Search results

Modelling health and economic impact of nutrition interventions

Diet related non-communicable diseases (NCDs), as well as micronutrient deficiencies, are of widespread and growing importance to public health. Authorities are developing programs to improve nutrient intakes via foods. To estimate the potential health andeconomic impact of these programs there is a wide variety of models. The aim of this review is to evaluate existing models to estimate the health and/or economic impact of nutrition interventions with a focus on reducing salt and sugar intake andincreasing vitamin D, iron, and folate/folic acid intake. The protocol of this systematic review has been registered with the International Prospective Register of Systematic Reviews (PROSPERO: CRD42016050873). The final search was conducted onPubMed and Scopus electronic databases and search strings were developed for salt/sodium, sugar, vitamin D, iron, and folic acid intake. Predefined criteria related to scientific quality, applicability, and funding/interest were used to evaluate the publications. In total 122 publications were included for a critical appraisal: 45 for salt/sodium, 61 for sugar, 4 for vitamin D, 9 for folic acid, and 3 for iron. The complexity of modelling the health and economic impact of nutrition interventions is dependent on the purpose and data availability. Although most of the models have the potential to provide projections of future impact, the methodological challenges are considerable. There is a substantial need for more guidance and standardization for future modelling, to compare results ofdifferent studies and draw conclusions about the health and economic impact of nutrition interventions.

Heuristic Coordination in Cooperative Multi-Agent Reinforcement Learning

Key to reinforcement learning in multi-agent systems is the ability to exploit the fact that agents only directly influence only a small subset of the other agents. Such loose couplings are often modelled using a graphical model: a coordination graph. Finding an (approximately) optimal joint action for a given coordination graph is therefore a central subroutine in cooperative multi-agent reinforcement learning (MARL). Much research in MARL focuses on how to gradually update the parameters of the coordination graph, whilst leaving the solving of the coordination graph up to a known typically exact and generic subroutine. However, exact methods { e.g., Variable Elimination { do not scale well, and generic methods do not exploit the MARL setting of gradually updating a coordination graph and recomputing the joint action to select. In this paper, we examine what happens if we use a heuristic method, i.e., local search, to select joint actions in MARL, and whether we can use outcome of this local search from a previous time-step to speed up and improve local search. We show empirically that by using local search, we can scale up to many agents and complex coordination graphs, and that by reusing joint actions from the previous time-step to initialise local search, we can both improve the quality of the joint actions found and the speed with which these joint actions are found.

Grounding Causality in Bayesian Networks Using Qualitative Reasoning

The complexity of analysing dynamical systems often lies in the difficulty to monitor each of their dynamic properties. In this article, we use qualitative models to present an exhaustive way of representing every possible state of a given system, and combine it with Bayesian networks to integrate quantitative information and reasoning under uncertainty. The result is a combined model able to give explanations relying on expert knowledge to predict the behaviour of a system. We illustrate our approach with a deterministic model to show how the combination is done, then extend this model to integrate uncertainty and demonstrate its benefits

Latent Hierarchical Model for Activity Recognition

We present a novel hierarchical model for human activity recognition. In contrast with approaches that successively recognize actions and activities, our approach jointly models actions and activities in a unified framework, and their labels are simultaneously predicted. The model is embedded with a latent layer that is able to capture a richer class of contextual information in both state-state and observation-state pairs. Although loops are present in the model, the model has an overall linear-chain structure, where the exact inference is tractable. Therefore, the model is very efficient in both inference and learning. The parameters of the graphical model are learned with a structured support vector machine. A data-driven approach is used to initialize the latent variables; therefore, no manual labeling for the latent states is required. The experimental results from using two benchmark datasets show that our model outperforms the state-of-the-art approach, and our model is computationally more efficient.

Using graphical models to explore relationships between variables underlying community energy initiatives.

Using a Gaussian Graphical Model to Explore Relationships Between Items and Variables in Environmental Psychology Research

Exploratory analyses are an important first step in psychological research, particularly in problem-based research where various variables are often included from multiple theoretical perspectives not studied together in combination before. Notably, exploratory analyses aim to give first insights into how items and variables included in a study relate to each other. Typically, exploratory analyses involve computing bivariate correlations between items and variables and presenting them in a table. While this is suitable for relatively small data sets, such tables can easily become overwhelming when datasets contain a broad set of variables from multiple theories. We propose the Gaussian graphical model as a novel exploratory analyses tool and present a systematic roadmap to apply this model to explore relationships between items and variables in environmental psychology research. We demonstrate the use and value of the Gaussian graphical model to study relationships between a broad set of items and variables that are expected to explain the effectiveness of community energy initiatives in promoting sustainable energy behaviors.