The importance of properly securing an organization’s information and computing resources has become paramount in modern business. Since the advent of the Internet, securing this organizational information has become increasingly difficult. Organizations deploy many security mechanisms in the protection of their data, intrusion detection systems in particular have an increasingly valuable role to play, and as networks grow, administrators need better ways to monitor their systems. Currently, many intrusion detection systems lack the means to accurately monitor and report on wireless segments within the corporate network. This dissertation proposes an extension to the NeGPAIM model, known as NeGPAIM-W, which allows for the accurate detection of attacks originating on wireless network segments. The NeGPAIM-W model is able to detect both wired and wireless based attacks, and with the extensions to the original model mentioned previously, also provide for correlation of intrusion attacks sourced on both wired and wireless network segments. This provides for a holistic detection strategy for an organization. This has been accomplished with the use of Fuzzy logic and neural networks utilized in the detection of attacks. The model works on the assumption that each user has, and leaves, a unique footprint on a computer system. Thus, all intrusive behaviour on the system and networks which support it, can be traced back to the user account which was used to perform the intrusive behavior.

In this research work, an approach for fire detection and estimation robots is presented. The approach is based on type-2 fuzzy logic system that utilizes measured temperature and light intensity to detect fires of various intensities at different distances. Type-2 fuzzy logic system (T2 FLS) is known for not needing exact mathematic model and for its capability to handle more complicated uncertain situations compared with Type-1 fuzzy logic system (T1 FLS). Due to lack of expertise for new facilities, a new approach for training experts’ expertise and setting up T2 FLS parameters from pure data is discussed in this thesis. Performance of both T1 FLS and T2 FLS regarding to same fire detection scenario are investigated and compared in this thesis. Simulation works have been done for fire detection robot of both free space scenario and new facility scenario to illustrate the operation and performance of proposed type-2 fuzzy logic system. Experiments are also performed using LEGO MINDSTROMS NXT robot to test the reliability and feasibility of the algorithm in physical environment with simple and complex situation.

This thesis describes the development and experimental results of a system to explore cloning of facial expressions between dissimilar face models, so new faces can be animated using the animations from existing faces. The system described in this thesis uses fuzzy membership functions and subtractive clustering to represent faces and expressions in an intermediate space. This intermediate space allows expressions for face models with different resolutions to be compared. The algorithm is trained for each pair of faces using particle swarm optimization, which selects appropriate weights and radii to construct the intermediate space. These techniques allow the described system to be more flexible than previous systems, since it does not require prior knowledge of the underlying implementation of the face models to function.

Unreinforced masonry construction is considered to be the most vulnerable forms of construction as demonstrated through recent earthquakes. In Canada, many densely populated cities such as (Vancouver, Montreal and Ottawa) have large inventories of seismically vulnerable masonry structures. Although measures have been taken to rehabilitate and increase the seismic resistance of important and historic structures, many existing unreinforced masonry structures have not been retrofitted and remain at risk in the event of a large magnitude earthquake. There is therefore a need to identify buildings at risk and develop tools for assessing the seismic vulnerability of existing unreinforced masonry structures in Canada. This thesis presents results from an ongoing research program which forms part of a multi-disciplinary effort between the University of Ottawa’s Hazard Mitigation and Disaster Management Research Centre and the Geological Survey of Canada (NRCAN) to assess the seismic vulnerability of buildings in dense urban areas such as Ottawa, Ontario. A risk-based seismic assessment tool (CanRisk) has been developed to assess the seismic vulnerability of existing unreinforced masonry and reinforced concrete structures. The seismic risk assessment tool exploits the use of fuzzy logic, a soft computing technique, to capture the vagueness and uncertainty within the evaluation of the performance of a given building. In order to conduct seismic risk assessments, a general building inventory and its spatial distribution and variability is required for earthquake loss estimations. The Urban Rapid Assessment Tool (Urban RAT) is designed for the rapid collection of building data in urban centres. This Geographic Information System (GIS) based assessment tool allows for intense data collection and revolutionizes the traditional sidewalk survey approach for collecting building data. The application of CanRisk and the Urban RAT tool to the City of Ottawa is discussed in the following thesis. Data collection of over 13,000 buildings has been obtained including the seismic risk assessment of 1,465 unreinforced masonry buildings. A case study of selected URM buildings located in the City of Ottawa was conducted using CanRisk. Data obtained from the 2011 Christchurch Earthquake in New Zealand was utilized for verification of the tool.

This thesis presents two modern control methods to address the Internet traffic congestion control issues. They are based on a distributed traffic management framework for the fast-growing Internet traffic in which routers are deployed with intelligent or optimal data rate controllers to tackle the traffic mass. The first one is called the IntelRate (Intelligent Rate) controller using the fuzzy logic theory. Unlike other explicit traffic control protocols that have to estimate network parameters (e.g., link latency, bottleneck bandwidth, packet loss rate, or the number of flows), our fuzzy-logic-based explicit controller can measure the router queue size directly. Hence it avoids various potential performance problems arising from parameter estimations while reducing much computation and memory consumption in the routers. The communication QoS (Quality of Service) is assured by the good performances of our scheme such as max-min fairness, low queueing delay and good robustness to network dynamics. Using the Lyapunov’s Direct Method, this controller is proved to be globally asymptotically stable. The other one is called the OFEX (Optimal and Fully EXplicit) controller using convex optimization. This new scheme is able to provide not only optimal bandwidth allocation but also fully explicit congestion signal to sources. It uses the congestion signal from the most congested link, instead of the cumulative signal from a flow path. In this way, it overcomes the drawback of the relatively explicit controllers that bias the multi-bottlenecked users, and significantly improves their convergence speed and throughput performance. Furthermore, the OFEX controller design considers a dynamic model by proposing a remedial measure against the unpredictable bandwidth changes in contention-based multi-access networks (such as shared Ethernet or IEEE 802.11). When compared with the former works/controllers, such a remedy also effectively reduces the instantaneous queue size in a router, and thus significantly improving the queueing delay and packet loss performance. Finally, the applications of these two controllers on wireless local area networks have been investigated. Their design guidelines/limits are also provided based on our experiences.

In general, it is difficult to automatically detect faults within large scale engineering plants early during their onset. This is due to a number of factors including the large number of components typically present in such plants and the complex interactions of these components, which are typically poorly understood. Traditionally, fault detection within these plants has been performed through the use of status monitoring systems employing limit checking fault detection. In this approach, upper and lower bounds are placed on what is prescribed as “normal” behaviour for each of the plant's collected status data signals and fault flags are generated if and when the given status data signal exceeds either of its bounds. This approach tends to generate relatively large numbers of false alarms, due to the technique's inability to model known signal dependencies, and it also tends to produce inconsistent fault flags, in the sense that the flags do not tend to be produced throughout the “fault” event. The limit checking approach also is not particularly adept at early fault detection tasks since as long as the given status data signal remains between the upper and lower bounds any signal behaviour is deemed as acceptable. Hence, behavioural changes in the status data signals go undetected until their severity is such that either the upper or lower bounds are exceeded. In this dissertation, two novel fault detection methodologies are proposed which are better suited to the early fault detection task than traditional limit checking. The first technique is directed at modeling of signals exhibiting unknown linear dependencies. This detection system utilizes fuzzy membership functions to model signal behaviour and through this modelling approach fault detection bounds are generated which meet a prescribed probability of false alarm rate. The second technique is directed at modelling signals exhibiting unknown non-linear, dynamic dependencies. This system utilizes recurrent neural network technology to model the signal behaviours and prescribed statistical methods are employed to determine appropriate fault detection thresholds. Both of these detection systems have been designed to be able to be retrofitted into existing industrial status monitoring system and, as such, they have been designed to achieve good modelling performance in spite of the coarsely quantized status data signals which are typical of industrial status monitoring systems constructed to employ limit checking. The fault detection properties of the proposed fault detection systems were also compared to an in situ limit checking fault detection system for a set of real-world data obtained from an operational large scale engineering plant. This comparison showed that both of the proposed fault detection systems achieved marked improvements over traditional limit checking both in terms of their false alarm rates and their fault detection sensitivities. / Graduate

Le but de cette thèse est l'optimisation de la production de l'électricité renouvelable pour site isolé de faible puissance. Un système, utilisant deux sources renouvelables : photovoltaïque et éolienne, est étudié afin d'améliorer le rendement énergétique de l'énergie produite. Pour la chaîne de conversion photovoltaïque, un contrôleur pour suivre le point de puissance maximale est conçu en utilisant l'approche de recherche directe (méthode Perturbe & Observe) combinée avec la logique floue, tout en prenant en compte le sens de variation des perturbations. Avec cette combinaison, on peut éviter des défauts de la méthode Perturbe & Observe, s'affranchir des informations sur les caractéristiques du panneau photovoltaïque et des conditions climatiques. Egalement, pour la chaîne de conversion éolienne de petite puissance fonctionnant à vitesse variable couplée à un générateur synchrone à aimant permanent, un contrôleur pour suivre le point de puissance maximale est proposé qui est basé sur le même principe par rapport à la chaîne de conversion photovoltaïque. Cette approche proposée a l'avantage de l'utilisation d'un capteur de tension au lieu d'un capteur de vitesse, ceci présente un intérêt certain notamment pour sites isolés par rapport aux autres solutions. Enfin, pour la réalisation d'un système de production d'électricité hybride, un superviseur est conçu pour obtenir un comportement optimal du système en fonction des variations de la charge et de la production en prenant en compte du système de stockage et de délestage. Pour chaque point abordé, des études en simulation sont fournies pour montrer l'efficacité des approches proposées. / The objective of this thesis is to optimize the production of renewable electricity for small isolated network. A system using two renewable sources: solar and wind power, is studied in order to improve the efficiency of energy extracted. For the photovoltaic conversion system, a maximum power point tracking controller is designed using direct searching approach (method Perturbe & Observe) combined with fuzzy logic, taking into account the direction of perturbation. This combination can avoid the disadvantages of the method Perturbe & Observe, and not requires any information about the generator's characteristics or climate conditions. Similarly, for the variable speed wind turbine using permanent magnet synchronous generator, a controller to track the maximum power point, based on the same principle with photovoltaic conversion system, is proposed. This approach has the advantage of using a voltage sensor instead of a speed sensor, this presents a particular interest for stand-alone system comparing to other solutions. Finally, for the realization of hybrid generation system, a fuzzy supervisor is adapted to obtain an optimal behavior of the system according to the variations of load demand and extracted power, taking into account the storage and dissipation system. For each issue, simulation studies are provided to show the effectiveness of the proposed approaches.

D.Ing. / “Innovation is the act of introducing something new” (Byrd & Brown, 2003). When companies are competing on the technology “playground” they need to be innovative. By analysis according to Byrd & Brown (Byrd & Brown, 2003) the “act of introducing”, relates to risk taking, and the “new” relates to creativity, and therefore these concepts, creativity and risk taking, in combination, are what innovation is all about. Risk management has become one of the greatest challenges of the 21st century, and one of the main components in innovation and the technology driven industry, intensifying the need for a systematic approach to managing uncertainties. During the development and design of complex engineering products, the input and teamwork of multiple participants from various backgrounds are required resulting in complex interactions. Risk interactions exist between the functional and physical elements within such a system and its sub-systems in various dimensions such as spatial interaction, information interaction etc. The relationships are of a multi-dimensional complexity that cannot be simplified using the standard task management tools (Yassine A. A., 2004). To find a meaningful starting point for the seemingly boundless subject of risk management the research takes a step back into the basic definition of risk management and follows an exploratory research methodology to explore each of the risk management processes (risk assessment, risk identification, risk analysis, risk evaluation, risk treatment and risk monitoring and review) and how these processes can be enhanced using the design structure matrix (DSM) and fuzzy logic thinking. The approach to risk management within an organisation should be seen as a holistic approach similar to the total quality management process, providing the ii opportunity to incorporated risk management during the design process as a concurrent task. The risk management model is then developed concurrently (during the design phase) using product development methodologies such as conceptual modeling and prototyping, and ultimately the prototype is tested using a case study. Finally resulting in a clustered DSM providing a visual representation of the system risk areas similar to the methodology used in Finite Element Analysis (FEA). The research combines alternative system representation and analysis techniques (Warfield, 2005), in particular the design structure matrix, and fuzzy logic to quantify the risk management effort neccessary to deal with uncertain and imprecise interactions between system elements.

Orientador: Marcelo Carvalho Minhoto Teixeira / Banca: Evaldo Assunção / Banca: Rodrigo Cardim / Banca: Cristiano Quevedo Andrea / Banca: Ruy de Oliveira / Resumo: O presente trabalho propõe duas novas metodologias de desenvolvimento: uma na área de medicina, no diagnóstico de hérnia inguinal utilizando a lógica fuzzy e outra, na área da agronomia, para estimação da produção de trigo utilizando o modelo de inferência adaptativo neuro fuzzy. Na primeira foi desenvolvido um aplicativo para dispositivos móveis, smartphones e tablets, auxiliando a tomada de decisão no diagnóstico de pacientes com suspeita de hérnia na região inguinal. Para isso, utilizou-se a linguagem JAVA juntamente com a biblioteca lógica fuzzy, denominada jfuzzylogic, e o sistema operacional Android para o desenvolvimento da aplicação. Para validar o aplicativo, utilizou-se a coleta de dados, via questionário, envolvendo 30 pacientes entrevistados em consulta médica. Como resultado, observou-se que o diagnóstico realizado pela equipe médica e o diagnóstico com o auxílio do aplicativo móvel, mostraram-se equivalentes nos casos dos pacientes acometidos com hérnia da região inguinal. Este software será disponibilizado gratuitamente, via web, para os profissionais da área da saúde. Já na segunda, investigou-se a habilidade de se desenvolver um modelo de inferência adaptativo neuro fuzzy para estimação da produtividade de trigo (Triticum aestivum) em função da adubação nitrogenada, com base em dados experimentais de cultivares de trigo, avaliada durante dois anos, em Selvíria-MS. Através dos dados de entrada e saída, o sistema de inferência neuro fuzzy adaptativo apreende e posteriormente pode estimar um novo valor de produção de trigo baseada em doses diferenciadas de nitrogênio. Os resultados mostraram que o sistema neuro fuzzy é viável para desenvolver um modelo de predição para estimar a produtividade de trigo em função da dose de nitrogênio. A produção estimada através do sitema neuro fuzzy proporcionou um erro RMSE (Raiz Quadrada do Erro Médio ... / Abstract: This work proposes two new application methods: one in the area of biomedical engineering in the diagnosis of inguinal hernias using fuzzy logic and another in the area of agriculture to estimate the wheat productivity using an adaptive neuro fuzzy inference system. The first was an application developed for mobile devices, smartphones and tablets, to assist decision making in the diagnosis of patients with suspected inguinal hernia. It was used the Java language together with the fuzzy logic library, denominated jfuzzylogic and the Android operating system for the application development. To validate the application it was used data obtained via questionnaire, involving 30 patients interviewed in medical consultation. As a result, it was observed that the diagnosis made by the medical team and diagnosis with the aid of the mobile application, were equivalent in cases of affected patients with hernia in the inguinal region. This software is available free of charge via the web, for professionals in the health field. In the second application method, it was investigated the ability to develop an adaptive neuro fuzzy inference system for estimating the productivity of wheat (Triticum aestivum) in relation to the nitrogen fertilization, based on experimental data of wheat cultivars during two years, in Selvíria-MS. Through the data input and output, the system of adaptive neuro fuzzy inference learns and subsequently can estimate a new value of wheat production based on different doses of nitrogen. The results showed that the neuro fuzzy system is feasible to develop a prediction model to estimate the productivity of wheat in relation to nitrogen rates. The RMSE (Root Mean Square Error) error of the estimated wheat productivity using the neuro fuzzy system was smaller than that obtained with the quadratic regression method, that is usually used in this kind of estimated, and also the relation between ... / Doutor

This Master’s thesis presents a design of models which are intended for evaluation of Braintrast’s suppliers. Based on the evaluation, there is selected the most optimal supplier according to parameters. The model uses fuzzy logic theory to support decision making. The solution is designed in programs MATLAB and MS Excel.