检索结果-内蒙古大学图书馆

6th SIAM International Conference on data mining

作者： Cao, Feng Ester, Martin Qian, Weining Zhou, Aoying Fudan Univ Dept Comp Sci & Engn Shanghai Peoples R China Simon Fraser Univ Sch Comp Sci Burnaby BC Canada

ISBN: (纸本)9780898716115

Clustering is an important task in mining evolving data streams. Beside the limited memory and one-pass constraints, the nature of evolving data streams implies the following requirements for stream clustering: no assumption on the number of clusters, discovery of clusters with arbitrary shape and ability to handle outliers. While a lot of clustering algorithms for data streams have been proposed, they offer no solution to the combination of these requirements. In this paper, we present Den Stream, a new approach for discovering clusters in an evolving data stream. The "dense" micro-cluster (named core-micro-cluster) is introduced to summarize the clusters with arbitrary shape, while the potential core-micro-cluster and outlier micro-cluster structures are proposed to maintain and distinguish the potential clusters and outliers. A novel pruning strategy is designed based on these concepts, which guarantees the precision of the weights of the micro-clusters with limited memory. Our performance study over a number of real and synthetic data sets demonstrates the effectiveness and efficiency of our method.

关键词： data mining algorithms Density based clustering Evolving data streams

来源：评论

学校读者我要写书评

暂无评论

Discovering Causal Structures from Time Series data via Enhanced Granger Causality 28th

Discovering Causal Structures from Time Series Data via Enha...

引用

28th Australasian Joint Conference on Artificial Intelligence (AI)

作者： Luo, Ling Liu, Wei Koprinska, Irena Chen, Fang Univ Sydney Sch Informat Technol Sydney NSW 2006 Australia NICTA Australian Technol Pk Lab Sydney NSW Australia Univ Technol Sydney Fac Engn & Informat Technol Sydney NSW 2007 Australia

ISBN: (纸本)9783319263502;9783319263496

Granger causality has been applied to explore predictive causal relations among multiple time series in various fields. However, the existence of non-stationary distributional changes among the time series variables poses significant challenges. By analyzing a real dataset, we observe that factors such as noise, distribution changes and shifts increase the complexity of the modelling, and large errors often occur when the underlying distribution shifts with time. Motivated by this challenge, we propose a new regression model for causal structure discovery - a Linear Model with Weighted Distribution Shift (linear WDS), which improves the prediction accuracy of the Granger causality model by taking into account the weights of the distribution-shift samples and by optimizing a quadratic-mean based objective function. The linear WDS is integrated in the Granger causality model to improve the inference of the predictive causal structure. The performance of the enhanced Granger causality model is evaluated on synthetic datasets and real traffic datasets, and the proposed model is compared with three different regression-based Granger causality models (standard linear regression, robust regression and quadratic-mean-based regression). The results show that the enhanced Granger causality model outperforms the other models especially when there are distribution shifts in the data.

关键词： data mining algorithms Causal inference Time series regression

来源：评论

学校读者我要写书评

暂无评论

data mining approach to predicting the performance of first year student in a university using the admission requirements

引用

EDUCATION AND INFORMATION TECHNOLOGIES 2019年第2期24卷 1527-1543页

作者： Adekitan, Aderibigbe Israel Noma-Osaghae, Etinosa Covenant Univ Dept Elect & Informat Engn Ota Ogun State Nigeria

The academic performance of a student in a university is determined by a number of factors, both academic and non-academic. Student that previously excelled at the secondary school level may lose focus due to peer pressure and social lifestyle while those who previously struggled due to family distractions may be able to focus away from home, and as a result excel at the university. University admission in Nigeria is typically based on cognitive entry characteristics of a student which is mostly academic, and may not necessarily translate to excellence once in the university. In this study, the relationship between the cognitive admission entry requirements and the academic performance of students in their first year, using their CGPA and class of degree was examined using six data mining algorithms in KNIME and Orange platforms. Maximum accuracies of 50.23% and 51.9% respectively were observed, and the results were verified using regression models, with R-2 values of 0.207 and 0.232 recorded which indicate that students' performance in their first year is not fully explained by cognitive entry requirements.

关键词： Academic performance Machine learning Educational data mining data mining algorithms Knowledge discovery Nigerian university

来源：评论

学校读者我要写书评

暂无评论

An New Algorithm-based Rough Set for Selecting Clustering Attribute in Categorical data 6

An New Algorithm-based Rough Set for Selecting Clustering At...

引用

6th International Conference on Advanced Computing and Communication Systems (ICACCS)

作者： Baroud, Muftah Mohamed Jomah Hashim, Siti Zaiton Mohd Zainal, Anazida Ahnad, Jamilah Univ Teknol Sch Comp 28 UTM Skudai Johor Bahru Skudai Malaysia Univ Teknol Fac Social Scince & Humanities UTM Skudai Johor Bahru Skudai Malaysia

ISBN: (纸本)9781728151977;9781728151960

Several algorithms strategies based on Rough Set Theory (RST) have been used for the selection of attributes and grouping objects that show similar features. On the other hand, most of these clustering techniques cannot deal tackle partitioning. In addition, these processes are computationally complexity and low purity. In this study, the researcher looked at the limitations of the two rough set based techniques used, Information-Theoretic Dependency Roughness (ITDR) and Maximum Indiscernible Attribute (MIA). They also proposed a novel method for selecting clustering attributes, Maximum mean Attribute (MMA). They compared the performance of MMA, ITDR and MIA technique, using UCI and benchmark datasets. Their results validated the performance of the MMA with regards to its purity and computational complexity.

关键词： Knowledge discovery data mining Rough set theory data mining algorithms Performance Attribute selection Attribute dependency Information system Clustering Categorical data

来源：评论

学校读者我要写书评

暂无评论

Research on Statistical Methods Related to the Added Value of Digital Economy Industry Based on data mining Algorithm 2

Research on Statistical Methods Related to the Added Value o...

引用

2nd IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2024

作者： Sun, Lijie Tianjin Agricultural University Tianjin China

ISBN: (纸本)9798350317558

As a new industry, digital economy industry is gradually becoming the main driving force of global economic growth. With the rapid development and popularization of information technology, the scale and influence of digital economy industry are expanding, and its contribution in added value is becoming increasingly significant. Therefore, the research on the added value of digital economy industry becomes particularly important. The purpose of this study is to deeply explore the formation mechanism, influencing factors and development trend of industrial added value in digital economy, and to provide scientific basis for policy making and industrial development. © 2024 IEEE.

关键词： Added value data mining algorithms Digital economy Industry Statistical methods statistical set theory

来源：评论

学校读者我要写书评

暂无评论

Visual and Instrument Helicopter Approach Stability Analysis Using data Fusion and data Analytics

Visual and Instrument Helicopter Approach Stability Analysis...

引用

AIAA Science and Technology Forum and Exposition (AIAA SciTech Forum)

作者： Robinson, Joseph N. Payan, Alexia P. Mavris, Dimitri N. Johnson, Charles Georgia Inst Technol Aerosp Syst Design Lab Sch Aerosp Engn 270 Ferst Dr Atlanta GA 30332 USA Georgia Inst Technol Adv Aerosp Anal Sch Aerosp Engn 270 Ferst Dr Atlanta GA 30332 USA FAA NextGen WJHTC Off Syst Safety Sect William J Hughes Tech CtrAviat Res Div Atlantic City NJ 08405 USA

ISBN: (数字)9781624106095

ISBN: (纸本)9781624106095

Approach and landing are among the most challenging and dangerous tasks required of helicopter pilots. Helicopter accident statistics suggest that the majority of helicopter accidents in the U.S. occur during either the approach or landing phases of flight and that unstabilized approaches are a leading cause due to the associated increased potential for loss of control, loss of situational awareness, or controlled flight into terrain. In the present work, routine flight data records obtained as part of a voluntary helicopter flight data monitoring program are used to identify, analyze, and evaluate approach events in a variety of helicopter flights from different mission types, such as emergency medical services, flight training, and research. A semi-automated process is developed which enables detection of the approach phase, construction of a nominal approach path, analysis of approach stability, and knowledge discovery through data mining. The process was able to identify 3950 visual and 183 instrument approaches in a set of 3749 operational helicopter flight data records. Analysis of visual approach events suggests that typical approaches are higher and steeper than expected. Thus, the traditional definition of a stabilized approach may not align with typical operations. Additionally, atypical approaches can be classified as highly stabilized, marginally unstabilized, or unstabilized depending on their associated stability measures.

关键词： Rotor Systems data Fusion Instrument Approach Procedure Helicopter Flight data Monitoring data mining algorithms Controlled Flight into Terrain data Analytics Flight Training Instrument Flight Rules Global Positioning System

来源：评论

学校读者我要写书评

暂无评论

data mining Techniques for Transformer Failure Prediction Model: A Systematic Literature Review 9

Data Mining Techniques for Transformer Failure Prediction Mo...

引用

9th IEEE Symposium on Computer Applications and Industrial Electronics (ISCAIE)

作者： Ravi, Nanthiine Nair Drus, Sulfeeza Mohd Krishnan, Prajindra Sankar Univ Tenaga Nas Kajang 43000 Selangor Malaysia

ISBN: (纸本)9781538685464

Transformer failure may occur in terms of tripping, resulting in an unplanned or unseen failure. Therefore, a good maintenance strategy is an essential component of a power system to prevent unanticipated failures. Routine preventive maintenance programs have traditionally been used in combination with regular tests. However, in recent years, predictive maintenance has become prevalent due to the demanding industrial needs. Due to the increased requirement, utilities are persistently looking for ways to overcome the challenge of power transformer failures. One of the most popular ways for fault prediction is data mining. data mining techniques can be applied in transformer failure prediction to provide the possibility of failure occurrence. Thus, this study aims to identify the common data mining techniques and algorithms that are implemented in studies related to various transformer failure types. The accuracy of each algorithm is also studied in this paper. A systematic literature review is carried out by identifying 160 articles from four main databases of which 6 articles are chosen in the end. This review found that the most common prediction technique used is classification. Among the classification algorithms, ANN is the prominent algorithm adopted by most of the researchers which has provided the highest accuracy compared to other algorithms. Further research can be done to investigate more on the transformer failures types and fair comparison between multiple algorithms in order to get more precise performance measurement.

关键词： transformer failure prediction data mining systematic literature review data mining algorithms classification

来源：评论

学校读者我要写书评

暂无评论

Research on Enterprise Marketing Resource Allocation Strategy Based on data mining Algorithm 3

Research on Enterprise Marketing Resource Allocation Strateg...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Zhang, Zifeng Shijiazhuang University of Applied Technology Hebei Shijiazhuang050081 China

ISBN: (纸本)9798350319125

In the enterprise, marketing can better make customers prefer this enterprise, and in this process, marketing resources are very important, due to the limited marketing resources, so reasonable allocation is an indispensable part. Ordinary resource allocation strategies do not better meet marketing expectations. analyze marketing resources, and indicators are divided according to resource allocation requirements to reduce resource allocation in the interfering factor. Then, artificial intelligence will form a resource allocation plan for the results of marketing resources for enterprises, and carry out the resource allocation results Comprehensive analysis. the data mining algorithm has an accurate effect on the resource allocation of enterprise marketing The rationality of resource allocation is better than that of ordinary resource allocation strategies. © 2023 IEEE.

关键词： artificial intelligence Corporate Marketing data mining algorithms Marketing distribution

来源：评论

学校读者我要写书评

暂无评论

Research on Student Course Selection on Learning Behavior Analysis Algorithm Based on data mining 2

Research on Student Course Selection on Learning Behavior An...

引用

2nd IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2024

作者： Yu, Xiaoting Modern College of Northwest University Xi'an City China

ISBN: (纸本)9798350317558

With the popularization of higher education, the problem of students' course selection behavior has gradually become prominent. Based on the in-depth investigation of students' course selection behavior, this study identifies the main existing problems and puts forward corresponding countermeasures. It is found that students have blindness and utilitarianism in choosing courses, which leads to unreasonable knowledge structure and affects their studies. In view of these problems, this paper puts forward corresponding solutions to help students choose courses more scientifically. © 2024 IEEE.

关键词： data mining algorithms Pearson correlation coefficient theory similarity measurement algorithm Student behavior analysis student course selection algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on data mining Algorithm in the Optimization of Real Estate Management 2

Research on Data Mining Algorithm in the Optimization of Rea...

引用

2nd IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2024

作者： Wan, Jianguo Guangxi Polytechnic of Construction Nanning China

ISBN: (纸本)9798350317558

Management methods and objectives play an important role in real estate operation and management, but there is problems of inaccurate management. With the rapid development of the real estate market, the competition in the real estate industry is becoming increasingly fierce. Under this background, how to optimize real estate management through data analysis and improve enterprise operational efficiency and profitability has become the focus of real estate enterprises. From the perspective of real estate management, this paper discusses how to use data analysis technology to optimize, in order to improve the management level and competitiveness of real estate enterprises. © 2024 IEEE.

关键词： Business management data mining algorithms Management style Objective discussion Real estate statistical set theory

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：