[pt] Redes neurais profundas são responsáveis pelo grande progresso em diversas tarefas perceptuais, especialmente nos campos da visão computacional,reconhecimento de fala e processamento de linguagem natural. Estes resultados produziram uma mudança de paradigma nas técnicas de reconhecimentode padrões, deslocando a demanda do design de extratores de característicaspara o design de arquiteturas de redes neurais. No entanto, o design de novas arquiteturas de redes neurais profundas é bastante demandanteem termos de tempo e depende fortemente da intuição e conhecimento de especialistas,além de se basear em um processo de tentativa e erro. Neste contexto, a idea de automatizar o design de arquiteturas de redes neurais profundas tem ganhado popularidade, estabelecendo o campo da busca por arquiteturas neurais(NAS - Neural Architecture Search). Para resolver o problema de NAS, autores propuseram diversas abordagens envolvendo o espaço de buscas, a estratégia de buscas e técnicas para mitigar o consumo de recursos destes algoritmos. O Q-NAS (Quantum-inspired Neural Architecture Search) é uma abordagem proposta para endereçar o problema de NAS utilizando um algoritmo evolucionário com inspiração quântica como estratégia de buscas. Este método foi aplicado de forma bem sucedida em classificação de imagens, superando resultados de arquiteturas de design manual nos conjuntos de dados CIFAR-10 e CIFAR-100 além de uma aplicação de mundo real na área da sísmica. Motivados por este sucesso, propõe-se nesta Dissertação o SegQNAS (Quantum-inspired Neural Architecture Search applied to Semantic Segmentation), uma adaptação do Q-NAS para a tarefa de segmentação semântica. Diversos experimentos foram realizados com objetivo de verificar a aplicabilidade do SegQNAS em dois conjuntos de dados do desafio Medical Segmentation Decathlon. O SegQNAS foi capaz de alcançar um coeficiente de similaridade dice de 0.9583 no conjunto de dados de baço, superando os resultados de arquiteturas tradicionais como U-Net e ResU-Net e atingindo resultados comparáveis a outros trabalhos que aplicaram NAS a este conjunto de dados, mas encontrando arquiteturas com muito menos parãmetros. No conjunto de dados de próstata, o SegQNAS alcançou um coeficiente de similaridade dice de 0.6887 superando a U-Net, ResU-Net e o trabalho na área de NAS que utilizamos como comparação. / [en] Deep neural networks are responsible for great progress in performance for several perceptual tasks, especially in the fields of computer vision, speech recognition, and natural language processing. These results produced a paradigm shift in pattern recognition techniques, shifting the demand from feature extractor design to neural architecture design. However, designing novel deep neural network architectures is very time-consuming and heavily relies on experts intuition, knowledge, and a trial and error process. In that context, the idea of automating the architecture design of deep neural networks has gained popularity, establishing the field of neural architecture search (NAS). To tackle the problem of NAS, authors have proposed several approaches regarding the search space definition, algorithms for the search strategy, and techniques to mitigate the resource consumption of those algorithms. Q-NAS (Quantum-inspired Neural Architecture Search) is one proposed approach to address the NAS problem using a quantum-inspired evolutionary algorithm as the search strategy. That method has been successfully applied to image classification, outperforming handcrafted models on the CIFAR-10 and CIFAR-100 datasets and also on a real-world seismic application. Motivated by this success, we propose SegQNAS (Quantum-inspired Neural Architecture Search applied to Semantic Segmentation), which is an adaptation of Q-NAS applied to semantic segmentation. We carried out several experiments to verify the applicability of SegQNAS on two datasets from the Medical Segmentation Decathlon challenge. SegQNAS was able to achieve a 0.9583 dice similarity coefficient on the spleen dataset, outperforming traditional architectures like U-Net and ResU-Net and comparable results with a similar NAS work from the literature but with fewer parameters network. On the prostate dataset, SegQNAS achieved a 0.6887 dice similarity coefficient, also outperforming U-Net, ResU-Net, and outperforming a similar NAS work from the literature.

Association rule hiding (ARH) is the process of modifying a transaction database to prevent sensitive patterns (association rules) from discovery by data miners. An optimal ARH technique successfully hides all sensitive patterns while leaving all nonsensitive patterns public. However, in practice, many ARH algorithms cause some undesirable side effects, such as failing to hide sensitive rules or mistakenly hiding nonsensitive ones. Evaluating the utility of ARH algorithms therefore involves measuring the side effects they cause. There are a wide array of ARH techniques in use, with evolutionary algorithms in particular gaining popularity in recent years. However, previous research in the area has focused on incremental improvement of existing algorithms. No work was found that compares the performance of ARH algorithms without the incentive of promoting a newly suggested algorithm as superior. To fill this research gap, this project compares three ARH algorithms developed between 2019 and 2022—ABC4ARH, VIDPSO, and SA-MDP— using identical and unbiased parameters. The algorithms were run on three real databases and three synthetic ones of various sizes, in each case given four different sets of sensitive rules to hide. Their performance was measured in terms of side effects, runtime, and scalability (i.e., performance on increasing database size). It was found that the performance of the algorithms varied considerably depending on the characteristics of the input data, with no algorithm consistently outperforming others at the task of mitigating side effects. VIDPSO was the most efficient in terms of runtime, while ABC4ARH maintained the most robust performance as the database size increased. However, results matching the quality of those in the papers originally describing each algorithm could not be reproduced, showing a clear need for validating the reproducibility of research before the results can be trusted. / ”Association rule hiding”, ungefär ”döljande av associationsregler” – hädanefter ARH – är en process som går ut på att modifiera en transaktionsdatabas för att förhindra att känsliga mönster (så kallade associationsregler) upptäcks genom datautvinning. En optimal ARH-teknik döljer framgångsrikt alla känsliga mönster medan alla ickekänsliga mönster förblir öppet tillgängliga. I praktiken är det dock vanligt att ARH-algoritmer orsakar oönskade sidoeffekter. Exempelvis kan de misslyckas med att dölja vissa känsliga regler eller dölja ickekänsliga regler av misstag. Evalueringen av ARH-algoritmers användbarhet inbegriper därför mätning av dessa sidoeffekter. Bland det stora urvalet ARH-tekniker har i synnerhet evolutionära algoritmer ökat i popularitet under senare år. Tidigare forskning inom området har dock fokuserat på inkrementell förbättring av existerande algoritmer. Ingen forskning hittades som jämförde ARH-algoritmer utan det underliggande incitamentet att framhäva överlägsenheten hos en nyutvecklad algoritm. Detta projekt ämnar fylla denna lucka i forskningen genom en jämförelse av tre ARH-algoritmer som tagits fram mellan 2019 och 2022 – ABC4ARH, VIDPSO och SA-MDP – med hjälp av identiska och oberoende parametrar. Algoritmerna kördes på sex databaser – tre hämtade från verkligheten, tre syntetiska av varierande storlek – och fick i samtliga fall fyra olika uppsättningar känsliga regler att dölja. Prestandan mättes enligt sidoeffekter, exekveringstid samt skalbarhet (dvs. prestation när databasens storlek ökar). Algoritmernas prestation varierade avsevärt beroende på indatans egenskaper. Ingen algoritm var konsekvent överlägsen de andra när det gällde att minimera sidoeffekter. VIDPSO var tidsmässigt mest effektiv, medan ABC4ARH var mest robust vid hanteringen av växande indata. Resultat i nivå med de som uppmättes i forskningsrapporterna som ursprungligen presenterat varje algoritm kunde inte reproduceras, vilket tyder på ett behov av att validera reproducerbarheten hos forskning innan dess resultat kan anses tillförlitliga.

[pt] Redes neurais profundas são modelos poderosos e flexíveis que ganharam a atenção da comunidade de aprendizado de máquina na última década. Normalmente, um especialista gasta um tempo significativo projetando a arquitetura neural, com longas sessões de tentativa e erro para alcançar resultados bons e relevantes. Por causa do processo manual, há um maior interesse em abordagens de busca de arquitetura neural, que é um método que visa automatizar a busca de redes neurais. A busca de arquitetura neural(NAS) é uma subárea das técnicas de aprendizagem de máquina automatizadas (AutoML) e uma etapa essencial para automatizar os métodos de aprendizado de máquina. Esta técnica leva em consideração os aspectos do espaço de busca das arquiteturas, estratégia de busca e estratégia de estimativa de desempenho. Algoritmos evolutivos de inspiração quântica apresentam resultados promissores quanto à convergência mais rápida quando comparados a outras soluções com espaço de busca restrito e alto custo computacional. Neste trabalho, foi aprimorado o Q-NAS: um algoritmo de inspiração quântica para pesquisar redes profundas por meio da montagem de subestruturas simples. O Q-NAS também pode evoluir alguns hiperparâmetros numéricos do treinamento, o que é um primeiro passo na direção da automação completa. Foram apresentados resultados aplicando Q-NAS, evoluído, sem transferência de conhecimento, no conjunto de dados CIFAR-100 usando apenas 18 GPU/dias. Nossa contribuição envolve experimentar outros otimizadores no algoritmo e fazer um estudo aprofundado dos parâmetros do Q-NAS. Nesse trabalho, foi possível atingir uma acurácia de 76,40%. Foi apresentado também o Q-NAS aprimorado aplicado a um estudo de caso para classificação COVID-19 x Saudável em um banco de dados de tomografia computadorizada de tórax real. Em 9 GPU/dias, conseguimos atingir uma precisão de 99,44% usando menos de 1000 amostras para dados de treinamento. / [en] Deep neural networks are powerful and flexible models that have gained the attention of the machine learning community over the last decade. Usually, an expert spends significant time designing the neural architecture, with long trial and error sessions to reach good and relevant results. Because of the manual process, there is a greater interest in Neural Architecture Search (NAS), which is an automated method of architectural search in neural networks. NAS is a subarea of Automated Machine Learning (AutoML) and is an essential step towards automating machine learning methods. It is a technique that aims to automate the construction process of a neural network architecture. This technique is defined by the search space aspects of the architectures, search strategy and performance estimation strategy. Quantum-inspired evolutionary algorithms present promising results regarding faster convergence when compared to other solutions with restricted search space and high computational costs. In this work, we enhance Q-NAS: a quantum-inspired algorithm to search for deep networks by assembling simple substructures. Q-NAS can also evolve some numerical hyperparameters, which is a first step in the direction of complete automation. Our contribution involves experimenting other types of optimizers in the algorithm and make an indepth study of the Q-NAS parameters. Additionally, we present Q-NAS results, evolved from scratch, on the CIFAR-100 dataset using only 18 GPU/days. We were able to achieve an accuracy of 76.40% which is a competitive result regarding other works in literature. Finally, we also present the enhanced QNAS applied to a case study for COVID-19 x Healthy classification on a real chest computed tomography database. In 9 GPU/days we were able to achieve an accuracy of 99.44% using less than 1000 samples for training data. This accuracy overcame benchmark networks such as ResNet, GoogleLeNet and VGG.

As AI develops, grows, and expands, the more benefits we can have from it. AI is used in multiple fields to assist humans, such as object recognition, self-driving cars, or design tools. However, AI could be used for more than assisting humans in their tasks. It could be employed to collaborate with humans as colleagues in shared tasks, which is usually described as Mixed-Initiative (MI) paradigm. This paradigm creates an interactive scenario that leverage on AI and human strengths with an alternating and proactive initiative to approach a task. However, this paradigm introduces several challenges. For instance, there must be an understanding between humans and AI, where autonomy and initiative become negotiation tokens. In addition, control and expressiveness need to be taken into account to reach some goals. Moreover, although this paradigm has a broader application, it is especially interesting for creative tasks such as games, which are mainly created in collaboration. Creating games and their content is a hard and complex task, since games are content-intensive, multi-faceted, and interacted by external users.  Therefore, this thesis explores MI collaboration between human game designers and AI for the co-creation of games, where the AI's role is that of a colleague with the designer. The main hypothesis is that AI can be incorporated in systems as a collaborator, enhancing design tools, fostering human creativity, reducing their workload, and creating adaptive experiences. Furthermore, This collaboration arises several dynamic properties such as control, expressiveness, and initiative, which are all central to this thesis. Quality-Diversity algorithms combined with control mechanisms and interactions for the designer are proposed to investigate this collaboration and properties. Designer and Player modeling is also explored, and several approaches are proposed to create a better workflow, establish adaptive experiences, and enhance the interaction. Through this, it is demonstrated the potential and benefits of these algorithms and models in the MI paradigm.

[pt] Um dos maiores problemas de todas as empresas prestadoras de serviço de sanea-mento e distribuição de água é o de perdas oriundas de irregularidades (comerciais). Dentre os países com mais de 20 milhões de habitantes que mais sofrem desse tipo de perdas, o Brasil ocupa a 14º posição com 40% de perdas na distribuição. A Em-presa A, estudo de caso deste trabalho, é uma companhia brasileira que atua no setor de saneamento e distribuição de água e, atua, principalmente, em 3 regiões, com valores de médias percentuais de perdas, em 2021, de 19%, 30% e 43%, respecti-vamente. Essas perdas são derivadas de muitos problemas, mas as principais são oriundas das fraudes nas ligações dos medidores de água, por exemplo: ligações clandestinas, by-pass e derivação de ramal. A principal forma de combater esse tipo de fraude é através de inspeções nos clientes. Geralmente utiliza-se um conjunto de heurísticas para identificar o suspeito de tal fraude ou irregularidade, porém esses métodos não retornam boas precisões. Na Empresa A, a precisão alcançada através das inspeções varia de 3% a 17% de região para região. Com isso, conclui-se que o procedimento não é eficaz. Sendo assim, o objetivo deste trabalho é desenvolver um sistema inteligente que possa identificar, com maior exatidão, o perfil de con-sumo do cliente que possui a fraude. O sistema desenvolvido é composto por duas metodologias baseadas em diversos algoritmos supervisionados de aprendizado de máquina. A primeira utiliza um filtro com intuito de agrupar os clientes com perfis similares. A segunda faz uso de um algoritmo evolutivo inspirado em computação quântica para a busca de hiperparâmetros e atributos. Além disso, ambas conside-ram comitês e exploram a utilização de variáveis históricas e exógenas pertinentes ao contexto. Os resultados obtidos mostraram-se superiores nas avaliações, quando comparadas aos verificados na Empresa A, alcançando até 44% de taxa de acerto. / [en] One of the biggest problems faced by all companies that provide sanitation and water distribution services is that of losses arising from (commercial) irregularities. Among the countries with more than 20 million inhabitants that suffer the most from this type of loss, Brazil occupies the 14th position with 40% of losses in dis-tribution. Company A, the case study of this work, is a Brazilian company that ope-rates in the sanitation and water distribution sector and operates mainly in 3 regions, with average percentage values of losses, in 2021, of 19%, 30 % and 43%, respec-tively. These losses derive from many problems, but the main ones arise from fraud in the connections of water meters, for example: clandestine connections, by-pass and branch derivation. The main way to combat this type of fraud is through custo-mer inspections. Generally, a set of heuristics is used to identify the suspect of such fraud or irregularity, but these methods do not return good accuracy. At Company A, the accuracy achieved through inspections varies from 3% to 17% from region to region. Thus, it is concluded that the procedure is not effective. Therefore, the objective of this work is to develop an intelligent system that can identify, with greater accuracy, the consumption profile of the customer who has the fraud. The developed system is composed of two methodologies based on several supervised machine learning algorithms. The first uses a filter in order to group customers with similar profiles. The second makes use of an evolutionary algorithm inspired by quantum computing to search for hyperparameters and attributes. In addition, both consider committees and explore the use of historical and exogenous variables re-levant to the context. The results obtained were superior in the evaluations, when compared to those verified in Company A, reaching up to 44% of success rate.

Systems biology is an emergent field focused on developing a system-level understanding of biological systems. In the last decade advances in genomics, transcriptomics and proteomics have gathered a remarkable amount data enabling the possibility of a system-level analysis to be grounded at a molecular level. The reverse-engineering of biochemical networks from experimental data has become a central focus in systems biology. A variety of methods have been proposed for the study and identification of the system's structure and/or dynamics. The objective of this dissertation is to introduce and propose solutions to some of the challenges inherent in reverse-engineering of biological systems. First, previously developed reverse engineering algorithms are studied and compared using data from a simulated network. This study draws attention to the necessity for a uniform benchmark that enables an ob jective comparison and performance evaluation of reverse engineering methods. Since several reverse-engineering algorithms require discrete data as input (e.g. dynamic Bayesian network methods, Boolean networks), discretization methods are being used for this purpose. Through a comparison of the performance of two network inference algorithms that use discrete data (from several different discretization methods) in this work, it has been shown that data discretization is an important step in applying network inference methods to experimental data. Next, a reverse-engineering algorithm is proposed within the framework of polynomial dynamical systems over finite fields. This algorithm is built for the identification of the underlying network structure and dynamics; it uses as input gene expression data and, when available, a priori knowledge of the system. An evolutionary algorithm is used as the heuristic search method for an exploration of the solution space. Computational algebra tools delimit the search space, enabling also a description of model complexity. The performance and robustness of the algorithm are explored via an artificial network of the segment polarity genes in the D. melanogaster. Once a mathematical model has been built, it can be used to run simulations of the biological system under study. Comparison of simulated dynamics with experimental measurements can help refine the model or provide insight into qualitative properties of the systems dynamical behavior. Within this work, we propose an efficient algorithm to describe the phase space, in particular to compute the number and length of all limit cycles of linear systems over a general finite field. This research has been partially supported by NIH Grant Nr. RO1GM068947-01. / Ph. D.

A pesar de que las medidas de seguridad en los sistemas de transporte cada vez son mayores, el aumento progresivo del número de vehículos que circulan por las ciudades y carreteras en todo el mundo aumenta, sin duda, la probabilidad de que ocurra un accidente. En este tipo de situaciones, el tiempo de respuesta de los servicios de emergencia es crucial, ya que está demostrado que cuanto menor sea el tiempo transcurrido entre el accidente y la atención hospitalaria de los heridos, mayores son sus probabilidades de supervivencia. Las redes vehiculares permiten la comunicación entre los vehículos, así como la comunicación entre los vehículos y la infraestructura [4], lo que da lugar a una plétora de nuevas aplicaciones y servicios en el entorno vehicular. Centrándonos en las aplicaciones relacionadas con la seguridad vial, mediante este tipo de comunicaciones, los vehículos podrían informar en caso de accidente al resto de vehículos (evitando así colisiones en cadena) y a los servicios de emergencia (dando información precisa y rápida, lo que sin duda facilitaría las tareas de rescate). Uno de los aspectos importantes a determinar sería saber qué información se debe enviar, quién será capaz de recibirla, y cómo actuar una vez recibida. Actualmente los vehículos disponen de una serie de sensores que les permiten obtener información sobre ellos mismos (velocidad, posición, estado de los sistemas de seguridad, número de ocupantes del vehículo, etc.), y sobre su entorno (información meteorológica, estado de la calzada, luminosidad, etc.). En caso de accidente, toda esa información puede ser estructurada y enviada a los servicios de emergencia para que éstos adecúen el rescate a las características específicas y la gravedad del accidente, actuando en consecuencia. Por otro lado, para que la información enviada por los vehículos accidentados pueda llegar correctamente a los servicios de emergencias, es necesario disponer de una infraestructura capaz de dar cobertura a todos los vehículos que circulan por una determinada área. Puesto que la instalación y el mantenimiento de dicha infraestructura conllevan un elevado coste, sería conveniente proponer, implementar y evaluar técnicas consistentes en dar cobertura a todos los vehículos, reduciendo el coste total de la infraestructura. Finalmente, una vez que la información ha sido recibida por las autoridades, es necesario elaborar un plan de actuación eficaz, que permita el rápido rescate de los heridos. Hay que tener en cuenta que, cuando ocurre un accidente de tráfico, el tiempo de personación de los servicios de emergencia en el lugar del accidente puede suponer la diferencia entre que los heridos sobrevivan o fallezcan. Además, es importante conocer si la calle o carretera por la que circulaban los vehículos accidentados ha dejado de ser transitable para el resto de vehículos, y en ese caso, activar los mecanismos necesarios que permitan evitar los atascos asociados. En esta Tesis, se pretende gestionar adecuadamente estas situaciones adversas, distribuyendo el tráfico de manera inteligente para reducir el tiempo de llegada de los servicios de emergencia al lugar del accidente, evitando además posibles atascos. / Barrachina Villalba, J. (2014). Using Ontologies and Intelligent Systems for Traffic Accident Assistance in Vehicular Environments [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/39004

[ES] El aprendizaje automático (ML por sus siglas en inglés) es conocido como la rama de la inteligencia artificial que reúne algoritmos estadísticos, probabilísticos y de optimización, que aprenden empíricamente. ML puede aprovechar el conocimiento y la experiencia que se han generado durante años en las empresas para realizar automáticamente diferentes procesos. Por lo tanto, ML se ha aplicado a diversas áreas de investigación, que estudian desde la medicina hasta la ingeniería del software. De hecho, en el campo de la ingeniería del software, el mantenimiento y la evolución de un sistema abarca hasta un 80% de la vida útil del sistema. Las empresas, que se han dedicado al desarrollo de sistemas software durante muchos años, han acumulado grandes cantidades de conocimiento y experiencia. Por lo tanto, ML resulta una solución atractiva para reducir sus costos de mantenimiento aprovechando los recursos acumulados. Específicamente, la Recuperación de Enlaces de Trazabilidad, la Localización de Errores y la Ubicación de Características se encuentran entre las tareas más comunes y relevantes para realizar el mantenimiento de productos software. Para abordar estas tareas, los investigadores han propuesto diferentes enfoques. Sin embargo, la mayoría de las investigaciones se centran en métodos tradicionales, como la indexación semántica latente, que no explota los recursos recopilados. Además, la mayoría de las investigaciones se enfocan en el código, descuidando otros artefactos de software como son los modelos. En esta tesis, presentamos un enfoque basado en ML para la recuperación de fragmentos en modelos (FRAME). El objetivo de este enfoque es recuperar el fragmento del modelo que realiza mejor una consulta específica. Esto permite a los ingenieros recuperar el fragmento que necesita ser trazado, reparado o ubicado para el mantenimiento del software. Específicamente, FRAME combina la computación evolutiva y las técnicas ML. En FRAME, un algoritmo evolutivo es guiado por ML para extraer de manera eficaz distintos fragmentos de un modelo. Estos fragmentos son posteriormente evaluados mediante técnicas ML. Para aprender a evaluarlos, las técnicas ML aprovechan el conocimiento (fragmentos recuperados de modelos) y la experiencia que las empresas han generado durante años. Basándose en lo aprendido, las técnicas ML determinan qué fragmento del modelo realiza mejor una consulta. Sin embargo, la mayoría de las técnicas ML no pueden entender los fragmentos de los modelos. Por lo tanto, antes de aplicar las técnicas ML, el enfoque propuesto codifica los fragmentos a través de una codificación ontológica y evolutiva. En resumen, FRAME está diseñado para extraer fragmentos de un modelo, codificarlos y evaluar cuál realiza mejor una consulta específica. El enfoque ha sido evaluado a partir de un caso real proporcionado por nuestro socio industrial (CAF, un proveedor internacional de soluciones ferroviarias). Además, sus resultados han sido comparados con los resultados de los enfoques más comunes y recientes. Los resultados muestran que FRAME obtuvo los mejores resultados para la mayoría de los indicadores de rendimiento, proporcionando un valor medio de precisión igual a 59.91%, un valor medio de exhaustividad igual a 78.95%, una valor-F medio igual a 62.50% y un MCC (Coeficiente de Correlación Matthews) medio igual a 0.64. Aprovechando los fragmentos recuperados de los modelos, FRAME es menos sensible al conocimiento tácito y al desajuste de vocabulario que los enfoques basados en información semántica. Sin embargo, FRAME está limitado por la disponibilidad de fragmentos recuperados para llevar a cabo el aprendizaje automático. Esta tesis presenta una discusión más amplia de estos aspectos así como el análisis estadístico de los resultados, que evalúa la magnitud de la mejora en comparación con los otros enfoques. / [CAT] L'aprenentatge automàtic (ML per les seues sigles en anglés) és conegut com la branca de la intel·ligència artificial que reuneix algorismes estadístics, probabilístics i d'optimització, que aprenen empíricament. ML pot aprofitar el coneixement i l'experiència que s'han generat durant anys en les empreses per a realitzar automàticament diferents processos. Per tant, ML s'ha aplicat a diverses àrees d'investigació, que estudien des de la medicina fins a l'enginyeria del programari. De fet, en el camp de l'enginyeria del programari, el manteniment i l'evolució d'un sistema abasta fins a un 80% de la vida útil del sistema. Les empreses, que s'han dedicat al desenvolupament de sistemes programari durant molts anys, han acumulat grans quantitats de coneixement i experiència. Per tant, ML resulta una solució atractiva per a reduir els seus costos de manteniment aprofitant els recursos acumulats. Específicament, la Recuperació d'Enllaços de Traçabilitat, la Localització d'Errors i la Ubicació de Característiques es troben entre les tasques més comunes i rellevants per a realitzar el manteniment de productes programari. Per a abordar aquestes tasques, els investigadors han proposat diferents enfocaments. No obstant això, la majoria de les investigacions se centren en mètodes tradicionals, com la indexació semàntica latent, que no explota els recursos recopilats. A més, la majoria de les investigacions s'enfoquen en el codi, descurant altres artefactes de programari com són els models. En aquesta tesi, presentem un enfocament basat en ML per a la recuperació de fragments en models (FRAME). L'objectiu d'aquest enfocament és recuperar el fragment del model que realitza millor una consulta específica. Això permet als enginyers recuperar el fragment que necessita ser traçat, reparat o situat per al manteniment del programari. Específicament, FRAME combina la computació evolutiva i les tècniques ML. En FRAME, un algorisme evolutiu és guiat per ML per a extraure de manera eficaç diferents fragments d'un model. Aquests fragments són posteriorment avaluats mitjançant tècniques ML. Per a aprendre a avaluar-los, les tècniques ML aprofiten el coneixement (fragments recuperats de models) i l'experiència que les empreses han generat durant anys. Basant-se en l'aprés, les tècniques ML determinen quin fragment del model realitza millor una consulta. No obstant això, la majoria de les tècniques ML no poden entendre els fragments dels models. Per tant, abans d'aplicar les tècniques ML, l'enfocament proposat codifica els fragments a través d'una codificació ontològica i evolutiva. En resum, FRAME està dissenyat per a extraure fragments d'un model, codificar-los i avaluar quin realitza millor una consulta específica. L'enfocament ha sigut avaluat a partir d'un cas real proporcionat pel nostre soci industrial (CAF, un proveïdor internacional de solucions ferroviàries). A més, els seus resultats han sigut comparats amb els resultats dels enfocaments més comuns i recents. Els resultats mostren que FRAME va obtindre els millors resultats per a la majoria dels indicadors de rendiment, proporcionant un valor mitjà de precisió igual a 59.91%, un valor mitjà d'exhaustivitat igual a 78.95%, una valor-F mig igual a 62.50% i un MCC (Coeficient de Correlació Matthews) mig igual a 0.64. Aprofitant els fragments recuperats dels models, FRAME és menys sensible al coneixement tàcit i al desajustament de vocabulari que els enfocaments basats en informació semàntica. No obstant això, FRAME està limitat per la disponibilitat de fragments recuperats per a dur a terme l'aprenentatge automàtic. Aquesta tesi presenta una discussió més àmplia d'aquests aspectes així com l'anàlisi estadística dels resultats, que avalua la magnitud de la millora en comparació amb els altres enfocaments. / [EN] Machine Learning (ML) is known as the branch of artificial intelligence that gathers statistical, probabilistic, and optimization algorithms, which learn empirically. ML can exploit the knowledge and the experience that have been generated for years to automatically perform different processes. Therefore, ML has been applied to a wide range of research areas, from medicine to software engineering. In fact, in software engineering field, up to an 80% of a system's lifetime is spent on the maintenance and evolution of the system. The companies, that have been developing these software systems for a long time, have gathered a huge amount of knowledge and experience. Therefore, ML is an attractive solution to reduce their maintenance costs exploiting the gathered resources. Specifically, Traceability Link Recovery, Bug Localization, and Feature Location are amongst the most common and relevant tasks when maintaining software products. To tackle these tasks, researchers have proposed a number of approaches. However, most research focus on traditional methods, such as Latent Semantic Indexing, which does not exploit the gathered resources. Moreover, most research targets code, neglecting other software artifacts such as models. In this dissertation, we present an ML-based approach for fragment retrieval on models (FRAME). The goal of this approach is to retrieve the model fragment which better realizes a specific query in a model. This allows engineers to retrieve the model fragment, which must be traced, fixed, or located for software maintenance. Specifically, the FRAME approach combines evolutionary computation and ML techniques. In the FRAME approach, an evolutionary algorithm is guided by ML to effectively extract model fragments from a model. These model fragments are then assessed through ML techniques. To learn how to assess them, ML techniques takes advantage of the companies' knowledge (retrieved model fragments) and experience. Then, based on what was learned, ML techniques determine which model fragment better realizes a query. However, model fragments are not understandable for most ML techniques. Therefore, the proposed approach encodes the model fragments through an ontological evolutionary encoding. In short, the FRAME approach is designed to extract model fragments, encode them, and assess which one better realizes a specific query. The approach has been evaluated in our industrial partner (CAF, an international provider of railway solutions) and compared to the most common and recent approaches. The results show that the FRAME approach achieved the best results for most performance indicators, providing a mean precision value of 59.91%, a recall value of 78.95%, a combined F-measure of 62.50%, and a MCC (Matthews correlation coefficient) value of 0.64. Leveraging retrieved model fragments, the FRAME approach is less sensitive to tacit knowledge and vocabulary mismatch than the approaches based on semantic information. However, the approach is limited by the availability of the retrieved model fragments to perform the learning. These aspects are further discussed, after the statistical analysis of the results, which assesses the magnitude of the improvement in comparison to the other approaches. / Marcén Terraza, AC. (2020). Design of a Machine Learning-based Approach for Fragment Retrieval on Models [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/158617

Σε αυτή την εργασία, μελετάμε την κλάση των Υψηλής Τάξης Νευρωνικών Δικτύων και ειδικότερα των Πι—Σίγμα Νευρωνικών Δικτύων. Η απόδοση των Πι—Σίγμα Νευρωνικών Δικτύων αξιολογείται με την εφαρμογή τους σε διάφορα πολύ γνωστά χαρακτηριστικά προβλήματα εκπαίδευσης νευρωνικών δικτύων. Στα πειράματα που πραγματοποιήθηκαν, για την εκπαίδευση των Πι—Σίγμα Νευρωνικών Δικτύων υλοποιήθηκαν και εφαρμόστηκαν Σειριακοί και Παράλληλοι/Κατανεμημένοι Εξελικτικοί Αλγόριθμοι. Πιο συγκεκριμένα χρησιμοποιήθηκαν οι σειριακές καθώς και οι παράλληλες/κατανεμημένες εκδοχές των Διαφοροεξελικτικών Αλγόριθμων. Η προτεινόμενη μεθοδολογία βασίστηκε σε αυτές τις εκδοχές και εφαρμόστηκε για την εκπαίδευση των Πι—Σίγμα δικτύων χρησιμοποιώντας συναρτήσεις ενεργοποίησης «κατώφλια». Επιπρόσθετα, όλα τα βάρη και οι μεροληψίες των δικτύων περιορίστηκαν σε ένα μικρό εύρος ακέραιων αριθμών, στο διάστημα [-32, 32]. Συνεπώς, τα εκπαιδευμένα Πι—Σίγμα νευρωνικά δίκτυα μπορούν να αναπαρασταθούν με ακεραίους των 6-bits. Αυτής της μορφής τα δίκτυα είναι πιο κατάλληλα για την εφαρμογή τους σε «υλικό» (hardware), από νευρωνικά δίκτυα με πραγματικά βάρη. Τα πειραματικά αποτελέσματα μας δείχνουν ότι η διαδικασία εκπαίδευσης είναι γρήγορη, σταθερή και αξιόπιστη. Ακόμα η εφαρμογή των παράλληλων/κατανεμημένων Εξελικτικών Αλγορίθμων για την εκπαίδευση των Πι—Σίγμα δικτύων μας επιδεικνύει αρκετά καλές ικανότητες γενίκευσης των εκπαιδευμένων δικτύων καθώς και προσφέρει επιτάχυνση στην διαδικασία εκπαίδευσης τους. / In this contribution, we study the class of Higher-Order Neural Networks and especially the Pi-Sigma Networks. The performance of Pi-Sigma Networks is evaluated through several well known neural network training benchmarks. In the experiments reported here, Evolutionary Algorithms and Parallel/Distributed Evolutionary Algorithms are implemented for Pi-Sigma neural networks training. More specifically the serial as well as a parallel/distributed version of the Differential Evolution have been employed. The proposed approach is applied to train Pi-Sigma networks using threshold activation functions. Moreover, the weights and biases were confined to a narrow band of integers, constrained in the range [-32, 32]. Thus the trained Pi-Sigma neural networks can be represented by just 6 bits. Such networks are better suited for hardware implementation than the real weight ones. Experimental results suggest that this training process is fast, stable and reliable and the trained Pi-Sigma networks, with both serial and parallel/distributed algorithms, exhibited good generalization capabilities. Furthermore, the usage of a distributed version of the Differential Evolution, has demonstrated a speedup of the training process.

Master of Science / Department of Electrical and Computer Engineering / Sanjoy Das / Stephen M. Welch / Multi-objective optimization problems deal with finding a set of candidate optimal solutions to be presented to the decision maker. In industry, this could be the problem of finding alternative car designs given the usually conflicting objectives of performance, safety, environmental friendliness, ease of maintenance, price among others. Despite the significance of this problem, most of the non-evolutionary algorithms which are widely used cannot find a set of diverse and nearly optimal solutions due to the huge size of the search space. At the same time, the solution set produced by most of the currently used evolutionary algorithms lacks diversity. The present study investigates a new optimization method to solve multi-objective problems based on the widely used swarm-intelligence approach, Particle Swarm Optimization (PSO). Compared to other approaches, the proposed algorithm converges relatively fast while maintaining a diverse set of solutions. The investigated algorithm, Partially Informed Fuzzy-Dominance (PIFD) based PSO uses a dynamic network topology and fuzzy dominance to guide the swarm of dominated solutions. The proposed algorithm in this study has been tested on four benchmark problems and other real-world applications to ensure proper functionality and assess overall performance. The multi-objective gene regulatory network (GRN) problem entails the minimization of the coefficient of variation of modified photothermal units (MPTUs) across multiple sites along with the total sum of similarity background between ecotypes. The results throughout the current research study show that the investigated algorithm attains outstanding performance regarding optimization aspects, and exhibits rapid convergence and diversity.