On exploiting structured human interactions to enhance sensing accuracy in cyber-physical systems

Hongwei Wang, Yunlong Gao, Shaohan Hu, Shiguang Wang, Renato Mancuso, Minje Kim, Poliang Wu, Lu Su, Lui Sha, Tarek Abdelzaher

Research output: Contribution to journalArticle

Abstract

In this article, we describe a general methodology for enhancing sensing accuracy in cyber-physical systems that involve structured human interactions in noisy physical environment. We define structured human interactions as domain-specific workflow. A novel workflow-aware sensing model is proposed to jointly correct unreliable sensor data and keep track of states in a workflow. We also propose a new inference algorithm to handle cases with partially known states and objects as supervision. Our model is evaluated with extensive simulations. As a concrete application, we develop a novel log service called Emergency Transcriber, which can automatically document operational procedures followed by teams of first responders in emergency response scenarios. Evaluation shows that our system has significant improvement over commercial off-theshelf (COTS) sensors and keeps track of workflow states with high accuracy in noisy physical environment.

Original languageEnglish (US)
Article number16
JournalACM Transactions on Cyber-Physical Systems
Volume1
Issue number3
DOIs
StatePublished - Jan 1 2017

Fingerprint

Work Flow
Sensing
Sensors
Interaction
Concretes
Emergency Response
Sensor
Emergency
High Accuracy
Scenarios
Human
Cyber Physical System
Methodology
Evaluation
Model
Simulation

Keywords

  • Medical
  • Sensing
  • Workflow

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Hardware and Architecture
  • Human-Computer Interaction
  • Control and Optimization

Cite this

On exploiting structured human interactions to enhance sensing accuracy in cyber-physical systems. / Wang, Hongwei; Gao, Yunlong; Hu, Shaohan; Wang, Shiguang; Mancuso, Renato; Kim, Minje; Wu, Poliang; Su, Lu; Sha, Lui; Abdelzaher, Tarek.

In: ACM Transactions on Cyber-Physical Systems, Vol. 1, No. 3, 16, 01.01.2017.

Research output: Contribution to journalArticle

Wang, Hongwei ; Gao, Yunlong ; Hu, Shaohan ; Wang, Shiguang ; Mancuso, Renato ; Kim, Minje ; Wu, Poliang ; Su, Lu ; Sha, Lui ; Abdelzaher, Tarek. / On exploiting structured human interactions to enhance sensing accuracy in cyber-physical systems. In: ACM Transactions on Cyber-Physical Systems. 2017 ; Vol. 1, No. 3.
@article{319f64ed3b89477489f5dd41f980380d,
title = "On exploiting structured human interactions to enhance sensing accuracy in cyber-physical systems",
abstract = "In this article, we describe a general methodology for enhancing sensing accuracy in cyber-physical systems that involve structured human interactions in noisy physical environment. We define structured human interactions as domain-specific workflow. A novel workflow-aware sensing model is proposed to jointly correct unreliable sensor data and keep track of states in a workflow. We also propose a new inference algorithm to handle cases with partially known states and objects as supervision. Our model is evaluated with extensive simulations. As a concrete application, we develop a novel log service called Emergency Transcriber, which can automatically document operational procedures followed by teams of first responders in emergency response scenarios. Evaluation shows that our system has significant improvement over commercial off-theshelf (COTS) sensors and keeps track of workflow states with high accuracy in noisy physical environment.",
keywords = "Medical, Sensing, Workflow",
author = "Hongwei Wang and Yunlong Gao and Shaohan Hu and Shiguang Wang and Renato Mancuso and Minje Kim and Poliang Wu and Lu Su and Lui Sha and Tarek Abdelzaher",
year = "2017",
month = "1",
day = "1",
doi = "10.1145/3064006",
language = "English (US)",
volume = "1",
journal = "ACM Transactions on Cyber-Physical Systems",
issn = "2378-962X",
number = "3",

}

TY - JOUR

T1 - On exploiting structured human interactions to enhance sensing accuracy in cyber-physical systems

AU - Wang, Hongwei

AU - Gao, Yunlong

AU - Hu, Shaohan

AU - Wang, Shiguang

AU - Mancuso, Renato

AU - Kim, Minje

AU - Wu, Poliang

AU - Su, Lu

AU - Sha, Lui

AU - Abdelzaher, Tarek

PY - 2017/1/1

Y1 - 2017/1/1

N2 - In this article, we describe a general methodology for enhancing sensing accuracy in cyber-physical systems that involve structured human interactions in noisy physical environment. We define structured human interactions as domain-specific workflow. A novel workflow-aware sensing model is proposed to jointly correct unreliable sensor data and keep track of states in a workflow. We also propose a new inference algorithm to handle cases with partially known states and objects as supervision. Our model is evaluated with extensive simulations. As a concrete application, we develop a novel log service called Emergency Transcriber, which can automatically document operational procedures followed by teams of first responders in emergency response scenarios. Evaluation shows that our system has significant improvement over commercial off-theshelf (COTS) sensors and keeps track of workflow states with high accuracy in noisy physical environment.

AB - In this article, we describe a general methodology for enhancing sensing accuracy in cyber-physical systems that involve structured human interactions in noisy physical environment. We define structured human interactions as domain-specific workflow. A novel workflow-aware sensing model is proposed to jointly correct unreliable sensor data and keep track of states in a workflow. We also propose a new inference algorithm to handle cases with partially known states and objects as supervision. Our model is evaluated with extensive simulations. As a concrete application, we develop a novel log service called Emergency Transcriber, which can automatically document operational procedures followed by teams of first responders in emergency response scenarios. Evaluation shows that our system has significant improvement over commercial off-theshelf (COTS) sensors and keeps track of workflow states with high accuracy in noisy physical environment.

KW - Medical

KW - Sensing

KW - Workflow

UR - http://www.scopus.com/inward/record.url?scp=85075488361&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85075488361&partnerID=8YFLogxK

U2 - 10.1145/3064006

DO - 10.1145/3064006

M3 - Article

AN - SCOPUS:85075488361

VL - 1

JO - ACM Transactions on Cyber-Physical Systems

JF - ACM Transactions on Cyber-Physical Systems

SN - 2378-962X

IS - 3

M1 - 16

ER -