检索结果-内蒙古大学图书馆

Greek long-term energy consumption prediction using artificial neural networks

ENERGY 2010年第2期35卷 512-517页

作者： Ekonomou, L. ASPETE Sch Pedag & Technol Educ Dept Elect Engn Educators Athens 14121 Greece

In this paper artificial neural networks (ANN) are addressed in order the Greek long-term energy consumption to be predicted. The multilayer perceptron model (MLP) has been used for this purpose by testing several possible architectures in order to be selected the one with the best generalizing ability. Actual recorded input and output data that influence long-term energy consumption were used in the training, validation and testing process. The developed ANN model is used for the prediction of 2005-2008, 2010, 2012 and 2015 Greek energy consumption. The produced ANN results for years 2005-2008 were compared with the results produced by a linear regression method, a support vector machine method and with real energy consumption records showing a great accuracy. The proposed approach can be useful in the effective implementation of energy policies, since accurate predictions of energy consumption affect the capital investment, the environmental quality, the revenue analysis, the market research management, while conserve at the same time the supply security. Furthermore it constitutes an accurate tool for the Greek long-term energy consumption prediction problem, which up today has not been faced effectively. (C) 2009 Elsevier Ltd. All rights reserved.

关键词： Artificial neural networks Energy consumption Gross domestic product Installed capacity Multilayer perceptron Prediction linear regression method Support vector machine method

来源：评论

学校读者我要写书评

暂无评论

Improving Long-Term Flood Forecasting Accuracy Using Ensemble Deep Learning Models and an Attention Mechanism

引用

JOURNAL OF HYDROLOGIC ENGINEERING 2024年第6期29卷 04024042-04024042页

作者： Kordani, Marjan Nikoo, Mohammad Reza Fooladi, Mahmood Ahmadianfar, Iman Nazari, Rouzbeh Gandomi, Amir H. Shahid Chamran Univ Ahvaz Dept Hydrol & Water Resources Ahvaz *** Iran Sultan Qaboos Univ Dept Civil & Architectural Engn Muscat 123 Oman Isfahan Univ Technol Dept Civil Engn Esfahan *** Iran Behbahan Khatam Alanbia Univ Technol Dept Civil Engn Behbahan *** Iran Univ Memphis Dept Civil Engn Herff Coll Engn Memphis TN 38152 USA Univ Technol Sydney Dept Engn & IT Ultimo NSW 2007 Australia Obuda Univ Univ Res & Innovat Ctr EKIK H-1034 Budapest Hungary

Floods, as major natural disasters, cause massive property destruction and death. Understanding the occurrence time of this event by advance notice helps consider operational flood prevention systems and platforms. Precise flood forecasting provides a suitable time for policymakers and the public to consider helpful responses to this event. This study introduces an innovative methodology to enhance the precision of long-term flood predictions by employing a multistep forecasting approach. Our approach leverages historical time-series data on precipitation and streamflow to train an autoencoder algorithm. The primary objective is to develop advanced forecasting models to predict 12-step-weekly ahead flood occurrences during the critical April to July period from 2019 to 2021 within the DuPage River basin, Illinois, USA. In order to achieve this goal, we explore three deep learning techniques: bidirectional long short-term memory (BI-LSTM), ensemble long short-term memory (E-LSTM), and ensemble long short-term memory-gated recurrent unit (E-LSTM-GRU). Then, we integrate an attention mechanism (AM) that utilizes dynamic fusion techniques to emphasize the salient features of ensemble models. A dedicated fusion model is developed for each forecasting stage, effectively consolidating the predictions from various deep-learning models. Additionally, two traditional machine learning techniques, namely MLP and SVM models, are used to compare and justify the efficiency of applied deep learning models. The performance evaluation of our approach using statistical error metrics, including coefficient of determination (R2), normalized root mean square error, normalized mean absolute error, mean absolute percentage error, Nash-Sutcliffe efficiency, Kling-Gupta efficiency, and percent bias, for the 12th step prediction reveals impressive results, with average values of 0.976, 2.393, 1.892, 20.956, 0.967, 0.923, and 2.307, respectively. These findings underscore the capability of our

关键词： Long-term flood forecasting Deep learning techniques Long-short-term memory (LSTM) model Attention mechanism Ensemble models linear regression method

来源：评论

学校读者我要写书评

暂无评论

Energy estimation models for video decoders: reconfigurable video coding-CAL case-study

引用

IET COMPUTERS AND DIGITAL TECHNIQUES 2015年第1期9卷 3-15页

作者： Ren, Rong Juarez, Eduardo Sanz, Cesar Raulet, Mickael Pescador, Fernando Univ Politecn Madrid Res Ctr Software Technol & Multimedia Syst CITSEM ES-28031 Madrid Spain CNRS UMR 6164 IETR INSA F-35043 Rennes France

In this study, a platform-independent energy estimation methodology is proposed to estimate the energy consumption of reconfigurable video coding (RVC)-CAL video codec specifications. This methodology is based on the performance monitoring counters (PMCs) of embedded platforms and demonstrates its portability, simplicity and accuracy for on-line estimation. It has two off-line procedure stages: the former, which automatically identifies the most appropriate PMCs with no specific detailed knowledge of the employed platform, and the latter, which trains the model using either a linear regression or a multivariable adaptive regression splines (MARS) method. Experimenting on an RVC-CAL decoder, the proposed PMC-driven model can achieve an average estimation error <10%. In addition, the maximal model computation overhead is 4.04%. The results show that the training video sequence has significant influence on the model accuracy. An experimental metric is introduced to achieve more stable accurate models based on a combination of training sequences. Furthermore, a comparison demonstrates better predictive ability of MARS techniques in scenarios with multi-core platforms. Finally, the experimental results show a good potential of energy efficiency improvement when the estimation model is combined into the RVC framework. In two different scenarios, the battery lifetime is increased 5.16% and 20.9%, respectively.

关键词： video coding video codecs regression analysis splines (mathematics) image sequences decoding platform-independent energy estimation methodology video decoders reconfigurable video coding performance monitoring counters energy consumption online estimation offline procedure stages linear regression method multivariable adaptive regression splines method MARS method RVC-CAL video codec specifications PMC-driven model accuracy model training video sequence predictive ability piecewise modelling techniques multicore platforms energy efficiency improvement

来源：评论

学校读者我要写书评

暂无评论

Both-branch amphiphilic polymer oil displacing system: Molecular weight, surfactant interactions and enhanced oil recovery performance

引用

COLLOIDS AND SURFACES A-PHYSICOCHEMICAL AND ENGINEERING ASPECTS 2016年 509卷 440-448页

作者： Ji, Yanfeng Wang, Duanping Cao, Xulong Guo, Lanlei Zhu, Yangwen Sinopec Shengli Oilfield Co Ltd Explorat & Dev Res Inst Dongying 257000 Peoples R China

Hydrophobically modified polyacrylamidepolymers were synthesized by an aqueous micellar copolymerization, the N-benzyl-N-n-hexadecyl acrylamide being used as hydrophobic comonomer. The effect of the molecular weight (MW) and surfactant interactions on the rheological properties and oil-water interfacial activity were studied. The results indicate that increasing MW, the critical aggregation concentration of amphiphilic polymer will be decreased, and the network structural strength increased, which was measured by fluorescent probes, DLS and electron microscope. Mixing with the surfactant, sodium dodecyl sulfate (SDS), the solution viscosity increased at first and decreased later on with increasing the ratio of SDS concentration, and the dynamic interfacial tension between oil and water can be reduced by two orders of magnitude compared to the polymer solution only. The result of enhance oil recovery performance of the polymer/surfactant compound system is that it can significantly reduce the residual oil saturation due to the synergistic effect of the increasing viscosity and surface activity. The overall recovery efficiency was raised by 10-25% OOIP compared to the baseline polymers. (C) 2016 Elsevier B.V. All rights reserved.

关键词： Both-branch amphiphilic polymer Polymer/surfactant compound system Aggregation behavior linear regression method Dynamic interfacial tension Enhanced oil recovery

来源：评论

学校读者我要写书评

暂无评论

Investigation on linearisation of data-driven transport research: two representative case studies

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2020年第7期14卷 675-683页

作者： Zou, Yun Kuang, Yan Zhi, Yue Qu, Xiaobo Sch Civil & Environm Engn Univ Technol Sydney Sydney NSW 4007 Australia Griffith Univ Griffith Sch Engn Gold Coast Qld 4222 Australia Binzhou Med Univ Sch Rehabil Med Yantai 264003 Peoples R China Chalmers Univ Technol Dept Architecture & Civil Engn S-41296 Gothenburg Sweden

Transportation engineering, as a practical engineering discipline, relies heavily on the accurate calibration of importation parameters from field data. In the real world, most transport relations possess inherent non-linearity. Two prevailing methods for handling non-linear regression are the non-linear least-squares method (LSM) with an iterative solution, and linearisation for the non-linear regression function. The second method applies a linear regression method to solve the non-linear regression problem but requires a data transformation of the observations from variant coordinates, and the objective function is suspected to be changed accordingly. This work describes the authors' investigation into the problem of non-linear regression through two illustrative examples, the calibration of three non-linear (either exponential or logarithmic) single-regime models for fundamental diagram and the regression of non-linear (power) bunker-consumption model, by applying the weighted LSM (WLSM) and the ordinary LSM to calibrate. It is found that linearising the regression model leads to deviations, and the data transformation can create even more concern with the WLSM because the weights can be redistributed after the data transformation. A further investigation into the linear regression and the non-linear regression gives more suggestions on the choice of regression method.

关键词： transportation least squares approximations mechanical engineering computing regression analysis data-driven transport research transportation engineering nonlinearity nonlinear regression function linear regression method nonlinear regression problem data transformation nonlinear bunker-consumption model regression model

来源：评论

学校读者我要写书评

暂无评论

vFitness: a web-based computing tool for improving estimation of in vitro HIV-1 fitness experiments

引用

BMC BIOINFORMATICS 2010年第8期11卷 1-6页

作者： Ma, Jingming Dykes, Carrie Wu, Tao Huang, Yangxin Demeter, Lisa Wu, Hulin Univ Rochester Sch Med & Dent Dept Biostat & Computat Biol Rochester NY 14642 USA Univ Rochester Sch Med & Dent Dept Med Rochester NY 14642 USA Univ S Florida Coll Publ Hlth Dept Epidemiol & Biostat Tampa FL USA

Background: The replication rate (or fitness) between viral variants has been investigated in vivo and in vitro for human immunodeficiency virus (HIV). HIV fitness plays an important role in the development and persistence of drug resistance. The accurate estimation of viral fitness relies on complicated computations based on statistical methods. This calls for tools that are easy to access and intuitive to use for various experiments of viral fitness. Results: Based on a mathematical model and several statistical methods (least-squares approach and measurement error models), a Web-based computing tool has been developed for improving estimation of virus fitness in growth competition assays of human immunodeficiency virus type 1 (HIV-1). Conclusions: Unlike the two-point calculation used in previous studies, the estimation here uses linear regression methods with all observed data in the competition experiment to more accurately estimate relative viral fitness parameters. The dilution factor is introduced for making the computational tool more flexible to accommodate various experimental conditions. This Web-based tool is implemented in C# language with Microsoft ***, and is publicly available on the Web at http://***/vFitness/.

关键词： Computing Tool Dilution Factor Mutant Virus Relative Fitness linear regression method

来源：评论

学校读者我要写书评

暂无评论

Spatio-temporal dynamics of vegetation in Jungar Banner of China during 2000–2017

引用

Journal of Arid Land 2019年第6期11卷 837-854页

作者： LI Xinhui LEI Shaogang CHENG Wei LIU Feng WANG Weizhong Engineering Research Center of Ministry of Education for Mine Ecological Restoration China University of Mining and TechnologyXuzhou 221116China School of Environment Science and Spatial Informatics China University of Mining and TechnologyXuzhou 221116China Environmental Restoration and Management Center of Jungar Banner Mining Area Erdos 017100China

It is known that the exploitation of opencast coal mines has seriously damaged the environments in the semi-arid *** status can reliably reflect the ecological degeneration and restoration in the opencast mining areas in the semi-arid ***-time series MODIS NDVI data are widely used to simulate the vegetation cover to reflect the disturbance and restoration of local *** this study, both qualitative(linear regression method and coefficient of variation(CoV)) and quantitative(spatial buffer analysis, and change amplitude and the rate of change in the average NDVI) analyses were conducted to analyze the spatio-temporal dynamics of vegetation during 2000–2017 in Jungar Banner of Inner Mongolia Autonomous Region, China, at the large(Jungar Banner and three mine groups) and small(three types of functional areas: opencast coal mining excavation areas, reclamation areas and natural areas) *** results show that the rates of change in the average NDVI in the reclamation areas(20%–60%) and opencast coal mining excavation areas(10%–20%) were considerably higher than that in the natural areas(<7%).The vegetation in the reclamation areas experienced a trend of increase(3–5 a after reclamation)-decrease(the sixth year of reclamation)-*** vegetation in Jungar Banner has a spatial heterogeneity under the influences of mining and reclamation *** ratio of vegetation improvement area to vegetation degradation area in the west, southwest and east mine groups during 2000–2017 was 8:1, 20:1 and 33:1, *** regions with the high CoV of NDVI above 0.45 were mainly distributed around the opencast coal mining excavation areas, and the regions with the CoV of NDVI above 0.25 were mostly located in areas with low(28.8%) and medium-low(10.2%) vegetation *** average disturbance distances of mining activities on vegetation in the three mine groups(west, southwest and east) were 800, 800 and 1000 m, *** greater t

关键词： NDVI spatio-temporal dynamics linear regression method mining activities opencast coal mining areas reclamation areas Jungar Banner

来源：评论

学校读者我要写书评

暂无评论

Comparison of two methods for the analysis of composite material

引用

JOURNAL OF MATERIALS PROCESSING TECHNOLOGY 2000年第1-3期106卷 87-93页

作者： Konderla, P Mokanek, T Wroclaw Univ Technol Inst Civil Engn PL-50371 Wroclaw Poland

The subject of this paper is the neural network and linear regression as tools for the estimation of the component-property relationship of composite materials. Test data were used for the teaching of an ANN, verifying its output and computing a representation of the regression polynomial. Two kinds of expert systems have been built and tested for different sets of input and output characterizing the component and the properties of the material. Numerical experiments were conducted for real data given by a concrete factory. The linear regression method and the developed ANNs can be used for predicting material properties when the components are known as well as for the inverted problem. The expert systems were described and compared. (C) 2000 Elsevier Science B.V. All rights reserved.

关键词： composite material linear regression method ANN

来源：评论

学校读者我要写书评

暂无评论

Asymmetric response aggregation heuristics for rating prediction and recommendation

引用

APPLIED INTELLIGENCE 2020年第5期50卷 1416-1436页

作者： Ji, Shujuan Yang, Wei Guo, Shenghui Chiu, Dickson K. W. Zhang, Chunjin Yuan, Xinyue Shandong Univ Sci & Technol Key Lab Wisdom Mine Informat Technol Shandong Pro Qingdao Peoples R China Univ Hong Kong Fac Educ Hong Kong Peoples R China Shandong Univ Sci & Technol NIC Qingdao 266590 Shandong Peoples R China

User-based collaborative filtering is widely used in recommendation systems, which normally comprises three steps: (1) finding the nearest conceptual neighbors, (2) aggregating the neighbors' ratings to predict the ratings of unrated items, and (3) generating recommendations based on the prediction. Existing algorithms mainly focus on steps 1 and 3 but neglect subtle treatments of aggregating neighbors' suggestions in step 2. Based on the discovery of psychology that (i) users' responses to positive and negative suggestions are different, and (ii) users may respond differently from one another, this paper proposes a Personal Asymmetry Response-based Suggestions Aggregation (PARSA) algorithm, which first uses a linear regression method to learn each user's response to negative/positive suggestions from neighbors and then uses a gradient descent algorithm for optimizing them. In addition, this paper designs an Identical Asymmetry Response-based Suggestions Aggregation (IARSA) baseline algorithm, which assumes that all the users' responses to suggestions are identical as references to verify the key contribution of the heuristics employed in our PARSA algorithm that user may responses differently to positive and negative suggestions. Three sets of experiments are designed and implemented over two real-life datasets (i.e., Eachmovie and Netflix) to evaluate the performance of our algorithms. Further, in order to eliminate the influence of different similarity measures, this paper selects three kinds of similarity measures to discover neighbors. Experimental results demonstrate that most people indeed pay more attention to negative suggestions and our algorithms achieve better prediction and recommendation performances than the compared algorithms under various similarity measures.

关键词： Collaborative filtering Response Positive suggestions Negative suggestions linear regression method

来源：评论

学校读者我要写书评

暂无评论

Application of lidar and measure correlate predict method in offshore wind resource assessments

引用

JOURNAL OF CLEANER PRODUCTION 2019年 215卷 534-543页

作者： Sharma, Pramod Kumar Warudkar, Vilas Ahmed, Siraj MANIT Dept Mech Engn Bhopal India

Currently, wind data measurement using lidars or other remote sensing instruments are increasing. Lidar measures the wind data over the full wind turbine, but it is not available for a complete period. This paper investigates the application of measure-correlate-predict technique to short-term lidar measurements in order to extrapolate wind shear index. The wind shear exponent from lidar measurements was compared from mast measurements because lidar and mast have a different measurement methodology. The short-term measurement campaign was conducted at Dhanushkodi to analyze the wind data. This paper discussed the application of measure-correlate-predict method to evaluate the performance of the measure-correlate-predict to extrapolate the short term wind shear exponent. A quantitative analysis of the measure-correlate-predict method has been made. The new approach of measuring wind shear exponent using lidar and measure-correlate-predict was used to test the measured data. The six metrics used to evaluate the MCP predictions in the present analysis. The five parameters used to compare the predicted distribution with the actual long-term wind data. The shear measured by lidar over a height range from 10 m to 220 m. Subsequently, the mast data and the MCP method are used to extrapolate the lidar measurement to get the long-term shear exponent. The reference wind data is used by the wind shear exponent from 10 m to 100 m from the met mast. Due to the reduction of error in the wind shear exponent measurement, the uncertainty can sufficiently reduce in the estimation of wind shear exponent. Comparison of the two correlations signifies that the LR method shows in linear relations that have higher intercepts and lower slopes. A difference is found for shear exponent in the range of 0.13-0.28. (C) 2019 Elsevier Ltd. All rights reserved.

关键词： Lidar Measure correlate predict linear regression method Virtual ratio method

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：