Cohesion and Organization Through Networked Computation in Overly Risky and Distinctly Isolated Areas

Abstract

Cohesion and Organization through Networked Computation in Overly Risky and Distinctly Isolated Areas (CONCORDIA) was an attempt to develop a set of algorithms for assessing team cohesion via wearable devices collecting physiological data from team members while they performed tasks designed specifically to assess team cohesion - COHESION and CubeCrusher. The algorithms utilized a variety of machine learning techniques to identify when a team members behavior started to deviate from that of the rest of their team, as well as to predict performance metrics. The results, while not conclusive, indicate that there is a significant probability that algorithms with a high level of accuracy and robustness can be developed. We also developed, in concurrence with the machine learning algorithms, a prototype interface for displaying team cohesion in real time according to physiological data. We provide suggestions for future research directions that could make such a system effective.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 01, 2024
Accession Number
AD1221027

Entities

People

  • Jeremy Gottlieb
  • Joan Zheng
  • Nathanael L. Keiser
  • Noam Benkler
  • Pete Roma

Organizations

  • Smart Information Flow Technologies

Tags

Fields of Study

  • Computer science

Readers

  • Distributed Systems and Data Platform Development
  • Organizational Psychology.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks