Data mining techniques and applications – A decade review from 2000 to 2011

Liao, Shu-Hsien; Chu, Pei-hui; Hsiao, Pei-Yuan

doi:10.1016/j.eswa.2012.02.063

Cited by 554 publications

(253 citation statements)

References 101 publications

Supporting

Mentioning

218

Contrasting

Unclassified

Order By: Relevance

“…The research scopes are the literature on application of data mining for SDM in crime prevention, applied index crime dataset and published for 16 year period between 2000 and 2015 which is summarized to provide knowledge for researchers in this area. The period is important because the internet was Clustering Classification opened to general users in 2000 and the widespread availability of information and communication technologies have played an important role in the development of methods for collecting data from online databases (Liao et al, 2012). In phase 2, this study identifies the suitable criteria to search and select articles.…”

Section: Methodological Framework For Researchmentioning

confidence: 99%

A Review on a Classification Framework for Supporting Decision Making in Crime Prevention

No¹,

Hamid²,

Mohemad³

et al. 2014

J. of Artificial Intelligence

View full text Add to dashboard Cite

Increasing volume of crimes has brought a serious problem to many countries across the world. Crime prevention is an important component of an overall strategy to reduce crime and to strengthen public safety. Although, Supporting Decision Making (SDM) in crime prevention is an important topic but a comprehensive literature review on the subject has yet to be implemented. Thus, this study presents a systematic and comprehensive review on a classification framework for SDM in crime prevention. Forty four journal articles on the subject published between 2000 and October, 2015 were analyzed and classified into two categories of index crime (violent crime and property crime) and six classes of data mining techniques (prediction, classification, visualization, regression, clustering and outlier detection). The results of this study clearly show that data mining especially prediction and clustering techniques have been applied most extensively in both index crime categories. The main data mining techniques used for SDM in crime prevention are Bayesian, neural network and nearest neighbor. This study also addresses the gaps between SDM in crime prevention and the needs of practitioners to encourage more researches in crime analysis. Finally, it concludes with some suggestions for future research on SDM in crime prevention.

show abstract

Section: Methodological Framework For Researchmentioning

confidence: 99%

A Review on a Classification Framework for Supporting Decision Making in Crime Prevention

No¹,

Hamid²,

Mohemad³

et al. 2014

J. of Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…The differences among these algorithms mainly lie in the way the classification task is approached, the structure of the learning function, and the procedure for determining the optimal function parameters (e.g. Liao et al, 2012). As each learning algorithm has its strengths and limitations, it is often a challenge to find a single classifier that performs best for a particular learning task (e.g.…”

Section: Machine Learningmentioning

confidence: 99%

Annotating mobile phone location data with activity purposes using machine learning algorithms

Liu

Janssens

Wets

et al. 2013

Expert Systems with Applications

View full text Add to dashboard Cite

Individual human travel patterns captured by mobile phone data have been quantitatively characterized by mathematical models, but the underlying activities which initiate the movement are still in a less-explored stage. As a result of the nature of how activity and related travel decisions are made in daily life, human activity-travel behavior exhibits a high degree of spatial and temporal regularities as well as sequential ordering. In this study, we investigate to what extent the behavioral routines could reveal the activities being performed at mobile phone call locations that are captured when users initiate or receive a voice call or message. Our exploration consists of four steps. First, we define a set of comprehensive temporal variables characterizing each call location. Feature selection techniques are then applied to choose the most effective variables in the second step. Next, a set of state-of-the-art machine learning algorithms including Support Vector Machines, Logistic Regression, Decision Trees and Random Forests are employed to build classification models. Alongside, an ensemble of the results of the above models is also tested. Finally, the inference performance is further enhanced by a post-processing algorithm. Using data collected from natural mobile phone communication patterns of 80 users over a period of more than one year, we evaluated our approach via a set of extensive experiments. Based on the ensemble of the models, we achieved prediction accuracy of 69.7%. Furthermore, using the post processing algorithm, the performance obtained a 7.6% improvement. The experiment results demonstrate the potential to annotate mobile phone locations based on the integration of data mining techniques with the characteristics of underlying activity-travel behavior, contributing towards the semantic comprehension and further application of the massive data.

show abstract

“…Here information gain is taken as an attribute selection measure to construct a decision tree in the C4. 5.table 3-4 shows the calculation of information gain and the figure 2-4 shows the generated decision tree.…”

Section: Explanation Of Decision Tree Algorithmmentioning

confidence: 99%

Genetic Algorithm to Solve the Problem of Small Disjunct In the Decision Tree Based Intrusion Detection System

Azad

Jha²

2015

IJCNIS

View full text Add to dashboard Cite

Abstract-Intrusion detection system is the most important part of the network security system because the volume of unauthorized access to the network resources and services increase day by day. In this paper a genetic algorithm based intrusion detection system is proposed to solve the problem of the small disjunct in the decision tree. In this paper genetic algorithm is used to improve the coverage of those rules which are cope with the problem of the small disjunct. The proposed system consists of two modules rule generation phase, and the second module is rule optimization module. We tested the effectiveness of the system with the help of the KDD CUP dataset and the result is compared with the REP Tree, Random Tree, Random Forest, Naï ve Bayes, and the DTLW IDS (decision tree based light weight intrusion detection system). The result shows that the proposed system provide the best result in comparison to the above mentioned classifiers.

show abstract

Data mining techniques and applications – A decade review from 2000 to 2011

Cited by 554 publications

References 101 publications

A Review on a Classification Framework for Supporting Decision Making in Crime Prevention

A Review on a Classification Framework for Supporting Decision Making in Crime Prevention

Annotating mobile phone location data with activity purposes using machine learning algorithms

Genetic Algorithm to Solve the Problem of Small Disjunct In the Decision Tree Based Intrusion Detection System

Contact Info

Product

Resources

About