LifeLine: A device for detecting abnormal patterns

J. Jenny Li, Peter Krivoshik, Andrey Suvorov, Claudia Fortes, Phillip Kenny

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper presents a reliable LifeLine, app or device, that uses multiple native hardware sensors in conjunction with motion detection methods and AI/machine learning algorithms to automatically detect life-threatening conditions. The app or device then autonomously responds to said conditions and sends alarm signals through various communication channels within milliseconds, without the need for user intervention. The app version is currently on Google Play. The testing of such an autonomous AI app or device imposes some new challenges due to the nondeterminism in AI agent’s reaction to various scenarios and the continuous learning of the AI agent with new knowledge.

Original languageEnglish
Title of host publicationProceedings of 2018 International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2018
PublisherAssociation for Computing Machinery
Pages76-81
Number of pages6
ISBN (Electronic)9781450364829
DOIs
StatePublished - 15 Aug 2018
Event2018 International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2018 - Union, United States
Duration: 15 Aug 201817 Aug 2018

Publication series

NameACM International Conference Proceeding Series

Conference

Conference2018 International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2018
Country/TerritoryUnited States
CityUnion
Period15/08/1817/08/18

Keywords

  • Classifier
  • Mobile app
  • Sensors.
  • Voice recognition

Fingerprint

Dive into the research topics of 'LifeLine: A device for detecting abnormal patterns'. Together they form a unique fingerprint.

Cite this