作者：
Ren, DaoSha, JinNanjing Univ
Sch Elect Sci & Engn Nanjing 210046 Jiangsu Peoples R China Nanjing Univ
Shenzhen Res Inst Nanjing 210046 Jiangsu Peoples R China
Low-Density Parity-Check (LDPC) codes have capacity-approaching error-correction performance which makes them popular in communication system. gradientdescent bit flipping (GDBF) algorithms show an error correction c...
详细信息
Low-Density Parity-Check (LDPC) codes have capacity-approaching error-correction performance which makes them popular in communication system. gradientdescent bit flipping (GDBF) algorithms show an error correction capability superior to most known BF algorithms. In this paper, we propose an improved gradientdescent bit flipping (IGDBF) algorithm for LDPC codes on BSC channel. Compared to GDBF algorithm, the proposed algorithm reconstructs the composition of energy function, and adds a penalty term to help it converge. Simulations show that the proposed algorithm has good performance and fast convergence rate.
Attitude estimation methods provide modern consumer, industrial, and space systems with an estimate of a body orientation based on noisy sensor measurements. The gradient descent algorithm is one of the most recent me...
详细信息
Attitude estimation methods provide modern consumer, industrial, and space systems with an estimate of a body orientation based on noisy sensor measurements. The gradient descent algorithm is one of the most recent methods for optimal attitude estimation, whose iterative nature demands adequate adjustment of the algorithm parameters, which is often overlooked in the literature. Here, we present the effects of the step size, the maximum number of iterations, and the initial quaternion, as well as different propagation methods on the quality of the estimation in noiseless and noisy conditions. A novel figure of merit and termination criterion that defines the algorithm's accuracy is proposed. Furthermore, the guidelines for selecting the optimal set of parameters in order to achieve the highest accuracy of the estimate using the fewest iterations are proposed and verified in simulations and experimentally based on the measurements acquired from an in-house developed model of a satellite attitude determination and control system. The proposed attitude estimation method based on the gradient descent algorithm and complementary filter automatically adjusts the number of iterations with the average below 0.5, reducing the demand on the processing power and energy consumption and causing it to be suitable for low-power applications.
Multispectral transmission imaging is widely recognized as a developmental approach for early breast cancer screening. However, a persistent challenge exists in image registration, particularly in processing human ima...
详细信息
Multispectral transmission imaging is widely recognized as a developmental approach for early breast cancer screening. However, a persistent challenge exists in image registration, particularly in processing human images, where registration often relies solely on single-wavelength information, leading to inadequate accuracy. This paper purposes a novel image registration method that involves summing pixel values from three color channels at identical pixel coordinates and utilizes an improved gradient descent algorithm to achieve image registration. Multispectral maps at wavelengths of 445 nm, 520 nm, and 620 nm serve as examples for testing and evaluation, with frames summed for registered images at each wavelength. Experimental results demonstrate the superior registration accuracy of this method compared to registering images of a single-wavelength independently. This advancement enhances the accuracy and reliability of multispectral transmission imaging in the early detection of breast cancer.
Proportional Integral and Derivative (PID) controller tuning is one of the most important factors in control systems engineering for achieving an efficient and desired system performance. There are many tuning methods...
详细信息
Proportional Integral and Derivative (PID) controller tuning is one of the most important factors in control systems engineering for achieving an efficient and desired system performance. There are many tuning methods available but in this article, Ziegler-Nichols (ZN) tuning method is proposed to determine the gain values ( K p , K i and K d ) of PID controller based on system behaviour. The ZN method is a heuristic and popular technique especially intended for PID controller tuning because of its advantages which are simple design, fast and perfect tuning, good reliability and mostly used in industrial applications. The speed response of Permanent Magnet Synchronous Motor (PMSM) is enhanced using PID controller tuned by proposed method. The PMSM is predominantly used in Electric Vehicles (EV), electric traction and industrial drive applications. The ZN method provides the distinctive dynamic speed response and also analyzes peak overshoot, settling time and steady-state error which are 1.677 %, 1.133 s and 1.16 times respectively, compared to the gradientdescent (GD) algorithm. In this article, the proposed ZN-PID controller is tuned offline and used in both outer and inner feedback loops to control the speed and torque respectively. This work primarily depends on transfer function model based Field Oriented Control (FOC) approach using MATLAB R2019b/Simulink software. The proposed ZN-PID controller improves the speed response of PMSM in terms of time domain specifications over existing GD-PID controller. The MATLAB R2019b/Simulation work is done and also tested the stability analysis with Bode plot. The hardware results are compared with MATLAB/Simulation results.
A new learning technique for local linear wavelet neural network (LLWNN) is presented in this paper. The difference of the network with conventional wavelet neural network (WNN) is that the connection weights between ...
详细信息
A new learning technique for local linear wavelet neural network (LLWNN) is presented in this paper. The difference of the network with conventional wavelet neural network (WNN) is that the connection weights between the hidden layer and output layer of conventional WNN are replaced by a local linear model. A hybrid training algorithm of Error Back propagation and Recursive Least Square (RLS) is introduced for training the parameters of LLWNN. The variance and centers of LLWNN are updated using back propagation and weights are updated using Recursive Least Square (RLS). Results on extracted breast cancer data from University of Wisconsin Hospital Madison show that the proposed approach is very robust, effective and gives better classification.
This article investigates the distributed secure state estimation problem of distributed systems where a set of agents estimates the state cooperatively in the presence of malicious agents. First, a sufficient conditi...
详细信息
This article investigates the distributed secure state estimation problem of distributed systems where a set of agents estimates the state cooperatively in the presence of malicious agents. First, a sufficient condition for the solvability of the distributed secure state estimation problem is proposed. Second, based on the obtained condition, a distributed switched gradientdescent (DSGD) algorithm is designed to solve the considered problem which is transformed into a distributed optimization problem. With the help of a candidate-removal mechanism, the proposed DSGD algorithm successfully generates reliable state estimates despite malicious agents. Finally, the effectiveness of the proposed algorithm is illustrated by a numerical example.
A mixture model with spatial constraint is proposed for image segmentation. This model assumes that the pixel label priors are similar if the pixels are close in geometry. An energy function is defined on the spatial ...
详细信息
A mixture model with spatial constraint is proposed for image segmentation. This model assumes that the pixel label priors are similar if the pixels are close in geometry. An energy function is defined on the spatial space for measuring the spatial information. We also derive an energy function on the observed data space from the log-likelihood function of the standard mixture model. We estimate the model parameters by minimizing the combination of the two energy functions, using the gradient descent algorithm. Then we use the parameters to compute the posterior probability. Finally, each pixel can be assigned to a class using the maximum a posterior decision rule. Numerical experiments are presented where the proposed method and other mixture model-based methods are tested on synthetic and real-world images. These experimental results demonstrate that the proposed method achieves competitive performance compared with other spatially constrained mixture model-based methods. (C) 2016 SPIE and IS&T
The development of an effective maximum power point tracking (MPPT) algorithm is important in order to achieve maximum power operation in a photovoltaic system (PV). In this study, a direct neural control (DNC) scheme...
详细信息
The development of an effective maximum power point tracking (MPPT) algorithm is important in order to achieve maximum power operation in a photovoltaic system (PV). In this study, a direct neural control (DNC) scheme is developed. The intelligent MPPT controller consists of a hybrid learning mechanism;an on-line learning rule based on gradient decent method and an off-line learning rule based on BigBang-Big Crunch (BB-BC) algorithm. The effectiveness of the proposed system is tested under partial shading conditions by applying the cascaded converter topology. The feasibility of the DNC is evaluated by the simulation results and compared to the conventional perturbation and observation (P&O) method. (C) 2015 Elsevier B.V. All rights reserved.
The conventional back-propagation algorithm is basically a gradient-descent method, it has the problems of local minima and slow convergence. A new generalized back-propagation algorithm which can effectively speed up...
详细信息
The conventional back-propagation algorithm is basically a gradient-descent method, it has the problems of local minima and slow convergence. A new generalized back-propagation algorithm which can effectively speed up the convergence rate and reduce the chance of being trapped in local minima is introduced. The new back-propagation algorithm is to change the derivative of the activation function so as to magnify the backward propagated error signal, thus the convergence rate can be accelerated and the local minimum can be escaped. In this letter, we also investigate the convergence of the generalized back-propagation algorithm with constant learning rate. The weight sequences in generalized back-propagation algorithm can be approximated by a certain ordinary differential equation (ODE). When the learning rate tends to zero, the interpolated weight sequences of generalized back-propagation converge weakly to the solution of associated ODE.
An effective approach is developed to establish affine Takagi-Sugeno (T-S) fuzzy model for a given nonlinear system from its input-output data. Firstly, the fuzzy c-regression model (FCRM) clustering technique is appl...
详细信息
An effective approach is developed to establish affine Takagi-Sugeno (T-S) fuzzy model for a given nonlinear system from its input-output data. Firstly, the fuzzy c-regression model (FCRM) clustering technique is applied to partition the product space of the given input-output data into hyper-plan-shaped clusters. Each cluster is essentially a basis of the fuzzy rule that describes the system behaviour, and the number of clusters is just the number of fuzzy rules. Particularly, a novel cluster validity criterion for FCRM is set up to choose the appropriate number of clusters (rules). Once the number of clusters is determined, the consequent parameters of each IF-THEN rule are directly obtained from the functional cluster representatives (affine linear functions). The antecedent fuzzy sets of each IF-THEN fuzzy rule are acquired by projecting the fuzzy partitions matrix U onto the axes of individual antecedent variable to obtain point-wise defined fuzzy sets and to approximate these point-wise defined fuzzy sets by normal bell-shaped membership functions. Additionally, a check and repartition algorithm is suggested to prevent the inappropriate premise structure where separate regions of data shared the same regression model. Finally, the gradient descent algorithm is included to adjust the fuzzy model precisely. An affine T-S fuzzy model with compact IF-THEN rules could thus be generated systematically. Several simulation examples are provided to demonstrate the accuracy and effectiveness of the affine T-S fuzzy modelling algorithm.
暂无评论