Effective Data Mining Research Articles

Improved dominance rough set-based classification system

Feature selection and classification is widely used in many areas of science and engineering, as large datasets become increasingly common. In particular, bioscience and medical datasets routinely contain several thousands of features. For effective data mining in such databases, many methods and techniques have been developed. Rough set is a mathematical theory for dealing with uncertainty. In dominance-based rough set extension of rough set, the set of objects partitioned into pre-defined and preference-ordered classes, the new rough set approach is able to approximate this partition by means of dominance relations. This paper suggests improved dominance-based rough set for classification of medical data. Dominance-based rough set can handle ordinal attribute. This paper proposed a technique for applying dominance-based rough set for nominal attribute. This proposed work suggests decision table to determine dominance relation, and then improved dominance-based rough set is applied to find lower, upper, boundary approximations in the entire dataset. Then attribute reduction based on proposed technique is applied to find the essential attribute required for classification. This proposed method can accurately classify medical datasets collected from UCI repository Web sites. This proposed method works in seven different datasets: They are heart disease dataset, Pima Indian diabetes dataset, Breast cancer Wisconsin dataset, heart valve dataset, jaundice datasets, dermatology dataset and lung cancer dataset. Comparing the classification accuracy with rule-based classifier (Zero R, decision table), tree-based classifier (J48, Random forest, Random Tree), neural network-based classifier (multilayer perceptron), lazy classifier (IBk, KStar, LWL), Bayesian-based classifier (Naive Bayes), benchmark algorithm k-nearest---neighbour, and classical rough set approach, improved dominance-based rough set gives higher accuracy.

Supervised Neural Network Targeting and Classification Analysis of Airborne EM, Magnetic and Gamma-ray Spectrometry Data for Mineral Exploration

The amount of multi-disciplinary (geology, geophysics, remote sensing, etc.) and multi-parameter geophysical (potential field, EM, gamma-ray spectrometry, etc.) data available for mineral exploration is ever increasing. The integration and analysis of the data require effective and efficient search engines or data mining tools. The search engines will take the signatures of known mineral deposits or interpreted mineralization targets (key words), search the data space and return potential new targets (matches), thus providing locations to the decision makers for follow-up. Two supervised feed-forward multilayer neural network (NN) search algorithms will be presented and analysed. The utility of the NN search tools will be demonstrated with the integration and analysis of airborne electromagnetic (EM), magnetic and radiometric data for mineralization targets in Iullemmeden Basin, Niger.

ИССЛЕДОВАНИЕ ФАКТОРОВ АДАПТАЦИИ СТУДЕНЧЕСТВА 2000-х ГОДОВ К ОБУЧЕНИЮ В ВУЗЕ МЕТОДАМИ DATA MINING

The article contains the results of studying the factors of students’ adaptation to the conditions of university training with one of the most effective technologies Data Mining - the method of analysis of variance. The results of modeling factors of adaptation of students of peripheral universities to the new method of Data Mining, implemented by the procedure of generalized linear model analysis of the data packet of Social Sciences SPSS Base are presented. The empirical base of modeling is the result of the poll of university students in Orel, Bryansk, Kursk and Belgorod. It is shown that in 2000s the main factor determining the adaptation of students to training in university, was the course of training and the gender factor, the faculty of training was less significant factor.

Research of Social Network Log Analysis System Based on MongoDB

This paper mainly studies the design of an efficient social network log analysis program based on the distribut- ed database, MongoDB. The so-called social network log analysis is to gather and store the log information generated when users access the social network pages, and then transform, clean and excavate. This article compares MongoDB da- tabase with traditional relational database, analyzes its advantages and application scenarios. Its anti-paradigm design due to the nest avoids the association, making queries and storage of the large data efficiently by: storing social network logs in the MongoDB; directly analyzing the logs with its built-in MapReduce programming model, and saving the results of the analysis as files for business people to use. Our study aims to discover the hidden users' access rules and patterns in the log data by effective data mining of the social network log data, thereby providing helpful information for optimizing website structure and business model. With the growth and expansion of the Internet enterprise scale, social network log information also grew step by step. In order to provide better services, it is necessary to under- stand the features and needs of the user's access, by analyz- ing and studying the user's behavior, so analysis of the Social network logs was suggested. It combined the traditional data mining and social network logs, by getting the useful infor- mation from a large number of social network logs data, counting and analyzing the users' behavior and page view, to finally infer the user's access modes. (1) It can play a role in many situations, such as network security, build the social network site and perform the market analysis of the e- commerce. It is a new research direction for data mining. NoSQL is the general name of the non-relational data- bases, which is a new data storage technology to meet the needs of the rapid growth of the Internet applications. Since it is easy to extend, has high write and read performance even for the large amount of data, and has flexible data mod- els, it have been well developed in some application scenari- os. MongoDB is a representative of NoSQL databases, the document-oriented data model it used, can automatically split the data and store them on different machines. This au- tomatic slicing mechanism achieves a distributed extension, the collections and documents in the database can be stored in many database nodes. The applications of MongoDB are very wide because of its good horizontal scalability: it is suitable for storing low-value and large-sized files; offers a data management technology which satisfies the high con- currency and the magnanimous data processing from the Internet development to cloud computing. Internet provides

A Conceptual Model of Admission System and Performance Evaluation for a University

admission process is a key process in a university. It affects the overall resources of the universities and its quality constraints. There are multiple constraints on which the decision to start or upgrade a typical course admission depends rather than only student to teacher ratio. There is need of effective data mining to find dependent constraints and trend, as it is suited as one of the best for analysis in education system. So firstly, a dimensional model of the university admission system is designed and then it is checked, whether the model validates the requirements or not. The study presented a way to find the trend in the education system for the courses with assessing admission capacity alongside with management and evaluation of different affecting factors on the student's performance. Keywordsional model, Higher education, Admission management system, Performance Evaluation

Digging deep into weighted patient data through multiple-level patterns

Large data volumes have been collected by healthcare organizations at an unprecedented rate. Today both physicians and healthcare system managers are very interested in extracting value from such data. Nevertheless, the increasing data complexity and heterogeneity prompts the need for new efficient and effective data mining approaches to analyzing large patient datasets. Generalized association rule mining algorithms can be exploited to automatically extract hidden multiple-level associations among patient data items (e.g., examinations, drugs) from large datasets equipped with taxonomies. However, in current approaches all data items are assumed to be equally relevant within each transaction, even if this assumption is rarely true.This paper presents a new data mining environment targeted to patient data analysis. It tackles the issue of extracting generalized rules from weighted patient data, where items may weight differently according to their importance within each transaction. To this aim, it proposes a novel type of association rule, namely the Weighted Generalized Association Rule (W-GAR). The usefulness of the proposed pattern has been evaluated on real patient datasets equipped with a taxonomy built over examinations and drugs. The achieved results demonstrate the effectiveness of the proposed approach in mining interesting and actionable knowledge in a real medical care scenario.

Taking Stock of Internet Consumer Trend Metrics

Internet chatter is a large and valuable data source that can be mined for real-time trend tracking and reaction to market changes. To be effective Internet data mining requires tools that can be used to enhance signal-to-noise ratios and quantify, organize, and qualify collected data. This has very significant implications for the cereal foods industry, because it can provide cereal food companies with early detection of and analysis mechanisms for emergent consumer trends, identify causal relationships between consumer trends to help optimize marketing and communication narratives, and assist in avoiding or mitigating the negative effects of black swan events. As such, real-time Internet chatter analysis can improve the flexibility of companies in reacting to changing circumstances. The tools developed by the financial industry to evaluate equity markets offer the potential to significantly amplify the power of Internet chatter analysis for the benefit of the cereal foods industry, as well as other indu...

Clustering Daily Metro Origin-Destination Matrix in Shenzhen China

The development of information technology gives rise to explosive growth of the amount of data. As a result, a more effective data mining method in pattern recognition is called into existence, which can properly reflect the inherent daily activity structure of metro travelers. This study is aimed to enrich the traditional clustering methods and provide practical information in dealing with traffic volume variation to the metro system operations. In this study, daily metro origin-destination (OD) data come from smart card records of Shenzhen, China, which cover 290 days and 118 stations. Principal component analysis (PCA) and singular value decomposition (SVD) are applied to conduct dimensionality reduction. Affinity propagation is then chosen to cluster the dimensionality reduced matrix to identify demand patterns of the metro OD matrix. Eleven representative categories are clustered and shown.

Data mining strategies to improve multiplex microbead immunoassay tolerance in a mouse model of infectious diseases.

Multiplex methodologies, especially those with high-throughput capabilities generate large volumes of data. Accumulation of such data (e.g., genomics, proteomics, metabolomics etc.) is fast becoming more common and thus requires the development and implementation of effective data mining strategies designed for biological and clinical applications. Multiplex microbead immunoassay (MMIA), on xMAP or MagPix platform (Luminex), which is amenable to automation, offers a major advantage over conventional methods such as Western blot or ELISA, for increasing the efficiencies in serodiagnosis of infectious diseases. MMIA allows detection of antibodies and/or antigens efficiently for a wide range of infectious agents simultaneously in host blood samples, in one reaction vessel. In the process, MMIA generates large volumes of data. In this report we demonstrate the application of data mining tools on how the inherent large volume data can improve the assay tolerance (measured in terms of sensitivity and specificity) by analysis of experimental data accumulated over a span of two years. The combination of prior knowledge with machine learning tools provides an efficient approach to improve the diagnostic power of the assay in a continuous basis. Furthermore, this study provides an in-depth knowledge base to study pathological trends of infectious agents in mouse colonies on a multivariate scale. Data mining techniques using serodetection of infections in mice, developed in this study, can be used as a general model for more complex applications in epidemiology and clinical translational research.

Research on the Era Environment of Data Mining

Modern society has entered an era of information technology, computer communication and network technology is changing the entire human and social, blowing a lot of information to bring convenience, it also brings a lot of new questions, the first is information overload , it is difficult to digest: the second is difficult to identify true and false information; third is difficult to ensure information security; fourth is the information in the form of inconsistent, difficult to handle, "Faced with these challenges, data mining techniques have emerged, and have a higher frame model security and privacy protection according distributed heterogeneous environments of data mining features, integrated use of new technologies SOA, ontology, WEB services, follow the user-centric concept, data mining system framework proposed an open service oriented. binding domain knowledge of data mining applications, follow the user-centered design philosophy presented to the user for data mining center of the body, on the one hand based on data mining and mining objects to organize data mining algorithms, on the other hand provide effective data mining application solutions for the user based on the application domain knowledge to help different areas of multi-level users to easily select data mining services.

An Optimized Algorithm for Association Rule Mining Using FP Tree

Data mining is used to deal with the huge size of the data stored in the database to extract the desired information and knowledge. It has various techniques for the extraction of data; association rule mining is the most effective data mining technique among them. It discovers hidden or desired pattern from large amount of data. Among the existing techniques the frequent pattern growth (FP growth) algorithm is the most efficient algorithm in finding out the desired association rules. It scans the database only twice for the processing. The issue with the FP growth algorithm is that it generates a huge number of conditional FP trees. In the proposed work, we have designed a new technique which mines out all the frequent item sets without the generation of the conditional FP trees. Unlike FP tree it scans the database only once which reduces the time efficiency of the algorithm. It also finds out the frequency of the frequent item sets to find out the desired association rules.

Association Rules Algorithm and Its Application in the Maintenance of the Tunnel

In this paper, effective data mining methods are adopted for the tunnel management information system to deal with safety issue data and work out the relationship among these safety issues in order to estimate risk, establish intelligent decision support, provide basis of governance for railway maintenance departments and remedy the defects of the existed management information systems. In view of the bottleneck of Apriori algorithm, two new algorithms are proposed in this paper. The first is AprioriN algorithm based on arrays, which converts the operation on database to the operation on memory via coding. The second is a high performance association rule mining algorithm based on FPtree, which accelerates the speed of traverse itemsets by adding an extra data structure. During the second scan of the database, a matrix is generated to save frequent 2-itemsets when the basic FP-tree is created. This paper attempts the improved algorithms to improve the efficiency. (Received, processed and accepted by the Chinese Representative Office.)

Feature Selection for Social Media Data

Feature selection is widely used in preparing high-dimensional data for effective data mining. The explosive popularity of social media produces massive and high-dimensional data at an unprecedented rate, presenting new challenges to feature selection. Social media data consists of (1) traditional high-dimensional, attribute-value data such as posts, tweets, comments, and images, and (2) linked data that provides social context for posts and describes the relationships between social media users as well as who generates the posts, and so on. The nature of social media also determines that its data is massive, noisy, and incomplete, which exacerbates the already challenging problem of feature selection. In this article, we study a novel feature selection problem of selecting features for social media data with its social context. In detail, we illustrate the differences between attribute-value data and social media data, investigate if linked data can be exploited in a new feature selection framework by taking advantage of social science theories. We design and conduct experiments on datasets from real-world social media Web sites, and the empirical results demonstrate that the proposed framework can significantly improve the performance of feature selection. Further experiments are conducted to evaluate the effects of user--user and user--post relationships manifested in linked data on feature selection, and research issues for future work will be discussed.

Studies on ICT Usage in the Academic CampusUsing Educational Data Mining

Inthe era of competition, change and complexity, innovation in teaching and learning practices in higher education sector has become unavoidable criteria.One of the biggest challenges that higher education system faces today is to assessthe services provided through Information and Communication Technology(ICT) facilities installed in the campus. This paper studies the responses collected through survey on ICT, in the campusof the University of Burdwan, among the students and research scholarswith the help ofan effective data mining methodology Variable Consistency Dominance-based Rough Set Approach (VC-DRSA) model to extract meaningful knowledge to improve the quality of managerial decisions in this sphere. It is an extended version of Dominance Rough Set Approach (DRSA) and is applied here to generate a set of recommendations that can help the university to improvise the existing services and augmenting the boundaries of ICT in future development.

DATA WAREHOUSING APPLICATIONS: AN ANALYTICAL TOOL FOR DECISION SUPPORT SYSTEM

Data-driven decision support systems, such as data warehouses can serve the requirement of extraction of information from more than one subject area. Data warehouses standardize the data across the organization so as to have a single view of information. Data warehouses (DW) can provide the information required by the decision makers. The data warehouse supports an on-line analytical processing (OLAP), the functional and performance requirements of which are quite different from those of the on-line transaction processing (OLTP) applications traditionally supported by the operational databases. Data warehouses provide on-line analytical processing (OLAP) tools for the interactive analysis of multidimensional data of varied granularities, which facilitates effective data mining. Data warehousing and OLAP have emerged as leading technologies that facilitate data storage, organization and then, significant retrieval. Both are essential elements of decision support, which has increasingly become a focus of the database industry. This paper provides a detailed picture of Data warehousing (DW), exploring the features of it, applications and the architecture of DW over Data Mining, Online Analytical Processing (OLAP), On-line Transaction Processing (OLTP) technologies.

Drug2Gene: an exhaustive resource to explore effectively the drug-target relation network

BackgroundInformation about drug-target relations is at the heart of drug discovery. There are now dozens of databases providing drug-target interaction data with varying scope, and focus. Therefore, and due to the large chemical space, the overlap of the different data sets is surprisingly small. As searching through these sources manually is cumbersome, time-consuming and error-prone, integrating all the data is highly desirable. Despite a few attempts, integration has been hampered by the diversity of descriptions of compounds, and by the fact that the reported activity values, coming from different data sets, are not always directly comparable due to usage of different metrics or data formats.DescriptionWe have built Drug2Gene, a knowledge base, which combines the compound/drug-gene/protein information from 19 publicly available databases. A key feature is our rigorous unification and standardization process which makes the data truly comparable on a large scale, allowing for the first time effective data mining in such a large knowledge corpus. As of version 3.2, Drug2Gene contains 4,372,290 unified relations between compounds and their targets most of which include reported bioactivity data. We extend this set with putative (i.e. homology-inferred) relations where sufficient sequence homology between proteins suggests they may bind to similar compounds. Drug2Gene provides powerful search functionalities, very flexible export procedures, and a user-friendly web interface.ConclusionsDrug2Gene v3.2 has become a mature and comprehensive knowledge base providing unified, standardized drug-target related information gathered from publicly available data sources. It can be used to integrate proprietary data sets with publicly available data sets. Its main goal is to be a ‘one-stop shop’ to identify tool compounds targeting a given gene product or for finding all known targets of a drug. Drug2Gene with its integrated data set of public compound-target relations is freely accessible without restrictions at http://www.drug2gene.com.

Study on Data Mining Techniques and Algorithms of Association Rules Data Mining

With the rapid development of network and database technology, data need to be processed massively increased, how to carry out effective data mining is a serious problem. The mature development of granular computing algorithm provides new ideas and new methods to study for data mining. Association rules of granular computing can reduce the number of object scanning data set, and improve the efficiency of the algorithm. In this paper we introduce the data source, classification, technology, system structure, operation process, application in other areas of data mining technology. Based on association rules of granular computing, data mining technology can provide quantitative basis for enterprise in screening assessment, so the service object has a stronger competitive advantage and focus more on its problems.

Application of Data Mining in Construction of Corruption Risks Prevention System

There are various types of corruption risks in the processes of public powers operation. This paper aims at the occupational corruption risks emerging from the exercise of public powers. Combined with the research on the construction project of the system and the introduction of data mining, this paper will probe into the scientific and effective data mining algorithms. By doing so, an electric cage is weaved to curb the abuse of powers by screening and selecting the early warning signs, thus guard against occupational corruption risk problems at the source.

Ontology Based Data Analysing Approach for Actionable Knowledge Discovery

In Data Mining, the effectiveness of association rules is limited by the huge quantity of delivered rules. In this manuscript, we propose a new approach to prune and filter discovered rules. An interactive and iterative framework is designed to assist the user along the analyzing task. The manuscript focus on medical data test set for detailed analysis and formation of the ontologies. In the proposed approach, the data set of medical records is entered in the back - end database. The development of associations and the ontology is fully dynamic. In case, any symptom is searched, the proposed approach search from the back end database and creates the ontology that is dynamic in execution. It refers that the unsupervised approach of ontology generation is implemented so that the unbiased results can be achieved. The implementation of proposed work shows the dynamic results in terms of rules found and their effectiveness in the real world scenario. 3 M) which is intended to make data mining workable in supporting decision-making actions in the real world. Current data mining tools and techniques drive a paradigm shift from traditional data-centred hidden pattern mining to domain-driven actionable knowledge discovery (AKD). AKD must cater for domain knowledge and environmental factors, balance technical significance and business expectations from both objective and subjective perspectives and support automatically converting patterns into deliverables in business friendly and operable forms such as actions or rules. In domain-driven framework, data mining analysts and domain-specific business analysts complement each other with regard to in-depth granularity and constrained environment through interactive system support. The involvement of domain experts and their knowledge can assist in developing highly effective domain specific data mining techniques, and reduce the complexity of knowledge discovery. The involvement of domain-related social intelligence into KDD process not only strengthens technical development and performance, but highlights business expectations and actionable capability of the identified results. In Data Mining, the effectiveness of association rules is strappingly limited by the huge quantity of delivered rules. In this manuscript, we propose a new approach to prune and filter discovered rules. An association rule is described as the implication X → Y where X and Y are sets of items and

Diagnosis of Breast Cancer using Decision Tree Models and SVM

Breast cancer represents the second important cause of cancer deaths in women today and it is the most common type of cancer in women. Disease diagnosis is one of the applications where data mining tools are proving successful results. Data mining with decision trees is popular and effective data mining classification approach. Decision trees have the ability to generate understandable classification rules, which are very efficient tool for transfer knowledge to physicians and medical specialists. In fundamental truth, they provide trails to find rules that could be evaluated for separating the input samples into one of several groups without having to state the functional relationship directly. The objective of this paper is to examine the performance of recent invented decision tree modeling algorithms and compared with one that achieved by radial basis function kernel support vector machine (RBFSVM) on the diagnosis of breast cancer using cytological proven tumor dataset. Four models have been evaluated in decision tree: Chi-squared Automatic Interaction Detection (CHAID), Classification and Regression tree (CR classification accuracy, sensitivity, and specificity.