Automatic image annotation, which aims at automatically identifying and then assigning semantic keywords to the meaningful objects in a digital image, is not a very difficult task for human but has been regarded as a ...
详细信息
Automatic image annotation, which aims at automatically identifying and then assigning semantic keywords to the meaningful objects in a digital image, is not a very difficult task for human but has been regarded as a difficult and challenging problem to machines. In this paper, we present a hierarchical annotation scheme considering that generally human s visual identification to a scenery object is a rough-to-fine hierarchical process. First, the input image is segmented into multiple regions and each segmented region is roughly labeled with a general keyword using the multi-classification support vector machine. Since the results of rough annotation affect fine annotation directly, we construct the statistical contextual relationship to revise the improper labels and improve the accuracy of rough annotation. To obtain reasonable fine annotation for those roughly classified regions, we propose an active semi-supervised expectation-maximization algorithm, which can not only find the representative pattern of each fine class but also classify the roughly labeled regions into corresponded fine classes. Finally, the contextual relationship is applied again to revise the improper fine labels. To illustrate the effectiveness of the presented approaches, a prototype image annotation system is developed, the preliminary results of which showed that the hierarchical annotation scheme is effective.
We are extremely pleased to present this special issue of the Journal of control Theory and *** dynamic programming (ADP) is a general and effective approach for solving optimal control and estimation problems by adap...
详细信息
We are extremely pleased to present this special issue of the Journal of control Theory and *** dynamic programming (ADP) is a general and effective approach for solving optimal control and estimation problems by adapting to uncertain environments over *** optimizes the sensing objectives accrued over a future time interval with respect to an adaptive control law,conditioned on prior knowledge of the system,its state,and uncertainties.A numerical search over the present value of the control minimizes a Hamilton-Jacobi-Bellman (HJB) equation providing a basis for real-time,approximate optimal control.
Accurate and effective parameter identification is an important engineering task in high performance control system design. One emerging approach to effectively identify such nonlinear or dynamic unknown parameters is...
详细信息
ISBN:
(纸本)9789746724913
Accurate and effective parameter identification is an important engineering task in high performance control system design. One emerging approach to effectively identify such nonlinear or dynamic unknown parameters is to use Particle Swarm Optimization (PSO) algorithm. Linear Permanent Magnet (LPM) motor is a high performance actuator employed in many applications that require direct linear motion without mechanical transmission for high acceleration and accurate positioning. Therefore, accurate motor parameters are necessary to effectively control the LPM motors. This paper proposes a simple PSO based method with chirp inputs to identify the LPM motor's parameters. The simulations and experiments are conducted to verify the results and determine the effectiveness of the proposed method.
This work presents a multimodal teleoperation framework that makes use of novel tools and techniques, such as: nonlinear teleoperators control, for ensuring position tracking in the presence of variable time-delays; r...
详细信息
This work presents a multimodal teleoperation framework that makes use of novel tools and techniques, such as: nonlinear teleoperators control, for ensuring position tracking in the presence of variable time-delays; relational positioning, for increasing operator performance on precise movement execution by visually and haptically displaying geometric constraints; and augmented reality, for visually combining real and virtual information in a compelling way. Experimental evidence is presented that validates the aptitude of the different components of the proposed framework.
This research proposes a method to eliminate friction effect and reduced tracking error on CNC milling machines. A CNC milling machine has many connected mechanical components which have friction effects such as ball ...
详细信息
ISBN:
(纸本)9789746724913
This research proposes a method to eliminate friction effect and reduced tracking error on CNC milling machines. A CNC milling machine has many connected mechanical components which have friction effects such as ball screws and rails. To control servo motors which are used to drive X-Y table in CNC milling machine, the conventional PID controller is widely used. In this research, Panasonic motor driver is set to the torque control mode. To compensate the friction effects, the friction feedforward compensation method is proposed. Moreover, to reduce the position tracking error, position feedforward controller is used. The simulation and implementation of position control in one axis of PID with Friction Feedforward Compensation and Position Feedforward controller (FFC-PFC) are presented.
Many real natural or man-made dynamic systems can be better characterized using a fractional order dynamic model. Since in such a case the order assumes a non-integer value, it is of interest to consider the effect of...
详细信息
Many real natural or man-made dynamic systems can be better characterized using a fractional order dynamic model. Since in such a case the order assumes a non-integer value, it is of interest to consider the effect of small perturbation around the nominal value. It is of practical importance to analyze the influence of the order variations on the system behavior. This paper establishes an analytical method for the analysis of the sensitivity function of LTI fractional order dynamic systems with respect to the orders. The continuous dependent condition of the orders of fractional Green's function is derived, which is proved as a necessary and sufficient condition. The singularity of fractional Green's functions is discussed. Several examples are included for illustration.
Auditory perception is one of the most important functions for robotics applications. Microphone arrays are widely used for auditory perception in which the spatial structure of microphones is usually known. In practi...
详细信息
Making good operation decisions during abnormal power plant conditions represents in many cases the possibility to avoid a unit trip or having economical losses. This paper introduces AsistO, an intelligent assistant ...
详细信息
In this letter, we present a novel approach of valve stiction detection using wavelet technology. A new non-invasive method is developed with the closed-loop normal operating data. The redundant dyadic discrete wavele...
详细信息
In this letter, we present a novel approach of valve stiction detection using wavelet technology. A new non-invasive method is developed with the closed-loop normal operating data. The redundant dyadic discrete wavelet transform is used to decompose the data at different resolution scales. Based on the Lipschitz regularity theory, wavelet coefficients analysis across scales is performed to detect the jumps in the controlled variables. Adaptive wavelet de-noising is then applied to the data. Features of the valve stiction patterns are extracted from the de-noised data and the valve stiction probability is calculated.
This paper deals with resource allocation in multi-project manufacturing system design, where more than one shared renewable resource type may be required by the manufacturing operation and the availability of each ty...
详细信息
This paper deals with resource allocation in multi-project manufacturing system design, where more than one shared renewable resource type may be required by the manufacturing operation and the availability of each type is time limited. The aim of the paper is to present a knowledge-based and constraint programming-driven approach to resource allocation where that data can be imprecise. The presented design scheme is used as a framework for developing a task oriented decision support tool for project portfolio prototyping (DST4P 3 ). The tool provides a prompt and interactive service to a set of routine queries defined in terms of both direct and inverse resource allocation tasks.
暂无评论