Ambient Assisted-Living (AAL) is becoming an important research field in Ambient Intelligence. Many technologies have emerged
related with pervasive computing vision, that can give support for AAL. One of the most reliable approaches is based on wireless
sensor networks (WSN). Based on this basic assumption we have taken the promising SunSPOT platform as base support, and build
upon it a services architecture for our AAL proposal. This architectural model allows us the decoupling of applications in
components such as ECG’s monitor, position system or location awareness.

  • Content Type Book Chapter
  • DOI 10.1007/978-3-540-85867-6_28
  • Authors
    • Javier Andréu, University of Granada Software Engineering Department C/ Periodista Daniel Saucedo Aranda s/n 18071 Granada Spain
    • Jaime Viúdez, University of Granada Software Engineering Department C/ Periodista Daniel Saucedo Aranda s/n 18071 Granada Spain
    • Juan A. Holgado, University of Granada Software Engineering Department C/ Periodista Daniel Saucedo Aranda s/n 18071 Granada Spain

Many infrastructural elements required to make pervasive computing a reality are now in place: some have been tested in the
labs, while others are already commercially available. However, the integration of these elements to create ubiquitous applications
is still a daunting task, as the developers have to delve into the low-level details of each of them. With this in mind, we
present UbiSOA, a service-oriented architecture and middleware that allows developers to integrate RFID tags, wireless sensor
networks, and other elements, into ubiquitous applications through the well-known service-oriented paradigm, using the language
of their choice.

  • Content Type Book Chapter
  • DOI 10.1007/978-3-540-85867-6_25
  • Authors
    • J. Antonio García-Macías, CICESE Research Center Computer Science Department Km. 107 Carretera Tijuana-Ensenada Ensenada Baja California Mexico
    • Edgardo Avilés-López, CICESE Research Center Computer Science Department Km. 107 Carretera Tijuana-Ensenada Ensenada Baja California Mexico

This paper presents a new version of an evolutionary algorithm that creates XSLT programs from scratch, given a single example
of their intended input and output. XSLT is a general purpose, document-oriented functional language, generally used to transform
XML documents (or, in general, solve any problem that can be coded as an XML document). Previously, an efficient solution
to the problem was proposed; in this paper, we improve on those results by testing different fitness functions, adding a new
operator and changing the type of output document that can be obtained. Results show that the best results are obtained without
considering the length of the XSLT program and including this new operator. The new type of output files used is also more
realistic, and improves on old results.

  • Content Type Book Chapter
  • DOI 10.1007/978-3-540-85863-8_20
  • Authors
    • P. García-Sánchez, University of Granada GeNeura Team. Departament of Computer Architecture and Computer Technology Spain
    • J. J. Merelo, University of Granada GeNeura Team. Departament of Computer Architecture and Computer Technology Spain
    • J. L. J. Laredo, University of Granada GeNeura Team. Departament of Computer Architecture and Computer Technology Spain
    • A. M. Mora, University of Granada GeNeura Team. Departament of Computer Architecture and Computer Technology Spain
    • P. A. Castillo, University of Granada GeNeura Team. Departament of Computer Architecture and Computer Technology Spain

In this paper we present the comparison of two localization systems where the Received Signal Strength (RSS) is measured to
compute the position of a mobile node. We have implemented two approaches based on channel modelling and fingerprinting respectively.
Our conclusions are supported by experimental results carried out in an indoor environment where a sensor network was deployed.
The results show that in the environment of our experiments the precision of the fingerprinting method is better than the
precision of the one based on channel modelling.

  • Content Type Book Chapter
  • DOI 10.1007/978-3-540-85863-8_88
  • Authors
    • Henar Martín, Universidad Politécnica de Madrid, ETSI Telecomunicación Ciudad Universitaria S/N 28040 Madrid Spain
    • Paula Tarrío, Universidad Politécnica de Madrid, ETSI Telecomunicación Ciudad Universitaria S/N 28040 Madrid Spain
    • Ana M. Bernardos, Universidad Politécnica de Madrid, ETSI Telecomunicación Ciudad Universitaria S/N 28040 Madrid Spain
    • José R. Casar, Universidad Politécnica de Madrid, ETSI Telecomunicación Ciudad Universitaria S/N 28040 Madrid Spain

In this paper, we describe a design and deployment experience of context-aware services for a particular application environment.
The design has been based on a conceptual framework, which identifies the main functional building blocks that a context-aware
system should have. In practice, the context-aware system has been built on an application server as a central element, which
interacts with different data bases where user and context information is stored. To enable positioning and communications,
a hybrid infrastructure combining WiFi and Bluetooth has been deployed. The user experience analysis shows that the acceptance
of the proposed context-aware services is related, firstly, to the stability of the communications and positioning infrastructure.

  • Content Type Book Chapter
  • DOI 10.1007/978-3-540-85863-8_84
  • Authors
    • Ana M. Bernardos, Universidad Politécnica de Madrid – ETSI Telecomunicación Ciudad Universitaria S/N 28040 Madrid Spain
    • Paula Tarrío, Universidad Politécnica de Madrid – ETSI Telecomunicación Ciudad Universitaria S/N 28040 Madrid Spain
    • Josué Iglesias, Universidad Politécnica de Madrid – ETSI Telecomunicación Ciudad Universitaria S/N 28040 Madrid Spain
    • José R. Casar, Universidad Politécnica de Madrid – ETSI Telecomunicación Ciudad Universitaria S/N 28040 Madrid Spain

In this paper, we address the problem of human activity classification from videos, giving a special emphasis to feature extraction
and good feature selection. Due to the cut down in cameras cost that have been in the last years, these kind of systems are
becoming popular for their wide application area. Taking a video blob tracker output, a feature extraction process is defined
to extract an extensive feature set, that is filtered in a later step to select the best features present. Three different
type of classifiers are trained with the result feature set and results are shown.

  • Content Type Book Chapter
  • DOI 10.1007/978-3-540-85863-8_86
  • Authors
    • Rodrigo Cilla, Universidad Carlos III de Madrid Computer Science Department, Applied Artificial Intelligence Group Avda. de la Universidad Carlos III, 22 28270 Colmenarejo (Madrid) Spain
    • Miguel A. Patricio, Universidad Carlos III de Madrid Computer Science Department, Applied Artificial Intelligence Group Avda. de la Universidad Carlos III, 22 28270 Colmenarejo (Madrid) Spain
    • Antonio Berlanga, Universidad Carlos III de Madrid Computer Science Department, Applied Artificial Intelligence Group Avda. de la Universidad Carlos III, 22 28270 Colmenarejo (Madrid) Spain
    • Jose M. Molina, Universidad Carlos III de Madrid Computer Science Department, Applied Artificial Intelligence Group Avda. de la Universidad Carlos III, 22 28270 Colmenarejo (Madrid) Spain

This paper proposes a method for merging Bluetooth and WLAN technologies to face the problem of indoor positioning. The method
consists in the construction of a fusion map based on calibrated WiFi RSS and simulated Bluetooth RSSI. On a recent work,
we have presented a different approach for fusing both technologies. The performance of this method is tested experimentally
and the comparison between the localization results obtained using both technologies and using only WiFi is presented.

  • Content Type Book Chapter
  • DOI 10.1007/978-3-540-85863-8_83
  • Authors
    • Sofía Aparicio, ETSI Telecomunicación, Universidad Politécnica de Madrid Madrid Spain
    • Javier Pérez, ETSI Telecomunicación, Universidad Politécnica de Madrid Madrid Spain
    • Paula Tarrío, ETSI Telecomunicación, Universidad Politécnica de Madrid Madrid Spain
    • Ana M. Bernardos, ETSI Telecomunicación, Universidad Politécnica de Madrid Madrid Spain
    • José R. Casar, ETSI Telecomunicación, Universidad Politécnica de Madrid Madrid Spain