While the characterization of food consumption level has been extensively studied in nutrition and psychology research, advancements in passive smartphone sensing have not been fully utilized to complement mobile food diaries in characterizing food consumption levels. In this study, a new dataset regarding the holistic food consumption behavior of 84 college students in Mexico was collected using a mobile application combining passive smartphone sensing and self-reports. We show that factors such as sociability and activity types and levels have an association to food consumption levels. Finally, we define and assess a novel ubicomp task, by using machine learning techniques to infer self-perceived food consumption level (eating as usual, overeating, undereating) with an accuracy of 87.81% in a 3-class classification task by using passive smartphone sensing and self-report data. Furthermore, we show that an accuracy of 83.49% can be achieved for the same classification task by using only smartphone sensing data and time of eating, which is an encouraging step towards building context-aware mobile food diaries and making food diary based apps less tedious for users.

Abstract-Society is moving towards a socio-technical ecosystem in which physical and virtual dimensions of life are intertwined and where people interactions ever more take place with or are mediated by machines. Hybrid Diversity-aware Collective Adaptive Systems (HDA-CAS) is a new generation of sociotechnical systems where humans and machines synergetically complement each other and operate collectively to achieve their goals. HDA-CAS introduce the fundamental properties of hybridity and collectiveness, hiding from the users the complexities associated with managing the collaboration and coordination of machine and human computing elements. In this paper we present an HDA-CAS system called SmartSociety, supporting computations with hybrid human/machine collectives. We describe the platform's architecture and functionality, validate it on two real-world scenarios involving human and machine elements and present a performance evaluation.

Abstract. In this paper, we introduce a privacy-enhanced Peer Manager, which is a fundamental building block for the implementation of a privacypreserving collective adaptive systems computing platform. The Peer Manager is a user-centered identity management platform that keeps information owned by a user private and is built upon an attribute-based privacy policy. Furthermore, this paper explores the ethical, privacy and social values aspects of collective adaptive systems and their extensive capacity to transform lives. We discuss the privacy, social and ethical issues around profiles and present their legal privacy requirements from the European legislation perspective.

Mood inference with mobile sensing data has been studied in ubicomp literature over the last decade. This inference enables context-aware and personalized user experiences in general mobile apps and valuable feedback and interventions in mobile health apps. However, even though model generalization issues have been highlighted in many studies, the focus has always been on improving the accuracies of models using different sensing modalities and machine learning techniques, with datasets collected in homogeneous populations. In contrast, less attention has been given to studying the performance of mood inference models to assess whether models generalize to new countries. In this study, we collected a mobile sensing dataset with 329K self-reports from 678 participants in eight countries (China, Denmark, India, Italy, Mexico, Mongolia, Paraguay, UK) to assess the effect of geographical diversity on mood inference models. We define and evaluate country-specific (trained and tested within a country), continent-specific (trained and tested within a continent), country-agnostic (tested on a country not seen on training data), and multi-country (trained and tested with multiple countries) approaches trained on sensor data for two mood inference tasks with population-level (non-personalized) and hybrid (partially personalized) models. We show that partially personalized country-specific models perform the best yielding area under the receiver operating characteristic curve (AUROC) scores of the range 0.78--0.98 for two-class (negative vs. positive valence) and 0.76--0.94 for three-class (negative vs. neutral vs. positive valence) inference. Further, with the country-agnostic approach, we show that models do not perform well compared to country-specific settings, even when models are partially personalized. We also show that continent-specific models outperform multi-country models in the case of Europe. Overall, we uncover generalization issues of mood inference models to new countries and how the geographical similarity of countries might impact mood inference.

No abstract