Abstract: IT securiteers - The human and technical dimension working for the organisation Current corporate governance regulations and international standards lead many organisations, big and small, to the creation of an information technology (IT) security function in their organisational chart or to the acquisition of services from the IT security industry. More often than desired, these teams are only useful for companies’ executives to tick the corresponding box in a certification process, be it ISO, ITIL, PCI, etc. Many IT security teams do not provide business value to their company. They fail to really protect the organisation from the increasing number of threats targeting its information systems. IT Security Management provides an insight into how to create and grow a team of passionate IT security professionals. We will call them “securiteers†. They will add value to the business, improving the information security stance of organisations.
Abstract: This book presents a selected collection of contributions on a focused treatment of important elements of Computational Intelligence. Unlike traditional computing, Computational Intelligence (CI) is tolerant of imprecise information, partial truth and uncertainty. The principle components of CI that currently have frequent application in Engineering and Manufacturing are: Neural Networks (NN), fuzzy logic (FL) and Support Vector Machines (SVM). In CI, NN and SVM are concerned with learning, while FL with imprecision and reasoning. This volume mainly covers a key element of Computational Intelligence learning. All the contributions in this volume have a direct relevance to neural network learning from neural computing fundamentals to advanced networks such as Multilayer Perceptrons (MLP), Radial Basis Function Networks (RBF), and their relations with fuzzy set and support vector machines theory. The book also discusses different applications in Engineering and Manufacturing. These are among applications where CI have excellent potentials for use. Both novice and expert readers should find this book a useful reference in the field of Computational Intelligence. The editors and the authors hope to have contributed to the field by paving the way for learning paradigms to solve real-world problems
Abstract: Abstract—In this work we propose the Distributed Bees Algorithm (DBA) for task allocation in a swarm of robots. In the proposed scenario, task allocation consists in assigning the robots to the found targets in a two-dimensional arena. The expected distribution is obtained from the targets’ qualities that are represented as scalar values. Decision-making mechanism is distributed and robots autonomously choose their assignments taking into account targets’ qualities and distances. We tested the scalability of the proposed DBA algorithm in terms of number of robots and number of targets. For that, the experiments were performed in the simulator for various sets of parameters, including number of robots, number of targets and targets’ utilities. Control parameters inherent to DBA were tuned to test
how they affect the final robot distribution. The simulation results show that by increasing the robot swarm size, the distribution error decreased.
Abstract: Salamanca is cataloged as one of the most polluted cities in Mexico. In order to observe the behavior and clarify the influence of wind parameters on the Sulphur Dioxide (SO2) concentrations a Self-Organizing Maps (SOM) Neural Network have been implemented at three monitoring locations for the period from January 1 to December 31, 2006. The maximum and minimum daily values of SO2 concentrations measured during the year of 2006 were correlated with the wind parameters of the same period. The main advantages of the SOM Neural Network is that it allows to integrate data from different sensors and provide readily interpretation results. Especially, it is powerful mapping and classification tool, which others information in an easier way and facilitates the task of establishing an order of priority between the distinguished groups of concentrations depending on their need for further research or remediation actions in subsequent management steps. For each monitoring location, SOM classifications were evaluated with respect to pollution levels established by Health Authorities. The classification system can help to establish a better air quality monitoring methodology that is essential for assessing the effectiveness of imposed pollution controls, strategies, and facilitate the pollutants reduction.
Abstract: Computed Tomography (CT) images provide a non-invasive alternative for observing soil structures, particularly pore space. Pore space in soil data indicates empty or free space in the sense that no material is present there except fluids such as air, water, and gas. Fluid transport depends on where pore spaces are located in the soil, and for this reason, it is important to identify pore zones. The low contrast between soil and pore space in CT images presents a problem with respect to pore quantification. In this paper, we present a methodology that integrates image processing, clustering techniques and artificial neural networks, in order to classify pore space in soil images. Image processing was used for the feature extraction of images. Three clustering algorithms were implemented (K-means, Fuzzy C-means, and Self Organising Maps) to segment images. The objective of clustering process is to find pixel groups of a similar grey level intensity and to organise them into more or less homogeneous groups. The segmented images are used for test a classifier. An Artificial Neural Network is characterised by a great degree of modularity and flexibility, and it is very efficient for large-scale and generic pattern recognition applications. For these reasons, an Artificial Neural Network was used to classify soil images into two classes (pore space and solid soil). Our methodology shows an alternative way to detect solid soil and pore space in CT images. The percentages of correct classifications of pore space of the total number of classifications among the tested images were 97.01%, 96.47% and 96.12%.
Abstract: The correct diagnosis of breast cancer is one of the major problems in the medical field. From the literature it has been found that different pattern recognition techniques can help them to improve in this domain. These techniques can help doctors form a second opinion and make a better diagnosis. In this paper we present a novel improvement in neural network training for pattern classification. The proposed training algorithm is inspired by the biological metaplasticity property of neurons and Shannon's information theory. During the training phase the Artificial metaplasticity Multilayer Perceptron (AMMLP) algorithm gives priority to updating the weights for the less frequent activations over the more frequent ones. In this way metaplasticity is modeled artificially. AMMLP achieves a more effcient training, while maintaining MLP performance. To test the proposed algorithm we used the Wisconsin Breast Cancer Database (WBCD). AMMLP performance is tested using classification accuracy, sensitivity and specificity analysis, and confusion matrix. The obtained AMMLP classification accuracy of 99.26%, a very promising result compared to the Backpropagation Algorithm (BPA) and recent classification techniques applied to the same database.
Abstract: A novel improvement in neural network training for pattern classification is presented in this paper. The proposed training algorithm is inspired by the biological metaplasticity property of neurons and Shannon’s information theory. This algorithm is applicable to artificial neural networks (ANNs) in general, although here it is applied to a multilayer perceptron (MLP). During the training phase, the artificial metaplasticity multilayer perceptron (AMMLP) algorithm assigns higher values for updating the weights in the less frequent activations than in the more frequent ones. AMMLP achieves a more efficient training and improves MLP performance. The well-known and readily available Wisconsin Breast Cancer Database (WBCD) has been used to test the algorithm. Performance of the AMMLP was tested through classification accuracy, sensitivity and specificity analysis, and confusion matrix analysis. The results obtained by AMMLP are compared with the backpropagation algorithm (BPA) and other recent classification techniques applied to the same database. The best result obtained so far with the AMMLP algorithm is 99.63%.
Notes: Selected Papers from the 3rd International Work-Conference on the Interplay between Natural and Artificial Computation (IWINAC 2009)
Abstract: The assessment of the risk of default on credit is important for financial institutions. Different Artificial Neural Networks (ANN) have been suggested to tackle the credit scoring problem, however, the obtained error rates are often high. In the search for the best ANN algorithm for credit scoring, this paper contributes with the application of an ANN Training Algorithm inspired by the neurons' biological property of metaplasticity. This algorithm is especially efficient when few patterns of a class are available, or when information inherent to low probability events is crucial for a successful application, as weight updating is overemphasized in the less frequent activations than in the more frequent ones. Two well-known and readily available such as: Australia and German data sets has been used to test the algorithm. The results obtained by AMMLP shown have been superior to state-of-the-art classification algorithms in credit scoring.
Abstract: Breast cancer is one of the leading causes of female mortality in the world, and early detection is an important means of reducing the mortality rate. The presence of microcalcification clusters has been considered as a very important indicator of malignant types of breast cancer, and its detection is important to prevent and treat the disease. This paper presents an effective approach, in order to detect microcalcification clusters in digitized mammograms, based on the synergy of image processing and partitional (hard and fuzzy) clustering techniques. Mathematical morphology has been used for image processing, and is used in this work as a first step, with the purpose of enhancing the contrast of microcalcifications. Image segmentation is an important task in the field of image processing, in order to identify regions with the same features. In the second step, we use image segmentation, using three partitional, hard and fuzzy clustering algorithms, such as k-Means, Fuzzy c-Means and Possibilistic Fuzzy c-Means, in order to make a comparison of the advantages and drawbacks offered by these algorithms, and which should help to improve the detection of microcalcification clusters in digitized mammograms.
Abstract: Computed Tomography (CT) images provide a non-invasive alternative for observing soil structures, particularly pore space. Pore space in soil data indicates empty or free space in the sense that no material is present there except fluids such as air, water, and gas. Fluid transport depends on where pore spaces are located in the soil, and for this reason, it is important to identify pore zones. The low contrast between soil and pore space in CT images presents a problem with respect to pore quantification. In this paper, we present a methodology that integrates image processing, clustering techniques and artificial neural networks, in order to classify pore space in soil images. Image processing was used for the feature extraction of images. Three clustering algorithms were implemented (K-means, fuzzy C-means, and self organizing maps) to segment images. The objective of clustering process is to find pixel groups of a similar grey level intensity and to organise them into more or less homogeneous groups. The segmented images are used for test a classifier. An artificial neural network is characterised by a great degree of modularity and flexibility, and it is very efficient for large-scale and generic pattern recognition applications. For these reasons, an artificial neural network was used to classify soil images into two classes (pore space and solid soil). Our methodology shows an alternative way to detect solid soil and pore space in CT images. The percentages of correct classifications of pore space of the total number of classifications among the tested images were 97.01%, 96.47% and 96.12%.
Abstract: Knowledge on soil pore geometry is important for understanding soil processes as it controls the movement and storage of fluids on various scales. With the advent of modern non-destructive tomography techniques there have been many attempts made to analyze pore space features mainly concentrating on the visualization Of Soil Structure. Multifractal formalism or the wavelet transform has been revealed as a useful tool in these cases where highly complex and heterogeneous media are studied. The field of 3D pore space analysis opens a challenging opportunity to develop techniques for quantifying and describing pore space properties. One of these quantifications can be the maximum depth pore network (MD), analogous as the quantification of the preferential flow paths. In this paper, a variation of the wavelet transform modulo maxima (WTMM) method used to compute multifractal behavior is presented. As a wavelet transform analysis (WTA), it allows us to focus on every scale which can be useful to select the range of scales where multifractal analysis (MFA) can be applied, revealing the MD global scaling patterns. In addition, the proposed method does not make any global estimate, so it can also be used to focus on local distribution of singularities. So, in the context of multiscaling structure analysis, the proposed wavelet-based method can complement box-counting analysis in order to statistically describe preferential flow path geometry and flow processes. The methodology is applied to determine the multifiractal behaviour of 3D images of soil samples with 45.1 mu m resolution (256 x 256 x 256 voxels) with closer porosities (ranging from 12% to 14%) and different spatial arrangements. (C) 2009 Elsevier B.V. All rights reserved.
Abstract: Informative geometric parameters are needed to describe the complex spatial arrangement of pore systems in porous media. Three-dimensional images (45.1 μm resolution) of soil samples exhibiting different spatial arrangements and porosities were analyzed to calculate their generalized dimensions (Dq) in the multifractal framework. Four different threshold criteria were used to transform the CT grey-scale imagery in the binary imagery of pore space and solid phase to study the influence of this choice in Dq values. Thresholds were based on the histograms of the CT units representing voxels. The selection of the threshold affected the value of the apparent porosity inferred from the CT images. The pore space structure could be described by the multifractal model only for the larger cubes sizes (side lengths ranging from 32 to 256 voxel sides) regardless of the thereshold criteria. Values of Dq were obtained by restricting multifractal analysis (MFA) to these cube sizes. The difference w between the Dq values for q = −1 to q = 5 was also dependent on the threshold criterion selection, and was used to compare the effect of the threshold criteria selection on the multiscaling behavior. The w values decreased exponentially as the apparent porosity increased. For the same threshold, the largest values of w, indicating the most developed multifractal structure, were found in the surface horizon where interactions with atmosphere and root activity were the most pronounced, and in the relatively deep illuvial horizons where the colloidal material was accumulated that was leached from the upper soil horizons. The strong influence of the image threshold on the parameters of the multifractal models suggests that structure of the grey image along with the frequency distribution of grey level may be a useful indicator for the threshold selection.
Abstract: Most soil parameters as the spatial variability of preferential pathways for water and chemical transport in field soils show complex variations at different scales that cannot accurately described with stationary assumptions. This is why multifractal formalism or the wavelet transform reveals as useful tools for classifying and quantifying the spatial variability of these preferential pathways. as visualized through dye infiltration experiment. The high-resolution images resulting front these experiments ale analyzed using both box-counting methods and wavelet transform analysis (WTA). T e box-counting methods reveals global scaling patterns while the WTA focuses oil local distribution of singularities. So, in the context of multiscaling structure analysis the wavelet methods call complement box-counting analysis which could be useful for statistically describing preferential flow path geometry and flow processes. The methodology is illustrated using well-known fractal structures as multifractal Sierpinsky carpets and results are illustrated with images of horizontal planes of the subsoil. acquired after dye infiltration into a 4m(2) plot located on a Vertisol soil near College Station, Texas.
Abstract: Metaplasticity property of biological synapses is interpreted in this paper as the concept of placing greater emphasis on training patterns that are less frequent. A novel implementation is proposed in which, during the network learning phase, a priority is given to weight updating of less frequent activations over the more frequent ones. Modeling this interpretation in the training phase, the hypothesis of an improved training is tested on the Multilayer Perceptron type network with Backpropagation training. The results obtained for the chosen application show a much more efficient training, while at least maintaining the Multilayer Perceptron performance.
Abstract: At present, the water resources are a strategic element, each time more necessary and limited becoming a source of conflicts. For that, it is fundamental to create an independent and competent entity with good reputation and social acceptation. This entity, must be able to obtain, store and process all data dispersed in different entities creating a network for these purposes. Finally, it must be able to organize different branches between the government and the final users. Using one of the well-known Multicriteria Decision Methods (MCDM) with several realistic alternatives and several criteria identified in expert seminars in Salta and Madrid, we have obtained hopeful results and more recently, new modifications introduced have generated better results
Abstract: In this work we take the concept of typicality from the cognitive and psychological point of view, and we apply their meaning to the interpretation of numerical data through fuzzy clustering algorithms. With the PFCM clustering algorithm, based on the Fuzzy c-Means clustering algorithm (FCM), we get a relative typicality (membership degree), and, also based on the Possibilitistic c- Means (PCM), an absolute typicality (typicality value). The results clearly show the advantages of the information obtained about the data set used, taking into account the different meaning of typicalities and the availability of both values with the clustering algorithm used
Abstract: This work proposes a method to generate a greater and bigger knowledge from a data set. The GKPFCM clustering algorithm is used for that. So, for a given number of clusters it identifies their location and their approximate shape. The relations among the variables of the data set can be found with these clusters, and they can be expressed as conditional rules such as "If/Then." The GKPFCM provides the membership values and the typicality values from which a knowledge base is generated through two fuzzy models, and this can be used in order to classify new data and to determine if these new data are typical, atypical or noise. So, a better expert decision can be made based on the results of these models.
Abstract: Many Artificial Neural Networks design algorithms or learning methods imply the minimization of an error objective function. During learning, weight values are updated following a strategy that tends to minimize the final mean error in the Network performance. Weight values are classically seen as a representation of the synaptic weights in biological neurons and their ability to change its value could be interpreted as artificial plasticity inspired by this biological property of neurons. In such a way, metaplasticity is interpreted in this paper as the ability to change the efficiency of artificial plasticity giving more relevance to weight updating of less frequent activations and resting relevance to frequent ones. Modeling this interpretation in the training phase, the hypothesis of an improved training is tested in the Multilayer Perceptron with Backpropagation case. The results show a much more efficient training maintaining the Artificial Neural Network performance.
Abstract: The spatial variability of preferential pathways for water and chemical transport in a field soil, as visualized through dye infiltration experiments, was studied by applying
multifractal and wavelet transform analysis (WTA). After dye infiltration into a 4m2 plot located on a Vertisol soil near College Station, Texas, horizontal planes in the subsoil were exposed at 5 cm intervals, and dye stain patterns were photographed. Box-counting methods and WTA were applied to all of the 16 digitalized high-resolution dye images and to
the dye-mass image obtained merging all sections. The well known Devil’s staircase multifractal was also used to illustrate wavelet-based analysis. Our results suggest that wavelet methods can complement box-counting analysis in the context of multiscaling structure analysis.
Abstract: Breast. cancer is one of the leading causes to women mortality in the world. Clusters of Microcalcifications (MCCs) in mammograms can be an important early sign of breast cancer, the detection is important to prevent and treat the disease. Coordinate Logic Filters (CLF), are very efficient in digital signal processing applications, such as noise removal, magnification, opening, closing, skeletonization, and coding, as well as in edge detection, feature extraction, and fractal modelling. This paper presents an edge detector of MCCs in Regions of Interest (ROI) from rnanunograms using a novel combination. The edge detector consist in the combination of image enhancement by histogram adaptive technique, a Self Organizing Map (SOM) Neural Network and CLF. The experiment results show that the proposed method can locate MCCs edges. Moreover, the proposed method is quantitatively evaluated by Pratt 039;s figure of merit together with two widely used edge detectors and visually compared, achieving the best results.
Abstract: Breast cancer is one of the leading causes to women mortality in the world. Cluster of Microcalcifications (MCC) in mammograms can be an important early sign of breast cancer, the detection is important to prevent and treat the disease. In this paper, we present a novel method for the detection of MCC in mammograms which consists of image enhancement by histogram adaptive equalization technique, MCC edge detection by Coordinate Logic Filters (CLF), generation, clustering and labelling of suboptimal features vectors by means of Self Organizing Map (SOM) Neural Network. Like comparison we applied an unsupervised clustering K-means in the stage of labelling of our method. In the labelling stage, we obtain better results with the proposed SOM Neural Network compared with the k-means algorithm. Then, we show that the proposed method can locate MCCs in an efficient way
Abstract: This paper tests a novel improvement in neural network training by implementing Metaplasticity Multilayer Perceptron (MMLP) Neural Networks (NNs), that are based on the biological property of metaplasticity. Artificial Metaplasticity bases its efficiency in giving more relevance to the less frequent patterns and subtracting relevance to the more frequent ones. The statistical distribution of training patterns is used to quantify how frequent a pattern is. We model this interpretation in the NNs training phase. Wisconsin breast cancer database (WBCD) was used to train and test MMLP. Our results were compared to recent research results on the same database, proving to be superior or at least an interesting alternative
Abstract: In this paper we are apply Artificial Metaplasticity MLP (MMLPs) to Breast Cancer Classification. Artificial Metaplasticity is a novel ANN training algorithm that gives more relevance to less frequent training patterns and subtract relevance to the frequent ones during training phase, achieving a much more efficient training, while at least maintaining the Multilayer Perceptron performance. Wisconsin Breast Cancer Database (WBCD) was used to train and test MMLPs. WBCD is a well-used database in machine learning, neural networks and signal processing. Experimental results show that MMLPs reach better accuracy than any other recent results
Abstract: This article presents a neural network model for the simulation of the neurological mechanism that produces limbs hiper-rigidity (spasticity). In this model, we take into account intrinsic plasticity, which is the property of biological neurons that consists in the shifting of the action potential threshold according to experience. In accordance to the computational model, a therapeutic technique for diminishing limbs spasticity is proposed and discussed
Abstract: Salamanca has been considered among the most polluted cities in Mexico. The vehicular park, the industry and the emissions produced by agriculture, as well as orography and climatic characteristics have propitiated the increment in pollutant concentration of Particulate Matter less than 10 $\mu g/m^{3}$ in diameter ($PM_{10}$). In this work, a Multilayer Perceptron Neural Network has been used to make the prediction of an hour ahead of pollutant concentration. A database used to train the Neural Network corresponds to historical time series of meteorological variables (wind speed, wind direction, temperature and relative humidity) and air pollutant concentrations of $PM_{10}$. Before the prediction, Fuzzy c-Means clustering algorithm have been implemented in order to find relationship among pollutant and meteorological variables. These relationship help us to get additional information that will be used for predicting. Our experiments with the proposed system show the importance of this set of meteorological variables on the prediction of $PM_{10}$ pollutant concentrations and the neural network efficiency. The performance estimation is determined using the Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). The results shown that the information obtained in the clustering step allows a prediction of an hour ahead, with data from past 2 hours.
Abstract: Swarm Robotics refers to the application of Swarm Intelligence techniques where a desired collective behavior emerges from the local interactions of robots with one another and with their environment. In this paper, a modified Bees Algorithm is proposed for multi-target search and coverage by an autonomous swarm of robotic “beesâ€. The objective is to find targets in an unknown area, send their estimated locations and fitness values to other robots in swarm which then provide the coverage of the found targets in a self-organized, decentralized way. The robots are equipped with ultrasonic sensors for obstacle avoidance, thermal sensors for target detection, and ZigBee modules for local communication. For the experiments, a small swarm of robots was built to test the performance of the modified Bees Algorithm. The experimental results show that the swarm is self-organized, decentralized and adaptive, and it can be successfully applied to the unknown area search and coverage.
Abstract: The guiding principle of process automation and soft computing is to achieve more robust, traceable and low cost solutions which incorporate the required intelligence to information technologies, thus enabling human centered functionalities. The application of Artificial Intelligence (IA) and Neural systems to the financial and banking industries has performed well in the areas of Risk Management improvement and Bankruptcy prediction. This paper contributes to analyze the synergies between logic and neural based approaches as the basis to enhance bankruptcy prediction models development.
Abstract: Unmanned Aerial Vehicle (UAV) is defined as aircraft without the onboard presence of pilots. UAVs have been used to perform intelligence, surveillance, and reconnaissance missions. The UAVs are not limited to military operations, they can also be used in commercial applications such as telecommunications, ground traffic control, search and rescue operations, crop monitoring, etc. In this paper, we propose a swarm intelligence-based method for UAVs' route optimization. The team of UAVs is used for area coverage with the defined set of waypoints. The problem can be interpreted as a well-known Traveling Salesman Problem where the task is to find the route of minimal length such that all the waypoints are visited only once. We applied the Ant System algorithm and compared it with the Nearest Neighbor Search. The experimental results confirm the effectiveness of our method, especially for a large number of waypoints.
Abstract: This paper describes the use of networked control algorithms in designing a robotic swarm. The main goal of a robotic swarm is to divide one task into multiple simpler tasks. Have we designed a swarm this way, the main challenge would be the problem of delay in communication between individual robots. This paper also goes through the Swarm Intelligence concept and proposes the Network Formation Control algorithms to control a group of robots.
Abstract: Over the last ten years, Salamanca has been considered among the most polluted cities in MeÌxico. Nowadays, there is an Automatic Environmental Monitoring Network (AEMN) which measures air pollutants (Sulphur Dioxide (SO2), Particular Matter (PM10), Ozone (O3), etc.), as well as environmental variables (wind speed, wind direction, temperature, and relative humidity), and it takes a sample of the variables every minute. The AEM Network is mainly based on three monitoring stations located at Cruz Roja, DIF, and Nativitas. In this work, we use the PFCM (Possibilistic Fuzzy c Means) clustering algorithm as a mean to get a combined measure, from the three stations, looking to provide a tool for better management of contingencies in the city, such that local or general action can be taken in the city according to the pollution level given by each station and the combined measure. Besides, we also performed an analysis of correlation between pollution and environmental variables. The results show a significative correlation between pollutant concentrations and some environmental variables. So, the combined measure and the correlations can be used for the establishment of general contingency thresholds.
Abstract: Breast cancer is one of the leading causes to women mortality in the world and early detection is an important means to reduce the mortality rate. The presence of microcalcifications clusters has been considered as a very important indicator of malignant types of breast cancer and its detection is important to prevent and treat the disease. This paper presents an alternative and effective approach in order to detect microcalcifications clusters in digitized mammograms based on the synergy of the image processing, pattern recognition and artificial intelligence. The mathematical morphology is an image processing technique used for the purpose of image enhancement. A k-means algorithm is used to cluster the data based on the features vectors and finally an artificial neural network-based classifier is applied and the classification performance is evaluated by a ROC curve. Experimental results indicate that the percentage of correct classification was 99.72%, obtaining 100% true positive (sensitivity) and 99.67% false positive (specificity), with the best classifier proposed. In case of the best classifier, we obtained a performance evaluation of classification of Az = 0.9875.
Abstract: The erosion-sedimentation-flooding processes in large zones of Argentine are a critical problem that involve complex relationships with technological, economic, social and environmental cause-effect. The increasing of agricultural activities in new areas previously with forestry or pasture could produce irreversible environmental impacts. It is necessary to prepare a spatial plan taking into consideration, economic development, social cohesion, environmental quality and progressive desertification. Multicriteria decision models contribute to the elaboration of that plan and provide an inestimable aid to decision makers. The objective of this paper is to elaborate a multicriteria model applied to the La Colacha Basin (Cordoba-Argentine). La Colacha Basin has 416 km2, it is a representative basin of a dry-sub-humid area where agriculture practices are progressively increased. Ten alternatives have been evaluated combining: (a) Agro-forest-pastoral (ASP), Present use (ACT) e Intensive use (INT), (b) with or without Soil conservation (CS), y (c) with or without Hydrological arrangement of the basin (OH). There have been selected 13 criteria. Different Multi-criteria Decision Methods, both of traditional or developed by the authors, have been used.
Abstract: This paper presents the results of some partitional clustering algorithms applied to the segmentation of color images in the RGB space. As more information is involved in the algorithm, and the distance measure is more flexible, the better the results. The selected algorithms for this work are the K-means, the FCM, the GK-B, and the GKPFCM. The GKPFCM gives the better results when all the algorithms are applied to the segmentation of two images, an image of bananas and the other one of tomates at different stages of ripeness in both cases. The results are interesting as it is possible to identify the objects, to determine the degree of ripeness, and to estimate the amount and proportion of ripe objects for a possible decision-making.
Abstract: The feature selection has been widely used to reduce the data dimensionality. Data reduction improve the classification performance, the approximation function, and pattern recognition systems in terms of speed, accuracy and simplicity. A strategy to reduce the number of features in local search are the sequential search algorithms. In this work is presented a feature selection method based on Sequential Forward Selection (SFS) and Feed Forward Neural Network (FFNN) to estimate the prediction error as a selection criterion. Three well-known database have been used to test the SFS-FFNN with Artificial Metaplasticity on Perceptron Multilayer (AMMLP). The AMMLP is a new method applied for classification of patterns. The results obtained by SFS-FFNN with AMMLP in classification accuracy are superior than obtained by conventional BP algorithm and other recent feature selection algorithms applied to the same database. By these reasons the proposed method SFS-FFNN with AMMLP is an interesting alternative to reduce the data dimensionality and provide a high accuracy.
Abstract: Ant Colony Optimization (ACO) is a group of algorithms inspired by the foraging behavior of ant colonies in nature. Like their biological counterparts, a colony of artificial ants is able to adapt to the changes in their environment, such as exhaustion of a food source and discovery of a new one. In this paper, one of the basic ACO algorithms, the Ant System algorithm, was applied for edge detection where the edge pixels represent food for the ants. A set of grayscale images obtained by a nonlinear contrast enhancement technique called Multiscale Adaptive Gain is used to create a variable environment. As the images change, the ant colony adapts to those changes leaving pheromone trails where the new edges appear while the pheromone trails that are not reinforced evaporate over time. Although the images were used to create an environmental setup in which the ants move, the colony's adaptive behavior could be demonstrated on any type of digital habitat.
Abstract: Risk Management improvement and credit risk evaluation are turning core areas of concern within the financial and banking industries. Specifically credit scoring, as one of the key analytical techniques in credit risk evaluation is envisioned as an arena in which the application of Artificial Intelligence (IA) and Neural systems has high potential for development. This paper contributes by presenting a novel Neural based approach to enhance credit scoring modeling inspired by the biological metaplasticity property of neurons.
Abstract: In this work we propose a method for sub-segmentation of images using the PFCM clustering algorithm. The sub-segmentation consists of finding, within the clusters found using the segmentation process, those data less representative, or atypical data, belonging to the clusters. These data represent, in many cases, the zones of interest during image analysis. Two different examples are used in order to show the results, and the advantages of identifying those elements of data forced to belong to a cluster, of which they are the less representative and, therefore may contain information of great interest in particular applications.
Abstract: In this paper we apply Artificial Metaplasticity to a Multilayer Perceptron (MLP) for image classification. Artificial Metaplasticity is a novel Artificial Neural Network (ANN) training algorithm that gives more relevance to less frequent training patterns and subtracts relevance to the frequent ones during training phase, achieving a much more efficient training, while at least maintaining the MLP performance. In this paper, we test Metaplasticity MLP (MMLP) algorithm on an image standard data set: the Wisconsin Breast Cancer Database (WBCD). WBCD is a well-used database in Machine Learning, ANN and Signal Processing. Experimental results show that MMLPs reach better accuracy than any other recent results.
Abstract: Air pollution is one of the most important environmental problems. Sulphur Dioxide (SO2) and Suspended Particles are considered the most important atmospheric pollutants. The prevision of industrial SO2 air pollutant concentrations would allow us to take preventive measures such as reducing the pollutant emission to the atmosphere. In This work we apply Feed Forward Artificial Neural Network to predict the air pollution concentrations in Salamanca, Mexico. The work focuses on the daily maximum concentration of SO2. A database used to train the neural network corresponds to historical time series of meteorological variables (wind speed, wind direction, temperature and relative humidity) and concentrations of SO2 along a year. Results of the experiments with the proposed system show the importance of the meteorological variable set on the prediction of SO2 concentrations and the neural network efficiency. The performance estimation is determined using the Root Mean Square Error (RMSE) and Mean Absolute Error (MAE).
Abstract: Over the last ten years, Salamanca has been considered among the most polluted cities in Mexico, with the most important air pollutants being SO2 and PM10. Currently, in Salamanca, an Environmental Monitoring Network (EMN) is installed in which time series of criteria pollutants and meteorological variables are obtained. Unfortunately air pollution level is computed in each monitoring station without taking into account those meteorological variables. In this paper, we propose a novel methodology to compute air pollution levels taking the meteorological variables as a decision factor by means of data fusion and neural networks. First, in preprocessing stage two Feature Vectors (FVSO2 and FVPM10) are built for each monitoring station. Next, in data fusion stage, a Representative Feature Vector by pollutant (RFVSO2 and RFVPM10) is built with the maximum value of the three FVs. Finally, an Artificial Neural Network (ANN) is trained with the RFV in order to classify future environmental situations. Self-Organizing Map (SOM) is the ANN applied. In this paper, time series of pollutant concentrations and meteorological variables are obtained from the EMN. EMN is composed for the three monitoring stations in Salamanca. Data used in this study have approved according to Proaire environmental authority standards.
Abstract: Abstract: This paper presents a novel feature extraction method using the combination of the Coordinate Logic Filters (CLF) and Artificial Neural Networks (ANN) applied to 2D signals (Images). The method consists of image enhancement by histogram adaptive equalization technique, features extraction by modifying gray levels applying a nonlinear adaptive transformation function and edge detection by Coordinate Logic Filters (CLF), generation, clustering and labelling of suboptimal features vectors by Self Organizing Map (SOM) Neural Network. For the detection we applied Back Propagation Neural Network (BPNN). This method is tested to detect Microcalcifications (MCs) in Regions of Interest (ROI) from mammograms. The experiment results show that the proposed method can locate MCs in an efficient way, moreover the method promise interesting advances in Medical Industry.
Abstract: Making use of biologically plausible artificial neural networks that implement Grossberg's presynaptic learning rule, we simulate the possible effects of calcium dysregulation in the neuron's activation function, to represent the most accepted model of Alzheimer's Disease: the calcium dysregulation hypothesis. According to Cudmore and Turrigiano calcium dysregulation alters the shifting dynamic of the neuron's activation function (intrinsic plasticity). We propose that this alteration might affect the stability of synaptic weights in which memories are stored. The results of the simulation supported the theoretical hypothesis, implying that the emergence of Alzheimer's disease's symptoms such as memory loss and learning problems might be correlated to intrinsic neuronal plasticity impairment due to calcium dysregulation.
Abstract: Several SAR image segmentation algorithms, also known as extended target detection algorithms are studied and the results are compared. The schemata obtained are evaluated using criteria based on the similarity with visual segmentation of the image, and the computational resources used in the process. Finally, based in the algorithms studied some supplementary techniques are proposed in order to improve the segmentation results or the computational cost.
Abstract: This work presents classification results of different water outputs in a house. Input variables are time and flow measurements in a point of the network distribution, and the identified classes are relevant consumptions as sink consumption, shower consumption, etc. Due to human influence on consumption data, we selected a classifier based on an interpretable model; that allows the incorporation of knowledge provided by users or experts. Thus, this study is based on the well known Anfis model and AGUA (real data taken for a project being developed in Guadalajara, Mexico) the data set corresponding to a supervised case. The result shows that the proposed algorithm works well, with recognition above 91%, and it could be used for a better profit of domestic water management.
Abstract: The CIMMACS’07 is the internationally recognized Forum for the dissemination of
the latest advances on Neural Networks, Fuzzy Systems, Evolutionary Computation,
Artificial Intelligence, Systems Theory, Man-Machine Systems, Cybernetics,
Simulation, Modelling, Optimization etc as well as their impact and their interaction
with other areas of Computer Science and Engineering. The various WSEAS
conferences on Neural Networks, Fuzzy Systems, Evolutionary Computation,
Artificial Intelligence, Systems Theory, Man-Machine Systems, Cybernetics,
Simulation, Modelling, Optimization has been successfully held each year since 1996
and has produced more than 150 volumes of Proceedings while the best papers and
the invited papers after extension and after peer review from 4 international referees,
are published in WSEAS Journals covered by all the major scientific indexes.
Abstract: Animal swarms in nature are able to adapt to dynamic changes in their envi-ronment, and through cooperation they can solve problems that are crucial for their survival. Only by means of local interactions with other members of the swarm and with the environment, they can achieve a common goal more efficiently than it would be done by a single individual. This problem-solving behavior that results from the multiplicity of such interactions is referred to as Swarm Intelligence. The mathematical models of swarming behavior in nature were initially proposed to solve optimization problems. Nevertheless, this decentralized approach can be a valuable tool for a variety of applications, where emerging global patterns represent a solution to the task at hand. Methods for the solution of difficult computational problems based on Swarm Intelligence have been experimentally demonstrated and reported in the literature. However, a general framework that would facilitate their design does not exist yet. In this dissertation, a new general design methodology for Swarm Intelligence tools is proposed. By defining a discrete space in which the members of the swarm can move, and by modifying the rules of local interactions and setting the adequate objective function for solutions evaluation, the proposed methodology is tested in various domains. The dissertation presents a set of case studies, and focuses on two general approaches. One approach is to apply Swarm Intelligence as a tool for optimization and feature extraction, and the other approach is to model multi-agent systems such that they resemble swarms of animals in nature providing them with the ability to autonomously perform a task at hand. Artificial swarms are designed to be autonomous, scalable, robust, and adaptive to the changes in their environment. In this work, the methods that exploit one or more of these features are presented. First, the proposed methodology is validated in a real-world scenario seen as a combinatorial optimization problem. Then a set of novel tools for feature extraction, more precisely the adaptive edge detection and the broken-edge linking in digital images is proposed. A novel data clustering algorithm is also proposed and applied to image segmentation. Finally, a scalable algorithm based on the proposed methodology is developed for distributed task allocation in multi-agent systems, and applied to a swarm of robots. The newly proposed general methodology provides a guideline for future developers of the Swarm Intelligence tools.
Abstract: Air pollution is one of the most important environmental problems in developed and undeveloped countries. As many cities in the world, Salamanca (Guanajuato, Mexico) has air pollution problems and is catalogued as one of the most polluted cities in the country. The main causes of air pollution in Salamanca are fixed emission sources, such as chemical industry and electricity generation. The environmental effects in the air are acute and big efforts have been done to measure the Sulphur Dioxide (SO2) and Particulate Matter less than 10 microns in diameter (PM10), the most important air pollutants in Salamanca. Unfortunately, the air pollution value is computed and reported by the Health Authorities with the daily average of SO2 and PM10 pollutant concentrations without take into account meteorological factors. However, It is shown by related studies that severe air pollution episodes are connected with anomalous weather conditions. In this PhD. Thesis, an intelligence monitoring model is proposed to estimate automatically the AQI in Salamanca. Proposed model apply the Sensor Data Fusion (SDF) and Artificial Neural Network (ANN) techniques. To estimate the AQI in Salamanca, the model take into account meteorological variables as decision factors. Proposed methodology analyzes (by minute) the pollutant concentrations and the meteorological variables time series to build the training patterns with relevant and representative information to train a Self-Organizing Map (SOM). To build the training patterns, maximum and minimum daily pollutant concentrations associated with their meteorological variables (wind direction and wind speed) were considered. In the SOM training process, a SOM with four neurons was created and trained. SOM results were analyzed and evaluated with established environmental levels by Environmental Authorities. Another SOM was created and trained with and adicional neuron. The evaluation criterio was done and evaluated to get the best results. ANN have shown their capacity as nonlinear classifiers. ANN gather subjacent information in cluster of measures becoming by the sensors at the same time that fuse the data. Furthermore, with ANN a discriminate function can be implemented, which remove the false episode of pollution, an important aspect in the classification of pollutant sensor data with instability. In function on the meteorological variables, ANN determine if the pollutant concentrations belong to an specific monitoring station. To implement the discriminant function, were selected the daily maximum and minimum concentrations and their associated meteorological variables of wind direction and wind speed. With SDF a quantitative approach information is obtained about the sensors separately. With the quantitative approach, a qualitative approach that help to take decisions about to environmental contingency. Applying SDF a complete estimation of the AQI is done with more resolution over a hazard region to the population. To show the benefits of the suggested and implemented model and methodology, representative days with pollution episodes have been analyzed, obtaining 1) to model the meteorological effects in the pollution concentration, 2) to classify the zone pollutant concentration according the Environmental Authorities and 3) to represent the pollution behaviour in function of the meteorological variables.
Abstract: In recent years technological advances have led to the generation and collection of large amount of mainly numerical data, and there is a great interest on processing them for extract knowledge and information with the main objective of making systems more efficient where these data were obtained from. Information in a database is found implicit in the values that represent the system different states while knowledge is implicit in relations between the different attribute values or features of the data base. Those relations are identified by groups (internal structure) that must be discovered and that describe relations between input and output states. For this purpose different techniques have been developed, one of which is through partitional clustering algorithms. In this thesis a contribution to knowledge is proposed and information extraction from numerical databases through fuzzy hybrid partitional clustering algorithms. Information is extracted by grouping and characterizing data in typical, atypical and noise, as well as application to image sub-segmentation where a new approach is proposed with interesting characteristics for detecting atypical pixels that could be linked to microcalcifications in order to detect breast cancer, or wood knots for assess its quality, both cases treated on this thesis, or in any other application for industry or health, in example, where it does not matter if pixels to find are in very small quantities. Knowledge is extracted through setting up two fuzzy models of type Takagi-Sugeno that allows automatic characterization and classification of new data. This will gives a system able to produce information about the processed numerical data with these models. On this job we have mainly used the hybrid clustering algorithm PFCM (Possibilistic Fuzzy c-Means) where which we have added an improvement whose algorithm were called GKPFCM (Gustafson-Kessel Possibilistic Fuzzy c-Means) and that allows to find groups with patterns more approximated to natural distributions of the data groups. This is reflected in an unsupervised learning for identification of bananas, ripe and unripe tomatoes also presented in this document. Within major achievements of this thesis development we can cite: Is proposed a new approach for sub-segmentation of digital images based on the clustering algorithm PFCM. The purpose is to identify data sub-groups of interest that could be atypical or typical data while in many applications, particularly in diagnosis, these last are the more interesting ones. In this thesis we show up two applications for real cases. Is improved the PFCM (GKPFCM) algorithm by embodying the Mahalanobis distance because the found groups have a better approximation to the data distribution. Also is proposed a construction of a classifier that makes possible to obtain information automatically from new data by classifying and characterising them as typical, atypical or noise. Classifier is based on two fuzzy models of type Takagi-Sugeno which obtains its parameters from results generated by the GKPFCM algorithm
Abstract: The Backpropagation Algorithm, BPA, is one of the most known and used algorithms to training the Artificial Neuronal Networks, ANNs. The BPA has been success used in problems of patterns classification in areas such as: Medicine, Bioinformatic, Telecommunications, Banking, Climatological Predictions, etc. However the BPA has some limitations that prevent to reach an optimal efficiency level (slowness problems, convergence and classification accuracy). These problems have provoked a big number researches to improve the BPA. However, in general none of the modifications have been capable of delivering satisfactory performance for all problems. In this doctoral Thesis is proposed an alternative to improve some of the BPA deficiencies. The suggested algorithm, is a neuronal model based on the biological property of the Metaplasticity. The Metaplasticity is a biological concept widely known in the fields of biology, medical computer science, neuroscience, physiology, neurology and others. The Metaplasticity is related to the processes of memory and of the learning. The main advantage of the suggested Artificial Metaplasticity algorithm, AMP, is that, it is able implementing in any ANNs, in this thesis, algorithm was implemented in a Multilayer Perceptron, MLP. The most efficient AMP model (as a function of learning time and performance) is the approach that connects metaplasticity and Shannon’s information theory, which establishes that less frequent patterns carry more information than frequent patterns. This model defines artificial metaplasticity as a learning procedure that produces greater modifications in the synaptic weights with less frequent patterns than frequent patterns, as a way of extracting more information from the former than from the latter.
Abstract: Swarm Robotics refers to the application of Swarm Intelligence techniques where a
desired collective behavior emerges from the local interactions of robots with one another and with
their environment. In this paper, a modified Bees Algorithm is proposed for multi-target search and coverage by an autonomous swarm of robotic "bees". The objective is to find targets in an unknown area, send their estimated locations and fitness values to other robots in swarm which then provide the coverage of the found targets in a self-organized, decentralized way. The robots are equipped with ultrasonic sensors for obstacle avoidance, thermal sensors for target detection, and ZigBee modules for local communication. For the experiments, a small swarm of robots was built to test the performance of the modified Bees Algorithm. The experimental results show that the swarm is selforganized, decentralized and adaptive, and it can be successfully applied to the unknown area search and coverage.
Abstract: At present, the water resources are a strategic element each time more necessary and limited becoming a source of conflicts. For that, it is fundamental to create an independent and competent entity with good reputation and social acceptation. This entity must be able to obtain, store and process all data dispersed in different entities creating a network for these purposes. Finally, it must be able to organize different branches between the government and the final users. Using one of the wellknown Multicriteria Decision Methods(MCDM) with several realistic alternatives and several criteria identified in expert seminars in Salta and Madrid, we have obtained hopeful results and more recently new modifications introduced have generated better results.
Abstract: Many Artificial Neural Networks design algorithms or learning methods imply the minimization of an error objective function. During learning, weight values are updated following a strategy that tends to minimize the final mean error in the Network performance. Weight values are classically seen as a representation of the synaptic weights in biological neurons and their ability to change its value could be
interpreted as artificial plasticity inspired by this biological property of neurons. In such a way, metaplasticity is interpreted in this paper as the ability to change the efficiency of artificial plasticity giving more relevance to weight updating of less
frequent activations and resting relevance to frequent ones. Modeling this interpretation in the training phase, the hypothesis of an improved training is tested in the Multilayer Perceptron with Backpropagation case. The results show a
much more efficient training maintaining the Artificial Neural Network performance.
