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.
In this paper, we propose a novel approach for identity verification based on the directional analysis of velocity-based partitions of an on-line signature. First, inter-feature dependencies in a signature are exploited by decomposing the shape (horizontal trajectory, vertical trajectory) into two partitions based on the velocity profile of the base-signature for each signer, which offers the flexibility...
Locally linear embedding (LLE) is an elegant nonlinear method for feature extraction and manifold learning, which attempt to project the original data into a lower dimensional feature space by preserving the local neighborhood structure. However, LLE algorithm fails when it is directly applied to video with multi-shot. In this paper, video manifold feature is defined firstly, and then using LLE we...
Rolling cart system is a highly nonlinear phenomenon in which links undergo tipping and rolling with no fixed base. This in turn requires that the system running states be predicted correctly. This paper makes a full analysis of the rolling cart states by applying observer-based adaptive wavelet neural network (OBAWNN) tracking sliding mode control scheme with system uncertainties, multiple time-delayed...
The behavior of nonlinearity and time-varying cause the pneumatic actuator systems are difficult to be controlled. This paper proposes a Fourier series-based adaptive sliding-mode controller for nonlinear pneumatic servo systems. The Fourier series-based functional approximation technique can approximate an unknown function, thus bypassing the model-based prerequisite. The learning laws for the coefficients...
Adaptive nonlinear output feedback control of GD-FNN(generalized dynamic fuzzy neural network) for underwater robot motion control using forming filter for wave disturbance is presented. This method completely construct nonlinear and uncertain parts of underwater robot by online adaptive learning algorithm without knowing fuzzy neural structure and training phase in advance. Output feedback control...
In conventional techniques for modeling Pneumatic artificial muscle, there are difficulties such as poor knowledge of the process, inaccurate process or complexity of the resulting mathematical model. Trying to solve these problems, this study investigates the method of establishing the model using a novel network-Echo State Network (ESN). We introduce the mechanism of this net and apply it to our...
In this paper, the neural impedance controller is formulated to regulate the contact force with the environment. When robot uncertainties are present, the performance of the impedance controller is degraded. To compensate for uncertainties in both robot dynamics and environment, neural network is introduced at the desired trajectory. The training signal is defined to satisfy the desired goal. This...
In this paper, adaptive NN (neural network) tracking control is proposed for ocean surface vessels with parametric uncertainties, unknown disturbances and rotary actuators. Based on the Lyapunov synthesis method and backstepping technique, adaptive NN tracking control is developed by incorporating the actuator configuration matrix and considering actuator saturation constraints. In the proposed adaptive...
For the DC chassis dynamometer, a nonlinear mathematical model was established based on the analysis of the transmission system of the DC dynamometer, and an adaptive controller based on RBF NN (radial basis function neural network) was proposed to control a dynamometer to load resistance intelligently to achieve stepless simulation of inertia. By using the Lyapunov synthesis approach, it was proved...
This paper presents a discrete-time variable structure control based on neural networks for a planar robotic manipulator. Radial basis function neural networks are used to learn about uncertainties affecting the system. The learning algorithm combines the growth criterion of the resource allocating network technique with an adaptive extended Kalman filter to update all network parameters. The analysis...
Nowadays, as fuel is an important resource for the whole world, researchers are trying a variety machine learning models for fuel flow prediction in industry, aerospace specifically. Different machine learning models have been applied in different applications. This paper will analyze these applications. Many useful points have been found by comparison of those experimental results.
The Activation and Competition System (ACS), developed by Buscema in 2009 is an original algorithm that can simulate a non linear associative memory, partially inspired by Grossberg's IAC is presented. The Universe Lines Algorithm (ULA) is an extension of ACS and developed in 2010. ULA is able to transform all the variables of an assigned dataset into a group of connected dynamical systems.
A feedforward compensator for rate-dependent hysteresis in piezoelectric actuators (PEA) is proposed. In this method, a model with parallel structure is proposed to approximate both hysteretic behavior and rate-dependent feature of the PEA. In the model, the rate-independent hysteretic performance is approximated by a neural network based on the so called expanded input space method, while the rate-dependent...
In this study, we intend to enhance a tactile display composed of two-axial micro actuators, using tactile illusions such as comb illusion and velvet hand illusion (VHI). The comb illusion causes a feeling of unevenness to the finger surfaces touching a comb's teeth tips by scratching the sides of the teeth. In VHI, a person rubs his/her hands together on either side of wires strung through a frame,...
This paper considers the stabilization of random Boolean networks. We first give a survey on the semi-tensor product approach to Boolean (control) networks, which is a new technique developed by us. Particularly, the stability and stabilization of Boolean (control) networks are reviewed. Then, under the same framework, the topological structure of the random Boolean networks is investigated and revealed...
We investigate the learning issue in the robust adaptive neural-network (NN) control process of manipulator with unknown system dynamics and disturbance. Based on recently developed deterministic theory, the regression vector of an appropriately designed robust adaptive NN controller satisfies the partial persistent exciting (PE) condition when tracking a periodic or periodic-like reference orbit,...
A self-organizing neural sliding mode controller (SONSMC) is presented for trajectory tracking control of multi-link robots with model errors and uncertain disturbances. This approach gives a new global sliding mode manifold for multi-link robots, which enable system trajectory to run on the sliding mode manifold at the start point and eliminate the reaching phase of the conventional sliding mode...
Seizures are defined as manifest of excessive and hypersynchronous activity of neurons in the cerebral cortex and represent a frequent malfunction of the human central nervous system. Therefore, the search for precursors and predictors of a seizure is of utmost clinical relevance and may even guide us to a deep understanding of the seizure generating mechanisms. In this study we analyzed invasive...
For better manipulability, a criterion in the form of a quadratic function is presented for the self-motion planning (SMP) of redundant manipulators with no target-configuration assigned. Such SMP scheme could automatically select the desirable configuration so that the manipulator could be more flexible and maneuverable. As physical limits generally exist in actual redundant manipulators, both joint...
A hybrid control algorithm is proposed based on a backstepping kinematic control and a PID sliding mode dynamic control with an adaptive neural network adjust gain of sliding mode control for trajectory tracking control of nonholonomic mobile robot. Parameters and non-parameter uncertainties of mobile robot can be solved by using the robust control which takes advantages of stability and robustness...
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.