The important role that mammography is playing in breast cancer detection can be attributed largely to the technical improvements and dedication of radiologists to breast imaging. A lot of work is being done to ensure...
详细信息
The important role that mammography is playing in breast cancer detection can be attributed largely to the technical improvements and dedication of radiologists to breast imaging. A lot of work is being done to ensure that these diagnosing steps are becoming smoother, faster and more accurate in classifying whether the abnormalities seen in mammogram images are benign or malignant. This paper takes a step in that direction by introducing a hybrid evolutionary neural network classifier (HENC) combining the evolutionary algorithm, which has a powerful global exploration capability, with gradient-based local search method, which can exploit the optimum offspring to develop a diagnostic aid that accurately differentiates malignant from benign pattern. The computational experiments show that the presented HENC approach can obtain better generalization and much lower computational cost than the existing methods reported recently in the literature using the widely accepted Wisconsin breast cancer diagnosis (WBCD) database with some improvements.
This paper presents a decision support tool for the effectiveness of a Quality Management System (QMS) in a company. To develop this tool, a new approach PAHP based on the combination of the Pareto Optimality Concept ...
详细信息
In this article, we investigate the synchronization of robot manipulators group under coordinated and cooperative scheme. In cooperative schemes all agents were fully interconnected, such that all robots have a weight...
详细信息
In this article, we investigate the synchronization of robot manipulators group under coordinated and cooperative scheme. In cooperative schemes all agents were fully interconnected, such that all robots have a weight on the overall dynamics. In the coordinated schemes the leader robot or the master robot establishes the synchronized action of all the slave systems. Based on emergent consensus algorithm, the proposed controller works to position synchronization of multiple robot manipulators. The control strategy is to synchronize the angular position and the velocity of each robot in the system with respect to the common desired trajectory and the angular positions and velocities of other robots. Modeled by an undirected graph, the cooperative robots network only requires local neighbor-to-neighbor information exchange between manipulators and does not assume the existence of an explicit leader in the team. However the objective in coordinated scheme is to design interconnections and feedback controllers for the slaves, such that their positions and velocities synchronize to those of the leader robot. It is assumed that network robots have the same number of joints and any configuration made possible by one in the group can be completed by each robot in the cooperative system.
This paper presents a method to compute optimal control strategies of discrete large scale nonlinear systems by using hierarchical fuzzy systems. The method is based on the decomposition principle of the global system...
详细信息
This paper presents a method to compute optimal control strategies of discrete large scale nonlinear systems by using hierarchical fuzzy systems. The method is based on the decomposition principle of the global system into interconnected subsystems becoming easier to study. Then, the differential dynamic programming procedure is applied in order to obtain the rule basis. After that, we construct limpid-hierarchical Mamdani fuzzy system in order to compute optimal control laws, for each subsystem. Simulation results of a rotary crane show that the proposed method yields to satisfactory performances. The robustness of the proposed approach is verified.
We address the problem of designing decentralized laws to control a team of general fully actuated manipulators which synchronize their movements while following the same desired trajectory. To this effect we investig...
详细信息
We address the problem of designing decentralized laws to control a team of general fully actuated manipulators which synchronize their movements while following the same desired trajectory. To this effect we investigate an adaptive control of an identical multiple manipulators, with unknown inertia parameters, tracking a common trajectory. It is also assumed that all the robots in the synchronization system have the same number of joints and equivalent joint work spaces, i.e. any possible configuration of a given robot in the system can be achieved by any other robot in the system. Adaptive controls are derived for group of manipulators using a consensus algorithm. This consensus algorithm is applied on the group level to estimate the time-varying group trajectory information in a distributed manner. The proposed strategy only requires local neighbor-to-neighbor information exchange between manipulators and does not assume the existence of any explicit leaders in the team. The interaction topology of a network of agents is represented using an indirected graph. The coordination strategy is to let each manipulator track its desired trajectory while synchronizing its motion with the others manipulator's motions so that differential position errors amongst robots converge to zero.
In this paper, we present a dynamic redundancy resolution technique for mobile manipulators using a position fuzzy controller. First, the dynamic model of the mobile manipulator in feasible motion space is given. Next...
详细信息
ISBN:
(纸本)9781424443451
In this paper, we present a dynamic redundancy resolution technique for mobile manipulators using a position fuzzy controller. First, the dynamic model of the mobile manipulator in feasible motion space is given. Next, a control algorithm is proposed which resolve the redundancy by decoupling the motion of the system into the end-effector motion in the task space and an internal motion in the null space and controls them in prioritized basis with priority given to the primary task. In order to achieve a good end-effector trajectory tracking, a position fuzzy controller is used to provide the torques needed to move the end-effector along the desired trajectory. Simulation results are given to illustrate the coordination of two subsystems in executing the desired trajectories.
In this paper, we present a dynamic redundancy resolution technique for mobile manipulators using a position fuzzy controller. First, the dynamic model of the mobile manipulator in feasible motion space is given. Next...
详细信息
In this paper, we present a dynamic redundancy resolution technique for mobile manipulators using a position fuzzy controller. First, the dynamic model of the mobile manipulator in feasible motion space is given. Next, a control algorithm is proposed which resolve the redundancy by decoupling the motion of the system into the end-effector motion in the task space and an internal motion in the null space and controls them in prioritized basis with priority given to the primary task. In order to achieve a good end-effector trajectory tracking, a position fuzzy controller is used to provide the torques needed to move the end-effector along the desired trajectory. Simulation results are given to illustrate the coordination of two subsystems in executing the desired trajectories.
The paper deals with the controllability study of a subclass of juggling systems, named linear juggler. It comes that despite the simple representation of such systems, their controllability is in general not easy to ...
详细信息
The paper deals with the controllability study of a subclass of juggling systems, named linear juggler. It comes that despite the simple representation of such systems, their controllability is in general not easy to establish, since they remain highly nonlinear dynamical systems. In this paper we are interested in the controllability properties of one degree of freedom linear juggling system.
Obstacle avoidance and path planning are the most important problems in mobile robots. Besides, finding methods for controlling and decreasing the real robot error in path have been another target for researchers inve...
详细信息
Obstacle avoidance and path planning are the most important problems in mobile robots. Besides, finding methods for controlling and decreasing the real robot error in path have been another target for researchers investigation. Usual methods have two separated parts, research target and path planning with obstacle avoidance. In this context, a fuzzy logic controller has been constructed in order to train an intelligent robot. Genetic algorithms are used to optimize the consequences of a Sugeno fuzzy logic optimal controller for the mobile robot navigation. This is to search a target in an environment with and without obstacles. Simulation results verify successful applications of method for real motion situations. An application have been effected in the Khepera robot demonstrating. The Khepera robot can go to the goal and avoid the obstacles successfully.
An adaptive fuzzy controller is constructed from a collection of fuzzy IF-THEN rules whose parameters are changed or adapted according to adaptive laws for the purpose of controlling a nonlinear plant to track a refer...
详细信息
An adaptive fuzzy controller is constructed from a collection of fuzzy IF-THEN rules whose parameters are changed or adapted according to adaptive laws for the purpose of controlling a nonlinear plant to track a reference trajectory. The fuzzy adaptive control is composed in two classes: direct and indirect one. The indirect fuzzy adaptive controller will be designed through two steps. The first one consists in the construction of a controller based on linguistic description about the unknown plant from human expert. To guaranty stability, a supervisory controller is added. The second step adjusts, on line, the parameters of the fuzzy controller based on the gradient descend. To ensure the robustness, fuzzy controller parameters are adjusted, on line, by a robust gradient descent method. Simulation results show the effectiveness of proposed algorithms in tracking of the inverse pendulum output.
暂无评论