This paper presents a proof of concept from which the metaphor of “fair trade” is validated as an alternative to manage the private information of users. Our privacy solution deals with user’s privacy as a tradable good for obtaining environmental services. Thus, users gain access to more valuable services as they share more personal information. This strategy, combined with optimistic access control and transaction registry mechanisms, enhances users’ confidence in the system while encouraging them to share their information, with the consequent benefit for the community. The study results are promising considering the user responses regarding the usefulness, ease of use, information classification and perception of control with the mechanisms proposed by the metaphor.
Leila S. Shafti, Pablo A. Haya, Manuel García-Herranz, Eduardo Pérez
Journal of Ambient Intelligence and Smart Environments 5 (6), 563-587 (2013) [download] (JCR, IF 2012: 1.298, Q2)
One of the goals in Ambient Intelligence is to enable Intelligent Environments to take decisions based on the perceived context. In our previous work, we successfully explored how the inhabitants can communicate their own preferences with the environment using Event-Condition-Action (ECA) rules. The easiness of the communication language combined with an appropriate explanation mechanism gives trust to the Intelligent Environment actions. However, defining every preference, and maintaining them up-to-date can be cumbersome. Therefore, a complementary mechanism is required to learn from user behavior and adapt to small changes without being explicitly requested for. Inferring behaviors effectively from data collected from sensors in an Intelligent Environment is a challenging problem. The main issues include primitive representation of data, the necessity of a high number of sensors, and dealing with few training data collected in a short time. We present MFE3/GADR, an evolutionary constructive induction method to ease inferring inhabitants’ preferences from data collected from simple sensors. We show that this method detects successfully relevant sensors and constructs highly informative features that abstract relations among them. The constructed features, in addition to improving significantly the learning accuracy, break down and encapsulate the performance of inhabitants into decision trees that can easily be converted to ECA rules for further use in the Intelligent Environment. Comparing the empirical results show that our method can reduce a large set of complex ECA rules that represent the preferences to a smaller set of simple ECA rules.
User Modeling and Adaptation for Daily Routines
Providing Assistance to People with Special Needs
Editors: Estefanía Martín, Pablo A. Haya, Rosa M. Carro
ISBN: 978-1-4471-4777-0 (Print) 978-1-4471-4778-7 (Online)
User Modeling and Adaptation for Daily Routines is motivated by the need to bring attention to how people with special needs can benefit from adaptive methods and techniques in their everyday lives. Assistive technologies, adaptive systems and context-aware applications are three well-established research fields. There is, in fact, a vast amount of literature that covers HCI-related issues in each area separately. However, the contributions in the intersection of these areas have been less visible, despite the fact that such synergies may have a great impact on improving daily living.
Presenting a comprehensive review of state-of-the-art practices on user modeling and adaptation for people with special needs, as well as some reflections on the challenges that need to be addressed in this direction, topics covered within this volume include the analysis, design, implementation and evaluation of adaptive systems to assist users with special needs to take decisions and fulfil daily routine activities. Particular emphasis is paid to major trends in user modeling, ubiquitous adaptive support, diagnostic and accessibility, recommender systems, social interaction, designing and building adaptive assistants for daily routines, field studies and automated evaluation.
Nine leading contributors write on key current research in the domain of adaptive applications for people with special needs, integrating and summarizing findings from the best known international research groups in these areas. User Modeling and Adaptation for Daily Routines highlights how adaptation technologies can ease daily living for all, and support sustainable high-quality healthcare, demographic ageing and social/economic inclusion.
Manuel García-Herranz, Fernando Olivera, Pablo Haya and Xavier Alamán
People interact with each other in many levels of attention, intention and meaning. This Interaction Continuum is used daily to deal with different contexts, adapting the interaction to communication needs and available resources. Nevertheless, computer-supported interaction has mainly focused on the most direct, explicit and intrusive types of human to human Interaction such as phone calls, emails, or video conferences. This paper presents the results of exploring and exploiting the potentials of undemanding interaction mechanisms, paying special attention to subtle communication and background interaction. As we argue the benefits of this type of interaction for people with special needs, we present a theoretical framework to define it and propose a proof of concept based on Augmented Objects and a color codification mechanism. Finally, we evaluate and analyze the strengths and limitations of such approach with people with cognitive disabilities.