Catálogo de publicaciones - libros

This paper addresses the extraction of small group configurations and activities in an intelligent meeting environment. The proposed approach takes a continuous stream of observations coming from different sensors in the environment as input. The goal is to separate distinct distributions of these observations corresponding to distinct group configurations and activities. In this paper, we explore an unsupervised method based on the calculation of the Jeffrey divergence between histograms over observations. The obtained distinct distributions of observations can be interpreted as distinct segments of group configuration and activity. To evaluate this approach, we recorded a seminar and a cocktail party meeting. The observations of the seminar were generated by a speech activity detector, while the observations of the cocktail party meeting were generated by both the speech activity detector and a visual tracking system. We measured the correspondence between detected segments and labelled group configurations and activities. The obtained results are promising, in particular as our method is completely unsupervised.

This paper presents an architecture to help the decision-making process of disaster managers. Here we focus on a core aspect of this process which is taking decisions in the presence of conflicting options. We exemplify this problem with three simple scenarios related to diverse contexts and provide an explanation on how our system will advice in all these cases.

In this paper a system is presented able to reproduce the actions of multiple moving objects into a 3D model. A multi-camera system is used for automatically detect, track and classify the objects. Data fusion from multiple sensors allows to get a more precise estimation of the position of detected moving objects and to solve occlusions problem. These data are then used to automatically place and animate objects avatars in a 3D virtual model of the scene, thus allowing users connected to this system to receive a 3D guide into the monitored environment.

The subject of this paper is fuzzy propositional calculus. The proposed approach is related to the basic fuzzy propositional logics, i.e. to each of the following three most important such systems (in short: BL): Łukasiewicz’s, Gödel’s, and product logic. The logical calculi considered here are based on a system of rules that define the methods used in proofs from assumptions. To simplify the considered proofs some set of laws called also ‘primitive rules’ is next introduced. It was shown that any fuzzy propositional formula provable under Hájek’s axioms of the logic BL is also provable under the above-proposed approach.

New designs of the Web switches must incorporate a client-and-server-aware adaptive dispatching algorithm to be able to optimize multiple static and dynamic services providing quality of service and service differentiation. This paper presents such an algorithm called FNRD (Fuzzy-Neural Request Distribution) which operates at layer-7 of the OSI protocol stack. This algorithm assigns each incoming request to the server with the least expected response time estimated using the fuzzy approach. FNRD has ability for learning and adaptation by means of a neural network feedback loop. We demonstrate through the simulations that our dispatching policy is more effective than state-of-the-art layer-7 reference dispatching policies CAP (Client-Aware Policy) and LARD (Locality Aware Request Distribution).

A multiple watermarking algorithm based on the Code Division Multiple Access (CDMA) spread spectrum technique is presented. Multiple copyright identifiers are convolutional encoded and block interleaved, and the orthogonal Gold sequences are used to spread spectrum of the copyright messages. The CDMA encoded copyright messages are embedded into the wavelet sub-bands. As a blind watermarking algorithm, the copyright identifiers are extracted without the original image. The experimental results show that the proposed algorithm improves the detection BER, and the multiple copyright identifiers have preferable robustness and invisibility.

In general, avatar-based communication has a merit that it can represent non-verbal information. The simplest way of representing the non-verbal information is to capture the human action/motion by a motion capture system and to visualize the received motion data through the avatar. However, transferring raw motion data often makes the avatar motion unnatural or unrealistic because the body structure of the avatar is usually a bit different from that of the human beings. We think this can be solved by transferring the meaning of motion, instead of the raw motion data, and by properly visualizing the meaning depending on characteristics of the avatar’s function and body structure. Here, the key issue is how to symbolize the motion meanings. Particularly, the problem is what kind of motions we should symbolize. In this paper, we introduce an algorithm to decide the symbols to be recognized referring to accumulated communication data, i.e., motion data.

Embodied Conversational Agents (ECAs) are computer generated life-like characters that interact with human users in face-to-face conversations. To achieve natural multi-modal conversations, ECA systems are very sophisticated and require many building assemblies and thus are difficult for individual research groups to develop. This paper proposes a generic architecture, the Universal ECA Framework, which is currently under development and includes a blackboard-based platform, a high-level protocol to integrate general purpose ECA components and ease ECA system prototyping.

In this paper a flexible method for a distance measure between communicative agents’ stored perceptions is proposed. It is assumed that each agent observes the states of external objects that are remembers them in a private temporal database in the form of base profiles. Distance measure is applied by the agent in the algorithm for the messages generation or during integration of other agents’ opinions collected during communication activities in order to create objective picture of the current state’s of objects. Proposed distance measure between base profiles is based on a computing of the costs of transformation one base profile into other. The objects’ movements hierarchy is introduced and mathematically explained using expected value and random variable.

It is considered a problem of harmonisation of diagnostic rules used in a distributed set of diagnostic centres, the rules being based on a approach. Harmonisation is reached due to an exchange of diagnostic cases among the reference sets stored in the centres. The method is based on general concepts of similarity, semi-similarity and structural compatibilitymeasures used to evaluation of adequacy of records in remote data files to the requirements connected with supporting decision making in a given, local diagnostic centre. The procedure of local reference set extension by diagnostic cases selection and acquisition is described.