检索结果-内蒙古大学图书馆

6th International Conference on Intelligent Computing

作者： Lin, Cheng Sheng Fan, Chin-Yuan Fan, Pei-Shu Wang, Yen-Wen Ming Dao Univ Dept Business Innovat & Dev Changhua 52345 Taiwan Univ Sci & Technol China Dept Ind Engn & Management Taipei Taiwan Chin yun Univ sci & Technol Dept Ind Engn & Management Taoyuan* Taiwan Sci & Technol Policy Res & Informat Ctr National Appl Res Lab Taipei Taiwan

ISBN: (纸本)9783642148309

This research applies clustering analysis technology of data mining to predict trend of the Technology Professionals turnover rate, including SUM (Self-Organizing Map) combined with Artificial neural network clustering analysis method. Meanwhile, this hybrid clustering method is applied to research the individual characteristics of turnover trend clusters. The turnover high peak period which is after Chinese calendar and an age bracket of high alteration circle has been consider for major research target and also used to be the transaction questionnaire. All Technology Professionals' case has been attached in Taiwan famous company. According to our research, the results show the high outstanding turnover trend circle mainly caused by non-identification of inner fidelity identification, leadership and management. The clustering accuracy rate reaches 92.7% by way of cross-verification. The application of this model, also helps rapidly prevent the problem for loss of key human-resource. Meanwhile, this will excite the organization to learn to enhance the enterprise competition ability and improve the efficiency.

关键词： Turnover Trend clustering Analysis Self-Organizing Map neural network clustering

来源：评论

学校读者我要写书评

暂无评论

A novel BiGRU multi-step wind power forecasting approach based on multi-label integration random forest feature selection and neural network clustering

引用

ENERGY CONVERSION AND MANAGEMENT 2024年 319卷

作者： Jiang, Zheyong Tan, Qingmei Li, Nan Che, Jinxing Tan, Xiukun Nanjing Univ Aeronaut & Astronaut Coll Econ & Management Nanjing 211106 Peoples R China Shenzhen Dajiang Innovat Technol Co Ltd Shenzhen 518000 Peoples R China Nanchang Inst Technol Sch Sci Nanchang 330099 Jiangxi Peoples R China

Accurate wind power forecasting helps to carry out effective scheduling and scientific management of wind power, and improve the security and reliability of the power grid. However, the intermittency, volatility and instability of wind energy make wind power forecasting challenging. Therefore, in order to improve the accuracy and stability of wind power forecasting, this paper proposes a bidirectional gated recurrent unit (BiGRU) multistep wind power forecasting approach based on multi-label integration random forest (MLRF) feature selection and neural network clustering (NNclustering). The proposed MLRF method extends the applicability of random forest through multiple criteria and enables feature selection for multi-step forecasting tasks of multi-factor time series to obtain optimal input features and time steps, which reduces the computational cost and improves the generalization ability of the model. The proposed NNclustering method establishes a novel convolution-based clustering structure and adjusts the parameters by gradient descent method to obtain the optimal clustering centers, and the robust data applicability of the method is validated in multiple seasonal experiments. The WOABiGRU forecasting model is constructed separately for each cluster, which reduces the modeling difficulty and better extracts the characteristics. The BiGRU model extracts more efficient characteristics by processing sequences in both directions and the important parameters of BiGRU are optimized by the whale optimization algorithm (WOA) to obtain the optimal forecasting model. Experimental results over multiple seasons show that the proposed hybrid approach has good forecasting performance and robustness, which provides a novel and efficient solution for wind power forecasting.

关键词： Multi-step wind power forecasting Multi-label integration random forest feature selection neural network clustering Bidirectional gate recurrent unit

来源：评论

学校读者我要写书评

暂无评论

Research on typical operating conditions of hydrogen production system with off-grid wind power considering the characteristics of proton exchange membrane electrolysis cell

引用

Global Energy Interconnection 2024年第5期7卷 642-652页

作者： Weiming Peng Yanhui Xu Gendi Li Jie Song Guizhi Xu Xiaona Xu Yan Pan State Key Lab of Alternate Electrical Power System with Renewable Energy Sources North China Electric Power UniversityChangping DistrictBeijing 102206P.R.China State Grid Smart Grid Research Institute Co. Ltd.Changping DistrictBeijing 102209P.R.China Huairou Laboratory Huairou DistrictBeijing 101499P.R.China

Hydrogen energy,with its abundant reserves,green and low-carbon characteristic,high energy density,diverse sources,and wide applications,is gradually becoming an important carrier in the global energy transformation and *** this paper,the off-grid wind power hydrogen production system is considered as the research object,and the operating characteristics of a proton exchange membrane(PEM)electrolysis cell,including underload,overload,variable load,and start-stop are *** this basis,the characteristic extraction of wind power output data after noise reduction is carried out,and then the self-organizing mapping neural network algorithm is used for clustering to extract typical wind power output scenarios and perform weight distribution based on the statistical *** trend and fluctuation components are superimposed to generate the typical operating conditions of an off-grid PEM electrolytic hydrogen production *** historical output data of an actual wind farm are used for the case study,and the results confirm the feasibility of the method proposed in this study for obtaining the typical conditions of off-grid wind power hydrogen *** results provide a basis for studying the dynamic operation characteristics of PEM electrolytic hydrogen production systems,and the performance degradation mechanism of PEM electrolysis cells under fluctuating inputs.

关键词： Wind power fluctuation Off-grid operation Hydrogen production by PEM electrolysis neural network clustering Typical working conditions

来源：评论

学校读者我要写书评

暂无评论

Using hybrid data mining and machine learning clustering analysis to predict the turnover rate for technology professionals

引用

EXPERT SYSTEMS WITH APPLICATIONS 2012年第10期39卷 8844-8851页

作者： Fan, Chin-Yuan Fan, Pei-Shu Chan, Te-Yi Chang, Shu-Hao Sci & Technol Policy Res & Informat Ctr Natl Appl Res Labs Taipei Taiwan China Univ Sci & Technol Dept Ind Engn & Management Taipei Taiwan

This study applies clustering analysis for data mining and machine learning to predict trends in technology professional turnover rates, including the hybrid artificial neural network and clustering analysis known as the self-organizing map (SOM). This hybrid clustering method was used to study the individual characteristics of turnover trend clusters. Using a transaction questionnaire, we studied the period of peak turnover, which occurs after the Chinese New Year, for individuals divided into various age groups. The turnover trend of technology professionals was examined in well-known Taiwanese companies. The results indicate that the high outstanding turnover trend circle was primarily caused by a lack of inner fidelity identification, leadership and management. Based on cross-verification, the clustering accuracy rate was 92.7%. This study addressed problems related to the rapid loss of key human resources and should help organizations learn how to enhance competitiveness and efficiency. (C) 2012 Elsevier Ltd. All rights reserved.

关键词： Turnover trend clustering analysis Self-organizing map neural network clustering

来源：评论

学校读者我要写书评

暂无评论

Self-organizing maps in geothermal exploration-A new approach for understanding geochemical processes and fluid evolution

引用

JOURNAL OF VOLCANOLOGY AND GEOTHERMAL RESEARCH 2017年 336卷 19-32页

作者： Brehme, Maren Bauer, Klaus Nukman, Mochamad Regenspurg, Simona Helmholtz Ctr Potsdam GFZ German Res Ctr Geosci Int Ctr Geothermal Res D-14473 Potsdam Germany Helmholtz Ctr Potsdam GFZ German Res Ctr Geosci Near Surface Geophys D-14473 Potsdam Germany UGM Yogyakarta Fac Math & Nat Sci Dept Phys Lantai 3 Gedung Fis FMIPA Yogyakarta Indonesia

Understanding geochemical processes is an important part of geothermal exploration to get information about the source and evolution of geothermal fluids. However, in most cases knowledge of fluid properties is based on few parameters determined in samples from the shallow subsurface. This study presents a new approach that allows to conclude from the combination of a variety of these data on processes occurring at depth in a geothermal reservoir. The neural network clustering technique called "self-organizing maps" (SOMs) successfully distinguished two different geothermal settings based on a hydrochemical database and disclosed the source, evolution and flow pathways of geothermal fluids. Scatter plots, as shown in this study, are appropriate presentations of element concentrations and the chemical interaction of water and rock at depth. One geological setting presented here is marked by fault dominated fluid pathways and minor influence of volcanic affected fluids with high concentrations of HCO3, Ca and Sr. The second is a magmatically dominated setting showing strong alteration features in volcanic rocks and accommodates acidic fluids with high SO4 and Si concentrations. Former studies, i.e., Giggenbach (1988), suggested Cl, HCO3 and SO4 to be generally the most important elements for understanding hydrochemical processes in geothermal reservoirs. Their relation has been widely used to classify different water types in geothermal fields. However, this study showed that non-standard elements are at least of same importance to reveal different fluid types in geothermal systems. Therefore, this study is an extended water classification approach using SOM for element correlations. SOM have been proven to be a successful method for analyzing even relatively small hydrochemical datasets in geothermal applications. (C) 2017 Elsevier B.V. All rights reserved.

关键词： SOM clustering Deep fluids Fluid evolution Geothermal reservoirs Statistics neural network clustering

来源：评论

学校读者我要写书评

暂无评论

Distributed Data Classification in Underwater Acoustic Sensors based on Local Time-Frequency Coherence Analysis

Distributed Data Classification in Underwater Acoustic Senso...

引用

Oceans Conference

作者： Petrut, Teodor Ioana, Cornel Mauuary, Didier Mallet, Julien Phillipe, Olivier Grenoble Inst Technol GIPSA Lab St Martin Dheres France CYBERIO Meylan France OSEAN SAS Toulon France

ISBN: (纸本)9781479936465

This paper introduces a stochastic approach that considers the distributed classification problem for a network of underwater acoustic sensors. The proposed classifier applies the third order polynomial regression to the instantaneous frequency extracted from time-frequency representation of different classes of signals and represent the polynomial's coefficients in a three-dimensional representation space. This automatic classifier is then compared to a non-parametric classifier based on the training of a standard neural network. The results of the proposed method on real data illustrate the efficiency of this algorithm, in terms of signal's characterization and lower communication bit rates between each sensor and the data center.

关键词： signal classification neural network clustering pattern recognition distributed signal processing time-frequency analysis

来源：评论

学校读者我要写书评

暂无评论

The use of cluster analysis for the synthesis of optimal frequency control law for induction drive

The use of cluster analysis for the synthesis of optimal fre...

引用

IEEE International Symposium on Power Electronics, Electrical Drives, Automation and Motion (SPEEDAM)

作者： Braslavsky, I. Ya. Kostylev, A. V. Tsibanov, D. V. Ural Fed Univ Ural Power Engn Inst Ekaterinburg Russia

ISBN: (纸本)9781479947492

the problem of the starting process optimization of frequency controlled induction motor is discussed. The using of the specially synthesized frequency u/f control law is proposed. The concept of synthesis of the control law on the criterion of minimum motor heating is described. The simplified synthesis of the control law based on neural clustering for motors with similar parameters is considered. Simulated and experimental results are given.

关键词： optimization scalar control induction motor neural network clustering

来源：评论

学校读者我要写书评

暂无评论

Modeling Oligo-Miocence channel sands (Dezful Embayment, SW Iran): an integrated facies classification workflow

引用

JOURNAL OF GEOPHYSICS AND ENGINEERING 2014年第4期11卷 045003-045003页

作者： Heydari, Mostafa Maddahi, Iradj Moradpour, Mehran Esmaeilpour, Sajjad Res Inst Petr Ind Explorat & Prod Res Ctr Tehran Iran

This study has been conducted on Mansuri onshore oilfield located in Dezful Embayment, south-west Iran. One of the hydrocarbon-bearing formations is a Oligo-Miocene Asmari formation-the most prolific Iranian reservoir rock. Like many other oilfields in the area, the trap in this field is deemed structural (anticline), formed during the collision of the Arabian plate with the Iranian plate and the folding of Neotethys deposits with a NW-SE trend. This study integrates three different quantitative studies from geology, geophysics and petrophysics disciplines to quantitate 'the qualitative study of seismic facies analysis based on trace shapes and 3D multi-attribute clustering'. First, stratigraphic sequences and seismic detectable facies were derived at one well location using the available high resolution core facies analysis and depositional environment assessment reports. Paleo and petrophysical logs from other wells were subsequently used for the extrapolation of stratigraphic sequences interpreted at the first well. Utilizing lithology discrimination obtained by wire-line log interpretation, facies were extrapolated to all wells in the area. Seismic 3D attribute analysis and seismic facies classification established a 3D facies volume accordingly, which was finally calibrated to geological facies at well locations. The ultimate extracted facies-guided geobody shows that good reservoir-quality channel sands have accumulated with NW/SE elongation at the ridge of the structure. As a result, this type of geometry has created a stratigraphic/structural hydrocarbon trap in this oilfield. Moreover, seismic facies analysis shows that buried channels do not parallel the predominant Arabian plate-originated channels (with SW-NE trends) in SW Zagros and are locally swerved in this area.

关键词： seismic facies claustering seismic channel extraction seismic attribute analysis seismic inversion hybrid clustering neural network clustering

来源：评论

学校读者我要写书评

暂无评论

Quality attributes of traditional food from blends of rice flour and jaggery syrup under different frying conditions

引用

JOURNAL OF AGRICULTURE AND FOOD RESEARCH 2024年 16卷

作者： Sivaranjani, S. Singh, Shagolshem Mukta Rao, P. Srinivasa Indian Inst Technol Kharagpur Agr & Food Engn Dept Kharagpur 721302 West Bengal India

Traditional foods are indigenous to the locality, and there are no standard preparation steps provided. Ariselu is a deep-fat fried product generally made up of rice flour and jaggery syrup. This study revealed the change in quality attributes of fried ariselu under various thicknesses (4 and 6 mm), frying temperature (150, 170 and 190 C-degrees) and frying time (60, 90, 120 and 150 s). A full factorial design was considered and neural network clustering was employed to find the correlation among the responses obtained. Oil content was found to have an inverse relationship with moisture that increases with an increase in frying conditions. The lightness and yellowness values of ariselu decreased from 44.70 to 26.82 and 28.55 to 11.57, respectively. However, the redness value increased during frying due to increased browning reactions. The thermal properties were determined to analyze the changes in conductivity, resistivity, specific heat capacity and diffusivity during the frying of ariselu. The textural attributes of ariselu indicate an increased hardness value with a rise in frying temperature due to moisture loss in ariselu. The results obtained show that an overall acceptability (OAA) of 4.28/5 was achieved at 170 C-degrees for 150 s with a 6 mm initial thickness. This research focuses on the optimum conditions required for frying ariselu with the desired quality attributes that would help the product establish in the commercial market.

关键词： Ariselu Oil content Textural properties Thermal conductivity Browning reaction neural network clustering

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：