کنفرانس مهندسی برق ایران

صفحه اصلی / سی و دومین کنفرانس بین المللی مهندسی برق

Active Data Fusion in Deep Neural Networks via Separation Index

نویسندگان :

Movahed Jamshidi¹ Ahmad Kalhor² Abdol-Hossein Vahabie³

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

کلمات کلیدی :

feature fusion،Separation Index (SI)،feature selection،deep neural networks

چکیده :

In this paper, we aim to enhance Convolutional Neural Networks (CNNs) by merging features from different pretrained models to improve information representation. Amidst advancements in network depth and architectures, we highlight feature fusion as a method for boosting CNN performance. Despite challenges in managing large feature sets and potential information loss during fusion, our paper introduces the Separation Index (SI) for feature selection. Unlike passive fusion, where all feature maps are simply concatenated, we employ the SI metric for active fusion. This method selects informative and discriminative features for the classification task, reducing computational complexity and model sizes. We evaluate our approach using medical and public datasets, specifically Skin Cancer data and CIFAR-10. The results demonstrate significant improvements in classification performance, confirming the effectiveness of our method. Notably, achieving a 95.63% classification accuracy on the CIFAR-10 dataset showcases the superiority of our approach over baselines and other competing methods.

لیست مقالات

لیست مقالات بایگانی شده

Study of Plasmonic Perfect Absorber Using Three Dimensional Silver Double Triangle-Shaped Nanoparticles

Mohammad Reza Rakhshani

Mach-Zehnder Interferometer Cell for Realization of Quantum Computer; A Feasibility Study

Mobin Motaharifar - Hassan Kaatuzian

Physiotherapy Algorithms on FUM-Physio Robot

Keyvan Tayaranian Marvian - Amir Hossein Nazari - Seyed Mohammad Tahamipour Zarandi - Mohammad Reza Akbarzadeh totonchi - Zahra Soltani - Alireza Akbarzadeh totonchi

A Novel Image Denoising Algorithm Based on Wavelet and Akamatsu Transforms Using Particle Swarm Optimization

Zeinab Pakdaman - Majid Amini-Valashani - Sattar Mirzakuchaki

Low Complexity Multi-User Indoor Localization Using Reconfigurable Intelligent Surface

Nooshin Afzali - Mohammad Javad Omidi - Keivan Navaie - Naghmeh Sadat Moayedian

Intelligent Near-Infrared Spectroscopy for Blood Glucose Level Classification

Shahrooz Sharifi - Amirhossein Maddah-Torghabehi - Mohammad-Reza Akbarzadeh-Totonchi

A New 10 Watt Power Amplifier for GSM 900 MHz base stations with 44% Bandwidth

Marzieh Chegini - HojjatAllah Nemati - Mahmoud Kamarei

ناحیه بندی تصاویر سار به کمک ویژگی های بافت استخراج شده از میدان تصادفی مارکوف گاوسی در سطح ناحیه

نرگس شکوهی - محمد صادق هلفروش - ریحانه غفاری - حبیب اله دانیالی

Estimation of the Arc Model Parameters Using Heuristic Optimization Methods

Sadegh Ghavami - Ali A Razi-kazemi

An Accurate Subthreshold Analytical Model for Black Phosphorus Heterojunction Dopingless Tunneling Field-Effect Transistors

Saeid Marjani - Mohamad Tolue Khayami

بیشتر

ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.8.0