神经网络作为一种新型的优化算法,可以替代自适应均衡算法中的横向滤波器,在数字通信系统中得到了广泛应用。
As a kind of new optimized algorithm, neural network can substitute for landscape orientation filter in adaptive equalization, and it has been widely used in digital communication system.
实验结果表明,此方法在滤除噪声时具有一般神经网络和中值滤波器所没有的优点,精度明显提高。
The proposed method has obvious advantages over other neural networks and median filter in filtering noise, and the precision of results are much higher.
该混频器主要由波导-微带过渡,输入、输出滤波器以及匹配网络和反向并联混频二极管对组成。
The mixer mainly consists of a waveguide-to-microstrip transition, input and output filters, matching networks and an antiparallel diode pair.
该混频器主要由波导一微带过渡,输入、输出滤波器以及匹配网络和三组反向并联混频二极管对组成。
The mixer mainly consists of a waveguide-to-microstrip transition, input and output filters, matching networks and an antiparallel Sckottky-barrier diode pair.
文中给出了一种新的RBF神经网络训练方法,即基于强跟踪滤波器的训练方法。
A new kind of training method of RBF neural network is given, which is a method based on strong tracking filter.
本文提出了一种新颖的基于模糊神经元网络的改进型中值滤波器。
In this paper, a novel improved median filter based on fuzzy neuron network is proposed.
文章将自适应噪声对消技术用于有源滤波器的电流检测,提出了一种基于神经元网络的自适应检测方法。
Using adaptive noise cancelling technology, an adaptive detecting approach of currents based on neural network for active power filter is proposed in this paper.
提出并分析了一种适用于控制并联有源电力滤波器的人工神经网络方法。
An artificial neural network method for control of shunt active power filters is presented and analyzed.
针对混合调制信号,提出了一种基于网络综合的旁瓣抑制方法,设计了异型旁瓣抑制滤波器。
As for the combined signal, the sidelobe suppression method based on network synthesis is put forward and the irregular sidelobe suppression filter is designed.
基于神经网络理论中能量函数的概念,提出了一种自适应IIR滤波器的设计方法。
A design method of adaptive IIR filtering based on the energy function of neural network is presented.
结合网络固有结构理论和模糊意见集中决策,解决了多支路滤波器组集中安装的问题。
The inherent structure theory of networks and concentrated ordering of lumping fuzzy suggestions are combined to solve the centralized placement of multi-branch filter.
本文从空间数字滤波器的角度研究了侧抑制网络的功能。
The lateral inhibitory network was studied as a spatial digital filter.
频率响应也可以由低压微尺寸压控变容器或者变容二极管控制,并且可被例示为与天线模块共存的调谐的谐振匹配滤波器网络。
The frequency response may also be controlled by a low voltage micro sized varicap, or a varactor diode, and instantiated as a tuned, resonant matching filter network residing with the antenna module.
这样,就将这类换能器类比为递归型数字滤波器,并可由数字网络理论分析和模拟换能器。
In this way, this kind of transducer is taken analogous to recursive digital filters, and it is possible to analyse and simulate the transducers based on the theory of digital network.
针对网络控制系统中的无限时间最优方法,设计了一种基于输入变化率的新型滤波器算法。
Aiming at infinite horizon optimal control method, a new filter algorithm based on input rate of change is designed.
在弱湍流情况下,基于自适应最小均方滤波器的系统误码率(BER)低于10 -8,可以满足网络通信的要求。
The bit error ratio (BER) of the system over weak turbulence based on adaptive filter is below 10 ~ (-8), which can satisfy the communication requirement.
仿真结果显示,复合余弦基神经网络图像去噪滤波器各项特性接近理想滤波器。
The simulation results reached nearly ideal filter characteristics, and the performance of removing image noise using this filter was compared with the median filter.
谐振匹配滤波器网络随后可被用于微调该带宽的频率。
The resonant matching filter network may then be used for fine tuning the frequency of that bandwidth.
一种新的基于数字滤波器理论的全互连复值递归神经网络训练方法被提出。
A new training approach for the training algorithm of a fully connected recurrent neural network based on the digital filter theory is proposed.
本文总结了线性调频信号的许多有用特性,讨论了近似于匹配滤波器的压缩网络传递函数。
At the present paper the available properties of the linear FM signal are summed up. And the transfer function of the compression network analogous to a matched filter is discussed.
改进了目前采用的开关电容网络阻抗标度设计法,使模拟滤波器可以用无源开关电容网络完成。
The variable impedance scaling method for design of SCN has been improved in the Paper, the resulting is that the analogue filter can be realized by Passive SCN.
研究一类同时具有时变时延和测量数据丢失的不确定网络化系统的鲁棒无源滤波器设计问题。
The problem of robust passive filtering for a class of uncertain networked system with time varying delays and missing measurements is studied.
为了提高卡尔曼滤波估计精度,提出了一种基于回归神经网络补偿卡尔曼滤波器估计误差的方法。
A method based on recurrent neural network compensation Kalman's evaluation error is proposed in order to enhance the evaluation precision.
本文核心研究LTCC新颖结构蓝牙天线和滤波器的设计及其神经网络辅助设计。
This dissertation focuses on novel Bluetooth antenna and filter in LTCC technology and the neural network-aided design of them.
考虑一类时延网络控制系统,提出了一种具有时延补偿功能的卡尔曼滤波器设计方法,并对系统进行状态估计。
Considering a class of networked control systems with time delays, a novel method was proposed to design Kalman filters with delay compensation, and it was used to estimate the state of the system.
考虑一类时延网络控制系统,提出了一种具有时延补偿功能的卡尔曼滤波器设计方法,并对系统进行状态估计。
Considering a class of networked control systems with time delays, a novel method was proposed to design Kalman filters with delay compensation, and it was used to estimate the state of the system.
应用推荐