Skip to main navigation Skip to search Skip to main content

Determine Bipolar Disorder Level from Patient Interviews Using Bi-LSTM and Feature Fusion

  • Jordan University of Science and Technology

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

10 Scopus citations

Abstract

Patients with Bipolar Disorder (BD) suffer from a brain disorder that cause them to change mood without reasons and prevent them from performing ordinary daily tasks. In this work, we classify patients with BD into one of its three levels: remission, hypo-mania, and mania, based solely on audio-visual recordings of structured interviews with these patients by the use of different deep learning techniques coupled with feature fusion and concatenation techniques along with a simple sliding window procedure. The results of our approach are promising and open up the door for many contributions and improvements in the future.

Original languageEnglish
Title of host publication2018 5th International Conference on Social Networks Analysis, Management and Security, SNAMS 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages182-189
Number of pages8
ISBN (Electronic)9781538695883
DOIs
StatePublished - 30 Nov 2018
Externally publishedYes
Event5th International Conference on Social Networks Analysis, Management and Security, SNAMS 2018 - Valencia, Spain
Duration: 15 Oct 201818 Oct 2018

Publication series

Name2018 5th International Conference on Social Networks Analysis, Management and Security, SNAMS 2018

Conference

Conference5th International Conference on Social Networks Analysis, Management and Security, SNAMS 2018
Country/TerritorySpain
CityValencia
Period15/10/1818/10/18

Keywords

  • Bidirectional Long Short-Term Memory
  • Bipolar Disorder
  • Deep Learning
  • Feature Fusion

Fingerprint

Dive into the research topics of 'Determine Bipolar Disorder Level from Patient Interviews Using Bi-LSTM and Feature Fusion'. Together they form a unique fingerprint.

Cite this