LabelMerger: Learning activities in uncontrolled environments

Seyed Iman Mirzadeh, Jessica Ardo, Ramin Fallahzadeh, Bryan Minor, Lorraine Evangelista, Diane Cook, Hassan Ghasemzadeh

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

Abstract

While inferring human activities from sensors embedded in mobile devices using machine learning algorithms has been studied, current research relies primarily on sensor data that are collected in controlled settings often with healthy individuals. Currently, there exists a gap in research about how to design activity recognition models based on sensor data collected with chronically-ill individuals and in free-living environments. In this paper, we focus on a situation where free-living activity data are collected continuously, activity vocabulary (i.e., class labels) are not known as a priori, and sensor data are annotated by end-users through an active learning process. By analyzing sensor data collected in a clinical study involving patients with cardiovascular disease, we demonstrate significant challenges that arise while inferring physical activities in uncontrolled environments. In particular, we observe that activity labels that are distinct in syntax can refer to semantically-identical behaviors, resulting in a sparse label space. To construct a meaningful label space, we propose LabelMerger, a framework for restructuring the label space created through active learning in uncontrolled environments in preparation for training activity recognition models. LabelMerger combines the semantic meaning of activity labels with physical attributes of the activities (i.e., domain knowledge) to generate a flexible and meaningful representation of the labels. Specifically, our approach merges labels using both word embedding techniques from the natural language processing domain and activity intensity from the physical activity research. We show that the new representation of the sensor data obtained by LabelMerger results in more accurate activity recognition models compared to the case where original label space is used to learn recognition models.

Original languageEnglish (US)
Title of host publicationProceedings - 2019 1st International Conference on Transdisciplinary AI, TransAI 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages64-67
Number of pages4
ISBN (Electronic)9781728141275
DOIs
StatePublished - Sep 2019
Event1st International Conference on Transdisciplinary AI, TransAI 2019 - Laguna Hills, United States
Duration: Sep 25 2019Sep 27 2019

Publication series

NameProceedings - 2019 1st International Conference on Transdisciplinary AI, TransAI 2019

Conference

Conference1st International Conference on Transdisciplinary AI, TransAI 2019
CountryUnited States
CityLaguna Hills
Period9/25/199/27/19

Keywords

  • Activity recognition
  • Machine learning
  • Mobile health
  • Word embedding

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications
  • Communication
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'LabelMerger: Learning activities in uncontrolled environments'. Together they form a unique fingerprint.

  • Cite this

    Mirzadeh, S. I., Ardo, J., Fallahzadeh, R., Minor, B., Evangelista, L., Cook, D., & Ghasemzadeh, H. (2019). LabelMerger: Learning activities in uncontrolled environments. In Proceedings - 2019 1st International Conference on Transdisciplinary AI, TransAI 2019 (pp. 64-67). [8940408] (Proceedings - 2019 1st International Conference on Transdisciplinary AI, TransAI 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/TransAI46475.2019.00019