Is That You Again? Adaptive Learning Techniques for User Identification in Smart Pill Bottle Systems

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Cyber-Physical Systems (CPS) continues to add more intelligence to various applications, including healthcare. A recent wave of research included the development of pill logging systems that monitor when a pill is extracted. Automatic pill logging systems are an important technology for medication adherence, medication error prevention, and tracing. However, most existing systems do not consider how multi-bottle settings or long-term bottle use can affect their ability to log accurately, forcing frequent re-training/recalibration. In this paper, we present adaptive learning techniques for subject identification across a pair of smart pill bottle systems. We collect inertial signals from subjects taking medication pills and encode the activity signals by transforming them into 2D texture images. Then we use pre-trained Convolutional Neural Network (CNN) models for image-based classification tasks. We evaluate our approach with experiments executed by 10 subjects and achieved improved differentiation capacity over existing models by using deep learning models, modified through domain adaptation and transfer learning.

Original languageEnglish (US)
Title of host publicationCPHS 2021 - Proceedings of the 2021 1st ACM International Workshop on Cyber-Physical-Human System Design and Implementation
PublisherAssociation for Computing Machinery, Inc
Pages27-32
Number of pages6
ISBN (Electronic)9781450384407
DOIs
StatePublished - May 18 2021
Event1st ACM International Workshop on Cyber-Physical-Human System Design and Implementation, CPHS 2021 - Nashville, United States
Duration: May 18 2021 → …

Publication series

NameCPHS 2021 - Proceedings of the 2021 1st ACM International Workshop on Cyber-Physical-Human System Design and Implementation

Conference

Conference1st ACM International Workshop on Cyber-Physical-Human System Design and Implementation, CPHS 2021
Country/TerritoryUnited States
CityNashville
Period5/18/21 → …

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Human-Computer Interaction
  • Computer Networks and Communications

Keywords

  • Deep learning
  • Domain adaptation
  • Inertial sensors
  • Smart pill bottles
  • Transfer learning

Fingerprint

Dive into the research topics of 'Is That You Again? Adaptive Learning Techniques for User Identification in Smart Pill Bottle Systems'. Together they form a unique fingerprint.

Cite this