Borrowing ideas from natural immunity, Artificial Immune Systems (AIS) offer a novel approach to solving many diagnosis, optimization and control problems. In the course of this research this paradigm was applied to the problem of optimizing urban traffic. The traffic was micro-simulated with each car on a two junction road system modeled individually. The cars themselves were programmed with 'personalities' to better simulate real traffic. A novel AIS was developed to detect, predict, and control anomalous traffic conditions. It was also used to optimize the flow of traffic through the road network. Benchmarking was performed against the well accepted TRANSYT traffic control system. Though the TRANSYT system performed better initially, the AIS control showed marked improvement over time as it adapted better to changing traffic conditions. This change was expected as TRANSYT is optimized for specific initial conditions unlike the AIS system which adapts to changes.

Most lending institutions are aware of the importance of having a well-performing credit scoring model or scorecard and know that, in order to remain competitive in the credit industry, it is necessary to continuously improve their scorecards. This is because better scorecards result in substantial monetary savings that can be stated in terms of millions of dollars. Thus, there has been increasing interest in the application of new classifiers in credit scoring from both practitioners and researchers in the last few decades. Most of the recent work in this field has focused on the use of new and innovative techniques to classify applicants as either 'credit-worthy' or 'non-credit-worthy', with the aim of improving scorecard performance. In this thesis, we investigate the suitability of intelligent systems techniques for credit scoring. In particular, intelligent systems that use immunological metaphors are examined and used to build a learning and evolutionary classification algorithm. Our model, named Simple Artificial Immune System (SAIS), is based on the concepts of the natural immune system. The model uses applicants' credit details to classify them as either 'credit-worthy' or 'non-credit-worthy'. As part of the model development, we also investigate several techniques for selecting variables from the applicants' credit details. Variable selection is important as choosing the best set of variables can have a significant effect on the performance of scorecards. Interestingly, our results demonstrate that the traditional stepwise regression variable selection technique seems to perform better than many of the more recent techniques. A further contribution offered by this thesis is a detailed description of the scorecard development process. A detailed explanation of this process is not readily available in the literature and our description of the process is based on our own experiences and discussions with industry credit risk practitioners. We evaluate our model using both publicly available datasets as well as a very large set of real-world consumer credit scoring data obtained from a leading Australian bank. The evaluation results reveal that SAIS is a competitive classifier and is appropriate for developing scorecards which require a class decision as an outcome. Another conclusion reached is one confirmed by the existing literature, that even though more sophisticated scorecard development techniques, including SAIS, perform well compared to the traditional statistical methods, their performances are not statistically significantly different from the statistical methods. As with other intelligent systems techniques, SAIS is not explicitly designed to develop practical scorecards which require the generation of a score that represents the degree of confidence that an applicant will belong to a particular group. However, it is comparable to other intelligent systems techniques which are outperformed by statistical techniques for generating p ractical scorecards. Our final remark on this research is that even though SAIS does not seem to be quite suitable for developing practical scorecards, we still believe that there is room for improvement and that the natural immune system of the body has a number of avenues yet to be explored which could assist with the development of practical scorecards.

This thesis presents a development of Structural Health Monitoring (SHM) and Fault Diagnosis based on Artificial Immune System (AIS), a biology-inspired method motivated from the Biological Immune System (BIS). Using the antigen to model structural health or damage condition of specific characteristics and the antibody to represent an information system or a database that can identify the specific damage pattern, the AIS can detect structural damage and then take action to ensure the structural integrity. In this study the antibodies for SHM were first trained and then tested. The feature space in training includes the natural frequencies and the modal shapes extracted from the simulated structural response data including both free-vibration and seismic response data. The concepts were illustrated for a 2-DOF linear mass-spring-damper system and promising results were obtained. It has shown that the methodology can be effectively used to detect, locate, and assess damage if it occurred. Consistently good results were obtained for both feature spaces of the natural frequencies and the modal shapes extracted from both response data sets. As the only exception, some significant errors were observed in the result for the seismic response data when the second modal shape was used as the feature space. The study has shown great promises of the methodology for structural health monitoring, especially in the case when the measurement data are not sufficient. The work lays a solid foundation for future investigations on the AIS application for large-scale complex structures.

An innovative artificial immune system (AIS) is proposed herein for structural health monitoring (SHM) to ensure the structural integrity and functionality. While satisfactory results were obtained by previous AIS schemes, their performance is strongly structural-parameter-value (SPV) dependent and deviations of SPVs in testing from training due to modeling errors and measurement noises significantly deteriorates the AIS' performance. This thesis presents a less SPV-dependent AIS with a three-phase architecture, including damage-existence-detection, damage-location-determination, and damage-severity-estimation, using specially designed feature vectors (FVs) based on structural modal parameters. The maximum-relative-modal-parameter-change is used to detect the damage's existence and estimate its severity, and the pattern in normalized-modal-parameter-change is used to determinate the damage's location. Comparisons between the proposed FVs and their existing counterparts were conducted for 2/3/4-degree-of-freedom structures to illustrate the superior performance and less SPV-dependence of the proposed method, particularly in determining damage location. The proposed AIS was tested on a 4-degree-of-freedom model using 440 randomly generated damage conditions with a different SPV set per condition. A success rate of 95.23% in the determination of damage's existence and its location was obtained. The trained AIS for the 4-degree-of-freedom model was further evaluated by a four-story and two-bay by two-bay prototype structure used in the benchmark problem proposed by the IASC-ASCE Structural Health Monitoring Task Group. Results have shown great potentials of the proposed approach in its real-world applications.

<p>It is believed that many of the mechanisms present in the biological immune system are well suited for adoption to the field of computer intrusion detection, in the form of artificial immune systems. In this report mechanisms in the biological immune system are introduced, their parallels in artificial immune systems are presented, and how they may be applied to intrusion detection in a computer environment is discussed. An artificial immune system is designed, implemented and applied to detect intrusive behavior in real network data in a simulated network environment. The effect of costimulation and clonal proliferation combined with somatic hypermutation to perform affinity maturation of detectors in the artificial immune system is explored through experiments. An exact expression for the probability of a match between two randomly chosen strings using the r-contiguous matching rule is developed. The use of affinity maturation makes it possible to perform anomaly detection by using smaller sets of detectors with a high level of specificity while maintaining a high level of cover and diversity, which increases the number of true positives, while keeping a low level of false negatives.</p>

It is believed that many of the mechanisms present in the biological immune system are well suited for adoption to the field of computer intrusion detection, in the form of artificial immune systems. In this report mechanisms in the biological immune system are introduced, their parallels in artificial immune systems are presented, and how they may be applied to intrusion detection in a computer environment is discussed. An artificial immune system is designed, implemented and applied to detect intrusive behavior in real network data in a simulated network environment. The effect of costimulation and clonal proliferation combined with somatic hypermutation to perform affinity maturation of detectors in the artificial immune system is explored through experiments. An exact expression for the probability of a match between two randomly chosen strings using the r-contiguous matching rule is developed. The use of affinity maturation makes it possible to perform anomaly detection by using smaller sets of detectors with a high level of specificity while maintaining a high level of cover and diversity, which increases the number of true positives, while keeping a low level of false negatives.

No description available.

O sistema imunológico dos vertebrados é extremamente complexo, sendo responsável por proteger o organismo contra agentes causadores de doenças. Para funcionar apropriadamente, é necessário que seus componentes reconheçam de forma eficaz os elementos patógenos, a fim de neutralizá-los, e também os elementos do próprio organismo, de forma a não reagirem a estes. Estas e outras características são similares àquelas exigidas em soluções para problemas de engenharia e computação. Desta forma, os sistemas imunológicos artificiais utilizam a contraparte biológica como metáfora para o desenvolvimento de diversas ferramentas computacionais utilizadas nas mais diversas tarefas. Esta dissertação utiliza os conceitos apresentados pelos sistemas imunológicos artificiais para o desenvolvimento de um novo algoritmo de aprendizado supervisionado, baseado principalmente no mecanismo de seleção clonal. O método proposto neste trabalho, denominado clonal selection classifier with data reduction (CSCDR), utiliza uma função de aptidão com base no número de classificações corretas e incorretas apresentadas por cada anticorpo. O algoritmo tenta maximizar este valor através do processo de seleção clonal, envolvendo mutação, maturação de afinidade e seleção dos melhores indivíduos, transformando a fase de treinamento em um problema de otimização. Isto leva a anticorpos com maior representatividade e, portanto, diminui a quantidade de protótipos gerados ao final do algoritmo. Experimentos em bases de dados sintéticas e bases de dados de problemas reais, utilizadas como benchmark para problemas de aprendizagem de máquina, demonstram a eficácia do algoritmo CSCDR como técnica de classificação. Quando comparado a outros classificadores conhecidos da literatura, o CSCDR apresenta desempenho similar e, quando comparado a algoritmos baseados em instâncias, o mesmo utiliza menores quantidades de protótipos para representar os dados, mantendo o desempenho. / The vertebrate immune system is an extremely complex system, being responsible for protecting the body against disease causing agents. To function properly, it is necessary its components effectively recognize the pathogens in order to neutralize them, and also elements of the body itself, so as not to react to these. These and other features are similar to those required solutions to problems in engineering and computing. Thus, artificial immune systems use biological counterpart as a metaphor for development of several computational tools used in various tasks. This dissertation uses the concepts presented by the artificial immune systems to develop a new supervised learning algorithm, based mainly on the mechanism of clonal selection. The method proposed in this work, named clonal selection classifier with data reduction (CSCDR), uses a fitness function based on the number of correct and incorrect classifications made by each antibody. The algorithm tries to maximize this value through the clonal selection process, involving mutation, affinity maturation and selection of the best individuals, turning the training phase in an optimization problem. This leads to more representative antibodies and therefore decreases the amount of prototypes generated at the end of the algorithm. Experiments on synthetic databases and real problem databases, used as benchmark to machine learning problems, demonstrate the effectiveness of the CSCDR algorithm as a classification technique. When compared to other well known classifiers in literature, CSCDR shows similar performance and when compared to instance based algorithms, CSCDR utilizes a smaller amount of prototypes to represent the data maintaining the same performance.

Made available in DSpace on 2014-06-11T19:24:01Z (GMT). No. of bitstreams: 0 Previous issue date: 2012-03-26Bitstream added on 2014-06-13T19:26:53Z : No. of bitstreams: 1 oliveira_il_me_sjrp.pdf: 432754 bytes, checksum: d67c9dc954bf3fa2db823177db9151a6 (MD5) / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP) / Os códigos maliciosos (malware) podem causar danos graves em sistemas de computação e dados. O mecanismo que o sistema imunológico humano utiliza para proteger e detectar os organismos que ameaçam o corpo humano demonstra ser eficiente e pode ser adaptado para a detecção de malware atuantes na Internet. Neste contexto, propõe-se no presente trabalho um sistema que realiza coleta distribuída, análise e detecção de programas maliciosos, sendo a detecção inspirada no sistema imunológico humano. Após a coleta de amostras de malware da Internet, as amostras são analisadas de forma dinâmica de modo a proporcionar rastros de execução em nível do sistema operacional e dos fluxos de rede que são usados para criar um modelo comportamental e para gerar uma assinatura de detecção. Essas assinaturas servem como entrada para o detector de malware e atuam como anticorpos no processo de detecção de antígenos realizado pelo sistema imunológico humano. Isso permite entender o ataque realizado pelo malware e auxilia nos processos de remoção de infecções / Malicious programs (malware) can cause severe damages on computer systems and data. The mechanism that the human immune system uses to detect and protect from organisms that threaten the human body is efficient and can be adapted to detect malware attacks. In this context, we propose a system to perform malware distributed collection, analysis and detection, this last inspired by the human immune system. After collecting malware samples from Internet, they are dynamically analyzed so as to provide execution traces at the operating system level and network flows that are used to create a behavioral model and to generate a detection signature. Those signatures serve as input to a malware detector, acting as the antibodies in the antigen detection process performed by immune human system. This allows us to understand the malware attack and aids in the infection removal procedures

O sistema imunológico dos vertebrados é extremamente complexo, sendo responsável por proteger o organismo contra agentes causadores de doenças. Para funcionar apropriadamente, é necessário que seus componentes reconheçam de forma eficaz os elementos patógenos, a fim de neutralizá-los, e também os elementos do próprio organismo, de forma a não reagirem a estes. Estas e outras características são similares àquelas exigidas em soluções para problemas de engenharia e computação. Desta forma, os sistemas imunológicos artificiais utilizam a contraparte biológica como metáfora para o desenvolvimento de diversas ferramentas computacionais utilizadas nas mais diversas tarefas. Esta dissertação utiliza os conceitos apresentados pelos sistemas imunológicos artificiais para o desenvolvimento de um novo algoritmo de aprendizado supervisionado, baseado principalmente no mecanismo de seleção clonal. O método proposto neste trabalho, denominado clonal selection classifier with data reduction (CSCDR), utiliza uma função de aptidão com base no número de classificações corretas e incorretas apresentadas por cada anticorpo. O algoritmo tenta maximizar este valor através do processo de seleção clonal, envolvendo mutação, maturação de afinidade e seleção dos melhores indivíduos, transformando a fase de treinamento em um problema de otimização. Isto leva a anticorpos com maior representatividade e, portanto, diminui a quantidade de protótipos gerados ao final do algoritmo. Experimentos em bases de dados sintéticas e bases de dados de problemas reais, utilizadas como benchmark para problemas de aprendizagem de máquina, demonstram a eficácia do algoritmo CSCDR como técnica de classificação. Quando comparado a outros classificadores conhecidos da literatura, o CSCDR apresenta desempenho similar e, quando comparado a algoritmos baseados em instâncias, o mesmo utiliza menores quantidades de protótipos para representar os dados, mantendo o desempenho. / The vertebrate immune system is an extremely complex system, being responsible for protecting the body against disease causing agents. To function properly, it is necessary its components effectively recognize the pathogens in order to neutralize them, and also elements of the body itself, so as not to react to these. These and other features are similar to those required solutions to problems in engineering and computing. Thus, artificial immune systems use biological counterpart as a metaphor for development of several computational tools used in various tasks. This dissertation uses the concepts presented by the artificial immune systems to develop a new supervised learning algorithm, based mainly on the mechanism of clonal selection. The method proposed in this work, named clonal selection classifier with data reduction (CSCDR), uses a fitness function based on the number of correct and incorrect classifications made by each antibody. The algorithm tries to maximize this value through the clonal selection process, involving mutation, affinity maturation and selection of the best individuals, turning the training phase in an optimization problem. This leads to more representative antibodies and therefore decreases the amount of prototypes generated at the end of the algorithm. Experiments on synthetic databases and real problem databases, used as benchmark to machine learning problems, demonstrate the effectiveness of the CSCDR algorithm as a classification technique. When compared to other well known classifiers in literature, CSCDR shows similar performance and when compared to instance based algorithms, CSCDR utilizes a smaller amount of prototypes to represent the data maintaining the same performance.