For some new multimedia applications using Mpeg-4 or Mpeg-7 video coding standards, it is important to find the main objects in a video frame. In this thesis, we propose a neuro-fuzzy modeling approach to the detection of human face and body. Firstly, a fuzzy clustering technique is performed to segment a video frame into clusters to generating several fuzzy rules. Secondly, chrominance and motion features are used to roughly classify the clusters into foreground and background, respectively. Finally, the fuzzy rules are refined by a fuzzy neural network, and the ambiguous regions between foreground and background are further distinguished by the fuzzy neural network. Our method improves the correctness of human face and body detection by getting training data more precisely. Besides, we can extract the VOs correctly even the VOs have no obvious motion in the video sequence.

We propose a novel approach for segmentation of human objects, including face and body, in image sequences. In modern video coding techniques, e.g., MPEG-4 and MPEG-7, human objects are usually the main focus for multimedia applications. We combine temporal and spatial information and employ a neuro-fuzzy mechanism to extract human objects. A fuzzy self-clustering technique is used to divide the video frame into a set of segments. The existence of a face within a candidate face region is ensured by searching for possible constellations of eye-mouth triangles and verifying each eye-mouth combination with the predefined template. Then rough foreground and background are formed based on a combination of multiple criteria. Finally, human objects in the base frame and the remaining frames of the video stream are precisely located by a fuzzy neural network which is trained by a SVD-based hybrid learning algorithm. Through experiments, we compare our system with two other approaches, and the results have shown that our system can detect face locations and extract human objects more accurately.

Mitigation of displacement and acceleration responses of a three story benchmark structure excited by seismic motions is pursued in this study. Multiple 20-kN magnetorheological (MR) dampers are installed in the three-story benchmark structure and managed by a global fuzzy logic controller to provide smart damping forces to the benchmark structure. Two configurations of MR damper locations are considered to display multiple-input, single-output and multiple-input, multiple-output control capabilities. Characterization tests of each MR damper are performed in a laboratory to enable the formulation of fuzzy inference models. Prediction of MR damper forces by the fuzzy models shows sufficient agreement with experimental results. A controlled-elitist multi-objective genetic algorithm is utilized to optimize a set of fuzzy logic controllers with concurrent consideration to four structural response metrics. The genetic algorithm is able to identify optimal passive cases for MR damper operation, and then further improve their performance by intelligently modulating the command voltage for concurrent reductions of displacement and acceleration responses. An optimal controller is identified and validated through numerical simulation and fullscale experimentation. Numerical and experimental results show that performance of the controller algorithm is superior to optimal passive cases in 43% of investigated studies. Furthermore, the state-space model of the benchmark structure that is used in numerical simulations has been improved by a modified version of the same genetic algorithm used in development of fuzzy logic controllers. Experimental validation shows that the state-space model optimized by the genetic algorithm provides accurate prediction of response of the benchmark structure to base excitation.

CNPq - Conselho Nacional de Desenvolvimento Científico e Tecnológico / Esse trabalho propõe a modelagem e o controle neuro-fuzzy aplicados na estabilidade estática de um veículo de duas rodas do tipo pêndulo invertido, utilizando como método de otimização a evolução diferencial. Durante a fase de modelagem, determinam-se as incertezas relacionadas aos parâmetros e também à resposta do modelo neuro-fuzzy. Verifica-se que este é capaz de se ajustar satisfatoriamente aos dados extraídos experimentalmente do veículo. Na determinação do controlador neuro-fuzzy, testam-se três estratégias de ajuste de parâmetros, sendo duas delas propostas neste texto, e os resultados são comparados entre si e aos obtidos através de controladores clássicos, e verifica-se experimentalmente e por meio de testes estatísticos que as abordagens propostas apresentam grande capacidade de adaptação às restrições impostas à planta, garantindo a estabilidade estática e a eficiência energética do sistema. / This work proposes the neuro-fuzzy modeling and control applied to the static stability of a two-wheeled inverted pendulum vehicle, using differential evolution as optimization technique. During the modeling phase, the uncertainties related to the parameters and also to the neuro-fuzzy model response are determined. It is possible to verify that the neuro-fuzzy system is capable of satisfactorily adjusts to the data experimentally extracted from the vehicle. In the determination of the neuro-fuzzy controller, three strategies of parameter adjustment are tested, two of them being proposed in this text, and the results are compared between them and those obtained through classical controllers, and it is verified experimentally and through tests that the proposed approaches present a great capacity to adapt to the constraints imposed on the plant, guaranteeing the static stability and the energy efficiency of the system. / Dissertação (Mestrado)