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
طراحی و ساخت چرخاننده سهدرگاهی صفحه E در موجبر باند X
زهرا عابدان - محمد حسین حسینی
Scalable Multipurpose Smart Indoor Lighting System for Wireless Sensor Networks
Atefesadat Seyedolhosseini - Reza Nemati - Hossein Maghsoumi - Shokrollah Karimian - Nasser Masoumi
Model Predictive Control for Optimal Drug Administration of Cancer Chemotherapy
Zahra Hosseinpour - Amirhossein Nikoofard - Erfan Nejabat
A 1.2GHz wide bandwidth integer-N type-I PLL
Javad Tavakoli - Hossein Yaghobi - Samad Sheikhaei
An Optimal Investigation into A Preventive Maintenance Scheduling Scheme for Electric Power Transmission Networks
Seyed Sina Taheri Otaghsara - Masoud Asghari Gharakheili
Computational Insights into the Superior Performance of ψ-Graphene in Li-S Batteries: A DFT Study
Donna Rashidi - Maryam Abbasi - Leila Sadeghbeigy - Matin Bakhtavari - Ebrahim Nadimi
Machine Learning-based Fundamental Stock Prediction Using Companies’ Financial Reports
Hossein Rezaei - Kamran Abdi - Mohsen Hooshmand
Optimal D2D Resource Allocation in Heterogeneous Cellular Networks by Decentralized Multi-Agent Deep Q-Learning
Pouya Akhoundzadeh - Ghasem Mirjalily - Mohammad taghi Sadeghi
True Random Number Generator Relying on Multiple Entropy Source and Triple Oscillator for Cryptography Purposes
Somayeh Gholam Mehraban - Mohsen Jalali - Mostafa Azadbakht
Small Target Detection Using an Enhanced Optimization Based Filter and Trajectory Tracking Via Pattern Matching Algorithm
Seyedeh Mahsa Zakipour Bahambari - Saeed Khankalantary
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 40.4.2