brains—will flounder unless researchers have access to the huge amounts of diverse experimental data being collected. However, the vast majority of bioscience research data that is gathered is never made available to other researchers, partly for the want of an adequate software for annotating experimental data, and partly for social reasons (researchers are rarely rewarded for publishing the actual data sets—just for journal articles summarizing findings). We have developed a novel software solution aimed at making it simpler for researchers to annotate and publish their research data. The first part of this solution is a desktop application, Catalyzer, which lets researchers structure their data at source, and complements existing ad hoc solutions in use in labs (including cryptic filenames, Word, Excel, paper lab books) while being simpler and more flexible than relational databases, which are too complex for most bioscience researchers to set up. The catalogs produced by Catalyzer are stored in XML with a user defined schema, which will simplify future data mining efforts across large numbers of distributed data sets. The approach can be summarized as ‘structure at source, integrate as required’, with the initial focus on enabling the researchers to structure their own research data; only then will other researchers be able to integrate across data sets. Copyright © 2006 John Wiley & Sons, Ltd.