A Neural Network Architecture for Autonomous Learning, Recognition, and Prediction in a Nonstationary World

In a constantly changing world, humans are adapted to alternate routinely between attending to familiar objects and testing hypotheses about novel ones. We can rapidly learn to recognize and narne novel objects without unselectively disrupting our memories of familiar ones. We can notice fine details that differentiate nearly identical objects and generalize across broad classes of dissimilar objects. This chapter describes a class of self-organizing neural network architectures--called ARTMAP-- that are capable of fast, yet stable, on-line recognition learning, hypothesis testing, and naming in response to an arbitrary stream of input patterns (Carpenter, Grossberg, Markuzon, Reynolds, and Rosen, 1992; Carpenter, Grossberg, and Reynolds, 1991). The intrinsic stability of ARTMAP allows the system to learn incrementally for an unlimited period of time. System stability properties can be traced to the structure of its learned memories, which encode clusters of attended features into its recognition categories, rather than slow averages of category inputs. The level of detail in the learned attentional focus is determined moment-by-moment, depending on predictive success: an error due to over-generalization automatically focuses attention on additional input details enough of which are learned in a new recognition category so that the predictive error will not be repeated. An ARTMAP system creates an evolving map between a variable number of learned categories that compress one feature space (e.g., visual features) to learned categories of another feature space (e.g., auditory features). Input vectors can be either binary or analog. Computational properties of the networks enable them to perform significantly better in benchmark studies than alternative machine learning, genetic algorithm, or neural network models. Some of the critical problems that challenge and constrain any such autonomous learning system will next be illustrated. Design principles that work together to solve these problems are then outlined. These principles are realized in the ARTMAP architecture, which is specified as an algorithm. Finally, ARTMAP dynamics are illustrated by means of a series of benchmark simulations.

A Neural Network Architecture for Figure-ground Separation of Connected Scenic Figures

A neural network model, called an FBF network, is proposed for automatic parallel separation of multiple image figures from each other and their backgrounds in noisy grayscale or multi-colored images. The figures can then be processed in parallel by an array of self-organizing Adaptive Resonance Theory (ART) neural networks for automatic target recognition. An FBF network can automatically separate the disconnected but interleaved spirals that Minsky and Papert introduced in their book Perceptrons. The network's design also clarifies why humans cannot rapidly separate interleaved spirals, yet can rapidly detect conjunctions of disparity and color, or of disparity and motion, that distinguish target figures from surrounding distractors. Figure-ground separation is accomplished by iterating operations of a Feature Contour System (FCS) and a Boundary Contour System (BCS) in the order FCS-BCS-FCS, hence the term FBF, that have been derived from an analysis of biological vision. The FCS operations include the use of nonlinear shunting networks to compensate for variable illumination and nonlinear diffusion networks to control filling-in. A key new feature of an FBF network is the use of filling-in for figure-ground separation. The BCS operations include oriented filters joined to competitive and cooperative interactions designed to detect, regularize, and complete boundaries in up to 50 percent noise, while suppressing the noise. A modified CORT-X filter is described which uses both on-cells and off-cells to generate a boundary segmentation from a noisy image.

Flexible and robust run-time configuration for self-managing systems

This paper describes a methodology for deploying flexible dynamic configuration into embedded systems whilst preserving the reliability advantages of static systems. The methodology is based on the concept of decision points (DP) which are strategically placed to achieve fine-grained distribution of self-management logic to meet application-specific requirements. DP logic can be changed easily, and independently of the host component, enabling self-management behavior to be deferred beyond the point of system deployment. A transparent Dynamic Wrapper mechanism (DW) automatically detects and handles problems arising from the evaluation of self-management logic within each DP and ensures that the dynamic aspects of the system collapse down to statically defined default behavior to ensure safety and correctness despite failures. Dynamic context management contributes to flexibility, and removes the need for design-time binding of context providers and consumers, thus facilitating run-time composition and incremental component upgrade.

Adaptability in organisms and artifacts: A multi level perspective on adaptive processes

Abstract Adaptability to changing circumstances is a key feature of living creatures. Understanding such adaptive processes is central to developing successful autonomous artifacts. In this paper two perspectives are brought to bear on the issue of adaptability. The first is a short term perspective which looks at adaptability in terms of the interactions between the agent and the environment. The second perspective involves a hierarchical evolutionary model which seeks to identify higher-order forms of adaptability based on the concept of adaptive meta-constructs. Task orientated and agent-centered models of adaptive processes in artifacts are considered from these two perspectives. The former isrepresented by the fitness function approach found in evolutionary learning, and the latter in terms of the concepts of empowerment and homeokinesis found in models derived from the self-organizing systems approach. A meta-construct approach to adaptability based on the identification of higher level meta-metrics is also outlined. 2009 Published by Elsevier B.V.

Relação entre as variáveis sociais, económicas e ambientais com o padrão da distribuição espaço-temporal dos casos de Dengue por munícipio no Brasil : de 2008 até 2012, utilizando o SOM

Atualmente, um dos principais desafios que afeta a saúde pública no Brasil é a crescente evolução no número de casos e epidemias provocados pelo vírus da dengue. Não existem estudos suficientes que consigam elucidar quais fatores contribuem para a evolução das epidemias de Dengue. Fatores como condições sanitárias, localização geográfica, investimentos financeiros em infraestrutura e qualidade de vida podem estar relacionados com a incidência de Dengue. Além disso, outra questão que merece um maior destaque é o estudo para se identificar o grau de impacto das variáveis determinantes da dengue e se existe um padrão que está correlacionado com a taxa de incidência. Desta forma, este trabalho tem como objetivo principal a correlação da taxa de incidência da dengue na população de cada município brasileiro, utilizando dados relativos aos aspectos sociais, econômicos, demográficos e ambientais. Outra contribuição relevante do trabalho, foi a análise dos padrões de distribuição espacial da taxa de incidência de Dengue e sua relação com os padrões encontrados utilizando as variáveis socioeconômicas e ambientais, sobretudo analisando a evolução temporal no período de 2008 até 2012. Para essa análises, utilizou-se o Sistema de Informação Geográfica (SIG) aliado com a mineração de dados, através da metodologia de rede neural mais especificamente o mapa auto organizável de Kohonen ou self-organizing maps (SOM). Tal metodologia foi empregada para a identificação de padrão de agrupamentos dessas variáveis e sua relação com as classes de incidência de dengue no Brasil (Alta, Média e Baixa). Assim, este projeto contribui de forma significativa para uma melhor compreensão dos fatores que estão associados à ocorrência de Dengue, e como essa doença está correlacionada com fatores como: meio ambiente, infraestrutura e localização no espaço geográfico.

Geografia eleitoral : análise espacial de vinte anos de resultados eleitorais

A Geografia Eleitoral definida como a análise da interação entre o espaço, o lugar e os processos eleitorais, compreende fundamentalmente três domínios: padrões de voto, influências geográficas nas eleições e a geografia da representação. A Geografia Eleitoral conta uma longa história, ao ponto de já ter tido um status próprio no âmbito da disciplina. Depois ter aparecido nos anos 70 e 80 com algum vigor no contexto português, esta abordagem dos fenómenos eleitorais tem sido relativamente negligenciada nos anos. Neste trabalho, conjugando as metodologias espaciais-analíticas mais tradicionais com um conjunto de novas tecnologias - como os Sistemas de Informação Geográfica (SIG) e os Self- Organizing Maps (SOM) -, pretendemos dar uma nova ênfase à Geografia Eleitoral nacional, realçando o seu caráter explicativo e abrindo portas a abordagens multidisciplinares dos dados eleitorais. Com base nos resultados das eleições legislativas portuguesas realizadas no período compreendido entre 1991 e 2011, analisamos neste trabalho os seguintes tópicos: a distribuição espacial dos resultados, em conjunto e individualmente, dos cinco partidos com representação parlamentar; a distribuição dos resultados deste conjunto de partidos por região, considerando uma das propostas de divisão administrativa referendada em 1998 e analisando a região da Estremadura e Ribatejo como um estudo de caso; os padrões gerados pela distribuição do bloco constituído pelos dois principais partidos (PS e PPD/PSD); o comportamento espacial dos blocos Direita/Centro-Direita e Esquerda/Centro- Esquerda; a abstenção eleitoral, confrontando os valores registados em cada freguesia com o resultado nacional; a comparação entre diferentes tipos de eleições; a distribuição dos resultados por partido nos dois principais distritos (Lisboa e Porto) que em conjunto representam mais de 40% da população portuguesa; o comportamento do Bloco de Esquerda, o mais jovem dos partidos considerados; e os mapeamentos das freguesias “sociais-democratas” e “socialistas”. Os resultados deste trabalho comprovam de forma geral, de que a georreferenciação dos dados eleitorais nacionais geram uma cartografia que permite confirmar aquilo que outras análises têm vindo a mostrar sobre o comportamento eleitoral dos portugueses. No entanto, existem aspectos específicos da distribuição espacial deste mesmo comportamento eleitoral que permitem aprofundar o conhecimento sobre a interacção entre o espaço e os processos eleitorais.

Contributions towards smart cities : exploring block level census data for the characterization of change in Lisbon

The interest in using information to improve the quality of living in large urban areas and its governance efficiency has been around for decades. Nevertheless, the improvements in Information and Communications Technology has sparked a new dynamic in academic research, usually under the umbrella term of Smart Cities. This concept of Smart City can probably be translated, in a simplified version, into cities that are lived, managed and developed in an information-saturated environment. While it makes perfect sense and we can easily foresee the benefits of such a concept, presently there are still several significant challenges that need to be tackled before we can materialize this vision. In this work we aim at providing a small contribution in this direction, which maximizes the relevancy of the available information resources. One of the most detailed and geographically relevant information resource available, for the study of cities, is the census, more specifically the data available at block level (Subsecção Estatística). In this work, we use Self-Organizing Maps (SOM) and the variant Geo-SOM to explore the block level data from the Portuguese census of Lisbon city, for the years of 2001 and 2011. We focus on gauging change, proposing ways that allow the comparison of the two time periods, which have two different underlying geographical bases. We proceed with the analysis of the data using different SOM variants, aiming at producing a two-fold portrait: one, of the evolution of Lisbon during the first decade of the XXI century, another, of how the census dataset and SOM’s can be used to produce an informational framework for the study of cities.

The use of artificial intelligence algorithms to guide surgical treatment of adolescent idiopathic scoliosis

La scoliose idiopathique de l’adolescent (SIA) est une déformation tri-dimensionelle du rachis. Son traitement comprend l’observation, l’utilisation de corsets pour limiter sa progression ou la chirurgie pour corriger la déformation squelettique et cesser sa progression. Le traitement chirurgical reste controversé au niveau des indications, mais aussi de la chirurgie à entreprendre. Malgré la présence de classifications pour guider le traitement de la SIA, une variabilité dans la stratégie opératoire intra et inter-observateur a été décrite dans la littérature. Cette variabilité s’accentue d’autant plus avec l’évolution des techniques chirurgicales et de l’instrumentation disponible. L’avancement de la technologie et son intégration dans le milieu médical a mené à l’utilisation d’algorithmes d’intelligence artificielle informatiques pour aider la classification et l’évaluation tridimensionnelle de la scoliose. Certains algorithmes ont démontré être efficace pour diminuer la variabilité dans la classification de la scoliose et pour guider le traitement. L’objectif général de cette thèse est de développer une application utilisant des outils d’intelligence artificielle pour intégrer les données d’un nouveau patient et les évidences disponibles dans la littérature pour guider le traitement chirurgical de la SIA. Pour cela une revue de la littérature sur les applications existantes dans l’évaluation de la SIA fut entreprise pour rassembler les éléments qui permettraient la mise en place d’une application efficace et acceptée dans le milieu clinique. Cette revue de la littérature nous a permis de réaliser que l’existence de “black box” dans les applications développées est une limitation pour l’intégration clinique ou la justification basée sur les évidence est essentielle. Dans une première étude nous avons développé un arbre décisionnel de classification de la scoliose idiopathique basé sur la classification de Lenke qui est la plus communément utilisée de nos jours mais a été critiquée pour sa complexité et la variabilité inter et intra-observateur. Cet arbre décisionnel a démontré qu’il permet d’augmenter la précision de classification proportionnellement au temps passé à classifier et ce indépendamment du niveau de connaissance sur la SIA. Dans une deuxième étude, un algorithme de stratégies chirurgicales basé sur des règles extraites de la littérature a été développé pour guider les chirurgiens dans la sélection de l’approche et les niveaux de fusion pour la SIA. Lorsque cet algorithme est appliqué à une large base de donnée de 1556 cas de SIA, il est capable de proposer une stratégie opératoire similaire à celle d’un chirurgien expert dans prêt de 70% des cas. Cette étude a confirmé la possibilité d’extraire des stratégies opératoires valides à l’aide d’un arbre décisionnel utilisant des règles extraites de la littérature. Dans une troisième étude, la classification de 1776 patients avec la SIA à l’aide d’une carte de Kohonen, un type de réseaux de neurone a permis de démontrer qu’il existe des scoliose typiques (scoliose à courbes uniques ou double thoracique) pour lesquelles la variabilité dans le traitement chirurgical varie peu des recommandations par la classification de Lenke tandis que les scolioses a courbes multiples ou tangentielles à deux groupes de courbes typiques étaient celles avec le plus de variation dans la stratégie opératoire. Finalement, une plateforme logicielle a été développée intégrant chacune des études ci-dessus. Cette interface logicielle permet l’entrée de données radiologiques pour un patient scoliotique, classifie la SIA à l’aide de l’arbre décisionnel de classification et suggère une approche chirurgicale basée sur l’arbre décisionnel de stratégies opératoires. Une analyse de la correction post-opératoire obtenue démontre une tendance, bien que non-statistiquement significative, à une meilleure balance chez les patients opérés suivant la stratégie recommandée par la plateforme logicielle que ceux aillant un traitement différent. Les études exposées dans cette thèse soulignent que l’utilisation d’algorithmes d’intelligence artificielle dans la classification et l’élaboration de stratégies opératoires de la SIA peuvent être intégrées dans une plateforme logicielle et pourraient assister les chirurgiens dans leur planification préopératoire.

Adaptive Real-time Anomaly-based Intrusion Detection using Data Mining and Machine Learning Techniques

Die zunehmende Vernetzung der Informations- und Kommunikationssysteme führt zu einer weiteren Erhöhung der Komplexität und damit auch zu einer weiteren Zunahme von Sicherheitslücken. Klassische Schutzmechanismen wie Firewall-Systeme und Anti-Malware-Lösungen bieten schon lange keinen Schutz mehr vor Eindringversuchen in IT-Infrastrukturen. Als ein sehr wirkungsvolles Instrument zum Schutz gegenüber Cyber-Attacken haben sich hierbei die Intrusion Detection Systeme (IDS) etabliert. Solche Systeme sammeln und analysieren Informationen von Netzwerkkomponenten und Rechnern, um ungewöhnliches Verhalten und Sicherheitsverletzungen automatisiert festzustellen. Während signatur-basierte Ansätze nur bereits bekannte Angriffsmuster detektieren können, sind anomalie-basierte IDS auch in der Lage, neue bisher unbekannte Angriffe (Zero-Day-Attacks) frühzeitig zu erkennen. Das Kernproblem von Intrusion Detection Systeme besteht jedoch in der optimalen Verarbeitung der gewaltigen Netzdaten und der Entwicklung eines in Echtzeit arbeitenden adaptiven Erkennungsmodells. Um diese Herausforderungen lösen zu können, stellt diese Dissertation ein Framework bereit, das aus zwei Hauptteilen besteht. Der erste Teil, OptiFilter genannt, verwendet ein dynamisches "Queuing Concept", um die zahlreich anfallenden Netzdaten weiter zu verarbeiten, baut fortlaufend Netzverbindungen auf, und exportiert strukturierte Input-Daten für das IDS. Den zweiten Teil stellt ein adaptiver Klassifikator dar, der ein Klassifikator-Modell basierend auf "Enhanced Growing Hierarchical Self Organizing Map" (EGHSOM), ein Modell für Netzwerk Normalzustand (NNB) und ein "Update Model" umfasst. In dem OptiFilter werden Tcpdump und SNMP traps benutzt, um die Netzwerkpakete und Hostereignisse fortlaufend zu aggregieren. Diese aggregierten Netzwerkpackete und Hostereignisse werden weiter analysiert und in Verbindungsvektoren umgewandelt. Zur Verbesserung der Erkennungsrate des adaptiven Klassifikators wird das künstliche neuronale Netz GHSOM intensiv untersucht und wesentlich weiterentwickelt. In dieser Dissertation werden unterschiedliche Ansätze vorgeschlagen und diskutiert. So wird eine classification-confidence margin threshold definiert, um die unbekannten bösartigen Verbindungen aufzudecken, die Stabilität der Wachstumstopologie durch neuartige Ansätze für die Initialisierung der Gewichtvektoren und durch die Stärkung der Winner Neuronen erhöht, und ein selbst-adaptives Verfahren eingeführt, um das Modell ständig aktualisieren zu können. Darüber hinaus besteht die Hauptaufgabe des NNB-Modells in der weiteren Untersuchung der erkannten unbekannten Verbindungen von der EGHSOM und der Überprüfung, ob sie normal sind. Jedoch, ändern sich die Netzverkehrsdaten wegen des Concept drif Phänomens ständig, was in Echtzeit zur Erzeugung nicht stationärer Netzdaten führt. Dieses Phänomen wird von dem Update-Modell besser kontrolliert. Das EGHSOM-Modell kann die neuen Anomalien effektiv erkennen und das NNB-Model passt die Änderungen in Netzdaten optimal an. Bei den experimentellen Untersuchungen hat das Framework erfolgversprechende Ergebnisse gezeigt. Im ersten Experiment wurde das Framework in Offline-Betriebsmodus evaluiert. Der OptiFilter wurde mit offline-, synthetischen- und realistischen Daten ausgewertet. Der adaptive Klassifikator wurde mit dem 10-Fold Cross Validation Verfahren evaluiert, um dessen Genauigkeit abzuschätzen. Im zweiten Experiment wurde das Framework auf einer 1 bis 10 GB Netzwerkstrecke installiert und im Online-Betriebsmodus in Echtzeit ausgewertet. Der OptiFilter hat erfolgreich die gewaltige Menge von Netzdaten in die strukturierten Verbindungsvektoren umgewandelt und der adaptive Klassifikator hat sie präzise klassifiziert. Die Vergleichsstudie zwischen dem entwickelten Framework und anderen bekannten IDS-Ansätzen zeigt, dass der vorgeschlagene IDSFramework alle anderen Ansätze übertrifft. Dies lässt sich auf folgende Kernpunkte zurückführen: Bearbeitung der gesammelten Netzdaten, Erreichung der besten Performanz (wie die Gesamtgenauigkeit), Detektieren unbekannter Verbindungen und Entwicklung des in Echtzeit arbeitenden Erkennungsmodells von Eindringversuchen.

Self-organized sociopolitical interactions as the best way to achieve organized patterns in human social systems: going beyond the top-down control of classical political regimes

La monografía presenta la auto-organización sociopolítica como la mejor manera de lograr patrones organizados en los sistemas sociales humanos, dada su naturaleza compleja y la imposibilidad de las tareas computacionales de los regímenes políticos clásico, debido a que operan con control jerárquico, el cual ha demostrado no ser óptimo en la producción de orden en los sistemas sociales humanos. En la monografía se extrapola la teoría de la auto-organización en los sistemas biológicos a las dinámicas sociopolíticas humanas, buscando maneras óptimas de organizarlas, y se afirma que redes complejas anárquicas son la estructura emergente de la auto-organización sociopolítica.

A hybrid approach of knowledge-based reasoning for structural assessment

La idea básica de detección de defectos basada en vibraciones en Monitorización de la Salud Estructural (SHM), es que el defecto altera las propiedades de rigidez, masa o disipación de energía de un sistema, el cual, altera la respuesta dinámica del mismo. Dentro del contexto de reconocimiento de patrones, esta tesis presenta una metodología híbrida de razonamiento para evaluar los defectos en las estructuras, combinando el uso de un modelo de la estructura y/o experimentos previos con el esquema de razonamiento basado en el conocimiento para evaluar si el defecto está presente, su gravedad y su localización. La metodología involucra algunos elementos relacionados con análisis de vibraciones, matemáticas (wavelets, control de procesos estadístico), análisis y procesamiento de señales y/o patrones (razonamiento basado en casos, redes auto-organizativas), estructuras inteligentes y detección de defectos. Las técnicas son validadas numérica y experimentalmente considerando corrosión, pérdida de masa, acumulación de masa e impactos. Las estructuras usadas durante este trabajo son: una estructura tipo cercha voladiza, una viga de aluminio, dos secciones de tubería y una parte del ala de un avión comercial.

A new linear initialization in SOM for biomolecular data

In the past decade, the amount of data in biological field has become larger and larger; Bio-techniques for analysis of biological data have been developed and new tools have been introduced. Several computational methods are based on unsupervised neural network algorithms that are widely used for multiple purposes including clustering and visualization, i.e. the Self Organizing Maps (SOM). Unfortunately, even though this method is unsupervised, the performances in terms of quality of result and learning speed are strongly dependent from the neuron weights initialization. In this paper we present a new initialization technique based on a totally connected undirected graph, that report relations among some intersting features of data input. Result of experimental tests, where the proposed algorithm is compared to the original initialization techniques, shows that our technique assures faster learning and better performance in terms of quantization error.

Simulated annealing technique for fast learning of SOM networks

The Self-Organizing Map (SOM) is a popular unsupervised neural network able to provide effective clustering and data visualization for multidimensional input datasets. In this paper, we present an application of the simulated annealing procedure to the SOM learning algorithm with the aim to obtain a fast learning and better performances in terms of quantization error. The proposed learning algorithm is called Fast Learning Self-Organized Map, and it does not affect the easiness of the basic learning algorithm of the standard SOM. The proposed learning algorithm also improves the quality of resulting maps by providing better clustering quality and topology preservation of input multi-dimensional data. Several experiments are used to compare the proposed approach with the original algorithm and some of its modification and speed-up techniques.

An incremental space to visualize dynamic data sets

In Information Visualization, adding and removing data elements can strongly impact the underlying visual space. We have developed an inherently incremental technique (incBoard) that maintains a coherent disposition of elements from a dynamic multidimensional data set on a 2D grid as the set changes. Here, we introduce a novel layout that uses pairwise similarity from grid neighbors, as defined in incBoard, to reposition elements on the visual space, free from constraints imposed by the grid. The board continues to be updated and can be displayed alongside the new space. As similar items are placed together, while dissimilar neighbors are moved apart, it supports users in the identification of clusters and subsets of related elements. Densely populated areas identified in the incSpace can be efficiently explored with the corresponding incBoard visualization, which is not susceptible to occlusion. The solution remains inherently incremental and maintains a coherent disposition of elements, even for fully renewed sets. The algorithm considers relative positions for the initial placement of elements, and raw dissimilarity to fine tune the visualization. It has low computational cost, with complexity depending only on the size of the currently viewed subset, V. Thus, a data set of size N can be sequentially displayed in O(N) time, reaching O(N (2)) only if the complete set is simultaneously displayed.

The Potential Of Kohonen Method For Classifying Rivers Focused On Regional Environmental Flow Determination With ELOHA

This article highlights the potential benefits that the Kohonen method has for the classification of rivers with similar characteristics by determining regional ecological flows using the ELOHA (Ecological Limits of Hydrologic Alteration) methodology. Currently, there are many methodologies for the classification of rivers, however none of them include the characteristics found in Kohonen method such as (i) providing the number of groups that actually underlie the information presented, (ii) used to make variable importance analysis, (iii) which in any case can display two-dimensional classification process, and (iv) that regardless of the parameters used in the model the clustering structure remains. In order to evaluate the potential benefits of the Kohonen method, 174 flow stations distributed along the great river basin “Magdalena-Cauca” (Colombia) were analyzed. 73 variables were obtained for the classification process in each case. Six trials were done using different combinations of variables and the results were validated against reference classification obtained by Ingfocol in 2010, whose results were also framed using ELOHA guidelines. In the process of validation it was found that two of the tested models reproduced a level higher than 80% of the reference classification with the first trial, meaning that more than 80% of the flow stations analyzed in both models formed invariant groups of streams.