Yes / Data streams have arisen as a relevant topic during the last few years as an efficient method for extracting knowledge from big data. In the robust layered ensemble model (RLEM) proposed in this paper for short-term traffic flow forecasting, incoming traffic flow data of all connected road links are organized in chunks corresponding to an optimal time lag. The RLEM model is composed of two layers. In the first layer, we cluster the chunks by using the Graded Possibilistic c-Means method. The second layer is made up by an ensemble of forecasters, each of them trained for short-term traffic flow forecasting on the chunks belonging to a specific cluster. In the operational phase, as a new chunk of traffic flow data presented as input to the RLEM, its memberships to all clusters are evaluated, and if it is not recognized as an outlier, the outputs of all forecasters are combined in an ensemble, obtaining in this a way a forecasting of traffic flow for a short-term time horizon. The proposed RLEM model is evaluated on a synthetic data set, on a traffic flow data simulator and on two real-world traffic flow data sets. The model gives an accurate forecasting of the traffic flow rates with outlier detection and shows a good adaptation to non-stationary traffic regimes. Given its characteristics of outlier detection, accuracy, and robustness, RLEM can be fruitfully integrated in traffic flow management systems.

Ever since the advent of the simplex algorithm, linear programming (LP) has been extensively used with great success in many diverse fields. The field of discrete optimization came to the forefront as a result of the impressive developments in the area of linear programming. Although discrete optimization problems can be viewed as belonging to the class of nonconvex programs, it has only been in recent times that optimization research has confronted the more formidable class of continuous nonconvex optimization problems, where the objective function and constraints are often highly nonlinear and nonconvex functions, defined in terms of continuous (and bounded) decision variables. Typical classes of such problems involve polynomial, or more general factorable functions. This dissertation focuses on employing the Reformulation-Linearization Technique (RLT) to enhance model formulations and to design effective solution techniques for solving several practical instances of continuous nonconvex optimization problems, namely, the hard and fuzzy clustering problems, risk management problems, and problems arising in control systems. Under the umbrella of the broad RLT framework, the contributions of this dissertation focus on developing models and algorithms along with related theoretical and computational results pertaining to three specific application domains. In the basic construct, through appropriate surrogation schemes and variable substitution strategies, we derive strong polyhedral approximations for the polynomial functional terms in the problem, and then rely on the demonstrated (robust) ability of the RLT for determining global optimal solutions for polynomial programming problems. The convergence of the proposed branch-and-bound algorithm follows from the tailored branching strategy coupled with consistency and exhaustive properties of the enumeration tree. First, we prescribe an RLT-based framework geared towards solving the hard and fuzzy clustering problems. In the second endeavor, we examine two risk management problems, providing novel models and algorithms. Finally, in the third part, we provide a detailed discussion on studying stability margins for control systems using polynomial programming models along with specialized solution techniques. / Ph. D.

Data Envelopment Analysis (Charnes et al, 1978) is a technique used to evaluate the relative efficiency of any process or an organization. The efficiency evaluation is relative, which means it is compared with other processes or organizations. In real life situations different processes or units seldom operate in similar environments. Within a relative efficiency context, if units operating in different environments are compared, the units that operate in less desirable environments are at a disadvantage. In order to ensure that the comparison is fair within the DEA framework, a two-stage framework is presented in this thesis. Fuzzy clustering is used in the first stage to suitably group the units with similar environments. In a subsequent stage, a relative efficiency analysis is performed on these groups. By approaching the problem in this manner the influence of environmental variables on the efficiency analysis is removed. The concept of environmental dependency index is introduced in this thesis. The EDI reflects the extent to which the efficiency behavior of units is due to their environment of operation. The EDI also assists the decision maker to choose appropriate peers to guide the changes that the inefficient units need to make. A more rigorous series of steps to obtain the clustering solution is also presented in a separate chapter (chapter 5). / Master of Science

This thesis presents the development of techniques which enable appliance recognition in an Advanced Electricity Meter (AEM) to aid individuals reduce their domestic electricity consumption. The key aspect is to provide immediate and disaggregated information, down to appliance level, from a single point of measurement. Three sets of features including the short term time domain, time dependent finite state machine behaviour and time of day are identified by monitoring step changes in the power consumption of the home. Associated with each feature set is a membership which depicts the amount to which that feature set is representative of a particular appliance. These memberships are combined in a novel framework to effectively identify individual appliance state changes and hence appliance energy consumption. An innovative mechanism is developed for generating short term time domain memberships. Hierarchical and nearest neighbour clustering is used to train the AEM by generating appliance prototypes which contain an indication of typical parameters. From these prototypes probabilistic fuzzy memberships and possibilistic fuzzy typicalities are calculated for new data points which correspond to appliance state changes. These values are combined in a weighted geometric mean to produce novel memberships which are determined to be appropriate for the domestic model. A voltage independent feature space in the short term time domain is developed based on a model of the appliance’s electrical interface. The components within that interface are calculated and these, along with an indication of the appropriate model, form a novel feature set which is used to represent appliances. The techniques developed are verified with real data and are 99.8% accurate in a laboratory based classification in the short term time domain. The work presented in this thesis demonstrates the ability of the AEM to accurately track the energy consumption of individual appliances.

Cette thèse en Informatique s'inscrit dans le cadre de gestion de la confiance et plus précisément des systèmes de recommandation. Ces systèmes sont généralement basés sur les retours d'expériences des utilisateurs (i.e., qualitatifs/quantitatifs) lors de l'utilisation des ressources sur le Web (ex. films, vidéos et service Web). Les systèmes de recommandation doivent faire face à trois types d'incertitude liés aux évaluations des utilisateurs, à leur identité et à la variation des performances des ressources au fil du temps. Nous proposons une approche robuste pour évaluer la confiance en tenant compte de ces incertitudes. Le premier type d'incertitude réfère aux évaluations. Cette incertitude provient de la vulnérabilité du système en présence d'utilisateurs malveillants fournissant des évaluations biaisées. Pour pallier cette incertitude, nous proposons un modèle flou de la crédibilité des évaluateurs. Ce modèle, basé sur la technique de clustering flou, permet de distinguer les utilisateurs malveillants des utilisateurs stricts habituellement exclus dans les approches existantes. Le deuxième type d'incertitude réfère à l'identité de l'utilisateur. En effet, un utilisateur malveillant a la possibilité de créer des identités virtuelles pour fournir plusieurs fausses évaluations. Pour contrecarrer ce type d'attaque dit Sybil, nous proposons un modèle de filtrage des évaluations, basé sur la crédibilité des utilisateurs et le graphe de confiance auquel ils appartiennent. Nous proposons deux mécanismes, l'un pour distribuer des capacités aux utilisateurs et l'autre pour sélectionner les utilisateurs à retenir lors de l'évaluation de la confiance. Le premier mécanisme permet de réduire le risque de faire intervenir des utilisateurs multi-identités. Le second mécanisme choisit des chemins dans le graphe de confiance contenant des utilisateurs avec des capacités maximales. Ces deux mécanismes utilisent la crédibilité des utilisateurs comme heuristique. Afin de lever l'incertitude sur l'aptitude d'une ressource à satisfaire les demandes des utilisateurs, nous proposons deux approches d'évaluation de la confiance d'une ressource sur leWeb, une déterministe et une probabiliste. La première consolide les différentes évaluations collectées en prenant en compte la crédibilité des évaluateurs. La deuxième s'appuie sur la théorie des bases de données probabilistes et la sémantique des mondes possibles. Les bases de données probabilistes offrent alors une meilleure représentation de l'incertitude sous-jacente à la crédibilité des utilisateurs et permettent aussi à travers des requêtes un calcul incertain de la confiance d'une ressource. Finalement, nous développons le système WRTrust (Web Resource Trust) implémentant notre approche d'évaluation de la confiance. Nous avons réalisé plusieurs expérimentations afin d'évaluer la performance et la robustesse de notre système. Les expérimentations ont montré une amélioration de la qualité de la confiance et de la robustesse du système aux attaques des utilisateurs malveillants / This thesis in Computer Science is part of the trust management field and more specifically recommendation systems. These systems are usually based on users’ experiences (i.e., qualitative / quantitative) interacting with Web resources (eg. Movies, videos and Web services). Recommender systems are undermined by three types of uncertainty that raise due to users’ ratings and identities that can be questioned and also due to variations in Web resources performance at run-time. We propose a robust approach for trust assessment under these uncertainties. The first type of uncertainty refers to users’ ratings. This uncertainty stems from the vulnerability of the system in the presence of malicious users providing false ratings. To tackle this uncertainty, we propose a fuzzy model for users’ credibility. This model uses a fuzzy clustering technique to distinguish between malicious users and strict users usually excluded in existing approaches. The second type of uncertainty refers to user’s identity. Indeed, a malicious user purposely creates virtual identities to provide false ratings. To tackle this type of attack known as Sybil, we propose a ratings filtering model based on the users’ credibility and the trust graph to which they belong. We propose two mechanisms, one for assigning capacities to users and the second one is for selecting users whose ratings will be retained when evaluating trust. The first mechanism reduces the attack capacity of Sybil users. The second mechanism chose paths in the trust graph including trusted users with maximum capacities. Both mechanisms use users’ credibility as heuristic. To deal with the uncertainty over the capacity of a Web resource in satisfying users’ requests, we propose two approaches for Web resources trust assessment, one deterministic and one probabilistic. The first consolidates users’ ratings taking into account users credibility values. The second relies on probability theory coupled with possible worlds semantics. Probabilistic databases offer a better representation of the uncertainty underlying users’ credibility and also permit an uncertain assessment of resources trust. Finally, we develop the system WRTrust (Web Resource Trust) implementing our trust assessment approach. We carried out several experiments to evaluate the performance and robustness of our system. The results show that trust quality has been significantly improved, as well as the system’s robustness in presence of false ratings attacks and Sybil attacks

Nas últimas décadas, as técnicas de mineração de dados têm desempenhado um importante papel em diversas áreas do conhecimento humano. Mais recentemente, essas ferramentas têm encontrado espaço em um novo e complexo domínio, nbo qual os dados a serem minerados estão fisicamente distribuídos. Nesse domínio, alguns algorithmos específicos para agrupamento de dados podem ser utilizados - em particular, algumas variantes do algoritmo amplamente Fuzzy C-Means (FCM), as quais têm sido investigadas sob o nome de agrupamento fuzzy colaborativo. Com o objetivo de superar algumas das limitações encontradas em dois desses algoritmos, cinco novos algoritmos foram desenvolvidos nesse trabalho. Esses algoritmos foram estudados em dois cenários específicos de aplicação que levam em conta duas suposições sobre os dados (i.e., se os dados são de uma mesma npopulação ou de diferentes populações). Na prática, tais suposições e a dificuldade em se definir alguns dos parâmetros (que possam ser requeridos), podemn orientar a escolha feita pelo usuário entre os algoitmos diponíveis. Nesse sentido, exemplos ilustrativos destacam as diferenças de desempenho entre os algoritmos estudados e desenvolvidos, permitindo derivar algumas conclusões que podem ser úteis ao aplicar agrupamento fuzzy colaborativo na prática. Análises de complexidade de tempo, espaço, e comunicação também foram realizadas / Data mining techniques have played in important role in several areas of human kwnowledge. More recently, these techniques have found space in a new and complex setting in which the data to be mined are physically distributed. In this setting algorithms for data clustering can be used, such as some variants of the widely used Fuzzy C-Means (FCM) algorithm that support clustering data ditributed across different sites. Those methods have been studied under different names, like collaborative and parallel fuzzy clustring. In this study, we offer some augmentation of the two FCM-based clustering algorithms used to cluster distributed data by arriving at some constructive ways of determining essential parameters of the algorithms (including the number of clusters) and forming a set systematically structured guidelines as to a selection of the specific algorithm dependeing upon a nature of the data environment and the assumption being made about the number of clusters. A thorough complexity analysis including space, time, and communication aspects is reported. A series of detailed numeric experiments is used to illustrate the main ideas discussed in the study

Esta Tese apresenta um conjunto de técnicas propostas com o objetivo de aprimorar processos de Agrupamento de Dados (AD). O principal objetivo é fornecer à comunidade científica um ferramental para uma análise completa de estruturas implícitas em conjuntos de dados, desde a descoberta dessas estruturas, permitindo o emprego de conhecimento prévio sobre os dados, até a análise de seu significado no contexto em que eles estão inseridos. São dois os pontos principais desse ferramental. O primeiro se trata do algoritmo para AD fuzzy semi-supervisionado SSL+P e sua evolução SSL+P*, capazes de levar em consideração o conhecimento prévio disponível sobre os dados em duas formas: rótulos e níveis de proximidade de pares de exemplos, aqui denominados Dicas de Conhecimento Prévio (DCPs). Esses algoritmos também permitem que a métrica de distância seja ajustada aos dados e às DCPs. O algoritmo SSL+P* também busca estimar o número ideal de clusters para uma determinada base de dados, levando em conta as DCPs disponíveis. Os algoritmos SSL+P e SSL+P* envolvem a minimização de uma função objetivo por meio de um algoritmo de Otimização Baseado em População (OBP). Esta Tese também fornece ferramentas que podem ser utilizadas diretamente neste ponto: as duas versões modificadas do algoritmo Particle Swarm Optimization (PSO), DPSO-1 e DPSO-2 e 4 formas de inicialização de uma população inicial de soluções. O segundo ponto principal do ferramental proposto nesta Tese diz respeito à análise de clusters resultantes de um processo de AD aplicado a uma base de dados de um domínio específico. É proposta uma abordagem baseada em Mineração de Textos (MT) para a busca em informações textuais, disponibilizadas digitalmente e relacionadas com as entidades representadas nos dados. Em seguida, é fornecido ao pesquisador um conjunto de palavras associadas a cada cluster, que podem sugerir informações que ajudem a identificar as relações compartilhadas por exemplos atribuídos ao mesmo cluster / This Thesis presents a whole set of techniques designed to improve the data clustering proccess. The main goal is to provide to the scientific community a tool set for a complete analyses of the implicit structures in datasets, from the identification of these structures, allowing the use of previous knowledge about the data, to the analysis of its meaning in their context. There are two main points involved in that tool set. The first one is the semi-supervised clustering algorithm SSL+P and its upgraded version SSL+P*, which are able of take into account the available knowlegdge about de data in two forms: class labels and pairwise proximity levels, both refered here as hints. These algorithms are also capable of adapting the distance metric to the data and the available hints. The SSL+P* algorithm searches the ideal number of clusters for a dataset, considering the available hints. Both SSL+P and SSL+P* techniques involve the minimization of an objective function by a Population-based Optimization algorithm (PBO). This Thesis also provides tools that can be directly employed in this area: the two modified versions of the Particle Swarm Optimization algorithm (PSO), DPSO-1 and DPSO-2, and 4 diferent methods for initializing a population of solutions. The second main point of the tool set proposed by this Thesis regards the analysis of clusters resulting from a clustering process applied to a domain specific dataset. A Text Mining based approach is proposed to search for textual information related to the entities represented by the data, available in digital repositories. Next, a set of words associated with each cluster is presented to the researcher, which can suggest information that can support the identification of relations shared by objects assigned to the same cluster

In the last one hundred years, the mankind has invented a lot of convenient tools for pursuing beautiful and comfortable living environment. Computer is one of the most important inventions, and its operation ability is incomparable with the mankind. Because computer can deal with a large amount of data fast and accurately, people use this advantage to imitate human thinking. Artificial intelligence is developed extensively. Methods, such as all kinds of neural networks, data mining, fuzzy logic, etc., apply to each side fields (ex: fingerprint distinguishing, image compressing, antennal designing, etc.). We will probe into to prediction technology according to the decision tree and fuzzy clustering. The fuzzy decision tree proposed the classification method by using fuzzy clustering method, and then construct out the decision tree to predict for data. However, in the distance function, the impact of the target space was proportional inversely. This situation could make problems in some dataset. Besides, the output model of each leaf node represented by a constant restricts the representation capability about the data distribution in the node. We propose a more reasonable definition of the distance function by considering both input and target differences with weighting factor. We also extend the output model of each leaf node to a local linear model and estimate the model parameters with a recursive SVD-based least squares estimator. Experimental results have shown that our improved version produces higher recognition rates and smaller mean square errors for classification and regression problems, respectively.

In order to gather information more efficiently, wireless sensor networks are partitioned into clusters. The most of the proposed clustering algorithms do not consider the location of the base station. This situation causes hot spots problem in multi-hop wireless sensor networks. Unequal clustering mechanisms, which are designed by considering the base station location, solve this problem. In this thesis, we propose a fuzzy unequal clustering algorithm (EAUCF) which aims to prolong the lifetime of wireless sensor networks. EAUCF adjusts the cluster-head radius considering the residual energy and the distance to the base station parameters of the sensor nodes. This helps decreasing the intra-cluster work of the sensor nodes which are closer to the base station or have lower battery level. We utilize fuzzy logic for handling the uncertainties in cluster-head radius estimation. We compare our algorithm with some popular algorithms in literature, namely LEACH, CHEF and EEUC, according to First Node Dies (FND), Half of the Nodes Alive (HNA) and energy-efficiency metrics. Our simulation results show that EAUCF performs better than other algorithms in most of the cases considering FND, HNA and energy-efficiency. Therefore, our proposed algorithm is a stable and energy-efficient clustering algorithm.

As the complexity of a spatial phenomenon increases, traditional modeling becomes impractical. Alternatively, data-driven modeling, which is based on the analysis of data characterizing the phenomena, can be used. In this thesis, the generation of understandable and reliable spatial models using observational data is addressed. An interpretability oriented data-driven fuzzy modeling approach is proposed. The methodology is based on construction of fuzzy models from data, tuning and fuzzy model simplification. Mamdani type fuzzy models with triangular membership functions are considered. Fuzzy models are constructed using fuzzy clustering algorithms and simulated annealing metaheuristic is adapted for the tuning step. To obtain compact and interpretable fuzzy models a simplification methodology is proposed. Simplification methodology reduced the number of fuzzy sets for each variable and simplified the rule base. Prototype software is developed and mean annual precipitation data of Turkey is examined as case study to assess the results of the approach in terms of both precision and interpretability. In the first step of the approach, in which fuzzy models are constructed from data, &quot / Fuzzy Clustering and Data Analysis Toolbox&quot / , which is developed for use with MATLAB, is used. For the other steps, the optimization of obtained fuzzy models from data using adapted simulated annealing algorithm step and the generation of compact and interpretable fuzzy models by simplification algorithm step, developed prototype software is used. If the accuracy is the primary objective then the proposed approach can produce more accurate solutions for training data than geographically weighted regression method. The minimum training error value produced by the proposed approach is 74.82 mm while the error obtained by geographically weighted regression method is 106.78 mm. The minimum error value on test data is 202.93 mm. An understandable fuzzy model for annual precipitation is generated only with 12 membership functions and 8 fuzzy rules. Furthermore, more interpretable fuzzy models are obtained when Gath-Geva fuzzy clustering algorithms are used during fuzzy model construction.