Decision making for disaster response

data visualization

Glowing globe representing information and data

Overview

Roles: Interviewing, Works-like Prototype
Skills: User Interviews, Natural Language Processing, Speech Recognition, Data Visualization, Python, Google Cloud API
Time: January - May 2021
Team: 5 (MechE, CogSci, DataSci, Business)

Developed as part of ME292C, Innovation in Disaster Response, Recovery, and Resilience. I conducted several stakeholder interviews and led the development of the prototype for NLP-based tagging and spatial mapping.

The Problem

For this project, we focused on information sharing for decision-makers in disaster response scenarios, working with NIWC Pacific. See intro video here.

The Process

Description of interviews, pain points, and market research. Introducing final prototype

The Result

See audio-only prototype.

NLP Prototype with Audio and Text

See text-only prototype.

Future Steps

The integrated example of audio and text tagging and mapping is shown below:

Reflection

It was interesting to work with NIWC on this project because they had a lot of domain expertise on the technical side, while we took a more user-centric approach to this complex problem. I think we were able to blend together both sides into our final prototypes, although it is likely that some of the problems such as latency and low-bandwidth in communication have to be solved by those with more technical expertise.