Evolutionary Extreme Learning Machine and Its Application to Image Analysis

Extreme learning machine (ELM) and evolutionary ELM (E-ELM) were proposed as a new class of learning algorithm for single-hidden layer feedforward neural network (SLFN). In order to achieve good generalization performance, E-ELM calculates the error on a subset of testing data for parameter optimization. Since E-ELMemploys extra data for validation to avoid the overfitting problem, more samples are needed for model training. In this paper, the cross-validation strategy is proposed to be embedded into the training phase so as to solve the overtraining problem. Based on this new learning structure, two extensions of E-ELM are introduced. Experimental results demonstrate that the proposed algorithms are efficient for image analysis.     

Aero-optic imaging deviation prediction based on ISSA-ELM

When the aircraft is moving at high speed in the atmosphere, aero-optical imaging deviation will appear due to the influence of aero-optical effect. In order to achieve real-time compensation during the flight of the aircraft, it is necessary to analyze and predict the obtained imaging deviation data. In order to improve the search speed and accuracy of the prediction algorithm and the ability to jump out of local optimum, in this paper, an improved sparrow search algorithm optimized extreme learning machine (ISSA-ELM) neural network model is proposed to predict the aero-optical imagine deviation. Finally, the performance of ISSA-ELM, ELM neural network and SSA-ELM neural network was tested. The results showed that compared with ELM and SSA-ELM algorithms, the convergence speed of ISSA-ELM was significantly enhanced, and the accuracy of data prediction was also significantly improved.     

Fading Channel Prediction for Mobile Radio Adaptive Transmission Systems

Adaptive transmission methods can potentially aid the achievement of high data rates required for mobile radio multimedia services. To realize this potential, the transmitter needs accurate channel state information (CSI) for the upcoming transmission frame. In most mobile radio systems, the CSI is estimated at the receiver and fed back to the transmitter. However, unless the mobile speed is very low, the estimated CSI cannot be used directly to select the parameters of adaptive transmission systems, since it quickly becomes outdated due to the rapid channel variation caused by multipath fading. To enable adaptive transmission for mobile radio systems, prediction of future fading channel samples is required. Several fundamental issues arise in the design and testing of fading prediction algorithms for adaptive transmission systems. These include complexity, robustness, choice of an appropriate channel model for algorithm validation, channel estimation and noise reduction required for reliable prediction, and design and analysis of adaptive transmission methods aided by fading prediction algorithms. We use these criteria in the review of recent advances in the area of fading channel prediction. We also demonstrate that reliable fading prediction makes adaptive transmission feasible in diverse wireless communication systems.     

一种新型的基于深度学习的时变信道预测方法

针对高速移动正交频分复用系统,提出了一种新型的基于深度学习的时变信道预测方法。为了避免网络参数随机初始化造成的影响,本文方法首先基于数据与导频信息获取较理想的信道估计,利用其对BP神经网络进行预训练处理,以获取理想的网络初始参数;然后,基于预训练获取网络初始值,利用基于导频获取的信道估计对BP神经网络进行再次训练,以获取最终的信道预测网络模型;最后,本文方法基于该预测网络模型通过线上预测实现了时变信道的单时刻与多时刻预测。仿真结果表明,本文方法可以显著地提高时变信道预测精度,且具有较低的计算复杂度。     

基于BP神经网络的飞行参数估测方法

对传统BP神经网络算法中收敛速度慢和存在局部极小点的问题进行了研究，提出了网络结构的改进方案和优化算法，提高了网络学习速度和预测精度；应用到飞行参数估测问题中，具有算法稳定、估测精确和动态自适应的特点。     

Network traffic prediction model based on improved VMD and PSO-ELM

The rapid update of computing power leads to exponential data traffic growth, and the incidence of network attacks is also increasing. It is significantly important to analyze and predict network traffic accurately in the early stage and take corresponding preventive measures. The existing network flow integrated forecasting models still have some bottlenecks that are difficult to solve, for example, the slow optimization speed of modal decomposition parameters, easy falling into local optimal solutions, the slow convergence speed of the training process, and poor generalization capability. In this paper, particle swarm optimization (PSO) is utilized to improve the parameters selection process of the variational mode decomposition (VMD) algorithm and the extreme learning machine (ELM) algorithm. First, the PSO-VMD combined with multi-scale permutation entropy (MPE) is utilized to decompose the original network flow, and multiple eigenmode components are obtained. Second, the PSO-ELM is utilized to train the network traffic prediction model, and the PSO parameters in PSO-ELM are updated through adaptive weight adjustment and synchronous learning factors to increase the training and prediction speed, and the component prediction results are reconstructed to get a high-precision network flow forecasting result. Finally, through the prediction and verification of the public network flow data of the WIDE backbone, the result of this experiment indicates that the VMD-PSO-ELM can break through the bottlenecks of slow optimization speed of VMD decomposition parameters, reduce the computational complexity of ELM, accelerate the convergence speed, and increase the forecasting accuracy.     

高速铣削工件表面粗糙度遗传-BP神经网络建模

遗传算法作为一种高效,并行的全局搜索优化方法,非常适合用于BP神经网络学习率的优化。文中通过基于遗传算法和BP神经网络提出了遗传-BP神经网络。以实验1、实验2、实验5、实验6、实验9、实验11、实验13和实验15下的高速铣削试验数据构建用于高速铣削工件表面粗糙度建模的训练样本对,并用回归的高速铣削工件表面粗糙度预测模型对实验3和实验7状态中的高速铣削工件表面粗糙度进行预测。通过比较表面粗糙度预测结果和实际结果,发现遗传-BP神经网络在高速铣削工件表面粗糙度进行建模方面是一种十分有效的方法。     

Artificial Neural Network Channel Estimation Based on Levenberg-Marquardt for OFDM Systems

The many advantages responsible for the widespread application of orthogonal frequency division multiplexing (OFDM) systems are limited by the multipath fading. In OFDM systems, channel estimation is carried out by transmitting pilot symbols generally. In this paper, we propose an artificial neural network (ANN) channel estimation technique based on levenberg-marquardt training algorithm as an alternative to pilot based channel estimation technique for OFDM systems over Rayleigh fading channels. In proposed technique, there are no pilot symbols which added to OFDM. Therefore, this technique is more bandwidth efficient compared to pilot-based channel estimation techniques. Also, this technique is making full use of the learning property of neural network. By using this feature, there is no need of any matrix computation and the proposed technique is less complex than the pilot based techniques. Simulation results show that ANN based channel estimator gives better results compared to the pilot based channel estimator for OFDM systems over Rayleigh fading channel.     

基于BP神经网络的OFDM系统信道估计

针对正交频分复用(Orthogonal Frequency Division Multiplexing,OFDM)系统中传统信道估计算法复杂度高或估计精度低的问题,给出一种基于反向传播(Back Propagation,BP)神经网络的信道估计方法.采用Simulink仿真工具构建OFDM信号采集平台,建立了基于BP神经网络的OFDM系统信道估计模型,并以均方误差和误码率为主要评价指标,分析了不同网络参数和导频数量对信道估计性能的影响.仿真结果表明,与传统信道估计算法相比,基于BP神经网络的信道估计算法可以提供更优的系统性能,而且可以减少导频数量,提高频带利用率.     

Mobile speed estimation for broadband wireless communications over Rician fading channels

In this paper, a new algorithm is proposed to estimate mobile speed for broadband wireless communications, which often encounter large number of fading channel taps causing severe intersymbol interference. Different from existing algorithms, which commonly assume that the fading channel coefficients are available for the speed estimators, the proposed algorithm is based on the received signals which contain unknown transmitted data, unknown frequency selective fading channel coefficients possibly including line-of-sight (LOS) components, and random receiver noise. Theoretical analysis is first carried out from the received signals, and a practical algorithm is proposed based on the analytical results. The algorithm employs a modified normalized auto-covariance of received signal power to estimate the speed of mobiles. The algorithm works well for frequency selective Rayleigh and Rician channels. The algorithm is very resistant to noise, it provides accurate speed estimation even if the signal-to-noise ratio (SNR) is as low as 0 dB. Simulation results indicate that the new algorithm is very reliable and effective to estimate mobile speed corresponding to a maximum Doppler up to 500 Hz. The algorithm has high computational efficiency and low estimation latency, with results being available within one second after communication is established.     

Cloud security situation prediction method based on grey wolfoptimization and BP neural network

Aiming at the accuracy and error correction of cloud security situation prediction, a cloud security situation prediction method based on grey wolf optimization (GWO) and back propagation (BP) neural network is proposed.Firstly, the adaptive disturbance convergence factor is used to improve the GWO algorithm, so as to improve theconvergence speed and accuracy of the algorithm. The Chebyshev chaotic mapping is introduced into the positionupdate formula of GWO algorithm, which is used to select the features of the cloud security situation prediction dataand optimize the parameters of the BP neural network prediction model to minimize the prediction output error.Then, the initial weights and thresholds of BP neural network are modified by the improved GWO algorithm toincrease the learning efficiency and accuracy of BP neural network. Finally, the real data sets of Tencent cloudplatform are predicted. The simulation results show that the proposed method has lower mean square error (MSE)and mean absolute error (MAE) compared with BP neural network, BP neural network based on genetic algorithm(GA-BP), BP neural network based on particle swarm optimization (PSO-BP) and BP neural network based onGWO algorithm (GWO-BP). The proposed method has better stability, robustness and prediction accuracy.     

Deep learning-based channel estimation for wireless ultraviolet MIMO communication systems

To solve the problems of pulse broadening and channel fading caused by atmospheric scattering and turbulence, multiple-input multiple-output(MIMO) technology is a valid way. A wireless ultraviolet(UV) MIMO channel estimation approach based on deep learning is provided in this paper. The deep learning is used to convert the channel estimation into the image processing. By combining convolutional neural network(CNN) and attention mechanism(AM), the learning model is designed to extract the depth f...     

Extreme learning machine approach for sensorless wind speed estimation

Precise predictions of wind speed play important role in determining the feasibility of harnessing wind energy. In fact, reliable wind predictions offer secure and minimal economic risk situation to operators and investors. This paper presents a new model based upon extreme learning machine (ELM) for sensor-less estimation of wind speed based on wind turbine parameters. The inputs for estimating the wind speed are wind turbine power coefficient, blade pitch angle, and rotational speed. In order to validate authors compared prediction of ELM model with the predictions with genetic programming (GP), artificial neural network (ANN) and support vector machine with radial basis kernel function (SVM-RBF). This investigation analyzed the reliability of these computational models using the simulation results and three statistical tests. The three statistical tests includes the Pearson correlation coefficient, coefficient of determination and root-mean-square error. Finally, this study compared predicted wind speeds from each method against actual measurement data. Simulation results, clearly demonstrate that ELM can be utilized effectively in applications of sensor-less wind speed predictions. Concisely, the survey results show that the proposed ELM model is suitable and precise for sensor-less wind speed predictions and has much higher performance than the other approaches examined in this study.     

Channel estimation and long-range prediction of fast fading channels for adaptive OFDM system

This correspondence presents the channel estimation and long-range prediction technique for adaptive-orthogonal-frequency-division-multiplexing (AOFDM) system. The efficient channel loading is accomplished by feeding the accurately predicted channel-state-information (CSI) back to transmitter. The frequency-selective wireless fading channel is modelled as a tapped-delay-line-filter governed by a first-order autoregressive (AR1) process; and an adaptive channel estimator based on the generalised-variable-step-size least-mean-square (GVSS-LMS) algorithm tracks AR1 correlation coefficient. To compensate for the signal fading due to channel state variations, a modified-Kalman-filter (MKF)-based channel estimator is utilised. In addition, channel tracking is also performed for predicting future CSI at receiver, based on the numeric-variable-forgetting-factor recursive-least-squares (NVFF-RLS) algorithm. Subsequently, adaptive bit allocation for AOFDM system is employed by using predicted CSI at transmitter. Here, the proposed combination of GVSS-LMS and MKF algorithms for robust channel estimation and the NVFF-RLS algorithm for efficient channel prediction is incorporated. The performance validation of presented method is carried out by using different channel realisations through simulation, and also by comparing it with fixed step-size LMS, MKF and fixed forgetting-factor RLS algorithm based conventional techniques. Eventually, the reliable performance of underlying AOFDM system can be achieved in terms of the lower mean squared estimation/prediction errors and alleviated symbol error rate.     

基于组合模型的短时交通流量预测算法

交通流量预测是实现智能交通技术的核心问题,及时准确地预测道路交通流量是实现动态交通管理的前提,短时交通流量的预测是交通流量预测的重要组成部分。该文针对十字路口的短时交通流量预测问题设计了基于交通流量序列分割和极限学习机(Extreme Learning Machine, ELM)组合模型的交通流量预测算法(Traffic Flow Prediction Based on Combined Model, TFPBCM)。该算法首先采用K-means对交通流量数据在时间上进行序列分割,然后采用ELM对各个序列进行建模和预测。仿真实验证明,与单一的BP(Back Propagation)神经网络和ELM相比,该组合模型算法建模时间为BP的1/10, ELM建模时间的4倍,均方误差为BP的1/50, ELM的1/20,该组合模型算法决定系数R2更接近于1,模型可信度更高。     

极端学习机在立体图像质量客观评价中的应用

基于传统神经网络训练速度慢、易陷入局部极小值和泛化性能低等问题,提出采用极端学习机(ELM,extreme learning machine)对立体图像质量进行了客观评价。ELM是单隐层前馈神经网络(SLFNs)的泛化,输入权重可以随机赋值并通过解析获得输出权值。与传统神经网络算法相比,ELM算法具有参数选择简单、学习速度快及泛化性能好等优点。实验结果表明,以sigmoid为激励函数,对241幅不同等级的立体图像测试样本进行测试,其正确等级分类率达到93.85%。研究了不同激励函数条件下不同隐藏层节点数对极端学习机网络性能的影响,且将ELM和传统BP及支持向量机(SVM)在立体图像质量评价中的性能进行了分析比较。     

Joint MAP channel estimation and data detection for OFDM in presence of phase noise from free running and phase locked loop oscillator

This paper addresses a computationally compact and statistically optimal joint Maximum a Posteriori (MAP) algorithm for channel estimation and data detection in the presence of Phase Noise (PHN) in iterative Orthogonal Frequency Division Multiplexing (OFDM) receivers used for high speed and high spectral efficient wireless communication systems. The MAP cost function for joint estimation and detection is derived and optimized further with the proposed cyclic gradient descent optimization algorithm. The proposed joint estimation and detection algorithm relaxes the restriction of small PHN assumptions and utilizes the prior statistical knowledge of PHN spectral components to produce a statistically optimal solution. The frequency-domain estimation of Channel Transfer Function (CTF) in frequency selective fading makes the method simpler, compared with the estimation of Channel Impulse Response (CIR) in the time domain. Two different time-varying PHN models, produced by Free Running Oscillator (FRO) and Phase-Locked Loop (PLL) oscillator, are presented and compared for performance difference with proposed OFDM receiver. Simulation results for joint MAP channel estimation are compared with Cramer-Rao Lower Bound (CRLB), and the simulation results for joint MAP data detection are compared with “NO PHN” performance to demonstrate that the proposed joint MAP estimation and detection algorithm achieve near-optimum performance even under multipath channel fading.     

基于神经网络的业务量预测研究

分别采用back—propagation（BP）算法和Favidon最小二乘学习算法训练神经网络（NN），并用于复杂业务流量预测。以自相似流量模型验证了2种NN学习算法的有效性，并分析比较了他们在流量预测中的可行性，得出Davidon最小二乘学习算法训练的NN比BP算法收敛速度快、收敛误差相差不多，验证了复杂自相似业务流的可预测性，为复杂自相似网络业务流预测的研究提供了一种有效途径。     

基于QPSO-ANN的发酵过程建模与优化

针对BP神经网络训练时间长、易陷入局部极小点问题,将量子微粒群算法QPSO与BP算法结合起来分两次训练神经网络,建立青霉素浓度预估模型。用青霉素发酵数据集对模型进行训练与检验。基于该模型,用QPSO算法对温度与pH控制轨线进行优化。实验表明,该发酵过程模型训练误差小、学习速度快、泛化能力强、预测精度高、可以实现多步预估。采用优化后的温度、pH控制轨线,青霉素浓度有所提高。     

粒子群优化BP神经网络的激光铣削质量预测模型

为了有效地控制激光铣削层质量,建立了激光铣削层质量（铣削层宽度、铣削层深度）与铣削层参数（激光功率、扫描速度和离焦量）的BP神经网络预测模型。采用粒子群算法优化了BP神经网络的权值和阈值,构建了基于粒子群神经网络的质量预测模型。所提出的PSO-BP算法解决了一般BP算法迭代速度慢,且易出现局部最优的问题,并以Al2O3陶瓷激光铣削质量预测为例,进行算法实现。仿真结果表明:提出的PSO-BP算法迭代次数大大减少,且预测误差明显减少。所构建的质量预测模型具有较高的预测精度和实用价值。