Measurement and Classification of Acoustic and Light events in Intensive Care Units for Enhanced Patient Recovery
Author(s)
De Filippi, Joshua
Advisor(s)
Editor(s)
Collections
Supplementary to:
Permanent Link
Abstract
This thesis presents a HIPAA-compliant system for monitoring and classifying acoustic and light events in Intensive Care Units (ICUs) to improve patient recovery. Using edge-device processing on a Raspberry Pi, the system detects alarms, speech, and light fluctuations without storing sensitive data. Key features include a modulation spectrum-based alarm detector, a CNN for voice activity detection, and precise light intensity tracking. The system offers actionable insights to optimize ICU conditions, promoting better patient outcomes and recovery.
Sponsor
Date
2024-12-06
Extent
Resource Type
Text
Resource Subtype
Thesis