Feature-Sharing in Cascade Detection Systems With Multiple Applications

Long N. Le, Douglas L Jones

Research output: Contribution to journalArticle

Abstract

Traditional distributed detection systems are often designed for a single target application. However, with the emergence of the Internet of Things paradigm, next-generation systems are expected to be a shared infrastructure for multiple applications. To this end, we propose a modular, cascade design for resource-efficient, multitask detection systems. Two (classes of) applications are considered in the system, a primary and a secondary one. The primary application has universal features that can be shared with other applications, to reduce the overall feature extraction cost, while the secondary application does not. In this setting, the two applications can collaborate via feature sharing. We provide a method to optimize the operation of the multi-application cascade system based on an accurate resource consumption model. In addition, the inherent uncertainties in feature models are articulated and taken into account. For evaluation, the twin-comparison argument is invoked, and it is shown that, with the optimal feature sharing strategy, a system can achieve 9 × resource saving and 1.43 × improvement in detection performance.

Original languageEnglish (US)
Article number7874174
Pages (from-to)466-478
Number of pages13
JournalIEEE Journal on Selected Topics in Signal Processing
Volume11
Issue number3
DOIs
StatePublished - Apr 2017

Fingerprint

Feature extraction
Costs
Uncertainty
Internet of things

Keywords

  • Cascade detection system
  • Internet of Things (IoT)
  • feature sharing
  • multiple applications
  • resource-aware optimization

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Feature-Sharing in Cascade Detection Systems With Multiple Applications. / Le, Long N.; Jones, Douglas L.

In: IEEE Journal on Selected Topics in Signal Processing, Vol. 11, No. 3, 7874174, 04.2017, p. 466-478.

Research output: Contribution to journalArticle

@article{39b553d5f01e4612aa4fe1e78799855a,
title = "Feature-Sharing in Cascade Detection Systems With Multiple Applications",
abstract = "Traditional distributed detection systems are often designed for a single target application. However, with the emergence of the Internet of Things paradigm, next-generation systems are expected to be a shared infrastructure for multiple applications. To this end, we propose a modular, cascade design for resource-efficient, multitask detection systems. Two (classes of) applications are considered in the system, a primary and a secondary one. The primary application has universal features that can be shared with other applications, to reduce the overall feature extraction cost, while the secondary application does not. In this setting, the two applications can collaborate via feature sharing. We provide a method to optimize the operation of the multi-application cascade system based on an accurate resource consumption model. In addition, the inherent uncertainties in feature models are articulated and taken into account. For evaluation, the twin-comparison argument is invoked, and it is shown that, with the optimal feature sharing strategy, a system can achieve 9 × resource saving and 1.43 × improvement in detection performance.",
keywords = "Cascade detection system, Internet of Things (IoT), feature sharing, multiple applications, resource-aware optimization",
author = "Le, {Long N.} and Jones, {Douglas L}",
year = "2017",
month = "4",
doi = "10.1109/JSTSP.2017.2679539",
language = "English (US)",
volume = "11",
pages = "466--478",
journal = "IEEE Journal on Selected Topics in Signal Processing",
issn = "1932-4553",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

TY - JOUR

T1 - Feature-Sharing in Cascade Detection Systems With Multiple Applications

AU - Le, Long N.

AU - Jones, Douglas L

PY - 2017/4

Y1 - 2017/4

N2 - Traditional distributed detection systems are often designed for a single target application. However, with the emergence of the Internet of Things paradigm, next-generation systems are expected to be a shared infrastructure for multiple applications. To this end, we propose a modular, cascade design for resource-efficient, multitask detection systems. Two (classes of) applications are considered in the system, a primary and a secondary one. The primary application has universal features that can be shared with other applications, to reduce the overall feature extraction cost, while the secondary application does not. In this setting, the two applications can collaborate via feature sharing. We provide a method to optimize the operation of the multi-application cascade system based on an accurate resource consumption model. In addition, the inherent uncertainties in feature models are articulated and taken into account. For evaluation, the twin-comparison argument is invoked, and it is shown that, with the optimal feature sharing strategy, a system can achieve 9 × resource saving and 1.43 × improvement in detection performance.

AB - Traditional distributed detection systems are often designed for a single target application. However, with the emergence of the Internet of Things paradigm, next-generation systems are expected to be a shared infrastructure for multiple applications. To this end, we propose a modular, cascade design for resource-efficient, multitask detection systems. Two (classes of) applications are considered in the system, a primary and a secondary one. The primary application has universal features that can be shared with other applications, to reduce the overall feature extraction cost, while the secondary application does not. In this setting, the two applications can collaborate via feature sharing. We provide a method to optimize the operation of the multi-application cascade system based on an accurate resource consumption model. In addition, the inherent uncertainties in feature models are articulated and taken into account. For evaluation, the twin-comparison argument is invoked, and it is shown that, with the optimal feature sharing strategy, a system can achieve 9 × resource saving and 1.43 × improvement in detection performance.

KW - Cascade detection system

KW - Internet of Things (IoT)

KW - feature sharing

KW - multiple applications

KW - resource-aware optimization

UR - http://www.scopus.com/inward/record.url?scp=85018528986&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018528986&partnerID=8YFLogxK

U2 - 10.1109/JSTSP.2017.2679539

DO - 10.1109/JSTSP.2017.2679539

M3 - Article

AN - SCOPUS:85018528986

VL - 11

SP - 466

EP - 478

JO - IEEE Journal on Selected Topics in Signal Processing

JF - IEEE Journal on Selected Topics in Signal Processing

SN - 1932-4553

IS - 3

M1 - 7874174

ER -