کنفرانس مهندسی برق ایران

صفحه اصلی / سی و سومین کنفرانس بین المللی مهندسی برق

Contrastive Learning Framework for fMRI Time-Series Classification in Left and Right Epilepsy Using Continues Wavelet Transform

نویسندگان :

Marzieh Soheili-nejad¹ Saeed Masoudnia² Hamid Soltanian-zadeh³

1- دانشگاه تهران 2- دانشگاه تهران 3- دانشگاه تهران

کلمات کلیدی :

rest-fMRI،Self-supervised learning،contrastive learning،CutMix،Continuous Wavelet Transform،SMOTE

چکیده :

Advancements in deep learning have shown substantial promise for medical image analysis, offering potential improvements in healthcare and patient outcomes. However, deep learning models often require large labeled datasets, which are challenging and costly to curate, particularly in the case of fMRI data. Resting-state fMRI (rest-fMRI) presents a unique classification challenge due to its high-dimensional, low sample size nature, making it difficult for traditional deep neural network to achieve reliable accuracy. Self Supervised Learning (SSL), particularly contrastive learning, has emerged as a viable solution to address these limitations. It enables the models to learn meaningful representations unlabeled rest-fMRI data. This study leverages the Continuous Wavelet Transform (CWT) for feature extraction, followed by contrastive learning with CutMix augmentation to capture rich representations from the rest-fMRI time-series data. To address the inherent class imbalance, we apply Synthetic Minority Over-sampling Technique (SMOTE) for data augmentation before final classification. By integrating robust feature extraction, contrastive learning, and targeted data augmentation, our method effectively addresses the challenges posed by high-dimensional data and limited sample sizes. Experimental results demonstrate that our proposed approach achieves high classification accuracy for distinguishing between left versus right epilepsy cases, even with limited and noisy data, while effectively minimizing overfitting.

لیست مقالات

لیست مقالات بایگانی شده

تجزیه وابستگی با استفاده از Q-Learning محافظه کار

امیر زارعی - علیرضا خیاطیان - پیمان ستوده

Design and fabrication of a microstrip phase shifter based on liquid crystal

Sadegh Rajabi Doulataabadi - Seyed Hossein Hosseini Biuki - Farid Khoshkhati - Seyed Abbas Jazayeri Moghadas - Mohammad Masoudi Mohammadi - Mehdi Ahmadi-Boroujeni

TID-based PSS2B to Overcome LFO Issue in Multi-machine Power Systems

Javad Morsali

طراحی یک اینورتر سه فاز چند سطحی ترکیبی جدید و بررسی کاربرد آن در کنترل موتور القایی

حسین جعفری - داریوش نظرپور - سجاد گلشن نواز - ابراهیم بابائی

Kalman Filter Fusion Based on Interactive Multiple Model for Target Tracking in Wireless Sensor Networks

Zahra Zamani - Behrouz Safarinejadian

A Linear Position Sensor Proposal by Development of a Variable Reluctance Linear Resolver

Arman Ramezannezhad - Peyman Naderi - Lieven Vandevelde

A Low-Power High-Precision Low-Dropout Regulator For Biomedical Implants

Vahid Baghbani khezerlu - Mohammad Yavari - Mortaza Mojarad

طراحی تنظیم‌کننده‌ی خروجی بهینه‌ی مبتنی بر یادگیری تقویتی ایمن با استفاده از تابع مانع کنترلی نمایی

سیدرضا اصغری - سعید شمقدری

An Iterative Post-processing Method for Speech Source Separation in Realistic Scenarios

Iman Shahriari - Hossein Zeinali

Optimal Design of a Synchronous Reluctance Motor Using BioGeography-Based Optimization

Tohid Sharifi - Mojtaba Mirsalim

ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 40.4.2