Papers by Keyword: Data Mining (DM)

Paper TitlePage

Authors: Zhen Dong Li, Fei Li
Abstract: Clustering algorithms, like K-means Algorithm, use distances in attribute space to cluster data. However the computation of distances in attribute space influences the accuracy. So innovatively, Variance-Similarity clustering algorithm defines similarity as a function of the attribute variance, and clusters data by the comparison of similarities. In computer simulation, the comparison of Variance-Similarity Algorithm and K-means Algorithm on UCI data sets presents that Variance-Similarity Algorithm has a better clustering accuracy than K-means Algorithm.
Authors: Jing Bo Yuan, Xiao Lin Wei, Shun Li Ding
Abstract: Association rules analysis is an important subject in data mining. At present, association rules mining algorithms frequently generate a large number of association rules, but most of the algorithm evaluations make advances only from an aspect, which makes the users select difficultly. Therefore, the comprehensive evaluation of association rules has become highly necessary. A comprehensive evaluation system of association rules based on the AHP (Analytic Hierarchy Process) was presented, which can evaluate the association rules from multi-angle and multi-dimensional. Many evaluation results are integrated into the system, eventually presenting a unified comprehensive coefficient to users. Practical data make it clear that the comprehensive evaluation system is rational and superior.
Authors: Gabriela Maria Atanasiu, Florin Leon, Bogdan F. Popa, Cornel Doniga
Abstract: This paper deals with the monitoring and assessment of structural performance of reinforced concrete residential buildings damaged during the lifetime by several important natural disasters such as earthquakes. The problem belongs to the risk management of built environment areas subjected to various natural catastrophes. In our work, we present a methodology based on modeling, simulation and nonlinear analysis applied on two classes of existing buildings located in the damaged infrastructure of earthquake sensitive cities. The decisions for risk mitigation taking into account the real seismic vulnerability of structures are based on GIS (Geographical Information Systems) mapping, and application of some artificial intelligence techniques. Finally, our paper discusses a new methodology for awareness and mitigation of seismic effects in case of future events in dense urban areas based on a case study for Iasi city, Romania.
Authors: Mohammad Raza Perwez, Naveed Ahmad, Muhammad Sajid Javaid, Muhammad Ehsan ul Haq
Abstract: Clinical Practice guidelines strongly relies on evidence based medical literature. In Health care domain decision support systems are playing a competent role in diagnosis and treatment from multiple diseases. Among different Hospitals all over the world the Information technology domain emphasis key roles in improvement of patient health care to great extent. The Concept of Data Mining (DM) and Decision Support systems (DSS) in medical domain provides an efficient mechanism to extract the multiple records of patient treatment diagnostics from previously stored records in Data base (DB) or Data Ware House (DWH) and compare these guidelines to perform strong analysis that results in efficient decision making. Along the previously mentioned techniques the era of Telemedicine has also being developed that results in generation of multiple techniques in diagnosis of multiple diseases and health improvement using Mobile Health care systems specially worth full for the rural areas where latest medical facilities are unavailable at the point of need. The required information in Database or in Data Ware House might be the historical data of patient or the health based summery of different patients in diverse stages. Now these days the emergence of distributed decision support systems in health care domain covers the health care treatment procedures in more comprehensive manner including surgical procedures and radiological treatment. In this paper we are going to analyze the multiple health care diagnosis procedures and treatment techniques using various decision support systems designed and implemented by various researchers all over the world and compare the effectiveness and efficiency of each decision support system in health care domain. Our research study is also helpful for physicians and health care practioners in analyzing multiple scenarios related to interesting pattern recognitions and intelligent decision making.
Authors: Xiao Qing Zhou, Jia Xiu Sun
Abstract: The open-up data mining system is one of developing directions of the present data mining system. In this paper we have put forward a data mining system based on the Web Services and given an applied example on the basis of analysis of the system. As the Web Services have stronger sealing and their joints are simple, they make the integration of the data mining system more flexible, heightening the working of the mining system.
Authors: Jin Rong Bai, Zhen Zhou An, Guo Zhong Zou, Shi Guang Mu
Abstract: Dynamic detection method based on software behavior is an efficient and effective way for anti-virus technology. Malware and benign executable differ mainly in the implementation of some special behavior to propagation and destruction. A program's execution flow is essentially equivalent to the stream of API calls. Analyzing the API calls frequency from six kinds of behaviors in the same time has the very well differentiate between malicious and benign executables. This paper proposed a dynamic malware detection approach by mining the frequency of sensitive native API calls and described experiments conducted against recent Win32 malware. Experimental results indicate that the detection rate of proposed method is 98% and the value of the AUC is 0.981. Furthermore, proposed method can identify known and unknown malware.
Authors: Shun An Cao, Jia Yuan Hu, Yan Huang, Jian Li Xie
Abstract: Carrying out the fault diagnosis of water-steam chemistry process in power plant has an important significance to ensuring high qualified rates of water and steam quality as well as maintaining safe operation of units. This paper proposed a fault diagnosis method based on improved credibility theory which is used to construct fuzzy diagnosis rules and data mining technique used to determine symptom weights and rule limens of reliability rules, and also improved the setting method of rule confidence. The adoption of data mining technique and new setting method of rule confidence can solve the problem that credibility reasoning results are influenced by person’s subjective factors, and make the reasoning process more scientific. Example results prove that this diagnosis model has a high accuracy, which indicates the significant practical value of the model.
Authors: Lei Ming Yan, Jin Han
Abstract: Community discovery is a crucial task in social network analysis, especially in describing the evolution of social networks. Although some works have focused on finding the dynamic community, there are still some open problems need to be conquered, such as analyzing the dynamic and weighted community. In this paper, we propose a framework for analyzing weighted communities and their evolutions via clustering correlated weight vectors to enhance existing community detection algorithms. The International trade network is used to verify our framework. Experiments show that the framework discovers and captures the evolving behaviors with temporal elements and weight values.
Authors: Zhi Ping Zhang, Lin Na Li, Li Jun Wang, Hai Yan Yu
Abstract: Data mining discovers knowledge and useful information from large amounts of data stored in databases. With the increasing popularity of object-oriented database system in advanced database applications, it is significantly important to study the data mining methods for object-oriented database. This paper proposes that higher-order logic programming languages and techniques is very suitable for object-oriented data mining, and presents a framework for object-oriented data mining based on higher-order logic programming. Such a framework is inductive logic programming which adopts higher-order logic programming language Escher as knowledge representation formalism. In addition, Escher is a generalization of the attribute-value representation, thus many higher-order logic learners under this framework can be upgraded directly from corresponding propositional learners.
Authors: Yan Qiu Zhang, Min Tu, Yuan Xu, Yu Li
Abstract: A wealth of stream data is produced in the application of wireless sensor network (WSN). The knowledge in stream data can be extracted by data mining and it is useful for decision making. However, it is challenging to apply classical data mining methods on the scenario of WSN due to the factors such as limited power supply, on-line mining, data conversion and dynamic topology. This paper proposed a framework for distributed data mining by combining the existing approaches with the intrinsic property of WSN.
Showing 1 to 10 of 606 Paper Titles