Limits...
Covert network analysis for key player detection and event prediction using a hybrid classifier.

Butt WH, Akram MU, Khan SA, Javed MY - ScientificWorldJournal (2014)

Bottom Line: National security has gained vital importance due to increasing number of suspicious and terrorist events across the globe.Use of different subfields of information technology has also gained much attraction of researchers and practitioners to design systems which can detect main members which are actually responsible for such kind of events.As a proof of concept, the proposed framework has been implemented and tested using different case studies including two publicly available datasets and one local network.

View Article: PubMed Central - PubMed

Affiliation: Department of Computer Engineering, College of Electrical and Mechanical Engineering, National University of Sciences and Technology, Islamabad 44000, Pakistan.

ABSTRACT
National security has gained vital importance due to increasing number of suspicious and terrorist events across the globe. Use of different subfields of information technology has also gained much attraction of researchers and practitioners to design systems which can detect main members which are actually responsible for such kind of events. In this paper, we present a novel method to predict key players from a covert network by applying a hybrid framework. The proposed system calculates certain centrality measures for each node in the network and then applies novel hybrid classifier for detection of key players. Our system also applies anomaly detection to predict any terrorist activity in order to help law enforcement agencies to destabilize the involved network. As a proof of concept, the proposed framework has been implemented and tested using different case studies including two publicly available datasets and one local network.

Show MeSH

Related in: MedlinePlus

Proposed framework for hybrid classifier.
© Copyright Policy - open-access
Related In: Results  -  Collection


getmorefigures.php?uid=PMC4127216&req=5

fig4: Proposed framework for hybrid classifier.

Mentions: For hybrid classifier, we combine kNN, GMM, and SVM classifiers using a weighted probabilistic ensemble. The classification of node υ using probabilistic classification prediction, based on measure of evidence from different classifiers, is performed as(14)class(υ)=argmax⁡∀classi(∑i=1cak∗PCk(y=classi ∣ υ)),where PCk(y = classi∣υ) is the probability of classi given a sample node using classifier k and ak is the weight associated with the probabilistic prediction of class Ck. Figure 4 shows the proposed ensemble framework for hybrid classifier.


Covert network analysis for key player detection and event prediction using a hybrid classifier.

Butt WH, Akram MU, Khan SA, Javed MY - ScientificWorldJournal (2014)

Proposed framework for hybrid classifier.
© Copyright Policy - open-access
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC4127216&req=5

fig4: Proposed framework for hybrid classifier.
Mentions: For hybrid classifier, we combine kNN, GMM, and SVM classifiers using a weighted probabilistic ensemble. The classification of node υ using probabilistic classification prediction, based on measure of evidence from different classifiers, is performed as(14)class(υ)=argmax⁡∀classi(∑i=1cak∗PCk(y=classi ∣ υ)),where PCk(y = classi∣υ) is the probability of classi given a sample node using classifier k and ak is the weight associated with the probabilistic prediction of class Ck. Figure 4 shows the proposed ensemble framework for hybrid classifier.

Bottom Line: National security has gained vital importance due to increasing number of suspicious and terrorist events across the globe.Use of different subfields of information technology has also gained much attraction of researchers and practitioners to design systems which can detect main members which are actually responsible for such kind of events.As a proof of concept, the proposed framework has been implemented and tested using different case studies including two publicly available datasets and one local network.

View Article: PubMed Central - PubMed

Affiliation: Department of Computer Engineering, College of Electrical and Mechanical Engineering, National University of Sciences and Technology, Islamabad 44000, Pakistan.

ABSTRACT
National security has gained vital importance due to increasing number of suspicious and terrorist events across the globe. Use of different subfields of information technology has also gained much attraction of researchers and practitioners to design systems which can detect main members which are actually responsible for such kind of events. In this paper, we present a novel method to predict key players from a covert network by applying a hybrid framework. The proposed system calculates certain centrality measures for each node in the network and then applies novel hybrid classifier for detection of key players. Our system also applies anomaly detection to predict any terrorist activity in order to help law enforcement agencies to destabilize the involved network. As a proof of concept, the proposed framework has been implemented and tested using different case studies including two publicly available datasets and one local network.

Show MeSH
Related in: MedlinePlus