Eduardo Mora

A new image prediction model based on spatio-temporal techniques

This paper addresses an image prediction problem focused on images with no identifiable objects. In it, we present several approaches to predict the next image of a given sequence, when the image lacks the well-defined objects, such as meteorological maps or satellite imagery. In these images no clear borders are present, and any object candidate moves, changes, appears and disappears in any image. Nevertheless, this evolution, though unrestricted, is gradual and, hence, prediction looks feasible. One of the approaches presented here, based on a spatio-temporal autoregressive (STAR) model, offers good results for these kinds of images.The main contribution of this paper is to adapt spatio-temporal models to an image prediction problem.As a byproduct of this research, we have achieved a new image compression method, suitable for images without defined shapes.

Vertical Partitioning Algorithms in Distributed Databases

Data distribution is a crucial problem affecting the cost and efficient use of these systems. The problem is further exacerbated by the lack of methods and support tools for the design of distributed databases. This paper outlines some of the main techniques currently used for data distribution, such as vertical partitioning and replication. Two vertical fragmentation methods are described, the classic NAVATHE method and the newer FURD method, as well as the two proposed in this paper, the FURD-FDEZ and the FURD WITH REPLICATION methods.

Preprocessing Phase in the PIETSI Project (Prediction of Time Evolution Images Using Intelligent Systems)

We outline the PIETSI project, the core of which is an image prediction strategy, and discuss common preliminary image processing tasks that are relevant when facing problems such as: useless background, information overlapping (solvable if dissimilar coding is being used) and memory usage, which can be described as “marginal information efficiency”.

Design and Implementation of Multimedia Environment for Simulation

The importance of simulation in all fields is widely recognized due to the impact it has on design, production and engineering. This paper presents a design methodology aimed at developing multimedia interfaces for the simulation of industrial processes, using an object oriented point of view. A division of its composing elements into three functional blocks is proposed. The design methodology is based on the carrying out of a series of interrelated tasks, which from a software engineering perspective, gives maximum performance, both for the development process and its subsequent updating.

Moving objects forecast in image sequences using autoregressive algorithms

The objective of this paper is to present an overall approach to forecasting the future position of the moving objects of an image sequence after processing the images previous to it. The proposed method makes use of classical techniques such as optical flow to extract objects’ trajectories and velocities, and autoregressive algorithms to build the predictive model. Our method can be used in a variety of applications, where videos with stationary cameras are used, moving objects are not deformed and change their position with time. One of these applications is traffic control, which is used in this paper as a case study with different meteorological conditions to compare with.

Meteorological image descriptors

The objective of this paper is to get a visual characterization of time evolution images, in particular, synoptic maps taken from Meteorology. Preliminary tasks required before image processing are reviewed. Two different types of numerical descriptors are extracted for characterizing the images, the called low level numerical descriptors, and the high level corresponding ones. The latter will be subsequently used for prediction tasks, meanwhile the former will be used for classification tasks. Three different relevant information sources in the images are identified as their low level descriptors. These are defined by the local density and orientation of the isobar lines, and the number of centres of high (H) and low (L) pressure. Regarding the high level descriptors, two main features are taken into account. The different procedures carried out to extract the previous descriptors for our images of interest are discussed.

Training Simulator for Garoña Nuclear Power Plant

The training of Nuclear Power Plant Operators is the utmost importance for the proper running of Plants, with the strictest of security conditions. Given the specific characteristics of this type of energy, the training of operators can be carried out only by means of simulators.

MULTIMEDIA ENVIRONMENTS: DESIGNS FOR SIMULATION

The importance of simulation in all fields is widely recognized due to the impact it has had on design, production, and engineering. Currently, computer technology offers rapid solutions and graphics facilities that contribute to the development and improvement of complex simulation programs and their user interfaces. This paper presents a methodology aimed at developing graphic interfaces for the simulation of industrial processes and with the possibility of extending the scope into the area of control. The first part summarizes the simulation process technique and the problem of the user interface design from an ergonomic perspective. The second part describes the design of the user interface. First, the kind of process to be simulated is identified. Focusing on the objects that are to be represented, these are named with their respective actions in the process and the interface. Finally, a prototype of process simulation of a nuclear plant is presented.

Distributed Simulation with Multimedia Interface

The training of the personnel plays a major role in the security and reliability of many industrial processes. In order to fulfil this objective it is necessary to develop applications that support distributed interactive simulation with an interface near the real world. This paper describes such type of application during the development of a training simulator prototype for a nuclear power plant. The simulator is based on a client/server architecture that allows the execution on different machines in a network and many users to participate in the same simulation. The interface was designed to support the interaction of the operators with the simulator through touch screens with high fidelity displays of the control room developed using the component technology. The main features of the simulator are the distributed execution of the models using inexpensive hardware and the flexibility of design and maintenance of the interface.

Tests of Different Regularization Terms in Small Networks

Several regularization terms, some of them widely applied to neural networks, such as weight decay and weight elimination, and some others new, are tested when applied to networks with a small number of connections handling continuous variables. These networks are found when using additive algorithms that work by adding processors. First the different methods and their rationale is presented. Then, results are shown, first for curve fitting problems. Since the network constructive algorithm is being used for system modeling, results are also shown for a toy problem that includes recurrency buildup, in order to test the influence of the regularization terms in this process. The results show that this terms can be of help in order to detect unnecessary connections. No clear winner has been found among the presented terms in these tests.