AnRAD: A Neuromorphic Anomaly Detection Framework for Massive Concurrent Data Streams

Qiuwen Chen, Ryan Luley, Qing Wu, Morgan Bishop, Richard W. Linderman, Qinru Qiu

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

The evolution of high performance computing technologies has enabled the large-scale implementation of neuromorphic models and pushed the research in computational intelligence into a new era. Among the machine learning applications, unsupervised detection of anomalous streams is especially challenging due to the requirements of detection accuracy and real-time performance. Designing a computing framework that harnesses the growing computing power of the multicore systems while maintaining high sensitivity and specificity to the anomalies is an urgent research topic. In this paper, we propose anomaly recognition and detection (AnRAD), a bioinspired detection framework that performs probabilistic inferences. We analyze the feature dependency and develop a self-structuring method that learns an efficient confabulation network using unlabeled data. This network is capable of fast incremental learning, which continuously refines the knowledge base using streaming data. Compared with several existing anomaly detection approaches, our method provides competitive detection quality. Furthermore, we exploit the massive parallel structure of the AnRAD framework. Our implementations of the detection algorithm on the graphic processing unit and the Xeon Phi coprocessor both obtain substantial speedups over the sequential implementation on general-purpose microprocessor. The framework provides real-time service to concurrent data streams within diversified knowledge contexts, and can be applied to large problems with multiple local patterns. Experimental results demonstrate high computing performance and memory efficiency. For vehicle behavior detection, the framework is able to monitor up to 16,000 vehicles (data streams) and their interactions in real time with a single commodity coprocessor, and uses less than 0.2 ms for one testing subject. Finally, the detection network is ported to our spiking neural network simulator to show the potential of adapting to the emerging neuromorphic architectures.

Original languageEnglish (US)
JournalIEEE Transactions on Neural Networks and Learning Systems
DOIs
StateAccepted/In press - Mar 17 2017

Fingerprint

Artificial intelligence
Learning systems
Microprocessor chips
Simulators
Neural networks
Data storage equipment
Testing
Coprocessor
Graphics processing unit

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence

Cite this

AnRAD : A Neuromorphic Anomaly Detection Framework for Massive Concurrent Data Streams. / Chen, Qiuwen; Luley, Ryan; Wu, Qing; Bishop, Morgan; Linderman, Richard W.; Qiu, Qinru.

In: IEEE Transactions on Neural Networks and Learning Systems, 17.03.2017.

Research output: Contribution to journalArticle

@article{3548db86f8fa422191379f56338a9e0d,
title = "AnRAD: A Neuromorphic Anomaly Detection Framework for Massive Concurrent Data Streams",
abstract = "The evolution of high performance computing technologies has enabled the large-scale implementation of neuromorphic models and pushed the research in computational intelligence into a new era. Among the machine learning applications, unsupervised detection of anomalous streams is especially challenging due to the requirements of detection accuracy and real-time performance. Designing a computing framework that harnesses the growing computing power of the multicore systems while maintaining high sensitivity and specificity to the anomalies is an urgent research topic. In this paper, we propose anomaly recognition and detection (AnRAD), a bioinspired detection framework that performs probabilistic inferences. We analyze the feature dependency and develop a self-structuring method that learns an efficient confabulation network using unlabeled data. This network is capable of fast incremental learning, which continuously refines the knowledge base using streaming data. Compared with several existing anomaly detection approaches, our method provides competitive detection quality. Furthermore, we exploit the massive parallel structure of the AnRAD framework. Our implementations of the detection algorithm on the graphic processing unit and the Xeon Phi coprocessor both obtain substantial speedups over the sequential implementation on general-purpose microprocessor. The framework provides real-time service to concurrent data streams within diversified knowledge contexts, and can be applied to large problems with multiple local patterns. Experimental results demonstrate high computing performance and memory efficiency. For vehicle behavior detection, the framework is able to monitor up to 16,000 vehicles (data streams) and their interactions in real time with a single commodity coprocessor, and uses less than 0.2 ms for one testing subject. Finally, the detection network is ported to our spiking neural network simulator to show the potential of adapting to the emerging neuromorphic architectures.",
author = "Qiuwen Chen and Ryan Luley and Qing Wu and Morgan Bishop and Linderman, {Richard W.} and Qinru Qiu",
year = "2017",
month = "3",
day = "17",
doi = "10.1109/TNNLS.2017.2676110",
language = "English (US)",
journal = "IEEE Transactions on Neural Networks and Learning Systems",
issn = "2162-237X",
publisher = "IEEE Computer Society",

}

TY - JOUR

T1 - AnRAD

T2 - A Neuromorphic Anomaly Detection Framework for Massive Concurrent Data Streams

AU - Chen, Qiuwen

AU - Luley, Ryan

AU - Wu, Qing

AU - Bishop, Morgan

AU - Linderman, Richard W.

AU - Qiu, Qinru

PY - 2017/3/17

Y1 - 2017/3/17

N2 - The evolution of high performance computing technologies has enabled the large-scale implementation of neuromorphic models and pushed the research in computational intelligence into a new era. Among the machine learning applications, unsupervised detection of anomalous streams is especially challenging due to the requirements of detection accuracy and real-time performance. Designing a computing framework that harnesses the growing computing power of the multicore systems while maintaining high sensitivity and specificity to the anomalies is an urgent research topic. In this paper, we propose anomaly recognition and detection (AnRAD), a bioinspired detection framework that performs probabilistic inferences. We analyze the feature dependency and develop a self-structuring method that learns an efficient confabulation network using unlabeled data. This network is capable of fast incremental learning, which continuously refines the knowledge base using streaming data. Compared with several existing anomaly detection approaches, our method provides competitive detection quality. Furthermore, we exploit the massive parallel structure of the AnRAD framework. Our implementations of the detection algorithm on the graphic processing unit and the Xeon Phi coprocessor both obtain substantial speedups over the sequential implementation on general-purpose microprocessor. The framework provides real-time service to concurrent data streams within diversified knowledge contexts, and can be applied to large problems with multiple local patterns. Experimental results demonstrate high computing performance and memory efficiency. For vehicle behavior detection, the framework is able to monitor up to 16,000 vehicles (data streams) and their interactions in real time with a single commodity coprocessor, and uses less than 0.2 ms for one testing subject. Finally, the detection network is ported to our spiking neural network simulator to show the potential of adapting to the emerging neuromorphic architectures.

AB - The evolution of high performance computing technologies has enabled the large-scale implementation of neuromorphic models and pushed the research in computational intelligence into a new era. Among the machine learning applications, unsupervised detection of anomalous streams is especially challenging due to the requirements of detection accuracy and real-time performance. Designing a computing framework that harnesses the growing computing power of the multicore systems while maintaining high sensitivity and specificity to the anomalies is an urgent research topic. In this paper, we propose anomaly recognition and detection (AnRAD), a bioinspired detection framework that performs probabilistic inferences. We analyze the feature dependency and develop a self-structuring method that learns an efficient confabulation network using unlabeled data. This network is capable of fast incremental learning, which continuously refines the knowledge base using streaming data. Compared with several existing anomaly detection approaches, our method provides competitive detection quality. Furthermore, we exploit the massive parallel structure of the AnRAD framework. Our implementations of the detection algorithm on the graphic processing unit and the Xeon Phi coprocessor both obtain substantial speedups over the sequential implementation on general-purpose microprocessor. The framework provides real-time service to concurrent data streams within diversified knowledge contexts, and can be applied to large problems with multiple local patterns. Experimental results demonstrate high computing performance and memory efficiency. For vehicle behavior detection, the framework is able to monitor up to 16,000 vehicles (data streams) and their interactions in real time with a single commodity coprocessor, and uses less than 0.2 ms for one testing subject. Finally, the detection network is ported to our spiking neural network simulator to show the potential of adapting to the emerging neuromorphic architectures.

UR - http://www.scopus.com/inward/record.url?scp=85015842110&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015842110&partnerID=8YFLogxK

U2 - 10.1109/TNNLS.2017.2676110

DO - 10.1109/TNNLS.2017.2676110

M3 - Article

C2 - 28328516

AN - SCOPUS:85015842110

JO - IEEE Transactions on Neural Networks and Learning Systems

JF - IEEE Transactions on Neural Networks and Learning Systems

SN - 2162-237X

ER -