Most edge detection algorithms include three main stages: smoothing, differentiation, and labeling. In this paper, we evaluate the performance of algorithms in which competitive learning is applied first to enhance ed...
详细信息
Most edge detection algorithms include three main stages: smoothing, differentiation, and labeling. In this paper, we evaluate the performance of algorithms in which competitive learning is applied first to enhance edges, followed by an edge detector to locate the edges. In this way, more detailed and relatively more unbroken edges can be found as compared to the results when an edge detector is applied alone. The algorithms compared are K-Means, SOM and SOGR for clustering, and Canny and GED for edge detection. Perceptionally, best results were obtained with the GED-SOGR algorithm. The SOGR is also considerably simpler and faster than the SOM algorithm.
The stringent requirements on size and power consumption constrain the conventional hearing aid devices from providing the patients an economic and user friendly solution, specifically for better noise cancellation. W...
详细信息
We have established a medical network in Asia-Pacific area with high-quality moving image on a super broad-banded internet line since February 2003. Broadcasting real-time surgery and teleconference with medical-quali...
详细信息
In this paper, we study how to collect n balls moving with constant velocities in the Euclidean plane by k robots moving on straight track-lines through the origin. Since all the balls might not be caught by robots, d...
详细信息
In this paper, we study how to collect n balls moving with constant velocities in the Euclidean plane by k robots moving on straight track-lines through the origin. Since all the balls might not be caught by robots, d...
详细信息
In this paper, we study how to collect n balls moving with constant velocities in the Euclidean plane by k robots moving on straight track-lines through the origin. Since all the balls might not be caught by robots, differently from Moving-Target TSP, we consider the following 3 problems in various situations: (i) deciding if k robots can collect all n balls, (ii) maximizing the number of the balls collected by k robots, and (iii) minimizing the number of the robots to collect all n balls. The situations considered here contain the cases in which track-lines are given (or not), and track-lines are identical (or not). For all problems and situations, we provide polynomial time algorithms or proofs of intractability, which clarify the tractability-intractability frontier in the ball collecting problems in the Euclidean plane.
Synthetic aperture radar (SAR) and SPOT images are becoming increasingly important and abundant in a variety of remote sensing and tactical applications. Thus, there is a strong interest in developing data encoding an...
详细信息
Biochemical processes often display a complicated dynamic behavior, the detailed understanding of which frequently constitutes a barrier between the theoretical foundations and practical implementations. One way of ha...
详细信息
Biochemical processes often display a complicated dynamic behavior, the detailed understanding of which frequently constitutes a barrier between the theoretical foundations and practical implementations. One way of handling the complexity is to use intelligent approaches in the design of controllers. The paper presents an analytic approach to design controllers based on radial basis function neural networks (RBFNN) with particular emphasis on the extraction of the error measure to be used in parameter tuning. The simulation studies stipulate that the control system exhibits a highly robust behavior against disturbances and sharp changes in the command signal. The most important contribution of the paper is that the method presented does not require the analytical details describing the plant dynamics available.
This paper addresses state-space realizations for nonlinear adjoint operators. In particular the relationship among nonlinear Hilbert adjoint operators, Hamiltonian extensions and port-controlled Hamiltonian systems a...
详细信息
This paper addresses state-space realizations for nonlinear adjoint operators. In particular the relationship among nonlinear Hilbert adjoint operators, Hamiltonian extensions and port-controlled Hamiltonian systems are clarified. The characterization of controllability, observability and Hankel operators, and controllability and observability functions will be derived based on it. Furthermore a duality between the controllability and observability functions will be proven. The statespace realizations ofsuch operators provide new insights to nonlinear control systems theory.
暂无评论