Multiuser Detection of Synchronous MC-CDMA in Multipath Fading Channels Using Hopfield Neural Networks

Sub-optimum multiuser reception using Hopfield Neural Network for synchronous Multicarrier Code-Division Multiple Access signals in a multipath fading channel is studied with respect to near-far ratio. We have shown that by the appropriate choice of Hopfield Neural Network parameters from the channel state information, the Hopfield network can collectively resolve the multipath fading effects and the multiple-access interference in the system. Moreover, the Hopfield Neural Network demonstrates multiple-access interference resilient performance regardless of the number of paths resolved at the receiver. We have also investigated the bit-error rate performance of the system with respect to channel estimation errors. Results show that performance of the proposed detection scheme is influenced by the correctness of the estimated channel state information.     

DC-link voltage control of three-phase PWM rectifier by using artificial bee colony based type-2 fuzzy neural network

The pulse width modulation (PWM) rectifiers are nonlinear systems due to semiconductor switches in their structure. Therefore, these rectifiers draw a distorted current from AC supply. Many different improvements have been proposed to overcome problems caused by PWM rectifiers. In this paper, DC-link voltage of three-phase PWM rectifier is regulated by using a Type-2 Fuzzy Neural Network (T2FNN) controller that parameters are optimized by using Artificial Bee Colony (ABC) optimization method. The parameters in antecedent and consequent parts of T2FNN are optimized by ABC optimization method. The performance of ABC-T2FNN controller is analyzed under different operating conditions through simulation model based on MATLAB. The operating conditions are considered as constant input, set point, a step DC load change, unbalanced AC supply and regenerative mode. The simulation results obtained from the proposed controller are verified by comparing with the results of the classical T2FNN. When the results of PWM rectifiers are investigated, it is seen that PWM rectifier based on the proposed controller has better dynamic response for all operating conditions than conventional T2FNN controller.     

模糊神经网络PID控制在焊缝跟踪中的应用

1 Introduction Real- time seam tracking is the key step for welding automation. Because welding itself is a complex process, the factors that affect the welding have uncertainty and non - linear characters. Therefore, classical control in seam tracking cannot carry a satisfying result. In latter- day, Fuzzy mathematic and Neural Network appearance, being used on uncertain nonlinear system, and have a good effect. The hybrid controller, which combines Fuzzy con- trol and PID control, uses F…     

Automated Recurrent Neural Network Design of a Neural Controller in a Custom Power Device

A general purpose implementation of the Tabu Search metaheuristic, called Universal Tabu Search, is used to optimally design a Locally Recurrent Neural Network architecture. Indeed, the design of a neural network is a tedious and time consuming trial and error operation that leads to structures whose optimality is not guaranteed. In this paper, the problem of choosing the number of hidden neurons and the number of taps and delays in the FIR and IIR network synapses is formalised as an optimisation problem whose cost function to be minimised is the network error calculated on a validation data set. The performances of the proposed approach have been tested on the design problem of a Neural Network controller of a Custom Power protection device.     

Bi-linearly weighted fractional max pooling

In this paper, we propose to extend the flexibility of the commonly used 2 × 2 non-overlapping max pooling for Convolutional Neural Network. We name it as Bi-linearly Weighted Fractional Max-Pooling. This proposed method enables max pooling operation below stride size 2, and is computed based on four bi-linearly weighted neighboring input activations. Currently, in a 2 × 2 non-overlapping max pooling operation, as spatial size is halved in both x and y directions, three-quarter of activations in the feature maps are discarded. As such reduction is too abrupt, amount of said pooling operation within a Convolutional Neural Network is very limited: further increasing the number of pooling operation results in too little activation left for subsequent operations. Using our proposed pooling method, spatial size reduction can be more gradual and can be adjusted flexibly. We applied a few combinations of our proposed pooling method into 50-layered ResNet and 19-layered VGGNet with reduced number of filters, and experimented on FGVC-Aircraft, Oxford-IIIT Pet, STL-10 and CIFAR-100 datasets. Even with reduced memory usage, our proposed methods showed reasonable improvement in classification accuracy with 50-layered ResNet. Additionally, with flexibility of our proposed pooling method, we change the reduction rate dynamically every training iteration, and our evaluation results indicated potential regularization effect.     

Stock prediction using deep learning

Stock market is considered chaotic, complex, volatile and dynamic. Undoubtedly, its prediction is one of the most challenging tasks in time series forecasting. Moreover existing Artificial Neural Network (ANN) approaches fail to provide encouraging results. Meanwhile advances in machine learning have presented favourable results for speech recognition, image classification and language processing. Methods applied in digital signal processing can be applied to stock data as both are time series. Similarly, learning outcome of this paper can be applied to speech time series data. Deep learning for stock prediction has been introduced in this paper and its performance is evaluated on Google stock price multimedia data (chart) from NASDAQ. The objective of this paper is to demonstrate that deep learning can improve stock market forecasting accuracy. For this, (2D)²PCA + Deep Neural Network (DNN) method is compared with state of the art method 2-Directional 2-Dimensional Principal Component Analysis (2D)²PCA + Radial Basis Function Neural Network (RBFNN). It is found that the proposed method is performing better than the existing method RBFNN with an improved accuracy of 4.8% for Hit Rate with a window size of 20. Also the results of the proposed model are compared with the Recurrent Neural Network (RNN) and it is found that the accuracy for Hit Rate is improved by 15.6%. The correlation coefficient between the actual and predicted return for DNN is 17.1% more than RBFNN and it is 43.4% better than RNN.     

Multiprocessor scheduling and neural network training methods using shuffled frog-leaping algorithm

In this paper, we designed novel methods for Neural Network (NN) and Radial Basis function Neural Networks (RBFNN) training using Shuffled Frog-Leaping Algorithm (SFLA). This paper basically deals with the problem of multi-processor scheduling in a grid environment. We, in this paper, introduce three novel approaches for the task scheduling problem using a recently proposed Shuffled Frog-Leaping Algorithm (SFLA). In a first attempt, the scheduling problem is structured as a problem of optimization and solved by SFLA. Next, this paper makes use of SFLA trained Artificial Neural Network (ANN) and Radial Basis function Neural Networks (RBFNN) for the problem of task scheduling. Interestingly, the proposed methods yield better performance than contemporary algorithms as evidenced by simulation results.     

Controlling a robot manipulator with fuzzy voice commands using a probabilistic neural network

Natural language commands are generated by intelligent human beings. As a result, they contain a lot of information. Therefore, if it is possible to learn from such commands and reuse that knowledge, it will be a very efficient process. In this paper, learning from such information rich voice commands for controlling a robot is studied. First, new concepts of fuzzy coach-player system and sub-coach are proposed for controlling robots with natural language commands. Then, the characteristics of the subjective human decision making process are discussed and a Probabilistic Neural Network (PNN) based learning method is proposed to learn from such commands and to reuse the acquired knowledge. Finally, the proposed concept is demonstrated and confirmed with experiments conducted using a PA-10 redundant manipulator.     

Centroid Neural Network with Pairwise Constraints for Semi-supervised Learning

Neural Processing Letters - A clustering algorithm for datasets with pairwise constraints using the Centroid Neural Network (Cent.NN) is proposed in this paper. The proposed algorithm, referred to...     

基于遗传算法的WNN在电力负荷短期预测中的应用

提出将小波神经网络和遗传算法相结合,用于电力系统短期负荷预测的新方法。具体是充分利用遗传算法的优越性,对小波神经网络的权值进行优化,然后利用优化得到的权值,对原始数据进行W N N训练。通过仿真,该种方法比传统利用神经网络进行负荷预测具有更高的精度。     

MMNNN: A tree-based Multicast Mechanism for NoC-based deep Neural Network accelerators

Network-on-Chip (NoC) devices have been widely used in multiprocessor systems. In recent years, NoC-based Deep Neural Network (DNN) accelerators have been proposed to connect neural computing devices using NoCs. Such designs dramatically reduce off-chip memory accesses of these platforms. However, the large number of one-to-many packet transfers significantly degrade performance with traditional unicast channels. We propose a multicast mechanism for a NoC-based DNN accelerator called Multicast Mechanism for NoC-based Neural Network accelerator (MMNNN). To do so, we propose a tree-based multicast routing algorithm with excellent scalability and the ability to minimize the number of packets in the network. We also propose a router architecture for single-flit packets. Our proposed router transfers flits to multiple destinations in a single process and has no head-of-line blocking issue, offering higher throughput and lower latency than traditional wormhole router architectures. Simulation results show that our proposed multicast mechanism offers excellent performance in classification latency, average packet latency, and energy consumption.     

A hybrid method based on dynamic compensatory fuzzy neural network algorithm for face recognition

Human face recognition skills can make simultaneous use of a variety of information from the face, including information about the age, sex, race, identity, and even current mood of the person. In this paper, a hybrid method combined Eigenface-LDA with Dynamic Compensatory Fuzzy Neural Network (DCFNN) is proposed for face recognition. Eigenfaces-LDA algorithm is used for face image of dimensionality reduction and finding a best subspace for classification, the extracted feature will be considered as the input of DCFNN. An improved Dynamic Fuzzy Neural Network is proposed by combing Dynamic Fuzzy Neural Network and Compensatory Fuzzy Neural Network to solve the problem of feature classification. The proposed method has been tested on ORL and Yale face database; the experimental results show that our method can reduce the dimension of facial features well and recognize faces that under different illumination, pose and expression accurately.     

基于GA-NN的碳通量预测因素选择

研究和选择碳循环的影响因素是预测碳通量的重要环节,也是研究碳循环机理的重要步骤。然而从众多的影响因素中选择重要的因素,依然存在着困难。提出利用相关分析、遗传算法和神经网络进行碳通量预测的主要因素选择的方法,首先用相关分析去处冗余的因素;然后利用遗传算法,以选择最小数目的因素时,最大碳通量的观测值和用神经网络预测值的相关系数为准则,来搜寻最优的影响因素。实验证明该方法能在不影响（或尽量小地影响）预测精度的前提下,有效地选择出碳通量预测的重要因素。     

A new approach for forecasting OPEC petroleum consumption based on neural network train by using flower pollination algorithm

Petroleum is the live wire of modern technology and its operations, with economic development being positively linked to petroleum consumption. Many meta-heuristic algorithms have been proposed in literature for the optimization of Neural Network (NN) to build a forecasting model. In this paper, as an alternative to previous methods, we propose a new flower pollination algorithm with remarkable balance between consistency and exploration for NN training to build a model for the forecasting of petroleum consumption by the Organization of the Petroleum Exporting Countries (OPEC). The proposed approach is compared with established meta-heuristic algorithms. The results show that the new proposed method outperforms existing algorithms by advancing OPEC petroleum consumption forecast accuracy and convergence speed. Our proposed method has the potential to be used as an important tool in forecasting OPEC petroleum consumption to be used by OPEC authorities and other global oil-related organizations. This will facilitate proper monitoring and control of OPEC petroleum consumption.     

Resolution of pattern recognition problems using a hybrid Genetic/Random Neural Network learning algorithm

Gelenbe has proposed a neural network, called a Random Neural Network, which calculates the probability of activation of the neurons in the network. In this paper, we propose to solve the patterns recognition problem using a hybrid Genetic/Random Neural Network learning algorithm. The hybrid algorithm trains the Random Neural Network by integrating a genetic algorithm with the gradient descent rule-based learning algorithm of the Random Neural Network. This hybrid learning algorithm optimises the Random Neural Network on the basis of its topology and its weights distribution. We apply the hybrid Genetic/Random Neural Network learning algorithm to two pattern recognition problems. The first one recognises or categorises alphabetic characters, and the second recognises geometric figures. We show that this model can efficiently work as associative memory. We can recognise pattern arbitrary images with this algorithm, but the processing time increases rapidly.     

基于概率神经网络的蛋白质相互作用分类器

蛋白质-蛋白质作用面上的结构特征对于研究蛋白质功能具有重要意义。提出了一种新的、基于统计直方图提取蛋白质作用面特征的方法,并且利用提取出的作用面特征,结合概率神经网络,实现了对作用面结构类型的分类预测。从预测结果来看,统计直方图提取出的特征,对蛋白质作用面结构具有很好的区分能力,而且可以通过调节划分的区间个数和节点的选取方式,达到对作用面结构的不同粒度的描述,以适用于不同目的的研究,这可能对与结构有关的某些生物信息学问题的研究具有启发性。利用概率神经网络对作用面结构进行分类预测,避开了费时的结构比对和数据库搜索,且训练快速,扩展能力强,正确率高,对独立测试集的911个蛋白复合物视在正确率达到90.67%。基于该算法的MATLAB分类器软件可以通过E-Mail与作者联系获取。     

基于统计聚类RBF神经网络的孤立点检测研究

孤立点挖掘是数据挖掘的一个重要领域,而统计分析方法在孤立点检测中具有天然的优势。本文将统计聚类方法融入RBF神经网络,提出了一种基于统计聚类RBF神经网络的新的孤立点检测算法——SCRBF。该算法包括两部分,先用统计聚类方法对神经网络进行初始化,然后根据网络的训练情况进行隐单元的简化,提高了神经网络的泛化能力,同时也降低了过拟合现象的出现概率。与LSC算法的对比实验表明,该算法是有效的。     

Verification of genuine and forged offline signatures using Siamese Neural Network (SNN)

Deep learning plays very important role in almost all domains and application areas of AI like computer vision, biometrics, NLP, Healthcare etc. However, when there is lack of training data then it is difficult to train a model. Siamese is one of the popular network in deep learning and applications. This network architecture is composed of two or more identical sub-network component and also shares same weights among them. The core benefit of this network is, it can learn from one input image along with one target image. Further it is identified as one shot learning. Generally, to avert falsification and discriminate geunine as well as forged signature, Convolutional Neural Network (CNN) is highly researched. The proposed work represents Siamese neural network using Convolutional Neural Network as a subnetwork for the proposed system. In Siamese network embedding vector is generated and to make this vector more robust, we proposed to add some statistical measures to it, which are calculated on embedding vector itself. Lastly contrastive loss function is applied to resultant embedding vector. The proposed network surpass the state-of-the-art results in terms of accuracy, FAR and FRR.

     

Image recognition of english vocabulary translation based on FPGA high-performance algorithm

English vocabulary translation image recognition is the essential system to analyze the text image and recognize the sentence. Many image processing techniques explain the Image recognition of English vocabulary translation in image data, but the accuracy is less. So the proposed Neural Network (NN) is introduced in this system. In this system analysis, the text input image enhances the input image quality and extracts the feature. To develop a Neural Network (NN), it is essential to analyze the solution process based on image processing technology and many appropriate problems. In the previous technique is very difficult to explain the input image to recognize the English vocabulary word. The image is first preprocessed to enhance the input image quality, and the next step to extract the image feature and the text image is classified. Therefore, the purpose of this article is to provide an overview of the use of the proposed Neural Network (NN) to solve common problems in Image recognition of English vocabulary translation. This proposed Neural Network (NN) methodology is the analysis. It improves the system accuracy with the help of FPGA Xilinx software. The work demonstrates the classification efficiency of 98.05% and tabulates the values that perform previous results in this widely related research field, giving accurate results.