Bio-inspired enhancement of reputation systems for intelligent environments

Providing security to the emerging field of ambient intelligence will be difficult if we rely only on existing techniques, given their dynamic and heterogeneous nature. Moreover, security demands of these systems are expected to grow, as many applications will require accurate context modeling. In this work we propose an enhancement to the reputation systems traditionally deployed for securing these systems. Different anomaly detectors are combined using the immunological paradigm to optimize reputation system performance in response to evolving security requirements. As an example, the experiments show how a combination of detectors based on unsupervised techniques (self-organizing maps and genetic algorithms) can help to significantly reduce the global response time of the reputation system. The proposed solution offers many benefits: scalability, fast response to adversarial activities, ability to detect unknown attacks, high adaptability, and high ability in detecting and confining attacks. For these reasons, we believe that our solution is capable of coping with the dynamism of ambient intelligence systems and the growing requirements of security demands.

Evaluating social choice techniques into intelligent environments by agent based social simulation

The primary hypothesis stated by this paper is that the use of social choice theory in Ambient Intelligence systems can improve significantly users satisfaction when accessing shared resources. A research methodology based on agent based social simulations is employed to support this hypothesis and to evaluate these benefits. The result is a six-fold contribution summarized as follows. Firstly, several considerable differences between this application case and the most prominent social choice application, political elections, have been found and described. Secondly, given these differences, a number of metrics to evaluate different voting systems in this scope have been proposed and formalized. Thirdly, given the presented application and the metrics proposed, the performance of a number of well known electoral systems is compared. Fourthly, as a result of the performance study, a novel voting algorithm capable of obtaining the best balance between the metrics reviewed is introduced. Fifthly, to improve the social welfare in the experiments, the voting methods are combined with cluster analysis techniques. Finally, the article is complemented by a free and open-source tool, VoteSim, which ensures not only the reproducibility of the experimental results presented, but also allows the interested reader to adapt the case study presented to different environments.

Accessible interaction solution based on confidence for the deployment of pervasive sensitive services in intelligent environments

Los servicios basados en las Tecnologías de la Información y las Comunicaciones (TIC) están cada vez más presentes en la vida de las personas. El avance de las TIC en términos técnicos y de aceptación social ha dado lugar la creación de nuevos modelos de provisión de servicios. Estos modelos de servicio implican una mayor integración con las actividades de las personas de forma que ya no solo están presentes en su ámbito profesional o de espacio ciudadano sino también en un ámbito más íntimo relacionado con su propia identidad. Así en la actualidad es común encontrar servicios conocedores del estado de salud de las personas, sus hábitos domésticos, su ideología, etc. Por tanto el análisis de los servicios actuales no puede limitarse a una componente técnica sino que es más necesario que nunca la inclusión de aspectos más relacionados con la forma de ser y sentir de sus usuarios. De esta forma no solo se garantizará la corrección técnica de sus funcionalidades sino que también se fomentará la generación de soluciones cívicamente seguras y respetuosas tanto con los derechos como con la forma de ser y sentir de sus usuarios. Desde el punto de vista de ingeniería, la perspectiva del usuario se ha englobado históricamente bajo el concepto de aceptación tecnológica. Dentro de este ámbito se puede interpretar que soluciones respetuosas y adaptadas a los usuarios fomentarán la aceptación por parte de éstos. La aceptación de una solución es algo deseable si bien es difícil de asegurar. Esta dificultad es debida al desconocimiento del número de variables que afectan a la aceptación de soluciones tecnológicas y a la dificultad de optimización de las variables conocidas. En esta tesis doctoral se estudia y caracteriza una de las variables que afecta a la aceptación de los servicios actuales: la confianza. Se define la confianza en términos psicológicos caracterizándola para permitir su uso en los métodos propios de la ingeniería. Además se proponen distintas herramientas que facilitan la optimización de la confianza en servicios cuya complejidad convierte a esta variable en una cuestión básica para mejorar la aceptación. Como contexto de trabajo para la tesis se ha escogido un servicio de salud desplegado en un hogar. Este escenario presenta una serie de restricciones de aceptación relativas a la tecnología utilizada para la creación de los servicios y la forma en que éstos gestionan la información adquirida del usuario. Se trata de servicios altamente sensibles y deslocalizados que pueden afectar a la percepción del usuario sobre el entorno, el hogar, y generar temores o rechazos que impidan su adopción final como solución válida. Una vez definido el marco genérico de trabajo, el objetivo principal de esta tesis doctoral se concreta en contribuir al fomento de la aceptación de nuevos servicios de salud pervasivos y personalizados y su despliegue en entornos inteligentes domésticos mediante un marco de diseño que promueva un estado psicológico de confianza en los usuarios. Para lograr abordar correctamente este objetivo se han proporcionado una serie de resultados tanto a nivel conceptual como tecnológico y experimental. En concreto se ha ofrecido una caracterización completa del sentimiento de confianza desde un punto de vista de ingeniería y una definición del concepto de servicio sensible deslocalizado o pervasivo. Además se ofrece un método para la inclusión del Diseño de Interacción, herramienta muy relacionada con la mejora de las variables de aceptación de tecnología, en los procesos de ingeniería de este tipo de servicios mediante un conjunto de patrones de interacción Persona – Entorno Inteligente. Finalmente se ha proporcionado el desarrollo de una arquitectura software para garantizar el correcto despliegue de estos servicios sensibles pervasivos en espacios inteligentes de una forma confiable. La discusión de los resultados obtenidos sugiere la extensión del modelo a diferentes servicios de la Sociedad de la Información que manejen datos sensibles tanto en el contexto del Hogar Digital como otros contextos donde el usuario realice actividades cotidianas, como los espacios de trabajo o los centros educativos. Las líneas de trabajo futuras contemplan la necesidad inminente de aplicar los resultados a desarrollos en curso, dentro de proyectos de investigación en los que participa el autor así como el desarrollo de nuevas líneas de investigación orientadas a la generación de nuevos espacios y tecnologías de interacción como el Colegio Digital, juguetes del futuro, sistemas de visualización confiables o sistemas de seguridad basados en el estado de las personas.

Adapting workflows to intelligent environments

Intelligent environments aim at supporting the user in executing her everyday tasks, e.g. by guiding her through a maintenance or cooking procedure. This requires a machine processable representation of the tasks for which workflows have proven an efficient means. The increasing number of available sensors in intelligent environments can facilitate the execution of workflows. The sensors can help to recognize when a user has finished a step in the workflow and thus to automatically proceed to the next step. This can heavily reduce the amount of required user interaction. However, manually specifying the conditions for triggering the next step in a workflow is very cumbersome and almost impossible for environments which are not known at design time. In this paper, we present a novel approach for learning and adapting these conditions from observation. We show that the learned conditions can even outperform the quality as conditions manually specified by workflow experts. Thus, the presented approach is very well suited for automatically adapting workflows in intelligent environments and can in that way increase the efficiency of the workflow execution. © 2011 IEEE.

Interfaces for Intelligent Environments

Presentaciones de la asignatura Interfaces para Entornos Inteligentes del Máster en Tecnologías de la Informática/Machine Learning and Data Mining.

Intelligent agents enabling negotiated control of pervasive environments

One of the important goals of the intelligent buildings especially in commercial applications is not only to minimize the energy consumption but also to enhance the occupant’s comfort. However, most of current development in the intelligent buildings focuses on an implementation of the automatic building control systems that can support energy efficiency approach. The consideration of occupants’ preferences is not adequate. To improve occupant’s wellbeing and energy efficiency in intelligent environments, we develop four types of agent combined together to form a multi-agent system to control the intelligent buildings. Users’ preferential conflicts are discussed. Furthermore, a negotiation mechanism for conflict resolution, has been proposed in order to reach an agreement, and has been represented in syntax directed translation schemes for future implementation and testing. Keywords: conflict resolution, intelligent buildings, multi-agent systems (MAS), negotiation strategy, syntax directed translation schemes (SDTS).

Engineering social awareness in work environments

A growing interest is seen for designing intelligent environments that support personally meaningful, sociable and rich everyday experiences. In this paper we describe an intelligent, large screen display called Panorama that is aimed at supporting and enhancing social awareness within an academic work environment. Panorama is not intended to provide instrumental or other productivity related information. Rather, the goal of Panorama is to enhance social awareness by providing interpersonal and rich information related to co-workers and their everyday interactions in the department. A two-phase assessment of Panorama showed to promote curiosity and interest in exploring different activities in the environment.

Review of computer vision in intelligent environment design

This paper discusses and compares the use of vision based and non-vision based technologies in developing intelligent environments. By reviewing the related projects that use vision based techniques in intelligent environment design, the achieved functions, technical issues and drawbacks of those projects are discussed and summarized, and the potential solutions for future improvement are proposed, which leads to the prospective direction of my PhD research.

Salutogenesis: a new paradigm for pervasive computing in healthcare environments?

Salutogenesis is now accepted as a part of the contemporary model of disease: an individual is not only affected by pathogenic factors in the environment, but those that promote well-being or salutogenesis. Given that "environment" extends to include the built environment, promotion of salutogenesis has become part of the architectural brief for contemporary healthcare facilities, drawing on an increasing evidence-base. Salutogenesis is inextricably linked with the notion of person-environment "fit". MyRoom is a proposal for an integrated architectural and pervasive computing model, which enhances psychosocial congruence by using real-time data indicative of the individual's physical status to enable the environment of his/her room (colour, light, temperature) to adapt on an on-going basis in response to bio-signals. This work is part of the PRTLI-IV funded programme NEMBES, investigating the use of embedded technologies in the built environment. Different care contexts require variations in the model, and iterative prototyping investigating use in different contexts will progressively lead to the development of a fully-integrated adaptive salutogenic single-room prototype.

Layered Graphical Models for Tracking Partially-Occluded Objects

Partial occlusions are commonplace in a variety of real world computer vision applications: surveillance, intelligent environments, assistive robotics, autonomous navigation, etc. While occlusion handling methods have been proposed, most methods tend to break down when confronted with numerous occluders in a scene. In this paper, a layered image-plane representation for tracking people through substantial occlusions is proposed. An image-plane representation of motion around an object is associated with a pre-computed graphical model, which can be instantiated efficiently during online tracking. A global state and observation space is obtained by linking transitions between layers. A Reversible Jump Markov Chain Monte Carlo approach is used to infer the number of people and track them online. The method outperforms two state-of-the-art methods for tracking over extended occlusions, given videos of a parking lot with numerous vehicles and a laboratory with many desks and workstations.

Deep learning architecture for gesture recognition

Pós-graduação em Engenharia Mecânica - FEG

Plataforma de evaluación de algoritmos para la identificación de usuarios

La minería de datos es un campo de las ciencias de la computación referido al proceso que intenta descubrir patrones en grandes volúmenes de datos. La minería de datos busca generar información similar a la que podría producir un experto humano. Además es el proceso de descubrir conocimientos interesantes, como patrones, asociaciones, cambios, anomalías y estructuras significativas a partir de grandes cantidades de datos almacenadas en bases de datos, data warehouses o cualquier otro medio de almacenamiento de información. El aprendizaje automático o aprendizaje de máquinas es una rama de la Inteligencia artificial cuyo objetivo es desarrollar técnicas que permitan a las computadoras aprender. De forma más concreta, se trata de crear programas capaces de generalizar comportamientos a partir de una información no estructurada suministrada en forma de ejemplos. La minería de datos utiliza métodos de aprendizaje automático para descubrir y enumerar patrones presentes en los datos. En los últimos años se han aplicado las técnicas de clasificación y aprendizaje automático en un número elevado de ámbitos como el sanitario, comercial o de seguridad. Un ejemplo muy actual es la detección de comportamientos y transacciones fraudulentas en bancos. Una aplicación de interés es el uso de las técnicas desarrolladas para la detección de comportamientos fraudulentos en la identificación de usuarios existentes en el interior de entornos inteligentes sin necesidad de realizar un proceso de autenticación. Para comprobar que estas técnicas son efectivas durante la fase de análisis de una determinada solución, es necesario crear una plataforma que de soporte al desarrollo, validación y evaluación de algoritmos de aprendizaje y clasificación en los entornos de aplicación bajo estudio. El proyecto planteado está definido para la creación de una plataforma que permita evaluar algoritmos de aprendizaje automático como mecanismos de identificación en espacios inteligentes. Se estudiarán tanto los algoritmos propios de este tipo de técnicas como las plataformas actuales existentes para definir un conjunto de requisitos específicos de la plataforma a desarrollar. Tras el análisis se desarrollará parcialmente la plataforma. Tras el desarrollo se validará con pruebas de concepto y finalmente se verificará en un entorno de investigación a definir. ABSTRACT. The data mining is a field of the sciences of the computation referred to the process that it tries to discover patterns in big volumes of information. The data mining seeks to generate information similar to the one that a human expert might produce. In addition it is the process of discovering interesting knowledge, as patterns, associations, changes, abnormalities and significant structures from big quantities of information stored in databases, data warehouses or any other way of storage of information. The machine learning is a branch of the artificial Intelligence which aim is to develop technologies that they allow the computers to learn. More specifically, it is a question of creating programs capable of generalizing behaviors from not structured information supplied in the form of examples. The data mining uses methods of machine learning to discover and to enumerate present patterns in the information. In the last years there have been applied classification and machine learning techniques in a high number of areas such as healthcare, commercial or security. A very current example is the detection of behaviors and fraudulent transactions in banks. An application of interest is the use of the techniques developed for the detection of fraudulent behaviors in the identification of existing Users inside intelligent environments without need to realize a process of authentication. To verify these techniques are effective during the phase of analysis of a certain solution, it is necessary to create a platform that support the development, validation and evaluation of algorithms of learning and classification in the environments of application under study. The project proposed is defined for the creation of a platform that allows evaluating algorithms of machine learning as mechanisms of identification in intelligent spaces. There will be studied both the own algorithms of this type of technologies and the current existing platforms to define a set of specific requirements of the platform to develop. After the analysis the platform will develop partially. After the development it will be validated by prove of concept and finally verified in an environment of investigation that would be define.