The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
We investigated the emergence of conventions for conflict resolutions in agent networks with various structures through pair wise reinforcement learning. Whereas coordinated agents encounter conflict situations in the course of actions, their resolutions are complex and computationally expensive due to mutual analysis of subsequent actions by both agents and communication costs of the interactions...
This paper presents method used hand gesture recognition in human-computer interaction and control. Nowadays in dataglove-driven motion capture field, researchers preprocess the raw sensor data of the glove with calibration methods for acquiring a high precision in the VR environment. But there are still alternative solutions. Some machine learning algorithms, for example the self-organizing map method,...
Characteristic features of feedforward artificial neural networks, acting as universal function approximators, are presented. The problem under consideration concerns inverse kinematics of a two-link planar manipulator. As shown in the article, a two-layer, feedforward neural network is able to learn the nonlinear mapping between the end-effector position domain and the joint angle domain of the manipulator...
In human body pose estimation, manifold learning is a popular technique for reducing the dimension of 2D images and 3D body configuration data. This technique, however, is especially vulnerable to silhouette variation such as caused by viewpoint changes. In this paper, we propose a novel approach that combines three separate manifolds for representing variations in viewpoint, pose and 3D body configuration...
The CMAC-based algorithm of critics & strategists is proposed in this article for application on robot tracking control. This tracking controller comprises position tracking controller and angle tracking controller, whose outputs are line rotation speed control value and angle control value respectively. Both of them include in two CMAC controllers dealing with online weight value adjustment through...
We present an innovative multi-robot communication idea of generic message interpretation system based on updated feed forward network (FFN). A message is passed using demonstration by robotic arm. Recurrent network model RNM is used to learn complex tasks' demonstration then simply learning action sequences; RNM comes with the limitations of time efficiency, storage and provides a rigid structure...
This paper presents a discrete-time decentralized control scheme for identification and trajectory tracking of a two degrees of freedom (DOF) robot manipulator. A recurrent high order neural network (RHONN) structure is used to identify the plant model and based on this model, a discrete-time control law is derived, which combines discrete-time block control and sliding modes techniques. The neural...
In this paper, we deal with the problem of inefficient context modules of recurrent networks (RNs), which form the basis of think aloud: a strategy for imitation. Learning from observation provides a fine way for knowledge acquisition of demonstrated task. In order to learn complex tasks then simply learning action sequences, strategy of think aloud imitation learning applies recurrent network model...
This paper deals with adaptive trajectory tracking for discrete-time MIMO nonlinear systems. A high order neural network (HONN) is used to approximate a decentralized control law designed by the backstepping technique as applied to a block strict feedback form (BSFF). The HONN learning is performed online by an Extended Kalman Filter (EKF) algorithm. The proposed scheme is implemented in real-time...
This paper presents implementation of a neural chip to proceed neural processing of the radial basis function (RBF) network. RBF network along with a primary PD controller is trained in on-line fashion. Radial basis function network processing is embedded on a field programmable gate array(FPGA) chip to achieve real-time control. To enable nonlinear function calculation, a floating point processor...
The aim of the present study is to validate a 2D kinematic model of human body in providing considerable features that they could be used for human actions classification. Human motion can be termed as a non-rigid, articulated motion, with body parts being piecewise rigid, held together by joints. The presented approach uses the fact that the human body has certain anthropometric proportion and uses...
This paper presents a discrete-time decentralized control scheme for identification and trajectory tracking of a five degrees of freedom (DOF) robot manipulator. A recurrent high order neural network (RHONN) structure is used to identify the robot model, and based on this model a discrete-time control law is derived, which combines discrete-time block control and sliding modes techniques. The neural...
Working conditions are monitoring parameters are huge and neural network learning time too long in the condition monitoring of multi word condition equipment. To improve monitoring efficiency, a joint rough set attribute reduction (RSAR) and Fuzzy ART (adaptive resonance theory) neural network method is proposed in this study. The dimension of an input vector to Fuzzy ART neural networks can be reduced...
Our parallel typed two-axial actuator was composed of two bimorph piezoelectric elements and two small links connected by three joints. We formulated kinematics for the parallel typed two-axial actuator because the endpoint is controlled in the two-dimensional coordinate. Since relationship between applied voltage and displacement cause by the voltage shows a hysteresis loop in the bimorph piezoelectric...
The overfitting is a problem of fundamental significance with great implications in the applications of neural network. To avoid overfitting, cross-validation has been proposed. However, in many cases the training set is too small so that cross-validation cannot be applied. Aiming at the problem, a new validation method based on expanded training sets is proposed in this paper. Experimental results...
A neural sliding mode controller is presented for trajectory tracking control of multi-link robots with uncertain external disturbances and system model errors. This approach gives a new global sliding mode manifold for the second-order multi-link robots, which enable system trajectory to run on the sliding mode manifold at the initial states and eliminate the reaching phase of conventional sliding...
Traditional connectionist models place an emphasis on learned weights. Based on neurobiological evidence, a new approach is developed and experimentally shown to be more robust for disambiguating novel combinations of stimuli. It does not require variable weights and avoids many training related issues. This approach is compared with traditional weight-learning methods. The network is better able...
In this paper, we propose a new kernel discriminant analysis using composite vectors (C-KDA). We show that employing composite vectors is similar to using more samples by analysis, which is a great advantage in classification problems when the size of training samples is small. Motivated by this, we apply composite vectors to kernel-based methods, which may have overfitting problems when training...
In various studies, it has been demonstrated that combining the decisions of multiple classifiers can lead to better recognition results. Plurality voting is one of the most widely used combination strategies. In this paper, we both theoretically and experimentally analyze the performance of a plurality voting-based ensemble classifier. Theoretical expressions for system performance are derived as...
High-dimension cerebellar model articulation controller with general basis function (CMAC_GBF) is developed and its learning convergence is also proved in this study. Up till now, the applications of CMAC are mainly used as controller or system identification (function mapping). Due to the guaranteed convergence and learning speed of CMAC, all the applications have shown good performance. But for...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.