From the requirement of satisfying regional monitoring and scheduling management under the characteristics of the regional grid and the connotation of intelligent grid as well as regulation and control integration man...
详细信息
Based on the bi-cooperative modulation mechanism in the human body, we present an enhanced and inhibited intelligent controller (EIIC), and provide its control algorithm in this paper. Corresponding to the related phy...
详细信息
While most commercial automated surface inspection system (ASIS) has built-in functions for defect detection and classification, achieving high classification performance on pickled and noisy strip surfaces has remain...
详细信息
While most commercial automated surface inspection system (ASIS) has built-in functions for defect detection and classification, achieving high classification performance on pickled and noisy strip surfaces has remained challenging because of the diversity in defect types and the similarity in patterns and features in 2D images captured by cameras. A novel technique using laser triangulation meters was implemented with 3D surface profiling for better defect detection on pickled and noisy strip surfaces in the lab environment. The experimental results have shown significant performance improvement in surface defect detection especially in identifying the severe defects from less severe or uninterested defects.
In this paper, a wavelet-based neural network is proposed for the control of nonlinear systems. Activation functions of neural network nodes are determined based on the wavelet transform. The controller can efficientl...
详细信息
ISBN:
(纸本)9781612848006
In this paper, a wavelet-based neural network is proposed for the control of nonlinear systems. Activation functions of neural network nodes are determined based on the wavelet transform. The controller can efficiently compensate for the undesired effects of hard nonlinearities such as saturation and/or dead zone of control input. Compared with standard neuro-controllers, the structure of the controller is definite and simple. The proposed controller is localizable and has a systematically chosen structure, which improves the close-loop performance. An off-line algorithm determines the number of nodes. In addition, an on-line algorithm adjusts the parameters of wavelet bases and network weights. Back propagation algorithm with a momentum term is used for updating the weights and parameters of activation functions. This controller reduces the quantity of network parameters, calculation cost and convergence time of online algorithms with respect to the conventional neural network. Also, the controller is able to control unstable and MIMO systems. To illustrate the capability and performance superiority of the proposed controller, two nonlinear systems are controlled and the corresponding results are compared.
Shape descriptors have been used frequently as features to characterize an image for classification and image retrieval tasks. The problem of recognizing classes of objects in images is important for annotation and in...
详细信息
This paper demonstrates the use of the Locality Sensitive Hashing technique operating in Euclidean metric space to build a data structure for Defense Meteorological Satellite Program (DMSP) satellite imagery database....
详细信息
Abstract The present paper proposes an approximation method to solve the problem of approximate nonlinear output regulation. In this approach, the solution of the regulator equations, consists of partial differential ...
详细信息
Abstract The present paper proposes an approximation method to solve the problem of approximate nonlinear output regulation. In this approach, the solution of the regulator equations, consists of partial differential equations and an algebraic equation, is analytically approximated by Galerkin approximation method. The proposed method is general and can be applied on a wide class of nonlinear systems that the output regulation problem is solvable for them. The effectiveness of the proposed method is investigated on the nonlinear output regulation problem for a benchmark mechanical system, the so-called TORA system.
作者:
Kave AryanpooHadi MoradiRobotics and AI Laboratory
School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran Robotics and AI Laboratory
Control & Intelligent Processing Center of Excellence School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran
Wireless signal fingerprints have been used to localize mobile devices in recent years. Especially, WLAN signals are of great importance, because of the ubiquity of WLAN infrastructure. In this paper, the possibility ...
详细信息
Wireless signal fingerprints have been used to localize mobile devices in recent years. Especially, WLAN signals are of great importance, because of the ubiquity of WLAN infrastructure. In this paper, the possibility of correlation between temperature and signal strength is investigated to improve the traditional fingerprinting method by incorporating the temperature into the process. The new approach is called the Temperature-Aided Fingerprinting (TAF) and even with current WLAN-enabled devices, which usually do not have a thermometer, TAF achieves a better performance than the traditional method. At the end, we open up a hypothesis that the observed difference is not caused by the temperature, rather by the crowdedness and the dynamics of the environment. This is left to be investigated in the future.
From the characteristics in regional grid, the connotation of smart grid and the change of regulation and control integrated management after meeting the requirement of operating monitoring and scheduling management i...
详细信息
We study the problem of finding the minimum-length curvature constrained closed path through a set of regions in the plane. This problem is referred to as the Dubins Traveling Salesperson Problem with Neighborhoods (D...
详细信息
We study the problem of finding the minimum-length curvature constrained closed path through a set of regions in the plane. This problem is referred to as the Dubins Traveling Salesperson Problem with Neighborhoods (DTSPN). Two algorithms are presented that transform this infinite dimensional combinatorial optimization problem into a finite dimensional asymmetric TSP by sampling and applying the appropriate transformations, thus allowing the use of existing approximation algorithms. We show for the case of disjoint regions, the first algorithm needs only to sample each region once to produce a tour within a factor of the length of the optimal tour that is independent of the number of regions. We present a second algorithm that performs no worse than the best existing algorithm and can perform significantly better when the regions overlap.
暂无评论