Papers by Ángela Ribeiro
10th IEEE International Conference on Fuzzy Systems. (Cat. No.01CH37297), 2001
Current work deals with the design of a local unit, microcontroller based to acquire signals from... more Current work deals with the design of a local unit, microcontroller based to acquire signals from a set of sensors and locally diagnose on the air quality. The local unit permits the interface with standards atmospheric and meteorological sensors, as well as the communication with a central unit by message passing protocol, via GSM. A fuzzy inference system has been developed to perform the approximate reasoning process performed by a human being, based on the perception of the environment conditions. The decision algorithm is based on a performance criterion, the one that forces the emergence of the pollution level with minimum communication and maximum environment safety. The processes running at the local unit have been modularly designed within the frame of a Client/Server architecture to ease its gradual growing and maintenance. The local unit bi-directionally communicates with several central units that record and visualize stationary data and acts at the reception of an emergency message. Communication is performed either following a remotely programmed pattern, event based or under the user demand.
The generation of human-friendly interfaces is an open field aiming at the development of tools t... more The generation of human-friendly interfaces is an open field aiming at the development of tools that allow non-expert users to take out the maximum profit of the integration of GIS and GPS tools. In this direction, a flexible and open software environment that integrates such technologies with the main objective of supplying a support tool to record field properties in
Precision Agriculture, 2005
In crop fields, weed density varies spatially in non-random patterns. Initial knowledge of weed d... more In crop fields, weed density varies spatially in non-random patterns. Initial knowledge of weed distribution would greatly improve weed management for Precision Agriculture operations. Site properties could be correlated to weed distribution, since the former vary among crop fields and also certain factors such as soil texture or nitrogen may condition the weed growth. This paper presents a method, based on artificial intelligence techniques, for inducing a model that appropriately predicts the heterogeneous distribution of wild-oat (Avena sterilis L.) in terms of some environmental variables. From several experiments, distinct rule sets have been found by applying a genetic algorithm to carry out the automatic learning process. The best rule set extracted was able to explain about 88% of weed variability.
10th IEEE International Conference on Fuzzy Systems. (Cat. No.01CH37297), 2001
Current work deals with the design of a local unit, microcontroller based to acquire signals from... more Current work deals with the design of a local unit, microcontroller based to acquire signals from a set of sensors and locally diagnose on the air quality. The local unit permits the interface with standards atmospheric and meteorological sensors, as well as the communication with a central unit by message passing protocol, via GSM. A fuzzy inference system has been developed to perform the approximate reasoning process performed by a human being, based on the perception of the environment conditions. The decision algorithm is based on a performance criterion, the one that forces the emergence of the pollution level with minimum communication and maximum environment safety. The processes running at the local unit have been modularly designed within the frame of a Client/Server architecture to ease its gradual growing and maintenance. The local unit bi-directionally communicates with several central units that record and visualize stationary data and acts at the reception of an emergency message. Communication is performed either following a remotely programmed pattern, event based or under the user demand.
Proceedings of the 2000 6th IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA 2000) (Cat. No.00TH8509), 2000
A fruitful field into the CNN research domain is being the development of analogic algorithms tha... more A fruitful field into the CNN research domain is being the development of analogic algorithms that combine single templates to perform complex image processing. The results would be extremely 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, concept derived from the AI field, is applied to the automatic generation of analogic algorithms, based in both geneticevolutionary search and heuristic approaches.
The generation of human-friendly GIS/GPS interfaces is an open field aiming at the development of... more The generation of human-friendly GIS/GPS interfaces is an open field aiming at the development of tools that allow non-expert users to reap maximum profit from the integration of GIS and GPS technologies. This project uses GeoMedia objects to develop an integrated system for both planning field-sampling tasks and for GPS guided navigating. All field properties are recorded in a spatial database. The system is composed of two software packages. First allows users to generate detailed sampling plans: maps, properties, and specific data acquisition processes. The second package uses DGPS to guide the user along the course previously defined, and controls data acquisition at each node of the defined grid. The data acquisition stage of the proposed system can be extremely useful in many domains, in spite of being specifically designed for Precision Agriculture.
This paper addresses the automation of the visual inspection process for eggs grading purposes at... more This paper addresses the automation of the visual inspection process for eggs grading purposes at the farm packers. Some preliminary tests have been performed looking for processing algorithms that hold for a trade-off between the accuracy and speed restrictions. First experimental work is conducted to an image analysis based on the enhancement of the discontinuities with respect to the image background before any quantification is accomplished. Finally sensor integration is suggested as a way to improve the reliability and to enlarge the repertoire of defects suitable to be detected.
The generation of human-friendly interfaces is an open field aiming at the development of tools t... more The generation of human-friendly interfaces is an open field aiming at the development of tools that allow non-expert users to take out the maximum profit of the integration of GIS and GPS tools. In this direction, a flexible and open software environment that integrates such technologies with the main objective of supplying a support tool to record field properties in
Palabras clave: Fusión sensorial, Sensores internos, Sistema de Posicionamiento Global (GPS), Err... more Palabras clave: Fusión sensorial, Sensores internos, Sistema de Posicionamiento Global (GPS), Errores GPS, Transformaciones aproximadas.
Studies in Fuzziness and Soft Computing, 2003
This paper addresses the issue of an adequate representation of a web page, to perform further on... more 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.
Lecture Notes in Computer Science, 2003
The Internet makes it possible to share and manipulate a vast quantity of information efficiently... more 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.
In some complex sensing machines, such as the feedback system of a robot, a camera, a digitising ... more In some complex sensing machines, such as the feedback system of a robot, a camera, a digitising device, etc., the accuracy of the measurement not only depends on the repeatability of the sensors, but also on the geometry of the machine itself 3. We present here a novel method for machine parameter estimation (calibration) based on evolutionary computing/genetic algorithms. This
Machine Vision Applications in Industrial Inspection VIII, 2000
ABSTRACT Many industrial inspection such visual quality control of metal laminates require billio... more ABSTRACT Many industrial inspection such visual quality control of metal laminates require billions of operations per second. Analog CNN array computer arises as an alternative to traditional digital processors, capable of make in a single chip Tera equivalent operations per second. A 4096 analog CNN processor array is able to perform complex space-time image analysis, being much faster than a camera-computer system in continuous inspection applications. Both chips have been implemented in CMOS technology and they are managed by a 32- bit high-performance low-cost micro-controller that closes the pan, tilt, lighting, focus and zoom loops required in the implementation of the active vision strategies. Several convolution masks for the Cellular Processors has been selected to detect particular changes in the texture, size, direction or orientation of the image entities, reprogramming &#39;on the fly&#39; the pixel resolution or shape when necessary. Laboratory results present these Cellular Processors and multiple resolution imager circuits as a promising architecture for visual inspection of industrial processes in real time.
Machine Vision Applications in Industrial Inspection VIII, 2000
The automatic classification of defective eggs constitutes a fundamental issue of the poultry ind... more The automatic classification of defective eggs constitutes a fundamental issue of 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 in a poultry farm. The 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 critical 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.
Mobile Robots XVI, 2002
ABSTRACT Present work describes an approximation to obtain the best estimation of the position of... more ABSTRACT Present work describes an approximation to obtain the best estimation of the position of the outdoor robot ROJO, a low cost lawnmower to perform unmanned precision agriculture task such are the spraying of pesticides in horticulture. For continuous location of ROJO, two redundant sensors have been installed onboard: a DGPS submetric precision model and an odometric system. DGPS system will allow an absolute positioning of the vehicle in the field, but GPS failures in the reception of the signals due to obstacles and electrical and meteorological disturbance, lead us to the integration of the odometric system. Thus, a robust odometer based upon magnetic strip sensors has been designed and integrated in the vehicle. These sensors continuosly deliver the position of the vehicle relative to its initial position, complementing the DGPS blindness periods. They give an approximated location of the vehicle in the field that can be in turn conveniently updated and corrected by the DGPS. Thus, to provided the best estimation, a fusion algorithm has been proposed and proved, wherein the best estimation is calculated as the maximum value of the join probability function obtained from both position estimation of the onboard sensors. Some results are presented to show the performance of the proposed sensor fusion technique.
Precision Agriculture, 2005
In crop fields, weed density varies spatially in non-random patterns. Initial knowledge of weed d... more In crop fields, weed density varies spatially in non-random patterns. Initial knowledge of weed distribution would greatly improve weed management for Precision Agriculture operations. Site properties could be correlated to weed distribution, since the former vary among crop fields and also certain factors such as soil texture or nitrogen may condition the weed growth. This paper presents a method, based on artificial intelligence techniques, for inducing a model that appropriately predicts the heterogeneous distribution of wild-oat (Avena sterilis L.) in terms of some environmental variables. From several experiments, distinct rule sets have been found by applying a genetic algorithm to carry out the automatic learning process. The best rule set extracted was able to explain about 88% of weed variability.
Uploads
Papers by Ángela Ribeiro