Performance optimization of criminal network hidden link prediction model with deep reinforcement learning
The scale of criminal networks (e.g. drug syndicates and terrorist networks) extends globally and poses national security threat to many nations as they also tend to be technologically advance (e.g. Dark Web and Silk Road cryptocurrency). Therefore, it is critical for law enforcement agencies to be...
Guardado en:
Autores principales: | , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Elsevier
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/39a19cfa06b64af39f8c11b1168792d8 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:39a19cfa06b64af39f8c11b1168792d8 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:39a19cfa06b64af39f8c11b1168792d82021-11-22T04:19:43ZPerformance optimization of criminal network hidden link prediction model with deep reinforcement learning1319-157810.1016/j.jksuci.2019.07.010https://doaj.org/article/39a19cfa06b64af39f8c11b1168792d82021-12-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S1319157819308584https://doaj.org/toc/1319-1578The scale of criminal networks (e.g. drug syndicates and terrorist networks) extends globally and poses national security threat to many nations as they also tend to be technologically advance (e.g. Dark Web and Silk Road cryptocurrency). Therefore, it is critical for law enforcement agencies to be equipped with the latest tools in criminal network analysis (CNA) to obtain key hidden links (relationships) within criminal networks to preempt and disrupt criminal network structures and activities. Current hidden or missing link predictive models that are based on Social Network Analysis models rely on ML techniques to improve the performance of the models in terms of predictive accuracy and computing power. Given the improvement in the recent performance of Deep Reinforcement Learning (DRL) techniques which could train ML models through self-generated dataset, DRL can be usefully applied to domains with relatively smaller dataset such as criminal networks. The objective of this study is to assess the comparative performance of a CNA hidden link prediction model developed using DRL techniques against classical ML models such as gradient boosting machine (GBM), random forest (RF) and support vector machine (SVM). The experiment results exhibit an improvement in the performance of the DRL model of about 7.4% over the next best performing classical RF model trained within 1500 iterations. The performance of these link prediction models can be scaled up with the parallel processing capabilities of graphical processing units (GPUs), to significantly improve the speed of training the model and the prediction of hidden links.Marcus LimAzween AbdullahNZ JhanjhiElsevierarticleHidden link predictionDeep reinforcement learningCriminal network analysisSocial network analysisGPUElectronic computers. Computer scienceQA75.5-76.95ENJournal of King Saud University: Computer and Information Sciences, Vol 33, Iss 10, Pp 1202-1210 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Hidden link prediction Deep reinforcement learning Criminal network analysis Social network analysis GPU Electronic computers. Computer science QA75.5-76.95 |
spellingShingle |
Hidden link prediction Deep reinforcement learning Criminal network analysis Social network analysis GPU Electronic computers. Computer science QA75.5-76.95 Marcus Lim Azween Abdullah NZ Jhanjhi Performance optimization of criminal network hidden link prediction model with deep reinforcement learning |
description |
The scale of criminal networks (e.g. drug syndicates and terrorist networks) extends globally and poses national security threat to many nations as they also tend to be technologically advance (e.g. Dark Web and Silk Road cryptocurrency). Therefore, it is critical for law enforcement agencies to be equipped with the latest tools in criminal network analysis (CNA) to obtain key hidden links (relationships) within criminal networks to preempt and disrupt criminal network structures and activities. Current hidden or missing link predictive models that are based on Social Network Analysis models rely on ML techniques to improve the performance of the models in terms of predictive accuracy and computing power. Given the improvement in the recent performance of Deep Reinforcement Learning (DRL) techniques which could train ML models through self-generated dataset, DRL can be usefully applied to domains with relatively smaller dataset such as criminal networks. The objective of this study is to assess the comparative performance of a CNA hidden link prediction model developed using DRL techniques against classical ML models such as gradient boosting machine (GBM), random forest (RF) and support vector machine (SVM). The experiment results exhibit an improvement in the performance of the DRL model of about 7.4% over the next best performing classical RF model trained within 1500 iterations. The performance of these link prediction models can be scaled up with the parallel processing capabilities of graphical processing units (GPUs), to significantly improve the speed of training the model and the prediction of hidden links. |
format |
article |
author |
Marcus Lim Azween Abdullah NZ Jhanjhi |
author_facet |
Marcus Lim Azween Abdullah NZ Jhanjhi |
author_sort |
Marcus Lim |
title |
Performance optimization of criminal network hidden link prediction model with deep reinforcement learning |
title_short |
Performance optimization of criminal network hidden link prediction model with deep reinforcement learning |
title_full |
Performance optimization of criminal network hidden link prediction model with deep reinforcement learning |
title_fullStr |
Performance optimization of criminal network hidden link prediction model with deep reinforcement learning |
title_full_unstemmed |
Performance optimization of criminal network hidden link prediction model with deep reinforcement learning |
title_sort |
performance optimization of criminal network hidden link prediction model with deep reinforcement learning |
publisher |
Elsevier |
publishDate |
2021 |
url |
https://doaj.org/article/39a19cfa06b64af39f8c11b1168792d8 |
work_keys_str_mv |
AT marcuslim performanceoptimizationofcriminalnetworkhiddenlinkpredictionmodelwithdeepreinforcementlearning AT azweenabdullah performanceoptimizationofcriminalnetworkhiddenlinkpredictionmodelwithdeepreinforcementlearning AT nzjhanjhi performanceoptimizationofcriminalnetworkhiddenlinkpredictionmodelwithdeepreinforcementlearning |
_version_ |
1718418215911030784 |