From data mining to knowledge mining: Application to intelligent agents

Chemchem, Amine; Drias, Habiba

doi:10.1016/j.eswa.2014.08.024

Cited by 22 publications

(14 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Clustering is a statistical approach for classification of patterns into groups based on similarities of internal features or characteristics. K-means is a common clustering algorithm that has been used in a wide variety of applications to partition a data set into K groups (de Miranda Santo et al, 2006;Chemchem and Drias, 2015). To do so, the user must assign a number K as the expected number of clusters.…”

Section: Tablementioning

confidence: 99%

Science foresight using life-cycle analysis, text mining and clustering: A case study on natural ventilation

Rezaeian

Montazeri

Loonen

2017

Technological Forecasting and Social Change

View full text Add to dashboard Cite

Science foresight comprises a range of methods to analyze past, present and expected research trends, and uses this information to predict the future status of different fields of science and technology. With the ability to identify high-potential development directions, science foresight can be a useful tool to support the management and planning of future research activities. Science foresight analysts can choose from a rather large variety of approaches. There is, however, relatively little information about how the various approaches can be applied in an effective way. This paper describes a three-step methodological framework for science foresight on the basis of published research papers, consisting of (i) life-cycle analysis, (ii) text mining and (iii) knowledge gap identification by means of automated clustering. The three steps are connected using the research methodology of the research papers, as identified by text mining. The potential of combining these three steps in one framework is illustrated by analyzing scientific literature on wind catchers; a natural ventilation concept which has received considerable attention from academia, but with quite low application in practice. The knowledge gaps that are identified show that the automated foresight analysis is indeed able to find uncharted research areas. Results from a sensitivity analysis further show the importance of using full-texts for text mining instead of only title, keywords and abstract. The paper concludes with a reflection on the methodological framework, and gives directions for its intended use in future studies.

show abstract

Section: Tablementioning

confidence: 99%

Science foresight using life-cycle analysis, text mining and clustering: A case study on natural ventilation

Rezaeian

Montazeri

Loonen

2017

Technological Forecasting and Social Change

View full text Add to dashboard Cite

show abstract

“…In [31,30] the authors note that agents -generally seen through the lens of autonomous agents and multi-agent systems, and knowledge discoverygenerally seen as a data mining exercise, initially emerged and established as separate standalone research fields but in the last two decades methods from both fields merged into a new field of research, the "agent mining". The agent mining concept was largely supported by numerous studies in the literature [15,32,145,110,40], which proposed agents for agent mining applications under various names such as knowledge driven agents [15], knowledge collector agents [145], or miner agents [6,40]. In [30] Cao et al identify three approaches on agents and knowledge discovery that are essential for the emergence and establishment of the machine agents in knowledge acquisition: the data mining-driven agents, the agent-driven data mining, and the agent mining itself, where the former two were precursors of the latter.…”

Section: The Mining Machine Agentsmentioning

confidence: 99%

“…In [40], based on the classification they proposed, the authors integrate the three approaches and introduce the Miner Intelligent Agent (MIA), a scalable knowledge-base cognitive agent that consists of a knowledge base, a meta-knowledge base, an induction rule mining module, and an inference engine. The knowledge base contains all the knowledge perceived and de-veloped by the agent in the form of if-then rules.…”

Section: Integration-based Agentsmentioning

confidence: 99%

“…The Inference Engine creates the feedback loop that reinforce the rule base in order to emulate the reasoning process. Following the same type of integration framework as the one described in [40], Kadhim et al [110] proposed MI-AKDD, a multi-intelligent agent for knowledge discovery in databases in cooperation with human experts. The MIAKDD agent integrates a combined rule generation-classification component which uses classification based on association.…”

Section: Integration-based Agentsmentioning

confidence: 99%

See 1 more Smart Citation

A multi-disciplinary review of knowledge acquisition methods: From human to autonomous eliciting agents

Leu

Abbass

2016

Knowledge-Based Systems

View full text Add to dashboard Cite

This paper offers a multi-disciplinary review of knowledge acquisition methods in human activity systems. The review captures the degree of involvement of various types of agencies in the knowledge acquisition process, and proposes a classification with three categories of methods: the human agent, the human-inspired agent, and the autonomous machine agent methods. In the first two categories, the acquisition of knowledge is seen as a cognitive task analysis exercise, while in the third category knowledge acquisition is treated as an autonomous knowledge-discovery endeavour. The motivation for this classification stems from the continuous change over time of the structure, meaning and purpose of human activity systems, which are seen as the factor that fuelled researchers' and practitioners' efforts in knowledge acquisition for more than a century.We show through this review that the KA field is increasingly active due to the higher and higher pace of change in human activity, and conclude by discussing the emergence of a fourth category of knowledge acquisition methods, which are based on red-teaming and co-evolution.

show abstract

“…Chen et al (2015) used file relation graph for malware detection and introduces novel belief propagation (BP) algorithm. Based on the previous detection techniques and the performance of the detection of mining and machine learning techniques, which may not be adequate for classifying and extracting all the features of malware, the proposed relation graph and the novel belief propagation classifier would be used for effectiveness and the accuracy of catching the malware variants Chemchem and Drias (2015). addressed the importance of performance and improvement in speeding up the process of reasoning engine.…”

mentioning

confidence: 99%

An Efficient Mining Based Approach Using PSO Selection Technique For Analysis and Detection of Obfuscated Malware

Zafar¹,

Soomro²

2018

JIACS

View full text Add to dashboard Cite

Malware plays a threatening role to the security of the data and information systems, as they created in different forms targeting data and networks. Malware developers use obfuscation techniques to hide malwares structure from detection of Anti-Virus (AV) programs, which use signature based detection; it is almost hard to detect the zero day attack and ineffective to analyze the hidden structure of malware. Such malicious codes are categorized as Oligomorphic, polymorphic and metamorphic Malware. Malware writers use packing mechanism to keep the malicious code harder during the signature-based detection and bypass easily. Mining techniques are one of the promising methods to analyze and detect hidden malware based on clustering and classification. This research focuses on improving accuracy and reducing processing time in the classification phase. This research approach mainly focused on the optimal attribute selection for classification to get the desired output. The proposed model uses Particle Swarm Optimization (PSO) for best attribute selection from the features set extracted from the packed and non-packed Portable Executable (PE) file format of malware and benign dataset. Classification tests have been prepared on the optimal subset of PE features in which Random Forrest classification outperforms from the rest of the classification algorithm.

show abstract

From data mining to knowledge mining: Application to intelligent agents

Cited by 22 publications

References 12 publications

Science foresight using life-cycle analysis, text mining and clustering: A case study on natural ventilation

Science foresight using life-cycle analysis, text mining and clustering: A case study on natural ventilation

A multi-disciplinary review of knowledge acquisition methods: From human to autonomous eliciting agents

An Efficient Mining Based Approach Using PSO Selection Technique For Analysis and Detection of Obfuscated Malware

Contact Info

Product

Resources

About