Maria C. Garcia-Alegre

A fuzzy system for the web page representation

This paper addresses the issue of an adequate representation of a web page, to perform further on classification and data mining. The approach focuses the textual part of web pages, which are represented by a two-dimension vector. The vector components are sorted by the relevance of each word in the text. Two approaches, analytical and fuzzy, that take advantage of characteristics of the HTML language are presented to compute the word relevance. Both models are contrasted in learning and classification tasks, to evaluate the suitability of each approach. The experiments show an obvious improvement of fuzzy method versus analytical one. The analytical and fuzzy approaches here presented are general, in the sense that every characteristic of the web pages could be easily integrated without additional cost.

Multi-modal defect detection of residual oxide scale on a cold stainless steel strip

This work presents two initial approaches and a novel technique for the industrial inspection of residual oxide scale on a cold stainless steel strip. The research aims to develop real-time systems to detect 50-μm defects. Initially, a spectrophotometric analysis provides the wavelength regions where differences between stainless steel and residual oxide scale reflectance are highlighted. The multi-modal approach is based on laser techniques that comprise three different strategies to gradually achieve a robust stainless steel industrial inspection through the evaluation of their performance. First, an inspection system based on a single commercial laser has been designed with a dynamic threshold module. In the second approach, the inspection task is accomplished by volatilizing a reduced area of the stainless steel surface with short pulses of a high-power ultraviolet laser and then analyzing the generated plasma with an intensifier camera. The third technique consists of an innovative smart vision system for surface visual inspection based on laser diode diffuse illumination. This vision system can be configured to work with two laser illumination modes: the diffuse coaxial lighting and the diffuse bright-field lighting. These techniques aim to gradually improve surface defect detection of a cold stainless steel strip. Furthermore, some of the results of the defect detection level obtained with each approach are displayed and discussed.

Eggshell defects detection based on color processing

The automatic classification of defective eggs constitutes a fundamental issue at the poultry industry for both economical and sanitary reasons. The early separation of eggs with spots and cracks is a relevant task as the stains can leak while progressing on the conveyor-belts, degrading all the mechanical parts. Present work is focused on the implementation of an artificial vision system for detecting in real time defective eggs at the poultry farm. First step of the algorithmic process is devoted to the detection of the egg shape to fix the region of interest. A color processing is then performed only on the eggshell to obtain an image segmentation that allows the discrimination of defective eggs from clean ones in critic time. The results are presented to demonstrate the validity of the proposed visual process on a wide sample of both defective and non-defective eggs.

Smart Building: Decision Making Architecture for Thermal Energy Management

Smart applications of the Internet of Things are improving the performance of buildings, reducing energy demand. Local and smart networks, soft computing methodologies, machine intelligence algorithms and pervasive sensors are some of the basics of energy optimization strategies developed for the benefit of environmental sustainability and user comfort. This work presents a distributed sensor-processor-communication decision-making architecture to improve the acquisition, storage and transfer of thermal energy in buildings. The developed system is implemented in a near Zero-Energy Building (nZEB) prototype equipped with a built-in thermal solar collector, where optical properties are analysed; a low enthalpy geothermal accumulation system, segmented in different temperature zones; and an envelope that includes a dynamic thermal barrier. An intelligent control of this dynamic thermal barrier is applied to reduce the thermal energy demand (heating and cooling) caused by daily and seasonal weather variations. Simulations and experimental results are presented to highlight the nZEB thermal energy reduction.

Web page classification: a soft computing approach

The Internet makes it possible to share and manipulate a vast quantity of information efficiently and effectively, but the rapid and chaotic growth experienced by the Net has generated a poorly organized environment that hinders the sharing and mining of useful data. The need for meaningful web-page classification techniques is therefore becoming an urgent issue. This paper describes a novel approach to web-page classification based on a fuzzy representation of web pages. A doublet representation that associates a weight with each of the most representative words of the web document so as to characterize its relevance in the document. This weight is derived by taking advantage of the characteristics of HTML language. Then a fuzzy-rule-based classifier is generated from a supervised learning process that uses a genetic algorithm to search for the minimum fuzzy-rule set that best covers the training examples. The proposed system has been demonstrated with two significantly different classes of web pages.

Perception and tracking of dynamic objects for optimization of avoidance strategies in autonomous piloting of vehicles

In the autonomous piloting of vehicles, the characterization of nearby dynamic object motion by perception and tracking techniques aids in the optimization of avoidance strategies. Knowledge of the features of object motion in goal-driven navigation allows for accurate deviation strategies to be implemented with appropriate anticipation. This perceptual competence is a fundamental issue in the design of unmanned commercial outdoor vehicles with an often reduced capability for maneuvering. To this aim, a grid map representation of the local panorama is proposed such that laser rangefinder images are converted into grid cells that are segmented and assigned to objects, allowing classification and monitoring. The motion properties of objects are thus used to establish avoidance behavior to smartly control the vehicle steering, such that a safe and optimal detour maneuver is carried out while driving to a target. The developed perceptual ability is demonstrated here in several tests performed in a relatively clutter-free area to detect and track walking pedestrians. Some results are also shown to highlight the modulation of moving object properties on trajectories described by a robot when a fuzzy avoidance strategy is used to control the steering angle.

Basic visual and motor agents for increasingly complex behavior generation on a mobile robot

Present work addresses the guidelines that have been followed to construct basic behavioral agents for visually guided navigation within the framework of a hierarchical architecture. Visual and motor interactions are described within this generic framework that allows for an incremental development of behavior from an initial basis set. Basic locomotion agents as, Stop&Backward, Avoid, and Forward are implemented by means of fuzzy knowledge bases to deal with the uncertainty and imprecision inherent to real systems and environments. Basic visual agents as, Saccadic, Find_Contour, and Center are raised under a space-variant representation pursuing an anthropomorphic approach. We illustrate how a complex behavior results from the combination of lower level agents always connected to the basic motor agents. The proposed methodology is validated on a caterpillar mobile robot in navigation tasks directed by an object description.

Automatic CNN multi-template tree generation

We deal with the cellular neural network (CNN) research in the development of analogic algorithms that combine single templates to perform complex image processing. The results can be very useful for pattern recognition in industrial and robotic applications. This work presents a general methodology for the automatic generation of analogic algorithms by means of a genetic search. A genetic algorithm for generating multi-template trees, a concept derived from the AI field, is applied to the automatic generation of analogic algorithms based on both the genetic-evolutionary search and heuristic approaches.

A context-awareness architecture for managing thermal energy in an nZEB building

Global warming is seriously affecting society, but also to a lesser extent the longevity of the population and migration of people from the countryside to the cities present challenges for governments. Smart applications (smart city, smart grid, smart buildings, smart water, smart health) offer an alternative to deal with these challenges. Pervasive sensors, with increasingly powerful features, allow innovative developments, making possible a progressive growth in the so-called smart applications. Because information is the backbone of any type of smart environment, this work presents an architecture approach to take advantage of the capabilities of advanced sensors. Specifically in this work this architecture is applied to renewable energy systems for a better management of the thermal energy. A semantic sensors network has been developed to provide context awareness for managing thermal flow in a near Zero Energy Building (nZEB). The key elements are an Ontology Web Language (OWL) to describe the sensors and contextual knowledge, and a Semantic Web Rule Language (SWRL) to represent rule-based inferences for context reasoning. The main goal is to improve thermal energy comfort in a building with a reduction in the energy used.

Estimation and prediction of the vehicle's motion based on visual odometry and kalman filter

The movement of the vehicle is an useful information for different applications, such as driver assistant systems or autonomous vehicles. This information can be known by different methods, for instance, by using a GPS or by means of the visual odometry. However, there are some situations where both methods do not work correctly. For example, there are areas in urban environments where the signal of the GPS is not available, as tunnels or streets with high buildings. On the other hand, the algorithms of computer vision are affected by outdoor environments, and the main source of difficulties is the variation in the ligthing conditions. A method to estimate and predict the movement of the vehicle based on visual odometry and Kalman filter is explained in this paper. The Kalman filter allows both filtering and prediction of vehicle motion, using the results from the visual odometry estimation.