Encyclopedia of Artificial Intelligence最新文献

{"title":"Information Theoretic Learning","authors":"Deniz Erdoğmuş, J. Príncipe","doi":"10.4018/978-1-59904-849-9.CH133","DOIUrl":"https://doi.org/10.4018/978-1-59904-849-9.CH133","url":null,"abstract":"INTRODUCTION Learning systems depend on three interrelated components: topologies, cost/performance functions, and learning algorithms. Topologies provide the constraints for the mapping, and the learning algorithms offer the means to find an optimal solution; but the solution is optimal with respect to what? Optimality is characterized by the criterion and in neural network literature, this is the least addressed component, yet it has a decisive influence in generalization performance. Certainly, the assumptions behind the selection of a criterion should be better understood and investigated. Traditionally, least squares has been the benchmark criterion for regression problems; considering classification as a regression problem towards estimating class posterior probabilities, least squares has been employed to train neural network and other classifier topologies to approximate correct labels. The main motivation to utilize least squares in regression simply comes from the intellectual comfort this criterion provides due to its success in traditional linear least squares regression applications – which can be reduced to solving a system of linear equations. For nonlinear regression, the assumption of Gaussianity for the measurement error combined with the maximum likelihood principle could be emphasized to promote this criterion. In nonparametric regression, least squares principle leads to the conditional expectation solution, which is intuitively appealing. Although these are good reasons to use the mean squared error as the cost, it is inherently linked to the assumptions and habits stated above. Consequently, there is information in the error signal that is not captured during the training of nonlinear adaptive systems under non-Gaussian distribution conditions when one insists on secondorder statistical criteria. This argument extends to other linear-second-order techniques such as principal component analysis (PCA), linear discriminant analysis (LDA), and canonical correlation analysis (CCA). Recent work tries to generalize these techniques to nonlinear scenarios by utilizing kernel techniques or other heuristics. This begs the question: what other alternative cost functions could be used to train adaptive systems and how could we establish rigorous techniques for extending useful concepts from linear and second-order statistical techniques to nonlinear and higher-order statistical learning methodologies?","PeriodicalId":320314,"journal":{"name":"Encyclopedia of Artificial Intelligence","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129833989","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Different Approaches for Cooperation with Metaheuristics","authors":"J. M. Cadenas, M. C. Garrido, E. M. Ballester, Carlos Cruz Corona, D. Pelta, J. Verdegay","doi":"10.4018/978-1-59904-849-9.CH073","DOIUrl":"https://doi.org/10.4018/978-1-59904-849-9.CH073","url":null,"abstract":"Working on artificial intelligence, one of the tasks we can carry on is optimization of the possible solutions of a problem. Optimization problems appear. In optimization problems we search for the best solution, or one good enough, to a problem among a lot of alternatives. Problems we try to solve are usual in daily living. Every person constantly works out optimization problems, e.g. finding the quickest way from home to work taking into account traffic restrictions. Humans can find efficiently solutions to these problems because these are easy enough. Nevertheless, problems can be more complex, for example reducing fuel consumption of a fleet of plains. Computational algorithms are required to tackle this kind of problems. A first approach to solve them is using an exhaustive search. Theoretically, this method always finds the solution, but is not efficient as its execution time grows exponentially. In order to improve this method heuristics were proposed. Heuristics are intelligent techniques, methods or procedures that use expert knowledge to solve tasks; they try to obtain a high performance referring to solution quality and used resources. Metaheuristics, term first used by Fred Glover in 1986 (Glover, 1986), arise to improve heuristics, and can be defined as (Melián, Moreno & Moreno, 2003) ‘intelligent strategies for designing and improving very general heuristic procedures with a high performance’. Since Glover the field has been extensively developed. The current trend is designing new metaheuristics that improve the solution to given problems. However, another line, very interesting, is reuse existing metaheuristics in a coordinated system. In this article we present two different methods following this line.","PeriodicalId":320314,"journal":{"name":"Encyclopedia of Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130659754","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bioinspired Associative Memories","authors":"R. Vázquez, Juan Humberto Sossa Azuela","doi":"10.4018/978-1-59904-849-9.CH039","DOIUrl":"https://doi.org/10.4018/978-1-59904-849-9.CH039","url":null,"abstract":"An associative memory AM is a special kind of neural network that allows recalling one output pattern given an input pattern as a key that might be altered by some kind of noise (additive, subtractive or mixed). Most of these models have several constraints that limit their applicability in complex problems such as face recognition (FR) and 3D object recognition (3DOR). Despite of the power of these approaches, they cannot reach their full power without applying new mechanisms based on current and future study of biological neural networks. In this direction, we would like to present a brief summary concerning a new associative model based on some neurobiological aspects of human brain. In addition, we would like to describe how this dynamic associative memory (DAM), combined with some aspects of infant vision system, could be applied to solve some of the most important problems of pattern recognition: FR and 3DOR.","PeriodicalId":320314,"journal":{"name":"Encyclopedia of Artificial Intelligence","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134283563","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intelligent Traffic Sign Classifiers","authors":"R. Vicen-Bueno, Elena Torijano Gordo, Antonio García González, M. Rosa-Zurera, R. Gil-Pita","doi":"10.4018/978-1-59904-849-9.CH141","DOIUrl":"https://doi.org/10.4018/978-1-59904-849-9.CH141","url":null,"abstract":"The Artificial Neural Networks (ANNs) are based on the behavior of the brain. So, they can be considered as intelligent systems. In this way, the ANNs are constructed according to a brain, including its main part: the neurons. Moreover, they are connected in order to interact each other to acquire the followed intelligence. And finally, as any brain, it needs having memory, which is achieved in this model with their weights. So, starting from this point of view of the ANNs, we can affirm that these systems are able to learn difficult tasks. In this article, the task to learn is to distinguish between different kinds of traffic signs. Moreover, this ANN learning must be done for traffic signs that are not in perfect conditions. So, the learning must be robust against several problems like rotation, translation or even vandalism. In order to achieve this objective, an intelligent extraction of information from the images is done. This stage is very important because it improves the performance of the ANN in this task.","PeriodicalId":320314,"journal":{"name":"Encyclopedia of Artificial Intelligence","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129853617","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CNS Tumor Prediction Using Gene Expression Data Part II","authors":"A. Islam, K. Iftekharuddin, E. George, D. Russomanno","doi":"10.4018/978-1-59904-849-9.CH047","DOIUrl":"https://doi.org/10.4018/978-1-59904-849-9.CH047","url":null,"abstract":"In this chapter, we propose a novel algorithm for characterizing a variety of CNS tumors. The proposed algorithm is illustrated with an analysis of an Affymetrix gene expression data from CNS tumor samples (Pomeroy et al., 2002). As discussed in the previous chapter entitled: CNS Tumor Prediction Using Gene Expression Data Part I, we used an ANOVA model to normalize the microarray gene expression measurements. In this chapter, we introduce a systemic way of building tumor prototypes to facilitate automatic prediction of CNS tumors.","PeriodicalId":320314,"journal":{"name":"Encyclopedia of Artificial Intelligence","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133258400","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evolutionary Computing Approach for Ad-Hoc Networks","authors":"Prayag Narula, S. Misra, S. K. Dhurandher","doi":"10.4018/978-1-59904-849-9.CH090","DOIUrl":"https://doi.org/10.4018/978-1-59904-849-9.CH090","url":null,"abstract":"Wireless ad-hoc networks are infrastructureless networks in which heterogeneous capable nodes assemble together and start communicating without any backbone support. These networks can be made truly dynamic and the nodes in these networks can move about freely while connecting and disconnecting with other nodes in the network. This property of ad-hoc networks to self-organize and communicate without any extrinsic support gives them tremendous flexibility and makes them perfect for applications such as emergencies, crisis-management, military and healthcare. For example, in case of emergencies such as earthquakes, often most of the existing wired network infrastructure gets destroyed. In addition, since most of the wireless networks such as GSM and IEEE 802.11 wireless LAN use wired infrastructure as their backbone, often they are also rendered useless. In such scenarios, ad-hoc networks can be deployed swiftly and used for coordinating relief and rescue operations. Ad-hoc networks can be used for communication between various stations in the battle-field, where setting up a wired or an infrastructure-based network is often considered impractical. Though a lot of research has been done on ad-hoc networks, a lot of problems such as security, qualityof-service (QoS) and multicasting need to be addressed satisfactorily before ad-hoc networks can move out of the labs and provide a flexible and cheap networking solution. Evolutionary computing algorithms are a class of bio-inspired computing algorithms. Bio-inspired computing refers to the collection of algorithms that use techniques learnt from natural biological phenomena and implement them to solve a mathematical problem (Olario & Zomaya, 2006). Natural phenomena such as evolution, genetics, and collective behavior of social organisms and functioning of a mammalian brain teach us a variety of techniques that can be effectively employed to solve problems in computer science which are inherently tough. In this Chapter and the chapter entitled, “Swarm Intelligence Approach for Wireless Ad Hoc Networks” of this book, we present some of the currently available important implementations of bio-inspired computing in the field of ad-hoc networks. This chapter looks at the problem of optimal clustering in ad-hoc networks and its solution using Genetic Programming (GP) approach. The chapter entitled, “Swarm Intelligence Approaches for Wireless Ad Hoc Networks” of this book, continues the same spirit and explains the use of the principles underlying Ant Colony Optimization (ACO) for routing in ad-hoc networks.","PeriodicalId":320314,"journal":{"name":"Encyclopedia of Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130134022","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adaptive Algorithms for Intelligent Geometric A Computing","authors":"M. Gavrilova","doi":"10.4018/978-1-59904-849-9.CH002","DOIUrl":"https://doi.org/10.4018/978-1-59904-849-9.CH002","url":null,"abstract":"This chapter spans topics from such important areas as Artificial Intelligence, Computational Geometry and Biometric Technologies. The primary focus is on the proposed Adaptive Computation Paradigm and its applications to surface modeling and biometric processing. Availability of much more affordable storage and high resolution image capturing devices have contributed significantly over the past few years to accumulating very large datasets of collected data (such as GIS maps, biometric samples, videos etc.). On the other hand, it also created significant challenges driven by the higher than ever volumes and the complexity of the data, that can no longer be resolved through acquisition of more memory, faster processors or optimization of existing algorithms. These developments justified the need for radically new concepts for massive data storage, processing and visualization. To address this need, the current chapter presents the original methodology based on the paradigm of the Adaptive Geometric Computing. The methodology enables storing complex data in a compact form, providing efficient access to it, preserving high level of details and visualizing dynamic changes in a smooth and continuous manner. The first part of the chapter discusses adaptive algorithms in real-time visualization, specifically in GIS (Geographic Information Systems) applications. Data structures such as Real-time Optimally Adaptive Mesh (ROAM) and Progressive Mesh (PM) are briefly surveyed. The adaptive method Adaptive Spatial Memory (ASM), developed by R. Apu and M. Gavrilova, is then introduced. This method allows fast and efficient visualization of complex data sets representing terrains, landscapes and Digital Elevation Models (DEM). Its advantages are briefly discussed. The second part of the chapter presents application of adaptive computation paradigm and evolutionary computing to missile simulation. As a result, patterns of complex behavior can be developed and analyzed. The final part of the chapter marries a concept of adaptive computation and topology-based techniques and discusses their application to challenging area of biometric computing.","PeriodicalId":320314,"journal":{"name":"Encyclopedia of Artificial Intelligence","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128597679","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Planning Agent for Geriatric Residences","authors":"J. Bajo, D. I. Tapia, S. Rodríguez, J. Corchado","doi":"10.4018/978-1-59904-849-9.CH193","DOIUrl":"https://doi.org/10.4018/978-1-59904-849-9.CH193","url":null,"abstract":"Agents and Multi-Agent Systems (MAS) have become increasingly relevant for developing distributed and dynamic intelligent environments. The ability of software agents to act somewhat autonomously links them with living animals and humans, so they seem appropriate for discussion under nature-inspired computing (Marrow, 2000). This paper presents AGALZ (Autonomous aGent for monitoring ALZheimer patients), and explains how this deliberative planning agent has been designed and implemented. A case study is then presented, with AGALZ working with complementary agents into a prototype environment-aware multi-agent system (ALZ-MAS: ALZheimer Multi-Agent System) (Bajo, Tapia, De Luis, Rodriguez & Corchado, 2007). The elderly health care problem is studied, and the possibilities of Radio Frequency Identification (RFID) (Sokymat, 2006) as a technology for constructing an intelligent environment and ascertaining patient location to generate plans and maximize safety are examined. This paper focuses in the development of natureinspired deliberative agents using a Case-Based Reasoning (CBR) (Aamodt & Plaza, 1994) architecture, as a way to implement sensitive and adaptive systems to improve assistance and health care support for elderly and people with disabilities, in particular with Alzheimer. Agents in this context must be able to respond to events, take the initiative according to their goals, communicate with other agents, interact with users, and make use of past experiences to find the best plans to achieve goals, so we propose the development of an autonomous deliberative agent that incorporates a Case-Based Planning (CBP) mechanism, derivative from Case-Based Reasoning (CBR) (Bajo, Corchado & Castillo, 2006), specially designed for planning construction. CBP-BDI facilitates learning and adaptation, and therefore a greater degree of autonomy than that found in pure BDI (Believe, Desire, Intention) architecture (Bratman, 1987). BDI agents can be implemented by using different tools, such as Jadex (Pokahr, Braubach & Lamersdorf, 2003), dealing with the concepts of beliefs, goals and plans, as java objects that can be created and handled within the agent at execution time.","PeriodicalId":320314,"journal":{"name":"Encyclopedia of Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132817045","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Blind Source Separation by ICA","authors":"M. Ferrer, A. Santana","doi":"10.4018/978-1-59904-849-9.CH042","DOIUrl":"https://doi.org/10.4018/978-1-59904-849-9.CH042","url":null,"abstract":"This work presents a brief introduction to the blind source separation using independent component analysis (ICA) techniques. The main objective of the blind source separation (BSS) is to obtain, from observations composed by different mixed signals, those different signals that compose them. This objective can be reached using two different techniques, the spatial and the statistical one. The first one is based on a microphone array and depends on the position and separation of them. It also uses the directions of arrival (DOA) from the different audio signals. On the other hand, the statistical separation supposes that the signals are statistically independent, that they are mixed in a linear way and that it is possible to get the mixtures with the right sensors (Hyvarinen, Karhunen & Oja, 2001) (Parra, 2002). The last technique is the one that is going to be studied in this work. It is due to this technique is the newest and is in a continuous development. It is used in different fields such as natural language processing (Murata, Ikeda & Ziehe, 2001) (Saruwatari, Kawamura & Shikano, 2001), bioinformatics, image processing (Cichocki & Amari, 2002) and in different real life applications such as mobile communications (Saruwatari, Sawai, Lee, Kawamura, Sakata & Shikano, 2003). Specifically, the technique that is going to be used is the Independent Component Analysis (ICA). ICA comes from an old technique called PCA (Principal Component Analysis) (Hyvarinen, Karhunen & Oja, 2001) (Smith, 2006). PCA is used in a wide range of scopes such as face recognition or image compression, being a very common technique to find patterns in high dimension data. The BSS problem can be of two different ways; the first one is when the mixtures are linear. It means that the data are mixed without echoes or reverberations, while the second one, due to these conditions, the mixtures are convolutive and they are not totally independent because of the signal propagation through dynamic environments. It is the “Cocktail party problem”. Depending on the mixtures, there are several methods to solve the BSS problem. The first case can be seen as a simplification of the second one. The blind source separation based on ICA is also divided into three groups; the first one are those methods that works in the time domain, the second are those who works in the frequency domain and the last group are those methods that combine frequency and time domain methods. A revision of the technique state of these methods is proposed in this work.","PeriodicalId":320314,"journal":{"name":"Encyclopedia of Artificial Intelligence","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116783501","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Component Analysis in Artificial Vision","authors":"O. Déniz-Suárez, Gloria Bueno García","doi":"10.4018/978-1-59904-849-9.CH056","DOIUrl":"https://doi.org/10.4018/978-1-59904-849-9.CH056","url":null,"abstract":"The typical recognition/classification framework in Artificial Vision uses a set of object features for discrimination. Features can be either numerical measures or nominal values. Once obtained, these feature values are used to classify the object. The output of the classification is a label for the object (Mitchell, 1997). The classifier is usually built from a set of “training” samples. This is a set of examples that comprise feature values and their corresponding labels. Once trained, the classifier can produce labels for new samples that are not in the training set. Obviously, the extracted features must be discriminative. Finding a good set of features, however, may not be an easy task. Consider for example, the face recognition problem: recognize a person using the image of his/her face. This is currently a hot topic of research within the Artificial Vision community, see the surveys (Chellappa et al, 1995), (Samal & Iyengar, 1992) and (Chellappa & Zhao, 2005). In this problem, the available features are all of the pixels in the image. However, only a number of these pixels are normally useful for discrimination. Some pixels are background, hair, shoulders, etc. Even inside the head zone of the image some pixels are less useful than others. The eye zone, for example, is known to be more informative than the forehead or cheeks (Wallraven et al, 2005). This means that some features (pixels) may actually increase recognition error, for they may confuse the classifier. Apart from performance, from a computational cost point of view it is desirable to use a minimum number of features. If fed with a large number of features, the classifier will take too long to train or classify. BACKGROUND","PeriodicalId":320314,"journal":{"name":"Encyclopedia of Artificial Intelligence","volume":"48 9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121757127","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}