Selecting a suitable kernel for relevance vector machine is one of most challenging aspects of successfully using this learning tool. Efficiently automating the search for such a kernel is therefore desirable. This paper proposes a datadriven kernel function construction and optimization method, which combines genetic programming(GP) and relevance vector regression to evolve an optimal or near-optimal kernel function, named GP-Kernel. The evolved kernel is compared to several widely used kernels on several regression benchmark datasets. Empirical results demonstrate that RVM using such GP-Kernel can outperform or match the best performance of standard kernels.
Relevance vector machine (RVM) is a state-of-theart technique for regression and classification, as a sparse Bayesian extension version of the support vector machine. The selection of a kernel and associated parameter is a critical step of RVM application. The real-world application and recent researches have emphasized the requirement to multiple kernel learning, in order to boost the fitting accuracy by adapting better the characteristics of the data. This paper presents a data-driven evolutionary approach, called Genetic Complex Multiple Kernel Relevance Vector Regression (GCMK RVR), which combines genetic programming(GP) and relevance vector regression to evolve an optimal or nearoptimal complex multiple kernel function. Each GP chromosome is a tree that encodes the mathematical expression of a complex multiple kernel function. Numerical experiments on several benchmark datasets show that the RVR involving this GCMK perform better than not only the widely used simple kernel, Polynomial, Gaussian RBF and Sigmoid kernel, but also the convex linear multiple kernel function.
Abstract-The estimation of aeroengine component deviation parameters (CDP)is an important portion of aeronautical propulsion system performance-seeking control (PSC), which employs linear Kalman filter based on piecewise state variable model (SVM) traditionally. But it's not easy to get SVM, and the process of linearizing the nonlinear model to get the SVM will introduce errors. So parameters nonlinear estimation was introduced based on the nonlinear aeroengine model directly. The nonlinear estimation model is established according to aeroengine operation balance and the measured and calculated values matching of measurable parameters. The nonlinear estimation was changed to a problem of solving complex nonlinear equations, which is equal to an optimization problem. Time-varying inertia weight particle swarm optimization (PSO) with constriction factor was employed to solve the problem in order to satisfy the requirement of precision and calculation speed. The simulation results of a given turbofan engine show that utilizing the improved PSO algorithm can estimate the CPD precisely with satisfied converging speed.
Creating complex and realistic crowd behaviors, such as pedestrian navigation behavior with dynamic obstacles, is a difficult and time consuming task. In this paper, we study one special type of crowd which is composed of urgent individuals, normal individuals, and normal groups. We use three steps to construct the crowd simulation in dynamic environment. The first one is that the urgent individuals move forward along a given path around dynamic obstacles and other crowd members. An optimal acceleration-velocity-bounded trajectory planning method is utilized to model their behaviors, which ensures that the durations of the generated trajectories are minimal and the urgent individuals are collision-free with dynamic obstacles (e.g., dynamic vehicles). In the second step, a pushing model is adopted to simulate the interactions between urgent members and normal ones, which ensures that the computational cost of the optimal trajectory planning is acceptable. The third step is obligated to imitate the interactions among normal members using collision avoidance behavior and flocking behavior. Various simulation results demonstrate that these three steps give realistic crowd phenomenon just like the real world.
scite is a Brooklyn-based startup that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.