PUCK

An automated prompting system for smart environments: Toward achieving automated prompting-challenges involved

Barnan Das, Diane J. Cook, Maureen Schmitter-Edgecombe, Adriana Seelye

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

The growth in popularity of smart environments has been quite steep in the last decade and so has the demand for smart health assistance systems. A smart homebased prompting system can enhance these technologies to deliver in-home interventions to users for timely reminders or brief instructions describing the way a task should be carried out for successful completion. This technology is in high demand given the desire of people who have physical or cognitive limitations to live independently in their homes. In this paper, with the introduction of the "PUCK" prompting system, we take an approach to automate prompting-based interventions without any predefined rule sets or user feedback. Unlike other approaches, we use simple off-the-shelf sensors and learn the timing for prompts based on real data that are collected with volunteer participants in our smart home test bed. The data mining approaches taken to solve this problem come with the challenge of an imbalanced class distribution that occurs nturally in the data. We propose a variant of an existing sampling technique, SMOTE, to deal with the class imbalance problem. To validate the approach, a comparative analysis with cost-sensitive learning is performed.

Original languageEnglish (US)
Pages (from-to)859-873
Number of pages15
JournalPersonal and Ubiquitous Computing
Volume16
Issue number7
DOIs
StatePublished - Oct 2012
Externally publishedYes

Fingerprint

Data mining
Health
Sampling
Feedback
Sensors
Costs
Comparative analysis
Volunteers
Sensor
Imbalance

Keywords

  • Automated prompting
  • Imbalanced class distribution
  • Machine learning
  • Prompting systems
  • Smart environments

ASJC Scopus subject areas

  • Hardware and Architecture
  • Computer Science Applications
  • Management Science and Operations Research

Cite this

PUCK : An automated prompting system for smart environments: Toward achieving automated prompting-challenges involved. / Das, Barnan; Cook, Diane J.; Schmitter-Edgecombe, Maureen; Seelye, Adriana.

In: Personal and Ubiquitous Computing, Vol. 16, No. 7, 10.2012, p. 859-873.

Research output: Contribution to journalArticle

Das, Barnan ; Cook, Diane J. ; Schmitter-Edgecombe, Maureen ; Seelye, Adriana. / PUCK : An automated prompting system for smart environments: Toward achieving automated prompting-challenges involved. In: Personal and Ubiquitous Computing. 2012 ; Vol. 16, No. 7. pp. 859-873.
@article{319146ba1e534813a6c84e4e8822b5b3,
title = "PUCK: An automated prompting system for smart environments: Toward achieving automated prompting-challenges involved",
abstract = "The growth in popularity of smart environments has been quite steep in the last decade and so has the demand for smart health assistance systems. A smart homebased prompting system can enhance these technologies to deliver in-home interventions to users for timely reminders or brief instructions describing the way a task should be carried out for successful completion. This technology is in high demand given the desire of people who have physical or cognitive limitations to live independently in their homes. In this paper, with the introduction of the {"}PUCK{"} prompting system, we take an approach to automate prompting-based interventions without any predefined rule sets or user feedback. Unlike other approaches, we use simple off-the-shelf sensors and learn the timing for prompts based on real data that are collected with volunteer participants in our smart home test bed. The data mining approaches taken to solve this problem come with the challenge of an imbalanced class distribution that occurs nturally in the data. We propose a variant of an existing sampling technique, SMOTE, to deal with the class imbalance problem. To validate the approach, a comparative analysis with cost-sensitive learning is performed.",
keywords = "Automated prompting, Imbalanced class distribution, Machine learning, Prompting systems, Smart environments",
author = "Barnan Das and Cook, {Diane J.} and Maureen Schmitter-Edgecombe and Adriana Seelye",
year = "2012",
month = "10",
doi = "10.1007/s00779-011-0445-6",
language = "English (US)",
volume = "16",
pages = "859--873",
journal = "Personal and Ubiquitous Computing",
issn = "1617-4909",
publisher = "Springer London",
number = "7",

}

TY - JOUR

T1 - PUCK

T2 - An automated prompting system for smart environments: Toward achieving automated prompting-challenges involved

AU - Das, Barnan

AU - Cook, Diane J.

AU - Schmitter-Edgecombe, Maureen

AU - Seelye, Adriana

PY - 2012/10

Y1 - 2012/10

N2 - The growth in popularity of smart environments has been quite steep in the last decade and so has the demand for smart health assistance systems. A smart homebased prompting system can enhance these technologies to deliver in-home interventions to users for timely reminders or brief instructions describing the way a task should be carried out for successful completion. This technology is in high demand given the desire of people who have physical or cognitive limitations to live independently in their homes. In this paper, with the introduction of the "PUCK" prompting system, we take an approach to automate prompting-based interventions without any predefined rule sets or user feedback. Unlike other approaches, we use simple off-the-shelf sensors and learn the timing for prompts based on real data that are collected with volunteer participants in our smart home test bed. The data mining approaches taken to solve this problem come with the challenge of an imbalanced class distribution that occurs nturally in the data. We propose a variant of an existing sampling technique, SMOTE, to deal with the class imbalance problem. To validate the approach, a comparative analysis with cost-sensitive learning is performed.

AB - The growth in popularity of smart environments has been quite steep in the last decade and so has the demand for smart health assistance systems. A smart homebased prompting system can enhance these technologies to deliver in-home interventions to users for timely reminders or brief instructions describing the way a task should be carried out for successful completion. This technology is in high demand given the desire of people who have physical or cognitive limitations to live independently in their homes. In this paper, with the introduction of the "PUCK" prompting system, we take an approach to automate prompting-based interventions without any predefined rule sets or user feedback. Unlike other approaches, we use simple off-the-shelf sensors and learn the timing for prompts based on real data that are collected with volunteer participants in our smart home test bed. The data mining approaches taken to solve this problem come with the challenge of an imbalanced class distribution that occurs nturally in the data. We propose a variant of an existing sampling technique, SMOTE, to deal with the class imbalance problem. To validate the approach, a comparative analysis with cost-sensitive learning is performed.

KW - Automated prompting

KW - Imbalanced class distribution

KW - Machine learning

KW - Prompting systems

KW - Smart environments

UR - http://www.scopus.com/inward/record.url?scp=84869147051&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84869147051&partnerID=8YFLogxK

U2 - 10.1007/s00779-011-0445-6

DO - 10.1007/s00779-011-0445-6

M3 - Article

VL - 16

SP - 859

EP - 873

JO - Personal and Ubiquitous Computing

JF - Personal and Ubiquitous Computing

SN - 1617-4909

IS - 7

ER -