Associative Classifiers for Medical Images

Antonie, Maria-Luiza; Zaı̈ane, Osmar R.; Coman, Alexandru

doi:10.1007/978-3-540-39666-6_5

Cited by 39 publications

(40 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…b) Redundant rule pruning: This rule pruning method discards specific rules with fewer confidence values than general rules. Several algorithms, such as CMAR [1], [2], and [15], adopt this approach for rule pruning. c) Database coverage: This pruning approach tests the generated rules against the training dataset, and only keeps the rules, which cover at least one training data object not considered by a higher ranked rule for later classification.…”

Section: Related Workmentioning

confidence: 99%

CIMDS: Adapting Postprocessing Techniques of Associative Classification for Malware Detection

Jiang

et al. 2010

IEEE Trans. Syst., Man, Cybern. C

View full text Add to dashboard Cite

Abstract-Malware is software designed to infiltrate or damage a computer system without the owner's informed consent (e.g., viruses, backdoors, spyware, trojans, and worms). Nowadays, numerous attacks made by the malware pose a major security threat to computer users. Unfortunately, along with the development of the malware writing techniques, the number of file samples that need to be analyzed, named "gray list," on a daily basis is constantly increasing. In order to help our virus analysts, quickly and efficiently pick out the malicious executables from the "gray list," an automatic and robust tool to analyze and classify the file samples is needed. In our previous work, we have developed an intelligent malware detection system (IMDS) by adopting associative classification method based on the analysis of application programming interface (API) execution calls. Despite its good performance in malware detection, IMDS still faces the following two challenges: 1) handling the large set of the generated rules to build the classifier; and 2) finding effective rules for classifying new file samples. In this paper, we first systematically evaluate the effects of the postprocessing techniques (e.g., rule pruning, rule ranking, and rule selection) of associative classification in malware detection, and then, propose an effective way, i.e., CIDCPF, to detect the malware from the "gray list." To the best of our knowledge, this is the first effort on using postprocessing techniques of associative classification in malware detection. CIDCPF adapts the postprocessing techniques as follows: first applying Chi-square testing and Insignificant rule pruning followed by using Database coverage based on the Chi-square measure rule ranking mechanism and Pessimistic error estimation, and finally performing prediction by selecting the best First rule. We have incorporated the CIDCPF method into our existing IMDS system, and we call the new system as CIMDS system. Case studies are performed on the large collection of file samples obtained from the Antivirus Laboratory at Kingsoft Corporation and promising experimental results demonstrate that the efficiency and ability of detecting malware from the "gray list" of our CIMDS system outperform popular antivirus software tools, such as McAfee VirusScan and Norton AntiVirus, as well as previous data-mining-based detection systems, which employed Naive Bayes, support vector machine, and decision tree techniques. In particular, our CIMDS system can greatly reduce the number of generated rules, which makes it easy for our virus analysts to identify the useful ones.

show abstract

Section: Related Workmentioning

confidence: 99%

CIMDS: Adapting Postprocessing Techniques of Associative Classification for Malware Detection

Jiang

et al. 2010

IEEE Trans. Syst., Man, Cybern. C

View full text Add to dashboard Cite

show abstract

“…Algorithms, such as those in Li et al (2001), Antonie et al (2003) and Antonie & Zaïane (2004), have used redundant rule pruning. They perform such pruning immediately after a rule is inserted into the compact data structure, the CR-tree.…”

Section: Redundant Rule Pruningmentioning

confidence: 99%

A review of associative classification mining

Thabtah

2007

The Knowledge Engineering Review

256

135

View full text Add to dashboard Cite

Associative classification mining is a promising approach in data mining that utilizes the association rule discovery techniques to construct classification systems, also known as associative classifiers. In the last few years, a number of associative classification algorithms have been proposed, i.e. CPAR, CMAR, MCAR, MMAC and others. These algorithms employ several different rule discovery, rule ranking, rule pruning, rule prediction and rule evaluation methods. This paper focuses on surveying and comparing the state-of-the-art associative classification techniques with regards to the above criteria. Finally, future directions in associative classification, such as incremental learning and mining low-quality data sets, are also highlighted in this paper.

show abstract

“…We argue that pruning is also very important in order to allow domain experts to tune a classifier by editing rules if necessary. Our previous experiments show that manual alteration of the rules can lead to significant improvement in the classification [3]. The techniques proposed to prune the rules are based on redundancy and noise elimination and precedence ranking.…”

Section: Pruning Rulesmentioning

confidence: 99%

On Pruning and Tuning Rules for Associative Classifiers

Zaı̈ane

Antonie

2005

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. The integration of supervised classification and association rules for building classification models is not new. One major advantage is that models are human readable and can be edited. However, it is common knowledge that association rule mining typically yields a sheer number of rules defeating the purpose of a human readable model. Pruning unnecessary rules without jeopardizing the classification accuracy is paramount but very challenging. In this paper we study strategies for classification rule pruning in the case of associative classifiers. Associative Classifiers and their massive modelAssociation rules are typically known as an important and common means for market basket analysis. However, it has been observed that association rules could be used to model relationships between class labels and features from a training set [4]. Therefore, association rules were used to efficiently build a classification model from very large training datasets. Since then, many associative classifiers were proposed mainly differing in the strategies used to select rules for classification and in the heuristics used for pruning rules [7,6,9]. Among the many advantages of associative classifiers we can highlight four major ones: -The training is very efficient regardless of the size of the training set; -Training sets with high dimensionality can be handled with ease and no assumptions are made on dependence or independence of attributes; -The classification is very fast; -The classification model is a set of rules easily understandable by humans and can be edited.The problems with associative classifiers are also remarkable. First, they inherit two complicated parameters from association rule mining, namely support and confidence. These are difficult to set and tune. Second, association rule mining generates a sheer number of rules commonly outnumbering the observations in the training set. This defeats the purpose of readability of the classification model since no human would be willing to sift through hundreds of thousands of rules for editing purposes. This leads to two other issues: How can we reduce the number of rules in the model and how can we effectively select rules to apply during classification? In this paper we address one of these issues: the reduction of classification rules. This problem is challenging because the goal is to prune rules while preventing the accuracy of the classifier from dipping.

show abstract

Associative Classifiers for Medical Images

Cited by 39 publications

References 12 publications

CIMDS: Adapting Postprocessing Techniques of Associative Classification for Malware Detection

CIMDS: Adapting Postprocessing Techniques of Associative Classification for Malware Detection

A review of associative classification mining

On Pruning and Tuning Rules for Associative Classifiers

Contact Info

Product

Resources

About