The Viscous Display explores the exchange of social information through transient public interfaces. Shaped by principles of 'underground public art', the Viscous Display is conceived as a novel mobile communi...
详细信息
ISBN:
(纸本)9781581138832
The Viscous Display explores the exchange of social information through transient public interfaces. Shaped by principles of 'underground public art', the Viscous Display is conceived as a novel mobile communication medium, where messages can be shared in public spaces. Inspired by biological learning systems; the Viscous Display learns sensorial information that form along traces of a participant's touch and maps this information onto a flexible display. Because it is made up of inexpensive materials, the Viscous Display is also a disposable artifact that may be collected in public spaces. It combines multi-modal sensing, learning algorithms, and a pliable silicone display.
The food retailing market has reached a mature stage where companies need to be competitive if they are to survive. Customers are ever more demanding and retailers need to design and introduce new ways of learning abo...
详细信息
A learning-based control approach is presented for force servoing of a robot with vision in an unknown environment. Firstly, mapping relationships between image features of the servoing object and the joint angles of ...
详细信息
A learning-based control approach is presented for force servoing of a robot with vision in an unknown environment. Firstly, mapping relationships between image features of the servoing object and the joint angles of the robot are derived and learned by a neural network. Secondly, a learning controller based on the neural network is designed for the robot to trace the object. Thirdly, a discrete time impedance control law is obtained for the force servoing of the robot,the on-line learning algorithms for three neural networks are developed to adjust the impedance parameters of the robot in the unknown environment. Lastly, wiping experiments are carried out by using a 6 DOF industrial robot with a CCD camera and a force/torque sensor in its end effector, and the experimental results confirm the effectiveness of the approach.
A parallel multi-layer perceptron network (MLPN) model with on-line learning algorithm is proposed. This parallel MLPN is on-line trained directly in a parallel form. The on-line learning algorithm is based on the Ext...
详细信息
A parallel multi-layer perceptron network (MLPN) model with on-line learning algorithm is proposed. This parallel MLPN is on-line trained directly in a parallel form. The on-line learning algorithm is based on the Extended Kalman Filter (EKF) algorithm. This parallel MLPN is able to learn the non-linear dynamic behaviour of unknown time-varying systems. The proposed parallel MLPN can be used to model the non-linear systems and perform multi-step-ahead prediction for control purpose. The performance of this model is demonstrated in modelling a multi-variable nonlinear continuous stirred tank reactor (CSTR).
Standard back propagation, as with many gradient based optimization methods converges slowly as neural network training problems become larger and more complex. This paper describes the employment of two algorithms to...
详细信息
Standard back propagation, as with many gradient based optimization methods converges slowly as neural network training problems become larger and more complex. This paper describes the employment of two algorithms to accelerate the training procedure in an automatic human face recognition system. As compared to standard back propagation, the convergence rate is improved by up to 98% with only a minimal increase in the complexity of each iteration.
Presented is a new architecture and a new learning algorithm that are exploited to resolve the blind source separation problem under stricter constraints than those considered to date. The mixing model that is assumed...
详细信息
Presented is a new architecture and a new learning algorithm that are exploited to resolve the blind source separation problem under stricter constraints than those considered to date. The mixing model that is assumed is an evolution of the well-known post-nonlinear (PNL) one: the PNL mixing block is followed by a convolutive mixing channel. The flexibility of the algorithm originates from the spline-SG neurons performing an on-line estimation of the score functions.
We propose a novel approach for segmentation of human objects, including face and body, in image sequences. Object segmentation is important for achieving a high compression ratio in modern video coding techniques, e....
详细信息
We propose a novel approach for segmentation of human objects, including face and body, in image sequences. Object segmentation is important for achieving a high compression ratio in modern video coding techniques, e.g., MPEG-4 and MPEG-7, and human objects are usually the main parts in the video streams of multimedia applications. Existing segmentation methods apply simple criteria to detect human objects, leading to the restriction of the usage or a high segmentation error. We combine temporal and spatial information and. employ a neuro-fuzzy mechanism to overcome these difficulties. A fuzzy self-chistering technique is used to divide the I base frame of a video stream into a set of segments which are then categorized as foreground or background based on a combination of multiple criteria. Then, human objects in the base frame and the remaining frames of the video stream are precisely located by a fuzzy neural network constructed with the fuzzy rules previously obtained and is trained by a singular value decomposition (SVD)-based hybrid learning algorithm. The proposed approach has been tested on several different video streams, and the results have shown that the approach can produce a much better segmentation than other methods.
In order to achieve more efficient voltage regulation in a power system, coordinated secondary voltage control has been proposed, bringing in the extra benefit of enhancement of power system voltage stability margin. ...
详细信息
In order to achieve more efficient voltage regulation in a power system, coordinated secondary voltage control has been proposed, bringing in the extra benefit of enhancement of power system voltage stability margin. This paper investigates a new potential application of coordinated''secondary voltage control by multiple FACTS voltage controllers in eliminating voltage violations in power system contingencies. The study is presented by the example New England ten-machine power system with two SVCs and two STATCOMs installed. The coordinated secondary voltage control is assigned to the SVCs and STATCOMs in order to eliminate voltage violations in system contingencies. In the paper, it is proposed that the secondary voltage control is implemented by a learning fuzzy logic controller. A key parameter of the controller is trained by P-type learning algorithm via offline simulation with the assistance of injection of artificial loads in controller's adjacent locations. A multiagent collaboration protocol, which is graphically represented as a finite-state machine, is proposed in the paper for the coordination among multiple SVCs and STATCOMs. As an agent, each SVC or STATCOM can provide multilocation coverage to eliminate voltage violations at its adjacent nodes in the power system. Agents can provide collaborative support to each other which is coordinated according to the proposed collaboration protocol.
Modeling of the relationship between the pressure and yield of biomaterials is an essential issue in supercritical fluid extraction. In this paper, neural networks are proposed for modeling of supercritical fluid extr...
详细信息
Modeling of the relationship between the pressure and yield of biomaterials is an essential issue in supercritical fluid extraction. In this paper, neural networks are proposed for modeling of supercritical fluid extraction. First a three-layer neural network with a fast learning algorithm is used, and its performance is compared to a conventional model of the Peng-Robinson equation of state. A novel hybrid model combining both a neural network and the Peng-Robinson equation is then proposed. With the learning capacity, the proposed models generally perform better than the conventional model that needs to select its parameters by trial and error. The effectiveness of the proposed approaches is demonstrated by simulation and comparison studies.
The brain is an organ especially differentiated to acquire algorithms in a self-organized fashion according to the genetic algorithm. These acquired algorithms allow the brain to respond to the ever-changing environme...
详细信息
暂无评论