Cover Image

Utilizing AlexNet Deep Transfer Learning for Ear Recognition

Convolution; Information retrieval; Knowledge management; Problem solving; AlexNet; Convolution neural network; Ear recognition; Fully-connected layers; Human recognition; Nonlinear problems; Problem domain; Transfer learning; Deep learning

Saved in:
Bibliographic Details
Main Authors: Almisreb A.A., Jamil N., Din N.M.
Other Authors: 50460937600
Format: Conference Paper
Published: Institute of Electrical and Electronics Engineers Inc. 2023
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.uniten.dspace-23703
record_format dspace
spelling my.uniten.dspace-237032023-05-29T14:51:07Z Utilizing AlexNet Deep Transfer Learning for Ear Recognition Almisreb A.A. Jamil N. Din N.M. 50460937600 6603538109 9335429400 Convolution; Information retrieval; Knowledge management; Problem solving; AlexNet; Convolution neural network; Ear recognition; Fully-connected layers; Human recognition; Nonlinear problems; Problem domain; Transfer learning; Deep learning Transfer Learning is an efficient approach of solving classification problem with little amount of data. In this paper, we applied Transfer Learning to the well-known AlexNet Convolution Neural Network (AlexNet CNN) for human recognition based on ear images. We adopted and fine-tuned AlexNet CNN to suit our problem domain. The last fully connected layer is replaced with another fully connected layer to recognize 10 classes instead of 1000 classes. Another Rectified Linear Unit (ReLU) layer is also added to improve the non-linear problem-solving ability of the network. To train the fine-tuned network, we allocate 250 ear images taken from 10 subjects for training, and 50 ear images are used for validation and testing. The proposed fine-tuned network works well in our application as we get 100% validation accuracy. � 2018 IEEE. Final 2023-05-29T06:51:07Z 2023-05-29T06:51:07Z 2018 Conference Paper 10.1109/INFRKM.2018.8464769 2-s2.0-85054421529 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85054421529&doi=10.1109%2fINFRKM.2018.8464769&partnerID=40&md5=2ce43c2725b51d5d87fad7d068497683 https://irepository.uniten.edu.my/handle/123456789/23703 8464769 8 12 Institute of Electrical and Electronics Engineers Inc. Scopus
institution Universiti Tenaga Nasional
building UNITEN Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Tenaga Nasional
content_source UNITEN Institutional Repository
url_provider http://dspace.uniten.edu.my/
description Convolution; Information retrieval; Knowledge management; Problem solving; AlexNet; Convolution neural network; Ear recognition; Fully-connected layers; Human recognition; Nonlinear problems; Problem domain; Transfer learning; Deep learning
author2 50460937600
author_facet 50460937600
Almisreb A.A.
Jamil N.
Din N.M.
format Conference Paper
author Almisreb A.A.
Jamil N.
Din N.M.
spellingShingle Almisreb A.A.
Jamil N.
Din N.M.
Utilizing AlexNet Deep Transfer Learning for Ear Recognition
author_sort Almisreb A.A.
title Utilizing AlexNet Deep Transfer Learning for Ear Recognition
title_short Utilizing AlexNet Deep Transfer Learning for Ear Recognition
title_full Utilizing AlexNet Deep Transfer Learning for Ear Recognition
title_fullStr Utilizing AlexNet Deep Transfer Learning for Ear Recognition
title_full_unstemmed Utilizing AlexNet Deep Transfer Learning for Ear Recognition
title_sort utilizing alexnet deep transfer learning for ear recognition
publisher Institute of Electrical and Electronics Engineers Inc.
publishDate 2023
_version_ 1806425546621452288
score 13.214268

Similar Items