Статті в журналах: "Combination of neural networks"

1

Zengguo Sun, Zengguo Sun, Guodong Zhao Zengguo Sun, Rafał Scherer Guodong Zhao, Wei Wei Rafał Scherer, and Marcin Woźniak Wei Wei. "Overview of Capsule Neural Networks." 網際網路技術學刊 23, no. 1 (January 2022): 033–44. http://dx.doi.org/10.53106/160792642022012301004.

Повний текст джерела

Анотація:

As a vector transmission network structure, the capsule neural network has been one of the research hotspots in deep learning since it was proposed in 2017. In this paper, the latest research progress of capsule networks is analyzed and summarized. Firstly, we summarize the shortcomings of convolutional neural networks and introduce the basic concept of capsule network. Secondly, we analyze and summarize the improvements in the dynamic routing mechanism and network structure of the capsule network in recent years and the combination of the capsule network with other network structures. Finally, we compile the applications of capsule network in many fields, including computer vision, natural language, and speech processing. Our purpose in writing this article is to provide methods and means that can be used for reference in the research and practical applications of capsule networks.

Стилі APA, Harvard, Vancouver, ISO та ін.

2

Aladag, Cagdas Hakan, Erol Egrioglu, and Ufuk Yolcu. "Forecast Combination by Using Artificial Neural Networks." Neural Processing Letters 32, no. 3 (October 30, 2010): 269–76. http://dx.doi.org/10.1007/s11063-010-9156-7.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

3

Wang, Yunhong, Songde Ma, T. N. Tan, and Guosui Liu. "Combination of multiple classifiers with neural networks." IFAC Proceedings Volumes 32, no. 2 (July 1999): 5332–37. http://dx.doi.org/10.1016/s1474-6670(17)56908-6.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

4

Meng, Ya Feng, Sai Zhu, and Rong Li Han. "A Fault Diagnosis Method Based on Combination of Neural Network and Fault Dictionary." Advanced Materials Research 765-767 (September 2013): 2078–81. http://dx.doi.org/10.4028/www.scientific.net/amr.765-767.2078.

Повний текст джерела

Анотація:

Neural network and Fault dictionary are two kinds of very useful fault diagnosis method. But for large scale and complex circuits, the fault dictionary is huge, and the speed of fault searching affects the efficiency of real-time diagnosing. When the fault samples are few, it is difficulty to train the neural network, and the trained neural network can not diagnose the entire faults. In this paper, a new fault diagnosis method based on combination of neural network and fault dictionary is introduced. The fault dictionary with large scale is divided into several son fault dictionary with smaller scale, and the search index of the son dictionary is organized with the neural networks trained with the son fault dictionary. The complexity of training neural network is reduced, and this method using the neural networks ability that could accurately describe the relation between input data and corresponding goal organizes the index in a multilayer binary tree with many neural networks. Through this index, the seeking scope is reduced greatly, the searching speed is raised, and the efficiency of real-time diagnosing is improved. At last, the validity of the method is proved by the experimental results.

Стилі APA, Harvard, Vancouver, ISO та ін.

5

Iosifidis, Alexandros, Anastasios Tefas, and Ioannis Pitas. "Human Action Recognition Based on Multi-View Regularized Extreme Learning Machine." International Journal on Artificial Intelligence Tools 24, no. 05 (October 2015): 1540020. http://dx.doi.org/10.1142/s0218213015400205.

Повний текст джерела

Анотація:

In this paper, we employ multiple Single-hidden Layer Feedforward Neural Networks for multi-view action recognition. We propose an extension of the Extreme Learning Machine algorithm that is able to exploit multiple action representations and scatter information in the corresponding ELM spaces for the calculation of the networks’ parameters and the determination of optimized network combination weights. The proposed algorithm is evaluated by using two state-of-the-art action video representation approaches on five publicly available action recognition databases designed for different application scenarios. Experimental comparison of the proposed approach with three commonly used video representation combination approaches and relating classification schemes illustrates that ELM networks employing a supervised view combination scheme generally outperform those exploiting unsupervised combination approaches, as well as that the exploitation of scatter information in ELM-based neural network training enhances the network’s performance.

Стилі APA, Harvard, Vancouver, ISO та ін.

6

Smith, Lauren C., and Adam Kimbrough. "Leveraging Neural Networks in Preclinical Alcohol Research." Brain Sciences 10, no. 9 (August 21, 2020): 578. http://dx.doi.org/10.3390/brainsci10090578.

Повний текст джерела

Анотація:

Alcohol use disorder is a pervasive healthcare issue with significant socioeconomic consequences. There is a plethora of neural imaging techniques available at the clinical and preclinical level, including magnetic resonance imaging and three-dimensional (3D) tissue imaging techniques. Network-based approaches can be applied to imaging data to create neural networks that model the functional and structural connectivity of the brain. These networks can be used to changes to brain-wide neural signaling caused by brain states associated with alcohol use. Neural networks can be further used to identify key brain regions or neural “hubs” involved in alcohol drinking. Here, we briefly review the current imaging and neurocircuit manipulation methods. Then, we discuss clinical and preclinical studies using network-based approaches related to substance use disorders and alcohol drinking. Finally, we discuss how preclinical 3D imaging in combination with network approaches can be applied alone and in combination with other approaches to better understand alcohol drinking.

Стилі APA, Harvard, Vancouver, ISO та ін.

7

Cherepanova, V. О., and I. V. Sylka. "Optimizing the Intellectual Property Management in Accordance with a Process-Functional Approach." Business Inform 9, no. 524 (2021): 41–51. http://dx.doi.org/10.32983/2222-4459-2021-9-41-51.

Повний текст джерела

Анотація:

The article is aimed at developing a way to optimize the management of intellectual property (IP) objects by a process-functional approach based on the use of neural networks in combination with planning networks in conditions of uncertainty. When analyzing the works of various scholars, conceptual approaches to the formation of IP management according to both the process and the functional approaches to management were considered. The use of artificial neural networks in intellectual property management at industrial enterprises in combination with network planning in conditions of uncertainty is systematized. Neural networks consist of different architectures, but to manage intellectual property it is advisable to use either Self-Organizing Maps (SOM) by Kohonen, or Generative Pre-trained Transformer 3 (GPT-3), or Rumelhart Multilayer Perceptron, or an combination of the above. It is proved that the proposed scientific approach (instrumentarium) in the form of neural networks and network planning allows reducing the time for implementation of works related to the management of intellectual property at industrial enterprises on the grounds of a process-functional approach. Based on the carried out study, the computation of spent time was carried out, which confirmed the efficiency of the implementation of neural networks in combination with network schedule for the management of intellectual property in industrial enterprises. Prospects for further research in this direction are the development and construction of a universal instrument using neural networks and network schedule. Further development of intellectual property management will increase production efficiency and profitability of enterprises.

Стилі APA, Harvard, Vancouver, ISO та ін.

8

Foon, See Lee, Nazira Anisa Rahim, Ahmad Zainal, and Zhang Jie. "Selective combination in multiple neural networks prediction using independent component regression approach." Chemical Engineering Research Bulletin 19 (September 10, 2017): 12. http://dx.doi.org/10.3329/cerb.v19i0.33772.

Повний текст джерела

Анотація:

Biological processes are highly nonlinear in nature and difficult to represent accurately by simple mathematical models. However, this problem can be solved by using neural network. Neural network is a prominent modeling tool especially when it comes to intricate process such as biological process. In this paper, a multiple single hidden layer with ten hidden neurons Feedforward Artificial Neural Network (FANN) was used to model the complex and dynamic relationships between the input (dilution rate, D) and outputs (conversion, y and dimensionless temperature value, θ) for the reactive biological process. Levenberg-Marquardt Backpropagation training method was used. The multiple neural networks predicted outputs were then combined through three different methods which area simple averaging, Principal Component Regression (PCR) and Independent Component Regression (ICR). Multiple neural networks which were created by the bootstrap approach help improved single neural network performance as well as the model robustness for nonlinear process modeling. Comparison was made between the three methods. The result showed that ICR is slightly superior between the three methods especially in noise level 1,2 and 3, however ICR slightly suffer in noise level 4 and 5. This is due to the independent component regression used the latent factors and non-Gaussian distribution of y and θ values for the combination.Chemical Engineering Research Bulletin 19(2017) 12-19

Стилі APA, Harvard, Vancouver, ISO та ін.

9

Lézoray, Olivier, and Hubert Cardot. "Comparing Combination Rules of Pairwise Neural Networks Classifiers." Neural Processing Letters 27, no. 1 (November 4, 2007): 43–56. http://dx.doi.org/10.1007/s11063-007-9058-5.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

10

Li, Yi Bing, and Fei Pan. "Study on the Combination of SOM and K-Means Algorithms in Manufacturing Process Quality Control." Applied Mechanics and Materials 427-429 (September 2013): 1315–18. http://dx.doi.org/10.4028/www.scientific.net/amm.427-429.1315.

Повний текст джерела

Анотація:

Nowadays, customers are seeking products of high quality and low cost. The use of neural networks in quality control has been a popular research topic over the last decade. An adaptive self-organizing mapping (SOM) neural network algorithm is proposed to overcome the shortages of traditional neural networks in this paper. In order to improve the classification effectiveness of SOM neural network, this paper designs an improved SOM neural network, which combined the SOM and K-means algorithms. The flow of combination of SOM and K-means algorithms was analyzed in this paper. And the case study of cement slide shoe bearing in manufacturing process was also given to illustrate the feasible and effective.

Стилі APA, Harvard, Vancouver, ISO та ін.

11

YEN, GARY, and HAIMING LU. "HIERARCHICAL GENETIC ALGORITHM FOR NEAR-OPTIMAL FEEDFORWARD NEURAL NETWORK DESIGN." International Journal of Neural Systems 12, no. 01 (February 2002): 31–43. http://dx.doi.org/10.1142/s0129065702001023.

Повний текст джерела

Анотація:

In this paper, we propose a genetic algorithm based design procedure for a multi-layer feed-forward neural network. A hierarchical genetic algorithm is used to evolve both the neural network's topology and weighting parameters. Compared with traditional genetic algorithm based designs for neural networks, the hierarchical approach addresses several deficiencies, including a feasibility check highlighted in literature. A multi-objective cost function is used herein to optimize the performance and topology of the evolved neural network simultaneously. In the prediction of Mackey–Glass chaotic time series, the networks designed by the proposed approach prove to be competitive, or even superior, to traditional learning algorithms for the multi-layer Perceptron networks and radial-basis function networks. Based upon the chosen cost function, a linear weight combination decision-making approach has been applied to derive an approximated Pareto-optimal solution set. Therefore, designing a set of neural networks can be considered as solving a two-objective optimization problem.

Стилі APA, Harvard, Vancouver, ISO та ін.

12

Greif, Kevin, and Kevin Lannon. "Physics Inspired Deep Neural Networks for Top Quark Reconstruction." EPJ Web of Conferences 245 (2020): 06029. http://dx.doi.org/10.1051/epjconf/202024506029.

Повний текст джерела

Анотація:

Deep neural networks (DNNs) have been applied to the fields of computer vision and natural language processing with great success in recent years. The success of these applications has hinged on the development of specialized DNN architectures that take advantage of specific characteristics of the problem to be solved, namely convolutional neural networks for computer vision and recurrent neural networks for natural language processing. This research explores whether a neural network architecture specific to the task of identifying t → Wb decays in particle collision data yields better performance than a generic, fully-connected DNN. Although applied here to resolved top quark decays, this approach is inspired by an DNN technique for tagging boosted top quarks, which consists of defining custom neural network layers known as the combination and Lorentz layers. These layers encode knowledge of relativistic kinematics applied to combinations of particles, and the output of these specialized layers can then be fed into a fully connected neural network to learn tasks such as classification. This research compares the performance of these physics inspired networks to that of a generic, fully-connected DNN, to see if there is any advantage in terms of classification performance, size of the network, or ease of training.

Стилі APA, Harvard, Vancouver, ISO та ін.

13

Cui, Dong Yan, and Zai Xing Xie. "Based on Information Fusion Integrated Wavelet Neural Network Fault Diagnosis." Advanced Materials Research 219-220 (March 2011): 1077–80. http://dx.doi.org/10.4028/www.scientific.net/amr.219-220.1077.

Повний текст джерела

Анотація:

In this paper, the integration of wavelet neural network fault diagnosis system is established based on information fusion technology. the effective combination of fault characteristic information proves that integration of wavelet neural networks make better use of a variety of characteristic information than the list of wavelet neural networks to solve difficulties and problems which are difficult to resolve by a single network.

Стилі APA, Harvard, Vancouver, ISO та ін.

14

Caswell, Joseph M. "Combination of Wavelet Analysis and Artificial Neural Networks Applied to Forecast of Daily Cosmic Ray Impulses." International Letters of Chemistry, Physics and Astronomy 34 (May 2014): 55–63. http://dx.doi.org/10.18052/www.scipress.com/ilcpa.34.55.

Повний текст джерела

Анотація:

Artificial neural network modelling has proven incredibly effective in an impressively wide range of scientific disciplines. The combination of these various methods with wavelet decomposition signal processing has similarly proven to be a powerful development for statistical forecasting of a number of environmental processes. Space weather modelling and prediction has often been applied to forecasting of solar activity and that of the planetary magnetic field. However, prediction of cosmic ray impulses has seen little development in the context of neural network modelling. In the present study, a combination of wavelet neural networks was adapted from previous research in order to predict daily average values of cosmic ray impulses 30 days in advance. Additional comparison of both neural network and linear regression modelling with and without wavelet decomposition was conducted for further demonstration of increased accuracy with wavelet neural networks in a simple input-output fitting model

Стилі APA, Harvard, Vancouver, ISO та ін.

15

DE STEFANO, CLAUDIO, CIRO D'ELIA, ALESSANDRA SCOTTO DI FRECA, and ANGELO MARCELLI. "CLASSIFIER COMBINATION BY BAYESIAN NETWORKS FOR HANDWRITING RECOGNITION." International Journal of Pattern Recognition and Artificial Intelligence 23, no. 05 (August 2009): 887–905. http://dx.doi.org/10.1142/s0218001409007387.

Повний текст джерела

Анотація:

In the field of handwriting recognition, classifier combination received much more interest than the study of powerful individual classifiers. This is mainly due to the enormous variability among the patterns to be classified, that typically requires the definition of complex high dimensional feature spaces: as the overall complexity increases, the risk of inconsistency in the decision of the classifier increases as well. In this framework, we propose a new combining method based on the use of a Bayesian Network. In particular, we suggest to reformulate the classifier combination problem as a pattern recognition one in which each input pattern is associated to a feature vector composed by the output of the classifiers to be combined. A Bayesian Network is then used to automatically infer the probability distribution for each class and eventually to perform the final classification. Experiments have been performed by using two different pools of classifiers, namely an ensemble of Learning Vector Quantization neural networks and an ensemble of Back Propagation neural networks, and handwritten specimen from the UCI Machine Learning Repository. The obtained performance has been compared with those exhibited by multi-classifier systems adopting the classifiers, but three of the most effective and widely used combining rules: the Majority Vote, the Weighted Majority Vote and the Borda Count.

Стилі APA, Harvard, Vancouver, ISO та ін.

16

Subotin, M., W. Marsh, J. McMichael, J. J. Fung, and I. Dvorchik. "Performance of Multi-Layer Feedforward Neural Networks to Predict Liver Transplantation Outcome." Methods of Information in Medicine 35, no. 01 (January 1996): 12–18. http://dx.doi.org/10.1055/s-0038-1634637.

Повний текст джерела

Анотація:

AbstractA novel multisolutional clustering and quantization (MCO) algorithm has been developed that provides a flexible way to preprocess data. It was tested whether it would impact the neural network’s performance favorably and whether the employment of the proposed algorithm would enable neural networks to handle missing data. This was assessed by comparing the performance of neural networks using a well-documented data set to predict outcome following liver transplantation. This new approach to data preprocessing leads to a statistically significant improvement in network performance when compared to simple linear scaling. The obtained results also showed that coding missing data as zeroes in combination with the MCO algorithm, leads to a significant improvement in neural network performance on a data set containing missing values in 59.4% of cases when compared to replacement of missing values with either series means or medians.

Стилі APA, Harvard, Vancouver, ISO та ін.

17

YAO, XIN. "EVOLUTIONARY ARTIFICIAL NEURAL NETWORKS." International Journal of Neural Systems 04, no. 03 (September 1993): 203–22. http://dx.doi.org/10.1142/s0129065793000171.

Повний текст джерела

Анотація:

Evolutionary artificial neural networks (EANNs) can be considered as a combination of artificial neural networks (ANNs) and evolutionary search procedures such as genetic algorithms (GAs). This paper distinguishes among three levels of evolution in EANNs, i.e. the evolution of connection weights, architectures and learning rules. It first reviews each kind of evolution in detail and then analyses major issues related to each kind of evolution. It is shown in the paper that although there is a lot of work on the evolution of connection weights and architectures, research on the evolution of learning rules is still in its early stages. Interactions among different levels of evolution are far from being understood. It is argued in the paper that the evolution of learning rules and its interactions with other levels of evolution play a vital role in EANNs.

Стилі APA, Harvard, Vancouver, ISO та ін.

18

De Beule, M., E. Maes, O. De Winter, W. Vanlaere, and R. Van Impe. "Artificial neural networks and risk stratification: A promising combination." Mathematical and Computer Modelling 46, no. 1-2 (July 2007): 88–94. http://dx.doi.org/10.1016/j.mcm.2006.12.024.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

19

Yang, Jiechao, Xuelei Wang, Ruihua Wang, and Huanjie Wang. "Combination of Convolutional Neural Networks and Recurrent Neural Networks for predicting soil properties using Vis–NIR spectroscopy." Geoderma 380 (December 2020): 114616. http://dx.doi.org/10.1016/j.geoderma.2020.114616.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

20

Basterrech, Sebastián, and Gerardo Rubino. "ECHO STATE QUEUEING NETWORKS: A COMBINATION OF RESERVOIR COMPUTING AND RANDOM NEURAL NETWORKS." Probability in the Engineering and Informational Sciences 31, no. 4 (May 17, 2017): 457–76. http://dx.doi.org/10.1017/s0269964817000110.

Повний текст джерела

Анотація:

This paper deals with two ideas appeared during the last developing phase in Artificial Intelligence: Reservoir Computing (RC) and Random Neural Networks. Both have been very successful in many applications. We propose a new model belonging to the first class, taking the structure of the second for its dynamics. The new model is called Echo State Queuing Network. The paper positions the model in the global Machine Learning area, and provides examples of its use and performances. We show on largely used benchmarks that it is a very accurate tool, and we illustrate how it compares with standard RC models.

Стилі APA, Harvard, Vancouver, ISO та ін.

21

OH, SUNG-KWUN, DONG-WON KIM, and WITOLD PEDRYCZ. "HYBRID FUZZY POLYNOMIAL NEURAL NETWORKS." International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems 10, no. 03 (June 2002): 257–80. http://dx.doi.org/10.1142/s0218488502001478.

Повний текст джерела

Анотація:

We propose a hybrid architecture based on a combination of fuzzy systems and polynomial neural networks. The resulting Hybrid Fuzzy Polynomial Neural Networks (HFPNN) dwells on the ideas of fuzzy rule-based computing and polynomial neural networks. The structure of the network comprises of fuzzy polynomial neurons (FPNs) forming the nodes of the first (input) layer of the HFPNN and polynomial neurons (PNs) that are located in the consecutive layers of the network. In the FPN (that forms a fuzzy inference system), the generic rules assume the form "if A then y = P(x) " where A is fuzzy relation in the condition space while P(x) is a polynomial standing in the conclusion part of the rule. The conclusion part of the rules, especially the regression polynomial uses several types of high-order polynomials such as constant, linear, quadratic, and modified quadratic. As the premise part of the rules, both triangular and Gaussian-like membership functions are considered. Each PN of the network realizes a polynomial type of partial description (PD) of the mapping between input and out variables. HFPNN is a flexible neural architecture whose structure is based on the Group Method of Data Handling (GMDH) and developed through learning. In particular, the number of layers of the PNN is not fixed in advance but is generated in a dynamic way. The experimental part of the study involves two representative numerical examples such as chaotic time series and Box-Jenkins gas furnace data.

Стилі APA, Harvard, Vancouver, ISO та ін.

22

Pandey, Sunil, Naresh Kumar Nagwani, and Shrish Verma. "Aspects of programming for implementation of convolutional neural networks on multisystem HPC architectures." Journal of Physics: Conference Series 2062, no. 1 (November 1, 2021): 012016. http://dx.doi.org/10.1088/1742-6596/2062/1/012016.

Повний текст джерела

Анотація:

Abstract The training of deep learning convolutional neural networks is extremely compute intensive and takes long times for completion, on all except small datasets. This is a major limitation inhibiting the widespread adoption of convolutional neural networks in real world applications despite their better image classification performance in comparison with other techniques. Multidirectional research and development efforts are therefore being pursued with the objective of boosting the computational performance of convolutional neural networks. Development of parallel and scalable deep learning convolutional neural network implementations for multisystem high performance computing architectures is important in this background. Prior analysis based on computational experiments indicates that a combination of pipeline and task parallelism results in significant convolutional neural network performance gains of up to 18 times. This paper discusses the aspects which are important from the perspective of implementation of parallel and scalable convolutional neural networks on central processing unit based multisystem high performance computing architectures including computational pipelines, convolutional neural networks, convolutional neural network pipelines, multisystem high performance computing architectures and parallel programming models.

Стилі APA, Harvard, Vancouver, ISO та ін.

23

Galtier, Mathieu N., and Gilles Wainrib. "A Biological Gradient Descent for Prediction Through a Combination of STDP and Homeostatic Plasticity." Neural Computation 25, no. 11 (November 2013): 2815–32. http://dx.doi.org/10.1162/neco_a_00512.

Повний текст джерела

Анотація:

Identifying, formalizing, and combining biological mechanisms that implement known brain functions, such as prediction, is a main aspect of research in theoretical neuroscience. In this letter, the mechanisms of spike-timing-dependent plasticity and homeostatic plasticity, combined in an original mathematical formalism, are shown to shape recurrent neural networks into predictors. Following a rigorous mathematical treatment, we prove that they implement the online gradient descent of a distance between the network activity and its stimuli. The convergence to an equilibrium, where the network can spontaneously reproduce or predict its stimuli, does not suffer from bifurcation issues usually encountered in learning in recurrent neural networks.

Стилі APA, Harvard, Vancouver, ISO та ін.

24

Yang, Jing Bing, Hui Ding, and Shu Dong Zhang. "A Study of Image Weak-Edge Detection Combination of BP Neural Networks." Advanced Materials Research 225-226 (April 2011): 21–25. http://dx.doi.org/10.4028/www.scientific.net/amr.225-226.21.

Повний текст джерела

Анотація:

This paper proposes an image weak-edge detection method based on the combination of edge features and BP neural networks. Through analyzing the basic characteristics of the image edge points, we construct 8 groups 3-D feature vectors as the training sample set, combining with the learning function based on gradient descent momentum and the Levenberg-Marquardt training function, to train the BP neural network, further complete the image edge detection. Finally, compared with the traditional edge detection methods, the experimental results show that this method can detect the weak-edge and corner-edge much better.

Стилі APA, Harvard, Vancouver, ISO та ін.

25

Mustaqim, Mustaqim, Budi Warsito, and Bayu Surarso. "COMBINATION OF SYNTHETIC MINORITY OVERSAMPLING TECHNIQUE (SMOTE) AND BACKPROPAGATION NEURAL NETWORK TO CONTRACEPTIVE IUD PREDICTION." MEDIA STATISTIKA 13, no. 1 (June 21, 2020): 36–46. http://dx.doi.org/10.14710/medstat.13.1.36-46.

Повний текст джерела

Анотація:

Data imbalance occurs when the amount of data in a class is more than other data. The majority class is more data, while the minority class is fewer. Imbalance class will decrease the performance of the classification algorithm. Data on IUD contraceptive use is imbalanced data. National IUD failure in 2018 was 959 or 3.5% from 27.400 users. Synthetic minority oversampling technique (SMOTE) is used to balance data on IUD failure. Balanced data is then predicted with neural networks. The system is for predicting someone when using IUD whether they have a pregnancy or not. This study uses 250 data with 235 major data (not pregnant) and 15 minor data (pregnant). From 250 data divided into two parts, 225 training and 25 testing data. Minority class on training data will be duplicated to 1524%, so that the amount of minority data become balanced with the majority data. The results of predictive with an accuracy rate of 99.9% at 1000 epoch.

Стилі APA, Harvard, Vancouver, ISO та ін.

26

Cai, Ze Fan, and Dao Ping Huang. "Application Overview of Neural Network in Fault Diagnosis." Applied Mechanics and Materials 697 (November 2014): 419–24. http://dx.doi.org/10.4028/www.scientific.net/amm.697.419.

Повний текст джерела

Анотація:

This paper introduces the system structure of neural network in fault diagnosis, and summarizes some applications of neural network in fault diagnosis. The most commonly used neural network in fault diagnosis is BP network. The second is RBF network and the third is ART. For each neural network, the paper will discuss the neural network, and the introduce some applications. It also introduces the combination of neural networks and other techniques. In the last part, this paper points out the development trend of the neural network in fault diagnosis.

Стилі APA, Harvard, Vancouver, ISO та ін.

27

Ahmad, Zainal, Nazira Anisa Rahim, Alireza Bahadori, and Jie Zhang. "AIR POLLUITON INDEX PREDICTION USING MULTIPLE NEURAL NETWORKS." IIUM Engineering Journal 18, no. 1 (May 30, 2017): 1–12. http://dx.doi.org/10.31436/iiumej.v18i1.684.

Повний текст джерела

Анотація:

Air quality monitoring and forecasting tools are necessary for the purpose of taking precautionary measures against air pollution, such as reducing the effect of a predicted air pollution peak on the surrounding population and ecosystem. In this study a single Feed-forward Artificial Neural Network (FANN) is shown to be able to predict the Air Pollution Index (API) with a Mean Squared Error (MSE) and coefficient determination, R2, of 0.1856 and 0.7950 respectively. However, due to the non-robust nature of single FANN, a selective combination of Multiple Neural Networks (MNN) is introduced using backward elimination and a forward selection method. The results show that both selective combination methods can improve the robustness and performance of the API prediction with the MSE and R2 of 0.1614 and 0.8210 respectively. This clearly shows that it is possible to reduce the number of networks combined in MNN for API prediction, without losses of any information in terms of the performance of the final API prediction model.

Стилі APA, Harvard, Vancouver, ISO та ін.

28

Tchernev, Elko B., Rory G. Mulvaney, and Dhananjay S. Phatak. "Investigating the Fault Tolerance of Neural Networks." Neural Computation 17, no. 7 (July 1, 2005): 1646–64. http://dx.doi.org/10.1162/0899766053723096.

Повний текст джерела

Анотація:

Particular levels of partial fault tolerance (PFT) in feedforward artificial neural networks of a given size can be obtained by redundancy (replicating a smaller normally trained network), by design (training specifically to increase PFT), and by a combination of the two (replicating a smaller PFT-trained network). This letter investigates the method of achieving the highest PFT per network size (total number of units and connections) for classification problems. It concludes that for nontoy problems, there exists a normally trained network of optimal size that produces the smallest fully fault-tolerant network when replicated. In addition, it shows that for particular network sizes, the best level of PFT is achieved by training a network of that size for fault tolerance. The results and discussion demonstrate how the outcome depends on the levels of saturation of the network nodes when classifying data points. With simple training tasks, where the complexity of the problem and the size of the network are well within the ability of the training method, the hidden-layer nodes operate close to their saturation points, and classification is clean. Under such circumstances, replicating the smallest normally trained correct network yields the highest PFT for any given network size. For hard training tasks (difficult classification problems or network sizes close to the minimum), normal training obtains networks that do not operate close to their saturation points, and outputs are not as close to their targets. In this case, training a larger network for fault tolerance yields better PFT than replicating a smaller, normally trained network. However, since fault-tolerant training on its own produces networks that operate closer to their linear areas than normal training, replicating normally trained networks ultimately leads to better PFT than replicating fault-tolerant networks of the same initial size.

Стилі APA, Harvard, Vancouver, ISO та ін.

29

Yang, Jia Xuan. "Ship Transportation Forecasting Based on Extension Neural Network." Applied Mechanics and Materials 241-244 (December 2012): 2055–58. http://dx.doi.org/10.4028/www.scientific.net/amm.241-244.2055.

Повний текст джерела

Анотація:

Over the last decade, neural networks have found application for solving a wide range of areas from business, commerce, data mining and service systems. Hence, this paper constructs a new model based extension theory and neural network to forecast the ship transportation. The new neural network is a combination of extension theory and neural network. It uses an extension distance to measure the similarity between data and cluster center, and seek out the useless data, then to use neural network to forecast. When presenting a test example of prediction of ship transportation, the results verifies the effectiveness and applicability of the novel extension neural network. Compared with other forecasting techniques, especially other various neural networks, the extension neural network permits an adaptive process for significant and new information, and gives simpler structure, shorter learning times and higher accuracy.

Стилі APA, Harvard, Vancouver, ISO та ін.

30

Yamazaki, Akio, and Teresa B. Ludermir. "Neural Network Training with Global Optimization Techniques." International Journal of Neural Systems 13, no. 02 (April 2003): 77–86. http://dx.doi.org/10.1142/s0129065703001467.

Повний текст джерела

Анотація:

This paper presents an approach of using Simulated Annealing and Tabu Search for the simultaneous optimization of neural network architectures and weights. The problem considered is the odor recognition in an artificial nose. Both methods have produced networks with high classification performance and low complexity. Generalization has been improved by using the backpropagation algorithm for fine tuning. The combination of simple and traditional search methods has shown to be very suitable for generating compact and efficient networks.

Стилі APA, Harvard, Vancouver, ISO та ін.

31

Cao, Hongjun, and Borja Ibarz. "Hybrid discrete-time neural networks." Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences 368, no. 1930 (November 13, 2010): 5071–86. http://dx.doi.org/10.1098/rsta.2010.0171.

Повний текст джерела

Анотація:

Hybrid dynamical systems combine evolution equations with state transitions. When the evolution equations are discrete-time (also called map-based), the result is a hybrid discrete-time system. A class of biological neural network models that has recently received some attention falls within this category: map-based neuron models connected by means of fast threshold modulation (FTM). FTM is a connection scheme that aims to mimic the switching dynamics of a neuron subject to synaptic inputs. The dynamic equations of the neuron adopt different forms according to the state (either firing or not firing) and type (excitatory or inhibitory) of their presynaptic neighbours. Therefore, the mathematical model of one such network is a combination of discrete-time evolution equations with transitions between states, constituting a hybrid discrete-time (map-based) neural network. In this paper, we review previous work within the context of these models, exemplifying useful techniques to analyse them. Typical map-based neuron models are low-dimensional and amenable to phase-plane analysis. In bursting models, fast–slow decomposition can be used to reduce dimensionality further, so that the dynamics of a pair of connected neurons can be easily understood. We also discuss a model that includes electrical synapses in addition to chemical synapses with FTM. Furthermore, we describe how master stability functions can predict the stability of synchronized states in these networks. The main results are extended to larger map-based neural networks.

Стилі APA, Harvard, Vancouver, ISO та ін.

32

Mahul, Antoine, and Alex Aussem. "Distributed Neural Networks for Quality of Service Estimation in Communication Networks." International Journal of Computational Intelligence and Applications 03, no. 03 (September 2003): 297–308. http://dx.doi.org/10.1142/s1469026803000999.

Повний текст джерела

Анотація:

We study an original scheme based on distributed feedforward neural networks, aimed at modelling several queueing systems in cascade fed with bursty traffic. For each queueing system, a neural network is trained to anticipate the average number of waiting packets, the packet loss rate and the coefficient of variation of the packet inter-departure time, given the mean rate, the peak rate and the coefficient of variation of the packet inter-arrival time. The latter serves for the calculation of the coefficient of variation of the cell inter-arrival time of the aggregated traffic which is fed as input to the next neural network along the path. The potential of this method is successfully illustrated on several single server FIFO (First In, First Out) queues and on small queueing networks made up from a combination of queues in tandem and in parallel fed by a superposition of ideal sources. Our long-term goal is the design of preventive control strategy in a multiservice communication network.

Стилі APA, Harvard, Vancouver, ISO та ін.

33

Almeer, Mohamed. "Virus Recognition Based on Combination of Hashing and Neural Networks." International Journal of Computing and Information Sciences 12, no. 2 (December 25, 2016): 237–42. http://dx.doi.org/10.21700/ijcis.2016.128.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

34

Fu, Yijie. "Combination of Random Forests and Neural Networks in Social Lending." Journal of Financial Risk Management 06, no. 04 (2017): 418–26. http://dx.doi.org/10.4236/jfrm.2017.64030.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

35

Bockreis, A., and J. Jager. "Odour monitoring by the combination of sensors and neural networks." Environmental Modelling & Software 14, no. 5 (March 1999): 421–26. http://dx.doi.org/10.1016/s1364-8152(98)00105-4.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

36

Ueda, N. "Optimal linear combination of neural networks for improving classification performance." IEEE Transactions on Pattern Analysis and Machine Intelligence 22, no. 2 (2000): 207–15. http://dx.doi.org/10.1109/34.825759.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

37

Westmeyer, Uwe. "Deep neural networks only in combination with traditional computer vision." ATZelektronik worldwide 12, no. 6 (December 2017): 26–31. http://dx.doi.org/10.1007/s38314-017-0077-3.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

38

SOUDAH, EDUARDO, JOSÉ F. RODRÍGUEZ, and ROBERTO LÓPEZ. "MECHANICAL STRESS IN ABDOMINAL AORTIC ANEURYSMS USING ARTIFICIAL NEURAL NETWORKS." Journal of Mechanics in Medicine and Biology 15, no. 03 (June 2015): 1550029. http://dx.doi.org/10.1142/s0219519415500293.

Повний текст джерела

Анотація:

Combination of numerical modeling and artificial intelligence (AI) in bioengineering processes are a promising pathway for the further development of bioengineering sciences. The objective of this work is to use Artificial Neural Networks (ANN) to reduce the long computational times needed in the analysis of shear stress in the Abdominal Aortic Aneurysm (AAA) by finite element methods (FEM). For that purpose two different neural networks are created. The first neural network (Mesh Neural Network, MNN) creates the aneurysm geometry in terms of four geometrical factors (asymmetry factor, aneurism diameter, aneurism thickness, aneurism length). The second neural network (Tension Neural Network, TNN) combines the results of the first neural network with the arterial pressure (new factor) to obtain the maximum stress distribution (output variable) in the aneurysm wall. The use of FEM for the analysis and design of bioengineering processes often requires high computational costs, but if this technique is combined with artificial intelligence, such as neural networks, the simulation time is significantly reduced. The shear stress obtained by the artificial neural models developed in this work achieved 95% of accuracy respect to the wall stress obtained by the FEM. On the other hand, the computational time is significantly reduced compared to the FEM.

Стилі APA, Harvard, Vancouver, ISO та ін.

39

Araújo Júnior, José M., Leandro L. S. Linhares, Fábio M. U. Araújo, and Otacílio M. Almeida. "Fuzzy wavelet neural networks applied as inferential sensors of neonatal incubator dynamics." Journal of Intelligent & Fuzzy Systems 39, no. 3 (October 7, 2020): 2567–79. http://dx.doi.org/10.3233/jifs-190129.

Повний текст джерела

Анотація:

Newborns with health complications have great difficulty in regulating the body temperature due to distinct factors, which include the high metabolism rate and low weight. In this context, neonatal incubators help maintaining good health conditions because they provide a thermally-neutral environment, which is adequate to ensure the least energy expenditure by the newborn. In the last decades, artificial neural networks (ANNs) have been established as one of the main tools for the identification of nonlinear systems. Among the various approaches used in the identification process, the fuzzy wavelet neural network (FWNN) can be regarded as a prominent technique, consisting of the combination of wavelet neural network (WNN) and adaptive network-based fuzzy inference system (ANFIS). This work proposes the use of FWNN to infer the temperature and humidity values inside the incubator in order to certify the equipment operation. Results obtained with the analyzed neural system have shown the generalization and inference capacities of FWNNs, thus allowing their application to practical tasks aiming to increase the efficiency of incubators.

Стилі APA, Harvard, Vancouver, ISO та ін.

40

Cheng, Zhou, and Tao Juncheng. "Adaptive combination forecasting model for China’s logistics freight volume based on an improved PSO-BP neural network." Kybernetes 44, no. 4 (April 7, 2015): 646–66. http://dx.doi.org/10.1108/k-09-2014-0201.

Повний текст джерела

Анотація:

Purpose – To accurately forecast logistics freight volume plays a vital part in rational planning formulation for a country. The purpose of this paper is to contribute to developing a novel combination forecasting model to predict China’s logistics freight volume, in which an improved PSO-BP neural network is proposed to determine the combination weights. Design/methodology/approach – Since BP neural network has the ability of learning, storing, and recalling information that given by individual forecasting models, it is effective in determining the combination weights of combination forecasting model. First, an improved PSO based on simulated annealing method and space-time adjustment strategy (SAPSO) is proposed to solve out the connection weights of BP neural network, which overcomes the problems of local optimum traps, low precision and poor convergence during BP neural network training process. Then, a novel combination forecast model based on SAPSO-BP neural network is established. Findings – Simulation tests prove that the proposed SAPSO has better convergence performance and more stability. At the same time, combination forecasting models based on three types of BP neural networks are developed, which rank as SAPSO-BP, PSO-BP and BP in accordance with mean absolute percentage error (MAPE) and convergent speed. Also the proposed combination model based on SAPSO-BP shows its superiority, compared with some other combination weight assignment methods. Originality/value – SAPSO-BP neural network is an original contribution to the combination weight assignment methods of combination forecasting model, which has better convergence performance and more stability.

Стилі APA, Harvard, Vancouver, ISO та ін.

41

Browning, Leo A., William Watterson, Erica Happe, Savannah Silva, Roberto Abril Valenzuela, Julian Smith, Marissa P. Dierkes, Richard P. Taylor, Natalie O. V. Plank, and Colleen A. Marlow. "Investigation of Fractal Carbon Nanotube Networks for Biophilic Neural Sensing Applications." Nanomaterials 11, no. 3 (March 4, 2021): 636. http://dx.doi.org/10.3390/nano11030636.

Повний текст джерела

Анотація:

We propose a carbon-nanotube-based neural sensor designed to exploit the electrical sensitivity of an inhomogeneous fractal network of conducting channels. This network forms the active layer of a multi-electrode field effect transistor that in future applications will be gated by the electrical potential associated with neuronal signals. Using a combination of simulated and fabricated networks, we show that thin films of randomly-arranged carbon nanotubes (CNTs) self-assemble into a network featuring statistical fractal characteristics. The extent to which the network’s non-linear responses will generate a superior detection of the neuron’s signal is expected to depend on both the CNT electrical properties and the geometric properties of the assembled network. We therefore perform exploratory experiments that use metallic gates to mimic the potentials generated by neurons. We demonstrate that the fractal scaling properties of the network, along with their intrinsic asymmetry, generate electrical signatures that depend on the potential’s location. We discuss how these properties can be exploited for future neural sensors.

Стилі APA, Harvard, Vancouver, ISO та ін.

42

Poudel, Sushan, and Dr R. Anuradha. "Speech Command Recognition using Artificial Neural Networks." JOIV : International Journal on Informatics Visualization 4, no. 2 (May 26, 2020): 73. http://dx.doi.org/10.30630/joiv.4.2.358.

Повний текст джерела

Анотація:

Speech is one of the most effective way for human and machine to interact. This project aims to build Speech Command Recognition System that is capable of predicting the predefined speech commands. Dataset provided by Google’s TensorFlow and AIY teams is used to implement different Neural Network models which include Convolutional Neural Network and Recurrent Neural Network combined with Convolutional Neural Network. The combination of Convolutional and Recurrent Neural Network outperforms Convolutional Neural Network alone by 8% and achieved 96.66% accuracy for 20 labels.

Стилі APA, Harvard, Vancouver, ISO та ін.

43

Jamróz, Dariusz, Tomasz Niedoba, Paulina Pięta, and Agnieszka Surowiak. "The Use of Neural Networks in Combination with Evolutionary Algorithms to Optimise the Copper Flotation Enrichment Process." Applied Sciences 10, no. 9 (April 29, 2020): 3119. http://dx.doi.org/10.3390/app10093119.

Повний текст джерела

Анотація:

The paper presents a way of combining neural networks with evolutionary algorithms in order to find optimal parameters of the copper flotation enrichment process. The neural network was used in order to build a model describing the flotation process. The network learning was carried out with the use of samples from previous empirical measurements of the actual process. The model created in this way made it possible to find optimal parameters not only from among the measurement spaces, but also those that go beyond the measurements. Then, evolutionary algorithms were used in order to find optimal flotation parameters. The learned neural network previously described was used to calculate the criterion in the evolutionary algorithm.

Стилі APA, Harvard, Vancouver, ISO та ін.

44

Pedersen, S. M., J. S. Jørgensen, and J. B. Pedersen. "Use of neural networks to diagnose acute myocardial infarction. II. A clinical application." Clinical Chemistry 42, no. 4 (April 1, 1996): 613–17. http://dx.doi.org/10.1093/clinchem/42.4.613.

Повний текст джерела

Анотація:

Abstract We investigated the ability of neural networks to diagnose acute myocardial infarction (AMI) from laboratory data only. Several networks were trained with different combinations of data obtained at admission and within the first 12 h and 24 h after admission. The data used included the electrocardiogram (ECG) and the concentrations in serum of potassium, creatine kinase B-subunit (CKB), and lactate dehydrogenase isoenzyme 1 for 250 patients with suspected AMI. Based on admission data, the correct diagnosis was predicted for 76% of the patients in the test group from the ECG data only, and the best combination of ECG results with other variables yielded correct diagnoses for 85% of the test group. Using all of the data available within 24 h, the network predicted the correct diagnosis for 99% of the test data. Almost the same high predictability was obtained by using only two CKB values-recorded at admission and within 12 h after admission-or by using just the latter one. Neural networks and quadratic discriminant analysis performed similarly, but the neural networks were more robust for combinations with many laboratory data.

Стилі APA, Harvard, Vancouver, ISO та ін.

45

Lavrov, I., Y. Gerasimenko, J. Burdick, H. Zhong, R. R. Roy, and V. R. Edgerton. "Integrating multiple sensory systems to modulate neural networks controlling posture." Journal of Neurophysiology 114, no. 6 (December 1, 2015): 3306–14. http://dx.doi.org/10.1152/jn.00583.2015.

Повний текст джерела

Анотація:

In this study we investigated the ability of sensory input to produce tonic responses in hindlimb muscles to facilitate standing in adult spinal rats and tested two hypotheses: 1) whether the spinal neural networks below a complete spinal cord transection can produce tonic reactions by activating different sensory inputs and 2) whether facilitation of tonic and rhythmic responses via activation of afferents and with spinal cord stimulation could engage similar neuronal mechanisms. We used a dynamically controlled platform to generate vibration during weight bearing, epidural stimulation (at spinal cord level S1), and/or tail pinching to determine the postural control responses that can be generated by the lumbosacral spinal cord. We observed that a combination of platform displacement, epidural stimulation, and tail pinching produces a cumulative effect that progressively enhances tonic responses in the hindlimbs. Tonic responses produced by epidural stimulation alone during standing were represented mainly by monosynaptic responses, whereas the combination of epidural stimulation and tail pinching during standing or epidural stimulation during stepping on a treadmill facilitated bilaterally both monosynaptic and polysynaptic responses. The results demonstrate that tonic muscle activity after complete spinal cord injury can be facilitated by activation of specific combinations of afferent inputs associated with load-bearing proprioception and cutaneous input in the presence of epidural stimulation and indicate that whether activation of tonic or rhythmic responses is generated depends on the specific combinations of sources and types of afferents activated in the hindlimb muscles.

Стилі APA, Harvard, Vancouver, ISO та ін.

46

Ahmad, Zainal, Tang Pick Ha, and Rabiatul â€˜Adawiah Mat Noor. "IMPROVING NONLINEAR PROCESS MODELING USING MULTIPLE NEURAL NETWORK COMBINATION THROUGH BAYESIAN MODEL AVERAGING (BMA)." IIUM Engineering Journal 9, no. 1 (September 29, 2010): 19–36. http://dx.doi.org/10.31436/iiumej.v9i1.94.

Повний текст джерела

Анотація:

Improving model generalization of aggregated multiple neural networks for nonlinear dynamic process modeling using Bayesian Model Averaging (BMA) is proposed in this paper. Using BMA method, the posterior probability of a particular network being the true model is used as the combination weight for aggregating the network despite of using fixed combination weight as the model. The posterior probabilities are calculated using the sum square error (SSE) from the training data on each of the sample time, and tested to the testing data. The selections for the final weight are based on the least SSE calculated when each of the posterior probability is applied to the testing data. The likelihood method is employed for calculating the network error for each input data. Then, it is used to calculate the combination weight for the networks. Two non-linear dynamic system-modeling case studies are selected for this proposed method, which are water tank level prediction and pH neutralization process. Application result demonstrates that the combination using BMA technique can significantly improve model generalization compared to other linear combination approaches.

Стилі APA, Harvard, Vancouver, ISO та ін.

47

Ji, Xiaohong, Ying Pan, Guoqing Jia, and Weidong Fang. "A neural network-based prediction model in water monitoring networks." Water Supply 21, no. 5 (February 15, 2021): 2347–56. http://dx.doi.org/10.2166/ws.2021.046.

Повний текст джерела

Анотація:

Abstract To improve the prediction accuracy of ammonia nitrogen in water monitoring networks, the combination of a bio-inspired algorithm and back propagation neural network (BPNN) has often been deployed. However, due to the limitations of the bio-inspired algorithm, it would also fall into the local optimal. In this paper, the seagull optimization algorithm (SOA) was used to optimize the structure of BPNN to obtain a better prediction model. Then, an improved SOA (ISOA) was proposed, and the common functional validation method was used to verify its optimization performance. Finally, the ISOA was applied to improve BPNN, which is known as the improved seagull optimization algorithm–back propagation (ISOA–BP) model. The simulation results showed that the prediction accuracy of ammonia nitrogen was greatly improved and the proposed model can be better applied to the prediction of complex water quality parameters in water monitoring networks.

Стилі APA, Harvard, Vancouver, ISO та ін.

48

Sánchez-Hevia, Héctor A., Roberto Gil-Pita, Manuel Utrilla-Manso, and Manuel Rosa-Zurera. "Age group classification and gender recognition from speech with temporal convolutional neural networks." Multimedia Tools and Applications 81, no. 3 (January 2022): 3535–52. http://dx.doi.org/10.1007/s11042-021-11614-4.

Повний текст джерела

Анотація:

AbstractThis paper analyses the performance of different types of Deep Neural Networks to jointly estimate age and identify gender from speech, to be applied in Interactive Voice Response systems available in call centres. Deep Neural Networks are used, because they have recently demonstrated discriminative and representation capabilities in a wide range of applications, including speech processing problems based on feature extraction and selection. Networks with different sizes are analysed to obtain information on how performance depends on the network architecture and the number of free parameters. The speech corpus used for the experiments is Mozilla’s Common Voice dataset, an open and crowdsourced speech corpus. The results are really good for gender classification, independently of the type of neural network, but improve with the network size. Regarding the classification by age groups, the combination of convolutional neural networks and temporal neural networks seems to be the best option among the analysed, and again, the larger the size of the network, the better the results. The results are promising for use in IVR systems, with the best systems achieving a gender identification error of less than 2% and a classification error by age group of less than 20%.

Стилі APA, Harvard, Vancouver, ISO та ін.

49

Kocyigit, Necati, and Huseyin Bulgurcu. "Modeling of overall heat transfer coefficient of a concentric double pipe heat exchanger with limited experimental data by using curve fitting and ANN combination." Thermal Science 23, no. 6 Part A (2019): 3579–90. http://dx.doi.org/10.2298/tsci171206111k.

Повний текст джерела

Анотація:

The modeling accuracy of artificial neural networks (ANN) was evaluated by using limited heat exchanger data acquired experimentally. The artificial neural networks were used for predicting the overall heat transfer coefficient of a concentric double pipe heat exchanger where oil flowed inside the inner tube while the water flowed in the outer tube. In the cases of parallel and counter flows, the experimental data were collected by testing heat exchanger in wide range of operating conditions. Curve fitting and artificial neural network combination was used for the estimation of the overall heat transfer coefficient to compensate the experimental errors in the data. The curve fitting was used to detect the trend and generate data points between the experimentally collected points. The artificial neural network was trained better from the generated data set. The feed forward type artificial neural network was trained by using the Levenberg-Marquardt algorithm. Two backpropagation network type artificial neural network algorithms were also used, and their performance were compared with the estimation of the Levenberg-Marquardt algorithm. The average estimation error between the predictions and the experimental data were in the range of 1.31e?4 to 4.35e?2%. The study confirmed that curve fitting and artificial neural network combination could be used effectively to estimate the overall heat transfer coefficient of heat exchanger.

Стилі APA, Harvard, Vancouver, ISO та ін.

50

Wang, Qiang, and Yang Yang. "Combined Prediction of Wind Power Using Multi-Dimension Embedding Phase Space." Applied Mechanics and Materials 321-324 (June 2013): 838–41. http://dx.doi.org/10.4028/www.scientific.net/amm.321-324.838.

Повний текст джерела

Анотація:

In order to diminish the effect of reconstructed parameters to prediction of chaotic, a combined model for wind power prediction based on multi-dimension embedding is proposed. The combined model makes use of neural network method to achieve combination of several neural networks models based on phase space reconstruction, which can synthesize information and fuse prediction deviation in different embedding dimension, resulting in forecast accuracy improved. Simulation is performed to the real power time series Fujin wind farm. The results show that the combined prediction model is effective, and the prediction error of neural network combination is less than 7%.

Стилі APA, Harvard, Vancouver, ISO та ін.

Статті в журналах з теми "Combination of neural networks"

Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями