This article presents the hardware implementation of the Radial Basis Function (RBF) neural network whose internal weights are updated in the real-time fashion by the back-propagation algorithm. The floating-point pro...
详细信息
ISBN:
(纸本)9781424418206
This article presents the hardware implementation of the Radial Basis Function (RBF) neural network whose internal weights are updated in the real-time fashion by the back-propagation algorithm. The floating-point processor is designed on a field programmable gat array (FPGA) chip to execute nonlinear functions required in the parallel processing calculation of the back-propagation algorithm. The performance of the on-line learning process of the RBF chip is compared numerically with the results of the RBF neural network learning program written in the MATLAB software under the same condition to check the feasibility of the implemented neural chip. The performance of the designed RBF neural chip is tested for the real-time pattern classification of the nonlinear XOR logic.
A new digital background calibration scheme for non-linearity of successive approximation register (SAR) analogto-digital convertor (ADC) is presented. Since non-linearity of high resolution SAR ADC is mainly caused b...
详细信息
A new digital background calibration scheme for non-linearity of successive approximation register (SAR) analogto-digital convertor (ADC) is presented. Since non-linearity of high resolution SAR ADC is mainly caused by the difference between the real and ideal weights of capacitor digital-to-analog convertor (CDAC) with respect to the normalized-full-scale, calibration of weights of more significant bits is necessary when the resolution of SAR ADC comes to more than 12 bits. By using back-propagation algorithm to train the normalized real weight of more significant bits (MSBs) in neural network without any change in SAR ADC circuit design, the calibration table for each bit is implemented and updated in the digital domain without interrupting normal ADC process, which is used to correct the raw SAR code in the background to improve the performance of ADC, which is suitable for some detection applications in particular circumstances. In MATLAB simulation, the signal to noise and distortion ratio (SNDR) and spurious-free dynamic range (SFDR) of a 14-bit with 1-bit redundancy SAR ADC model are improved to 85.59 dB and 97.27 dB from 56.65 dB to 77.07 dB using the proposed calibration scheme, at a standard deviation of a unit capacitor of 2%.
This paper presents an optimization method using Non-dominated Sorting Genetic algorithm (NSGA) III to drive support vector machine (SVM). In the NSGA III algorithm, brake specific fuel consumption (BSFC), NOx and CO2...
详细信息
This paper presents an optimization method using Non-dominated Sorting Genetic algorithm (NSGA) III to drive support vector machine (SVM). In the NSGA III algorithm, brake specific fuel consumption (BSFC), NOx and CO2 are optimized by changing the engine control parameters including spark angle, VVT-I (intake), VVT-E (exhaust) and exhaust gas recirculation (EGR). The engine GT-Power physical model is used to generate training data for the SVM, and verify the accuracy of the results of NSGA III algorithm during the optimization process. The SVM with fast calculation speed is used in the calculation of NSGA III fitness evaluation. In addition, enhancing training is utilized to improve the accuracy of the SVM model in this research. When the optimization method is applied to the Atkinson cycle gasoline engine, its high efficiency has been presented. In the three plans obtained by GT-Power physical model with all four parameters optimized, the maximum reduction rates of BSFC, NOx, CO2 and CO (g/kW.h) reached 7.07%, 35.90%, 6.62% and 5.50% respectively. The SVM model is compared with back-propagation algorithm, and the result proves that SVM is more suitable for such problems. Finally, based on the Pareto optimal solution obtained by the optimization method, it significantly promotes the solution of multiobjective optimization problems. Theoretically, the time cost of the optimization method in this paper can reach 1/23 of that for the optimization algorithm directly driving physical model.
This paper considers the problem of automatically extracting a foreground element with its alpha matte in green screen images by training a multi-layer perceptron (MLP) with the back-propagation algorithm. The classif...
详细信息
ISBN:
(纸本)9781509000807
This paper considers the problem of automatically extracting a foreground element with its alpha matte in green screen images by training a multi-layer perceptron (MLP) with the back-propagation algorithm. The classifier learns to identify green backgrounds, foreground object contours, and the corresponding alpha values for subsequent digital compositing. We developed our own dataset to train and test the MLP for alpha matte extraction. To speed up the generation of the training set, a second method for semi-automatic alpha matte extraction is proposed. Different experiments show that automatic matte extraction, based on the MLP, generates high-quality matting visually and it is also shown that results depend on the training and the architecture of the classifier. To the best of our knowledge, this is the first effort that applies neural networks to the problem of alpha matte extraction.
In this paper, a novel hybrid approach for deterministic and probabilistic occupancy detection is proposed with a novel heuristic optimization and back-propagation (BP) based algorithms. Generally, PB based neural net...
详细信息
In this paper, a novel hybrid approach for deterministic and probabilistic occupancy detection is proposed with a novel heuristic optimization and back-propagation (BP) based algorithms. Generally, PB based neural network (BPNN) suffers with the optimal value of weight, bias, trapping problem in local minima and sluggish convergence rate. In this paper, the GSA (Gravitational Search algorithm) is implemented as a new training technique for BPNN is order to enhance the performance of the BPNN algorithm by decreasing the problem of trapping in local minima, enhance the convergence rate and optimize the weight and bias value to reduce the overall error. The experimental results of BPNN with and without GSA are demonstrated and presented for fair comparison and adoptability. The demonstrated results show that BPNNGSA has outperformance for training and testing phase in form of enhancement of processing speed, convergence rate and avoiding the trapping problem of standard BPNN. The whole study is analyzed and demonstrated by using R language open access platform. The proposed approach is validated with different hidden-layer neurons for both experimental studies based on BPNN and BPNNGSA.
A new algorithm for learning principal curves with definite mathematical representations is proposed based on combining the principal component analysis (PCA) and back-propagation (BP) network. The algorithm successfu...
详细信息
ISBN:
(纸本)9780769529769
A new algorithm for learning principal curves with definite mathematical representations is proposed based on combining the principal component analysis (PCA) and back-propagation (BP) network. The algorithm successfully turns an unsupervised learning problem into a supervised one by projecting a data set to its first component line and identifying the relation between the data points and their corresponding projection indices with BP network. This algorithm has been proved distinctly superior to the HS algorithm.
In recent years, back-propagation neural networks have become a popular tool for modelling environmental systems. However, as a result of the relative newness of the technique to this field, users appear to have limit...
详细信息
In recent years, back-propagation neural networks have become a popular tool for modelling environmental systems. However, as a result of the relative newness of the technique to this field, users appear to have limited knowledge about how ANNs operate and how to optimise their performance. In this paper, the stages observed when training a back-propagation neural network: are examined in detail for a particular case study;the forecasting of salinity in the River Murray at Murray Bridge, South Australia, 14 days in advance. Particular attention is paid to the behaviour of the network as it approaches a local minimum in the error surface. The effect of the presence of infrequent patterns in the training set on generalisation ability is investigated. The nature of the error surface in the vicinity of local minima is examined and options for optimising network performance (i.e. training speed and generalisation ability) are presented for real time forecasting situations. (C) 1998 Elsevier Science Ltd. All rights reserved.
Designing a monochromatic spatially-structured light field that recovers the pre-specified profile of optical force (OF) exerted on a particle is an inverse problem. It usually requires high dimensional optimization a...
详细信息
Designing a monochromatic spatially-structured light field that recovers the pre-specified profile of optical force (OF) exerted on a particle is an inverse problem. It usually requires high dimensional optimization and involves lengthy calculations, thus remaining little studied despite decades of research on OF. We report here the first attempt to attack this inverse design problem. The modus operandi relies on the back-propagation algorithm, which is facilitated by the currently available machine learning framework, and, in particular, by an exact and efficient expression of OF that shows only polynomial and trigonometric functional dependence on the engineered parameters governing the structured light field. Two illustrative examples are presented in which the inversely designed structured light fields reproduce, respectively, a predefined spatial pattern of OF and a negative longitudinal OF in a transversely trapping area.
Artificial neural networks of the back-propagation type are being used increasingly for modelling environmental systems. One of the most difficult, and least understood, tasks in the design of back-propagation network...
详细信息
Artificial neural networks of the back-propagation type are being used increasingly for modelling environmental systems. One of the most difficult, and least understood, tasks in the design of back-propagation networks is the choice of adequate internal network parameters and appropriate network geometries. Although some guidance is available for the choice of these values, they are generally determined using a trial and error approach. This paper describes the effect of geometry and internal parameters on network performance for a particular case study. Although the information obtained from the tests carried out in this research is specific to the problem considered, it provides users of back-propagation networks with a valuable guide on the behaviour of networks under a wide range of operating conditions. The results obtained indicate that learning rate, momentum, the gain of the transfer function, epoch size and network geometry have a significant impact on training speed, but not on generalisation ability. The type of transfer and error function used was found to have a significant impact on learning speed as well as generalisation ability. (C) 1998 Elsevier Science Ltd. All rights reserved.
IPv6 was designed to solve the issue of adopting IPv4 addresses by presenting a large number of address spaces. Currently, many networking devices consider IPv6 as a supportive IPv6-enabled device that includes router...
详细信息
IPv6 was designed to solve the issue of adopting IPv4 addresses by presenting a large number of address spaces. Currently, many networking devices consider IPv6 as a supportive IPv6-enabled device that includes routers, notebooks, personal computers, and mobile phones. Security has increasingly become a significant issue in exploiting networks and obtaining the benefits of IPv6. One of the important protocols in IPv6 implementation that is used for neighbor and router discovery is ICMPv6. However, this protocol can be used by attackers to deny network services through ICMPv6 DDoS flooding attacks that decrease the network performance. To solve this problem, this study proposes an intelligent ICMPv6 DDoS flooding-attack detection framework using back-propagation neural network (v6IIDS) in IPv6 networks. This study also explores and analyzes the detection accuracy of the proposed v6IIDS framework. The effectiveness of the v6IIDS framework is demonstrated by using real data-sets obtained from an NAv6 laboratory. The data-set traffic is based on a test-bed environment created on the basis of certain parameters used as inputs to generate a new data-set. The results prove that the proposed framework is capable of detecting ICMPv6 DDoS flood attacks with a detection accuracy rate of 98.3%.
暂无评论