Traditional Data Mining Algorithms Research Articles

Research of the FP-Growth Algorithm Based on Cloud Environments

The emergence of cloud computing solves the problems that traditional data mining algorithms encounter when dealing with large data. This paper studies the FP-Growth algorithm and proposes a parallel linked list-based FPG algorithm based on MapReduce programming model, named as the PLFPG algorithm. And then it describes the main idea of algorithm. Finally, by using different data sets to test the algorithm, the experimental result shows that PLFPG algorithm has higher efficiency and better flexibility and scalability.

Data Mining Techniques for Wireless Sensor Networks: A Survey

Recently, data management and processing for wireless sensor networks (WSNs) has become a topic of active research in several fields of computer science, such as the distributed systems, the database systems, and the data mining. The main aim of deploying the WSNs-based applications is to make the real-time decision which has been proved to be very challenging due to the highly resource-constrained computing, communicating capacities, and huge volume of fast-changed data generated by WSNs. This challenge motivates the research community to explore novel data mining techniques dealing with extracting knowledge from large continuous arriving data from WSNs. Traditional data mining techniques are not directly applicable to WSNs due to the nature of sensor data, their special characteristics, and limitations of the WSNs. This work provides an overview of how traditional data mining algorithms are revised and improved to achieve good performance in a wireless sensor network environment. A comprehensive survey of existing data mining techniques and their multilevel classification scheme is presented. The taxonomy together with the comparative tables can be used as a guideline to select a technique suitable for the application at hand. Based on the limitations of the existing technique, an adaptive data mining framework of WSNs for future research is proposed.

A Hybrid Algorithm of Traffic Accident Data Mining on Cause Analysis

Road traffic accident databases provide the basis for road traffic accident analysis, the data inside which usually has a radial, multidimensional, and multilayered structure. Traditional data mining algorithms such as association rules, when applied alone, often yield uncertain and unreliable results. An improved association rule algorithm based on Particle Swarm Optimization (PSO) put forward by this paper can be used to analyze the correlation between accident attributes and causes. The new algorithm focuses on characteristics of the hyperstereo structure of road traffic accident data, and the association rules of accident causes can be calculated more accurately and in higher rates. A new concept of Association Entropy is also defined to help compare the importance between different accident attributes. T-test model and Delphi method were deployed to test and verify the accuracy of the improved algorithm, the result of which was a ten times faster speed for random traffic accident data sampling analyses on average. In the paper, the algorithms were tested on a sample database of more than twenty thousand items, each with 56 accident attributes. And the final result proves that the improved algorithm was accurate and stable.

Clustering Customer Shopping Trips with Network Structure

Moving objects can be tracked with sensors such as RFID tags or GPS devices. Their movement can be represented as sequences of time-stamped locations. Studying such spatio-temporal movement sequences to discover spatial sequential patterns holds promises in many real-world settings. A few interesting applications are customer shopping traverse pattern discovery, vehicle traveling pattern discovery, and route prediction. Traditional spatial data mining algorithms suitable for the Euclidean space are not directly applicable in these settings. We propose a new algorithm to cluster movement paths such as shopping trips for pattern discovery. In our work, we represent the spatio-temporal series as sequences of discrete locations following a pre-defined network. We incorporate a modified version of the Longest Common Subsequence (LCS) algorithm with the network structure to measure the similarity of movement paths. With such spatial networks we implicitly address the existence of spatial obstructs as well. Experiments were performed on both hand-collected real-life trips and simulated trips in grocery shopping. The initial evaluation results show that our proposed approach, called Net-LCSS, can be used to support effective and efficient clustering for shopping trip pattern discovery.

RUSBoost: A Hybrid Approach to Alleviating Class Imbalance

Class imbalance is a problem that is common to many application domains. When examples of one class in a training data set vastly outnumber examples of the other class(es), traditional data mining algorithms tend to create suboptimal classification models. Several techniques have been used to alleviate the problem of class imbalance, including data sampling and boosting. In this paper, we present a new hybrid sampling/boosting algorithm, called RUSBoost, for learning from skewed training data. This algorithm provides a simpler and faster alternative to SMOTEBoost, which is another algorithm that combines boosting and data sampling. This paper evaluates the performances of RUSBoost and SMOTEBoost, as well as their individual components (random undersampling, synthetic minority oversampling technique, and AdaBoost). We conduct experiments using 15 data sets from various application domains, four base learners, and four evaluation metrics. RUSBoost and SMOTEBoost both outperform the other procedures, and RUSBoost performs comparably to (and often better than) SMOTEBoost while being a simpler and faster technique. Given these experimental results, we highly recommend RUSBoost as an attractive alternative for improving the classification performance of learners built using imbalanced data.

Sound Isolation by Harmonic Peak Partition For Music Instrument Recognition

Identification of music instruments in polyphonic sounds is difficult and challenging, especially where heterogeneous harmonic partials are overlapping with each other. This has stimulated the research on sound separation for content-based automatic music information retrieval. Numerous successful approaches on musical data feature extraction and selection have been proposed for instrument recognition in monophonic sounds. Unfortunately, none of those algorithms can be successfully applied to polyphonic sounds. Based on recent research in sound classification of monophonic sounds and studies in speech recognition, Moving Picture Experts Group (MPEG) standardized a set of features of the digital audio content data for the purpose of interpretation of the informationmeaning. Most of themare in a formof largematrix or vector of large size, which are not suitable for traditional data mining algorithms; while other features in smaller size are not sufficient for instrument recognition in polyphonic sounds. Therefore, these acoustical features themselves alone cannot be successfully applied to classification of polyphonic sounds. However, these features contain critical information, which implies music instruments' signatures. We have proposed a novel music information retrieval system with MPEG-7-based descriptors and we built classifiers which can retrieve the important time-frequency timbre information and isolate sound sources in polyphonic musical objects, where two instruments are playing at the same time, by energy clustering between heterogeneous harmonic peaks.

Privacy-preserving SVM classification

Traditional Data Mining and Knowledge Discovery algorithms assume free access to data, either at a centralized location or in federated form. Increasingly, privacy and security concerns restrict this access, thus derailing data mining projects. What is required is distributed knowledge discovery that is sensitive to this problem. The key is to obtain valid results, while providing guarantees on the nondisclosure of data. Support vector machine classification is one of the most widely used classification methodologies in data mining and machine learning. It is based on solid theoretical foundations and has wide practical application. This paper proposes a privacy-preserving solution for support vector machine (SVM) classification, PP-SVM for short. Our solution constructs the global SVM classification model from data distributed at multiple parties, without disclosing the data of each party to others. Solutions are sketched out for data that is vertically, horizontally, or even arbitrarily partitioned. We quantify the security and efficiency of the proposed method, and highlight future challenges.

Mining of Multi-Relational Association Rules

Association rule mining is one of the most important and basic technique in data mining,which has been studied extensively and has a wide range of applications.However,as traditional data mining algorithms usually only focus on analyzing data organized in single table,applying these algorithms in multi-relational data environment will result in many problems.This paper summarizes these problems,proposes a framework for the mining of multi-relational association rule,and gives a definition of the mining task.After classifying the existing work into two categories,it describes the main techniques used in several typical algorithms,and it also makes comparison and analysis among them.Finally,it points out some issues unsolved and some future further research work in this area.

Spatial associative classification: propositional vs structural approach

In Spatial Data Mining, spatial dimension adds a substantial complexity to the data mining task. First, spatial objects are characterized by a geometrical representation and relative positioning with respect to a reference system, which implicitly define both spatial relationships and properties. Second, spatial phenomena are characterized by autocorrelation, i.e., observations of spatially distributed random variables are not location-independent. Third, spatial objects can be considered at different levels of abstraction (or granularity). The recently proposed SPADA algorithm deals with all these sources of complexity, but it offers a solution for the task of spatial association rules discovery. In this paper the problem of mining spatial classifiers is faced by building an associative classification framework on SPADA. We consider two alternative solutions for associative classification: a propositional and a structural method. In the former, SPADA obtains a propositional representation of training data even in spatial domains which are inherently non-propositional, thus allowing the application of traditional data mining algorithms. In the latter, the Bayesian framework is extended following a multi-relational data mining approach in order to cope with spatial classification tasks. Both methods are evaluated and compared on two real-world spatial datasets and results provide several empirical insights on them.