检索结果-内蒙古大学图书馆

Application of optimized artificial intelligence algorithm to evaluate the heating energy demand of non-residential buildings at European level

引用

ENERGY 2019年 176卷 380-391页

作者： Ciulla, G. D'Amico, A. Lo Brano, V. Traverso, M. Univ Palermo Dept Engn DI Palermo Italy Rhein Westfal TH Aachen Inst Sustainabil Civil Engn Aachen Germany

A reliable preliminary forecast of heating energy demand of a building by using a detailed dynamic simulation software typically requires an in-depth knowledge of the thermal balance, several input data and a very skilled user. The authors will describe how to use Artificial Neural Networks to predict the demand for thermal energy linked to the winter climatization of non-residential buildings. To train the neural network it was necessary to develop an accurate energy database that represents the basis of the training of a specific Artificial Neural Networks. Data came from detailed dynamic simulations performed in the TRNSYS environment. The models were built according to the standards and laws of building energy requirements in seven different European countries, for 3 cities in each country and with 13 different shape factors, obtaining 2184 detailed dynamic simulations of non-residential buildings designed with high energy performances. The authors identified the best ANN topology developing a tool for determining, both quickly and simply, the heating energy demand of a non-residential building, knowing only 12 well-known thermo-physical parameters and without any computational cost or knowledge of the thermal balance. The reliability of this approach is demonstrated by the low standard deviation less than 5 kWh/(m(2).year). (C) 2019 Elsevier Ltd. All rights reserved.

关键词： Building simulation Thermal balance High energy performance Artificial neural network learning algorithm Decision support tool

来源：评论

学校读者我要写书评

暂无评论

Ensemble-type numerical uncertainty information from single model integrations

引用

JOURNAL OF COMPUTATIONAL PHYSICS 2015年 292卷 30-42页

作者： Rauser, Florian Marotzke, Jochem Korn, Peter Max Planck Inst Meteorol D-20146 Hamburg Germany

We suggest an algorithm that quantifies the discretization error of time-dependent physical quantities of interest (goals) for numerical models of geophysical fluid dynamics. The goal discretization error is estimated using a sum of weighted local discretization errors. The key feature of our algorithm is that these local discretization errors are interpreted as realizations of a random process. The random process is determined by the model and the flow state. From a class of local error random processes we select a suitable specific random process by integrating the model over a short time interval at different resolutions. The weights of the influences of the local discretization errors on the goal are modeled as goal sensitivities, which are calculated via automatic differentiation. The integration of the weighted realizations of local error random processes yields a posterior ensemble of goal approximations from a single run of the numerical model. From the posterior ensemble we derive the uncertainty information of the goal discretization error. This algorithm bypasses the requirement of detailed knowledge about the models discretization to generate numerical error estimates. The algorithm is evaluated for the spherical shallow-water equations. For two standard test cases we successfully estimate the error of regional potential energy, track its evolution, and compare it to standard ensemble techniques. The posterior ensemble shares linear-error-growth properties with ensembles of multiple model integrations when comparably perturbed. The posterior ensemble numerical error estimates are of comparable size as those of a stochastic physics ensemble. (C) 2015 Elsevier Inc. All rights reserved.

关键词： Numerical errors learning algorithm Stochastic methods Ensemble methods Geophysical fluid dynamics Mixed finite volume/finite difference scheme Icosahedral grid Shallow water equations Automatic differentiation algorithmic differentiation

来源：评论

学校读者我要写书评

暂无评论

Optimal Node Selection for Hybrid Attack in Underwater Acoustic Sensor Networks: A Virtual Expert-Guided Bandit algorithm

引用

IEEE SENSORS JOURNAL 2020年第3期20卷 1679-1687页

作者： Li, Xinbin Zhou, Yi Yan, Lei Zhao, Haihong Yan, Xiaodong Luo, Xi Yanshan Univ Inst Elect Engn Qinhuangdao 066004 Hebei Peoples R China

In this study, adversarial graph bandit theory is used to rapidly select the optimal attack node in underwater acoustic sensor networks (UASNs) with unknown topology. To ensure the flexibility and elusiveness of underwater attack, we propose a bandit-based hybrid attack mode that combines active jamming and passive eavesdropping. We also present a virtual expert-guided online learning algorithm to select the optimal node without priori topology information and complex calculation. The virtual expert mechanism is proposed to guide the algorithm learning. The expert establishes a virtual topology configuration, which addresses the blind exploration and energy consumption of attackers to a large extent. With the acoustic broadcast characteristic, we also put forward an expert self-updating method to follow the changes of real networks. This method enables the algorithm to commendably adapt to the dynamic environments. Simulation results verify the strong adaptability and robustness of the proposed algorithm.

关键词： Network attack learning algorithm multi armed bandit underwater acoustic sensor networks

来源：评论

学校读者我要写书评

暂无评论

A new boosting algorithm for improved time-series forecasting with recurrent neural networks

引用

INFORMATION FUSION 2008年第1期9卷 41-55页

作者： Assaad, Mohammad Bone, Romuald Cardot, Hubert Univ Tours Lab Informat F-37200 Tours France

Ensemble methods for classification and regression have focused a great deal of attention in recent years. They have shown, both theoretically and empirically, that they are able to perform substantially better than single models in a wide range of tasks. We have adapted an ensemble method to the problem of predicting future values of time series using recurrent neural networks (RNNs) as base learners. The improvement is made by combining a large number of RNNs, each of which is generated by training on a different set of examples. This algorithm is based on the boosting algorithm where difficult points of the time series are concentrated on during the learning process however, unlike the original algorithm, we introduce a new parameter for tuning the boosting influence on available examples. We test our boosting algorithm for RNNs on single-step-ahead and multi-step-ahead prediction problems. The results are then compared to other regression methods, including those of different local approaches. The overall results obtained through our ensemble method are more accurate than those obtained through the standard method, backpropagation through time, on these datasets and perform significantly better even when long-range dependencies play an important role. (C) 2006 Elsevier B.V. All rights reserved.

关键词： learning algorithm boosting recurrent neural networks time series forecasting multi-step-ahead prediction

来源：评论

学校读者我要写书评

暂无评论

Reliability Enhancements in Memristive Neural Network Architectures

引用

IEEE TRANSACTIONS ON NANOTECHNOLOGY 2019年 18卷 866-878页

作者： Gnawali, Krishna Prasad Paudel, Bijay Raj Mozaffari, Seyed Nima Tragoudas, Spyros Southern Illinois Univ Dept Elect & Comp Engn Carbondale IL 62901 USA Nvidia Corp Santa Clara CA 95051 USA

Memristive Crossbar Arrays (MCAs) are widely used in designing fast and compact neuromorphic systems. However, such systems require on-chip implementation of the backpropagation algorithm to accommodate process variations. This paper proposes a low hardware overhead on-chip implementation of the backpropagation algorithm that utilizes effectively the very dense MCAs. On-chip learning using the proposed architecture increases the reliability of the neuromorphic system in the presence of process variations in the neural component. The second contribution of this paper is an architectural enhancement to cope with another reliability consideration, namely the aging transistors in the MCA. Experimental results show the impact of reliability enhancement.

关键词： Stochastic Gradient Descent learning algorithm Neuromorphic Computing Memristive Crossbar Array Non-Volatile Memory Transistor Aging

来源：评论

学校读者我要写书评

暂无评论

The Multilayer Random Neural Network

引用

NEURAL PROCESSING LETTERS 2013年第2期37卷 111-133页

作者： Aguilar, Jose Molina, Cristhian Univ Los Andes CEMISID Dept Computac Escuela Ingn Sistemas Merida Venezuela

We propose in this paper an extended model of the random neural networks, whose architecture is multi-feedback. In this case, we suppose different layers where the neurons have communication with the neurons of the neighbor layers. We present its learning algorithm and its possible utilizations;specifically, we test its use in an encryption mechanism where each layer is responsible of a part of the encryption or decryption process. The multilayer random neural network is a stochastic neural model, in this way the entire proposed encryption model has that feature.

关键词： Random neural network Multilayer artificial neural network learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Analysis and convergence theorem of complex quadratic form as decision boundary for data classification

引用

ELECTRONICS LETTERS 2015年第7期51卷 561-U150页

作者： Cordero, R. Suemitsu, W. I. Pinto, J. O. P. Univ Fed Rio de Janeiro Dept Elect Engn Rio De Janeiro Brazil Univ Fed Mato Grosso do Sul Dept Elect Engn Campo Grande Brazil

The application of the complex quadratic form as the decision boundary for complex-valued data classification is described. This function is always real when its matrix is Hermitian. Thus, a simple sign function to classify the input data is used. This matrix is obtained through an iterative learning process similar to the Rosenblatt algorithm. The concept of the Frobenius matrix norm is used to prove that the proposed learning algorithm converges if a solution exists. This approach is different from other complex-valued neural networks that use optimisation techniques or feature mapping. An artificial neuron that uses a complex quadratic form as the decision boundary is called a complex quadratic neural unit.

关键词： Hermitian matrices convergence data analysis decision making iterative methods learning (artificial intelligence) neural nets pattern classification CQNU CVNN Frobenius matrix norm Hermitian matrix Rosenblatt algorithm artificial neuron complex quadratic form analysis complex quadratic neural unit complex-valued data classification complex-valued neural networks convergence theorem decision boundary feature mapping iterative learning process learning algorithm optimisation techniques simple sign function

来源：评论

学校读者我要写书评

暂无评论

The Use of Neural Network Predictors for Analyzing the Elevator Vibrations

引用

ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING 2014年第2期39卷 1157-1170页

作者： Taplak, Hamdi Erkaya, Selcuk Yildirim, Sahin Uzmay, Ibrahim Erciyes Univ Vocat Sch Kayseri TR-38039 Kayseri Turkey Erciyes Univ Fac Engn Dept Mechatron Engn TR-38039 Kayseri Turkey

In spite of advanced electro-mechanical technology on passenger or load elevators, elevator accidents still occur. Therefore, it is necessary to analyze vibrations of elevators with and without load for predicting some possible faults on their mechanical parts. This study proposes an adaptive neural network predictor to estimate and evaluate the vibrations on elevator systems. For this purpose, elevator vibrations are measured from two points of the elevator system for different working conditions, and different types of neural network analyzers are employed to evaluate the system vibrations. Simulation results show that neural networks can be used as an adaptive analyzer for such systems in the experimental applications.

关键词： Elevator vibration Neural network learning algorithm

来源：评论

学校读者我要写书评

暂无评论

THE ALSM algorithm - AN IMPROVED SUBSPACE METHOD OF CLASSIFICATION

引用

PATTERN RECOGNITION 1983年第4期16卷 421-427页

作者： OJA, E KUUSELA, M HELSINKI UNIV TECHNOL DEPT TECH PHYSINFORMAT TECH LABSF-02150 ESPOO 15FINLAND

The subspace methods of classification are decision-theoretic pattern recognition methods in which each class is represented in terms of a linear subspace of the Euclidean pattern or feature space. In most reported subspace methods, a priori criteria have been applied to improve either the class representation or the discriminatory power of the subspaces. Recently, construction of the class subspaces by learning has been suggested by Kohonen, resulting in an improved classification accuracy. A variant of the original learning rule is analyzed and results are given on its application to the classification of phonemes in automatic speech recognition.

关键词： Pattern recognition Subspace method learning algorithm Orthogonal expansion

来源：评论

学校读者我要写书评

暂无评论

A spheres-based support vector machine for pattern classification

引用

NEURAL COMPUTING & APPLICATIONS 2019年第1-Sup期31卷 379-396页

作者： Peng, Xinjun Shanghai Normal Univ Dept Math Shanghai 200234 Peoples R China

This paper proposes a new spheres-based support vector machine (SSVM) for binary data classification. The proposed SSVM is formulated by clustering the training points according to the similarity between classes, i.e., it constructs two spheres simultaneously by solving a single optimization programming problem, in which each point is as far as possible away from the sphere center of opposite class and its projection value on the directed line segment between the two centers is as far as possible not larger than the corresponding radius. This SSVM has a perfect geometric interpretation for its dual problem. By considering the characteristics of the dual optimization problem of SSVM, an efficient learning algorithm for SSVM, which can be easily extended to other SVM-type classifiers, based on the gradient descent and the clipping strategy is further presented. Computational results on several synthetic as well as benchmark datasets indicate the significant advantages of the SSVM classifier in the computational cost and test accuracy.

关键词： Support vector machine Spheres Projection Geometric interpretation learning algorithm

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：