ÁÖ¸Þ´º ¹Ù·Î°¡±â ÄÁÅÙÃ÷ ¹Ù·Î°¡±â
½½¶óÀ̵å À̹ÌÁö
The 34th HSN 2024 HSN »õ·Î¿î½ÃÀÛ:
Hyper_converged Services and iNfrastructures
½½¶óÀ̵å À̹ÌÁö
The 34th HSN 2024 HSN »õ·Î¿î½ÃÀÛ:
Hyper_converged Services and iNfrastructures
¼¼ºÎÇÁ·Î±×·¥
:
Session#A4 : Next-Generation Mobile/Wearable ÁÂÀå : ±è¼º¹Î ±³¼ö/KAIST
¹ßÇ¥Á¦¸ñ : On-device Machine Learning for Digital Healthcare: The Case of Sleep Medicine
¹ßÇ¥ÀÚ : ±èÇü½Å À̸ÞÀÏ :
¼Ò¼Ó : ¼­¿ï´ë ºÎ¼­ : µ¥ÀÌÅÍ»çÀ̾ð½ºÇаú
Á÷À§ : Á¶±³¼ö ¹ßÇ¥ÀϽà : 1/26(±Ý) ¼¼¼Ç#A4 08:50~10:20
¹ßÇ¥ÀÚ¾à·Â :
2020 – ÇöÀç ¼­¿ï´ëÇб³ µ¥ÀÌÅÍ»çÀ̾𽺴ëÇпø Á¶±³¼ö
2019 – 2020 Google ¼ÒÇÁÆ®¿þ¾î ¿£Áö´Ï¾î
2016 – 2019 UC ¹öŬ¸® Àü±âÄÄÇ»ÅÍ°øÇкΠ¹Ú»çÈÄ ¿¬±¸¿ø
2016 ¼­¿ï´ëÇб³ Àü±âÄÄÇ»ÅÍ°øÇкΠ¹Ú»ç
°­¿¬¿ä¾à :
Obstructive sleep apnea (OSA) is a prevalent sleep disorder affecting approximately one billion people world-wide. The current gold standard for diagnosing OSA, Polysomnography (PSG), involves an overnight hospital stay with multiple attached sensors, leading to potential inaccuracies due to the first-night effect. To address this, we present SlAction, a non-intrusive OSA detection system for daily sleep environments using infrared videos. Recognizing that sleep videos exhibit minimal motion, this work investigates the fundamental question: "Are respiratory events adequately reflected in human motions during sleep?" Analyzing the largest sleep video dataset of 5,098 hours, we establish correlations between OSA events and human motions during sleep. Our approach uses a low frame rate (2.5 FPS), a large size (60 seconds) and step (30 seconds) for sliding window analysis to capture slow and long-term motions related to OSA. Furthermore, we utilize a lightweight deep neural network for resource-constrained devices, ensuring all video streams are processed locally without compromising privacy. Evaluations show that SlAction achieves an average F1 score of 87.6% in detecting OSA across various environments. Implementing SlAction on NVIDIA Jetson Nano enables real-time inference (~3 seconds for a 60-second video clip), highlighting its potential for early detection and personalized treatment of OSA.
¸ñ·Ïº¸±â
ÈÄ¿ø±â°ü ±¤°í¿µ»ó
more