Extensible Attribute Similarity Data Mining for Categorical Data Streams in Web Usage Framework

Extracting knowledge from data streams received from observed objects through data mining is required in various domains. However, there is a lack of any kind of guidance on which techniques can or should be used in which contexts. Meta mining technology can help build processes of data processing based on knowledge models taking into account the specific features of the objects. This paper proposes a meta mining ontology framework that allows selecting algorithms for solving specific data mining tasks and build suitable processes. The proposed ontology is constructed using existing ontologies and is extended with an ontology of data characteristics and task requirements. Different from the existing ontologies, the proposed ontology describes the overall data mining process, used to build data processing processes in various domains, and has low computational complexity compared to others. The authors developed an ontology merging method and a sub-ontology extraction method, which are implemented based on OWL API via extracting and integrating the relevant axioms.

Download Full-text

A Novel Cosine Similarity Like Data Clustering Method for Effective Data Classification in Data Mining

International Journal of Innovative Technology and Exploring Engineering - Special Issue ◽

10.35940/ijitee.h6417.069820 ◽

2020 ◽

Vol 9 (8) ◽

pp. 340-346

Keyword(s):

Data Mining ◽

Similarity Measure ◽

Categorical Data ◽

Data Clustering ◽

Similarity Measures ◽

Numerical Data ◽

Data Classification ◽

Fundamental Goal ◽

Learning Technique ◽

Categorical Data Clustering

In data mining ample techniques use distance based measures for data clustering. Improving clustering performance is the fundamental goal in cluster domain related tasks. Many techniques are available for clustering numerical data as well as categorical data. Clustering is an unsupervised learning technique and objects are grouped or clustered based on similarity among the objects. A new cluster similarity finding measure, which is cosine like cluster similarity measure (CLCSM), is proposed in this paper. The proposed cluster similarity measure is used for data classification. Extensive experiments are conducted by taking UCI machine learning datasets. The experimental results have shown that the proposed cosinelike cluster similarity measure is superior to many of the existing cluster similarity measures for data classification.

Download Full-text

Improved minimum-minimum roughness algorithm for clustering categorical data

International Journal of ADVANCED AND APPLIED SCIENCES ◽

10.21833/ijaas.2021.10.006 ◽

2021 ◽

Vol 8 (10) ◽

pp. 43-50

Author(s):

Truong et al. ◽

Keyword(s):

Machine Learning ◽

Data Mining ◽

Hierarchical Clustering ◽

Categorical Data ◽

Clustering Algorithm ◽

Clustering Algorithms ◽

Experimental Results ◽

Data Sets ◽

Top Down ◽

Hierarchical Clustering Algorithm

Clustering is a fundamental technique in data mining and machine learning. Recently, many researchers are interested in the problem of clustering categorical data and several new approaches have been proposed. One of the successful and pioneering clustering algorithms is the Minimum-Minimum Roughness algorithm (MMR) which is a top-down hierarchical clustering algorithm and can handle the uncertainty in clustering categorical data. However, MMR tends to choose the category with less value leaf node with more objects, leading to undesirable clustering results. To overcome such shortcomings, this paper proposes an improved version of the MMR algorithm for clustering categorical data, called IMMR (Improved Minimum-Minimum Roughness). Experimental results on actual data sets taken from UCI show that the IMMR algorithm outperforms MMR in clustering categorical data.

Download Full-text

Web Usage Mining and the Challenge of Big Data

Big Data ◽

10.4018/978-1-4666-9840-6.ch042 ◽

2016 ◽

pp. 899-928

Author(s):

Abubakr Gafar Abdalla ◽

Tarig Mohamed Ahmed ◽

Mohamed Elhassan Seliaman

Keyword(s):

Data Mining ◽

Pattern Discovery ◽

Web Usage Mining ◽

Data Mining Techniques ◽

Web Log ◽

Web Usage ◽

Web Logs ◽

Usage Patterns ◽

Rich Data ◽

The Web

The web is a rich data mining source which is dynamic and fast growing, providing great opportunities which are often not exploited. Web data represent a real challenge to traditional data mining techniques due to its huge amount and the unstructured nature. Web logs contain information about the interactions between visitors and the website. Analyzing these logs provides insights into visitors' behavior, usage patterns, and trends. Web usage mining, also known as web log mining, is the process of applying data mining techniques to discover useful information hidden in web server's logs. Web logs are primarily used by Web administrators to know how much traffic they get and to detect broken links and other types of errors. Web usage mining extracts useful information that can be beneficial to a number of application areas such as: web personalization, website restructuring, system performance improvement, and business intelligence. The Web usage mining process involves three main phases: pre-processing, pattern discovery, and pattern analysis. Various preprocessing techniques have been proposed to extract information from log files and group primitive data items into meaningful, lighter level abstractions that are suitable for mining, usually in forms of visitors' sessions. Major data mining techniques in web usage mining pattern discovery are: clustering, association analysis, classification, and sequential patterns discovery. This chapter discusses the process of web usage mining, its procedure, methods, and patterns discovery techniques. The chapter also presents a practical example using real web log data.

Download Full-text

First Look on Web Mining Techniques to Improve Business Intelligence of E-Commerce Applications

Advances in Business Information Systems and Analytics - Handbook of Research on Advanced Data Mining Techniques and Applications for Business Intelligence ◽

10.4018/978-1-5225-2031-3.ch018 ◽

2017 ◽

pp. 298-314 ◽

Cited By ~ 2

Author(s):

G. Sreedhar ◽

A. Anandaraja Chari

Keyword(s):

Data Mining ◽

Web Mining ◽

Web Content ◽

Web Data ◽

Web Data Mining ◽

Useful Knowledge ◽

Web Usage ◽

Web Structure ◽

Web Structure Mining ◽

Content Mining

Web Data Mining is the application of data mining techniques to extract useful knowledge from web data like contents of web, hyperlinks of documents and web usage logs. There is also a strong requirement of techniques to help in business decision in e-commerce. Web Data Mining can be broadly divided into three categories: Web content mining, Web structure mining and Web usage mining. Web content data are content availed to users to satisfy their required information. Web structure data represents linkage and relationship of web pages to others. Web usage data involves log data collected by web server and application server which is the main source of data. The growth of WWW and technologies has made business functions to be executed fast and easier. As large amount of transactions are performed through e-commerce sites and the huge amount of data is stored, valuable knowledge can be obtained by applying the Web Mining techniques.

Download Full-text

Web Usage Mining Issues in Big Data

Impacts and Challenges of Cloud Business Intelligence - Advances in Systems Analysis, Software Engineering, and High Performance Computing ◽

10.4018/978-1-7998-5040-3.ch007 ◽

2021 ◽

pp. 102-112

Author(s):

Sunny Sharma ◽

Manisha Malhotra

Keyword(s):

Data Mining ◽

Big Data ◽

User Behavior ◽

Web Usage Mining ◽

Web Personalization ◽

Data Mining Techniques ◽

Meaningful Information ◽

Web Usage ◽

Use Of Data ◽

The Web

Web usage mining is the use of data mining techniques to analyze user behavior in order to better serve the needs of the user. This process of personalization uses a set of techniques and methods for discovering the linking structure of information on the web. The goal of web personalization is to improve the user experience by mining the meaningful information and presented the retrieved information in a way the user intends. The arrival of big data instigated novel issues to the personalization community. This chapter provides an overview of personalization, big data, and identifies challenges related to web personalization with respect to big data. It also presents some approaches and models to fill the gap between big data and web personalization. Further, this research brings additional opportunities to web personalization from the perspective of big data.

Download Full-text

Effectiveness of Web Usage Mining Techniques in Business Application

Advances in Data Mining and Database Management - Web Usage Mining Techniques and Applications Across Industries ◽

10.4018/978-1-5225-0613-3.ch013 ◽

2017 ◽

pp. 324-350 ◽

Cited By ~ 2

Author(s):

Ahmed El Azab ◽

Mahmood A. Mahmood ◽

Abd El-Aziz

Keyword(s):

Data Mining ◽

Academic Research ◽

Web Usage Mining ◽

Web Pages ◽

Web Data ◽

Web Data Mining ◽

Web Usage ◽

Business Application ◽

Common Interests ◽

The Web

Web usage mining techniques and applications across industries is still exploratory and, despite an increase in academic research, there are challenge of analyze web which quantitatively capture web users' common interests and characterize their underlying tasks. This chapter addresses the problem of how to support web usage mining techniques and applications across industries by combining language of web pages and algorithms that used in web data mining. Existing research in web usage mining techniques tend to focus on finding out how each techniques can apply in different industries fields. However, there is little evidence that researchers have approached the issue of web usage mining across industries. Consequently, the aim of this chapter is to provide an overview of how the web usage mining techniques and applications across industries can be supported.

Download Full-text

Analysis of Click Stream Patterns using Soft Biclustering Approaches

International Journal of Information Technologies and Systems Approach ◽

10.4018/jitsa.2011010104 ◽

2011 ◽

Vol 4 (1) ◽

pp. 53-66 ◽

Cited By ~ 1

Author(s):

P. K. Nizar Banu ◽

H. Inbarani

Keyword(s):

Machine Learning ◽

Data Mining ◽

Web Mining ◽

Web Usage Mining ◽

Web Personalization ◽

Partial Matching ◽

Web Usage ◽

Needed Information ◽

Highly Correlated ◽

Web Server Logs

As websites increase in complexity, locating needed information becomes a difficult task. Such difficulty is often related to the websites’ design but also ineffective and inefficient navigation processes. Research in web mining addresses this problem by applying techniques from data mining and machine learning to web data and documents. In this study, the authors examine web usage mining, applying data mining techniques to web server logs. Web usage mining has gained much attention as a potential approach to fulfill the requirement of web personalization. In this paper, the authors propose K-means biclustering, rough biclustering and fuzzy biclustering approaches to disclose the duality between users and pages by grouping them in both dimensions simultaneously. The simultaneous clustering of users and pages discovers biclusters that correspond to groups of users that exhibit highly correlated ratings on groups of pages. The results indicate that the fuzzy C-means biclustering algorithm best and is able to detect partial matching of preferences.

Download Full-text

Data-Driven Modelling of Smart Building Ventilation Subsystem

Journal of Sensors ◽

10.1155/2019/3572019 ◽

2019 ◽

Vol 2019 ◽

pp. 1-14 ◽

Cited By ~ 5

Author(s):

Grigore Stamatescu ◽

Iulia Stamatescu ◽

Nicoleta Arghira ◽

Ioana Fagarasan

Keyword(s):

Data Mining ◽

Data Streams ◽

Data Driven ◽

Support Vector ◽

Commercial Building ◽

Monitoring And Control ◽

Smart Building ◽

Building Ventilation ◽

Using Data ◽

Rich Data

Considering the advances in building monitoring and control through networks of interconnected devices, effective handling of the associated rich data streams is becoming an important challenge. In many situations, the application of conventional system identification or approximate grey-box models, partly theoretic and partly data driven, is either unfeasible or unsuitable. The paper discusses and illustrates an application of black-box modelling achieved using data mining techniques with the purpose of smart building ventilation subsystem control. We present the implementation and evaluation of a data mining methodology on collected data from over one year of operation. The case study is carried out on four air handling units of a modern campus building for preliminary decision support for facility managers. The data processing and learning framework is based on two steps: raw data streams are compressed using the Symbolic Aggregate Approximation method, followed by the resulting segments being input into a Support Vector Machine algorithm. The results are useful for deriving the behaviour of each equipment in various modi of operation and can be built upon for fault detection or energy efficiency applications. Challenges related to online operation within a commercial Building Management System are also discussed as the approach shows promise for deployment.

Download Full-text