Aim: While studies using global positioning systems (GPS) have the potential to refine measures of exposure to the neighbourhood environment in health research, one limitation is that they do not typically identify time spent undertaking journeys in motorised vehicles when contact with the environment is reduced. This paper presents and tests a novel methodology to explore the impact of this concern. Methods: Using a case study of exposure assessment to food environments, an unsupervised computational algorithm is employed in order to infer two travel modes: motorised and non-motorised, on the basis of which trips were extracted. Additional criteria are imposed in order to improve robustness of the algorithm. Results: After removing noise in the GPS data and motorised vehicle journeys, 82.43% of the initial GPS points remained. In addition, after comparing a sub-sample of trips classified visually of motorised, non-motorised and mixed mode trips with the algorithm classifications, it was found that there was an agreement of 88%. The measures of exposure to the food environment calculated before and after algorithm classification were strongly correlated. Conclusion: Identifying non-motorised exposures to the food environment makes little difference to exposure estimates in urban children but might be important for adults or rural populations who spend more time in motorised vehicles

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

Recommender systems support decisions in various domains ranging from simple items such as books and movies to more complex items such as financial services, telecommunication equipment, and software systems. In this context, recommendations are determined, for example, on the basis of analyzing the preferences of similar users. In contrast to simple items which can be enumerated in an item catalog, complex items have to be represented on the basis of variability models (e.g., feature models) since a complete enumeration of all possible configurations is infeasible and would trigger significant performance issues. In this paper, we give an overview of a potential new line of research which is related to the application of recommender systems and machine learning techniques in feature modeling and configuration. In this context, we give examples of the application of recommender systems and machine learning and discuss future research issues.

Constraint solving is applied in different application contexts. Examples thereof are the configuration of complex products and services, the determination of production schedules, and the determination of recommendations in online sales scenarios. Constraint solvers apply, for example, search heuristics to assure adequate runtime performance and prediction quality. Several approaches have already been developed showing that machine learning (ML) can be used to optimize search processes in constraint solving. In this article, we provide an overview of the state of the art in applying ML approaches to constraint solving problems including constraint satisfaction, SAT solving, answer set programming (ASP) and applications thereof such as configuration, constraint-based recommendation, and model-based diagnosis. We compare and discuss the advantages and disadvantages of these approaches and point out relevant directions for future work.

User preferences are a crucial input needed by recommender systems to determine relevant items. In single-shot recommendation scenarios such as content-based filtering and collaborative filtering, user preferences are represented, for example, as keywords, categories, and item ratings. In conversational recommendation approaches such as constraint-based and critiquing-based recommendation, user preferences are often represented on the semantic level in terms of item attribute values and critiques. In this article, we provide an overview of preference representations used in different types of recommender systems. In this context, we take into account the fact that preferences aren’t stable but are rather constructed within the scope of a recommendation process. In which way preferences are determined and adapted is influenced by various factors such as personality traits, emotional states, and cognitive biases. We summarize preference construction related research and also discuss aspects of counteracting cognitive biases.