0% Complete
صفحه اصلی
/
سی و سومین کنفرانس بین المللی مهندسی برق
Implementation of an Optimized Deep Learning Model to Assess Pediatric Sleep Apnea Severity Using SpO2 Signals on Resource-Limited Microcontrollers
نویسندگان :
Erfan Mortazavi
1
Hanieh Mohammadi
2
Bahram Tarvirdizadeh
3
Khalil Alipour
4
Mohammad Ghamari
5
1- دانشگاه تهران
2- دانشگاه تهران
3- دانشگاه تهران
4- دانشگاه تهران
5- California Polytechnic State University
کلمات کلیدی :
Sleep apnea-hypopnea (SAH)،Blood oxygen saturation (SpO2)،Convolutional neural network (CNN)،Long short-term memory (LSTM)،Attention،Apnea–hypopnea index (AHI)،Microcontroller
چکیده :
Accurately diagnosing pediatric sleep apnea-hypopnea (SAH) is a complex task in pediatric healthcare. Traditional methods like polysomnography (PSG) test, though effective, can be uncomfortable and impractical for children. This study explores a less invasive approach using deep learning to analyze blood oxygen saturation (SpO2) signals. A total of 844 SpO2 signals from the CHAT dataset were utilized, with the data split into 60% for training, 30% for testing, and 10% for validation to train a convolutional neural network (CNN)-long short-term memory (LSTM)-Attention model. The model achieved a kappa score of 0.62 and a four-class accuracy of 74.91% in estimating the apnea-hypopnea index (AHI) and classifying sleep apnea severity. The primary challenge was deploying the model on the resource-constrained STM32H743IIT6 microcontroller. TensorFlow toolkit optimization techniques were implemented to minimize model size and resource usage while preserving satisfactory accuracy, despite the microcontroller's sufficient 1MB data RAM. Each technique was evaluated in memory-constrained environments, leading to post-quantization deployment. The best optimized model maintained an accuracy of 73.63% and a kappa score of 0.60, demonstrating the feasibility of portable, non-invasive diagnostic tools.
لیست مقالات
لیست مقالات بایگانی شده
Market-oriented Optimal Control Strategy for an Integrated Energy Storage System and Wind Farm
Sajad Esameili - Mohammad Amini - Amir Khorsandi - Seyed Hamid Fathi - Seyed Hossein Hosseinian - Jafar Millimonfared
Iranian stock market fluctuations: from social news to forecasting models
Maryam Sharifinia - Farzaneh Ghayour Baghbani
A High Responsivity Plasmonic Internal Photoemission detector for Optical Communication
Faramarz Alihosseini - Aref Rasoulzadeh Zali - Tavakol Pakizeh - Hesam Zandi
Full Soft Switching Interleaved High Voltage Gain Converter For Renewable Energy Systems
Baharak Akhlaghi
Probabilistic Dynamic Economic Dispatch in Presence of Wind Farms
Homayoun Berahmandpour - Shahram Montasar Kuhsari - Hassan Rastegar
A Circularly Polarized Metal-Only Holographic Leaky-Wave Antenna Based on Spoof Surface Plasmon Polaritons
Reza Ashrafi Mohabadi - Sajjad Zohrevand - Mohammad Amin Chaychizadeh - Nader Komjani
طراحی کنترلکننده مد لغزشی دینامیک برای سیستم تعلیق فعال غیر خطی با عملگر غیرایدهآل
مونا عظیمی - الهه مرادی
Multi-Agents Gaussian Estimation and Coverage Control Client-Server Architecture
Mohammad َAzizian Shishavan - Mahdi Zeinali - Azam Salari
طراحی یک ماتریس باتلر 4×4 فشرده برای کاربرد در سیستم های شکل دهنده پرتو در شبکه های WLAN
آزاده ایمانی - محمد سجاد بیاتی
Temporary Goal Method: A Solution for the Problem of Getting Stuck in Motion Planning Algorithms
Danial Khan mohamad zade - Samaneh Hosseini Semnani
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.0.4