<p dir="ltr">Decision-making is inherently a human activity that can have significant impacts on system performance in engineering design scenarios while working in an interdisciplinary team. Most design activities are commonly interdependent and consist of the contribution of multiple design agents who are required to collaborate to satisfy the system constraints and improve overall performance. It is perhaps not surprising that researchers have attempted to understand and analyze interdisciplinary design communications to identify the factors that influence the decisions of the design agents. A better understanding of these factors will help researchers in developing socio-technical systems that extend human capabilities in collaborative design activity. The knowledge of mechanisms underlying team communications can help us to predict the changes in a system's overall performance. Our proposed research work aims at analyzing the communication patterns using natural language processing. We are using a computational model to process the exchange of communication during a design process. We have performed intent analysis and dialogue-flow modeling to draw insights on backup behavior of team members, task initiation, team social regulation, etc on top of our baseline model. To understand the change in performance at different instances, we analyzed the entropy change in the design parameters included in the talk and have trained a machine on custom embeddings to learn the meaning of words used in a design setting. Our ultimate goal is to design a graph-based approach to characterize the dynamic and interactive structure of socio-technical communication as a conversation network to derive insights that would lead to better decision-making in a design team.</p>

Ml-Based Modeling of Communication and Decision Making in Design Teams

Paper Proceedings: https://asmedigitalcollection.asme.org/IDETC-CIE/IDETC-CIE2021/volume/85369

ASME 2021 International Design Engineering Technical Conferences & Computers and Information in Engineering Conference (IDETC/CIE2021)

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.