Utilizing AlexNet Deep Transfer Learning for Ear Recognition

Ali Abd Almisreb, Nursuriati Jamil, Norashidah Md Din

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

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.

Original languageEnglish
Title of host publicationProceedings - 2018 4th International Conference on Information Retrieval and Knowledge Management
Subtitle of host publicationDiving into Data Sciences, CAMP 2018
EditorsShyamala Doraisamy, Azreen Azman, Dayang Nurfatimah Awg Iskandar, Muthukkaruppan Annamalai, Stefan Ruger, Fakhrul Hazman Yusoff, Nurazzah Abd. Rahman, Alistair Moffat, Shahrul Azman Mohd Noah
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages8-12
Number of pages5
ISBN (Print)9781538638125
DOIs
Publication statusPublished - 13 Sep 2018
Event4th International Conference on Information Retrieval and Knowledge Management: Diving into Data Sciences, CAMP 2018 - Kota Kinabalu, Sabah, Malaysia
Duration: 26 Mar 201828 Mar 2018

Publication series

NameProceedings - 2018 4th International Conference on Information Retrieval and Knowledge Management: Diving into Data Sciences, CAMP 2018

Other

Other4th International Conference on Information Retrieval and Knowledge Management: Diving into Data Sciences, CAMP 2018
CountryMalaysia
CityKota Kinabalu, Sabah
Period26/03/1828/03/18

Fingerprint

Convolution
Neural networks
neural network
learning
Testing
ability
Transfer learning

All Science Journal Classification (ASJC) codes

  • Library and Information Sciences
  • Artificial Intelligence
  • Information Systems
  • Decision Sciences (miscellaneous)
  • Information Systems and Management

Cite this

Almisreb, A. A., Jamil, N., & Md Din, N. (2018). Utilizing AlexNet Deep Transfer Learning for Ear Recognition. In S. Doraisamy, A. Azman, D. N. A. Iskandar, M. Annamalai, S. Ruger, F. H. Yusoff, N. Abd. Rahman, A. Moffat, ... S. A. M. Noah (Eds.), Proceedings - 2018 4th International Conference on Information Retrieval and Knowledge Management: Diving into Data Sciences, CAMP 2018 (pp. 8-12). [8464769] (Proceedings - 2018 4th International Conference on Information Retrieval and Knowledge Management: Diving into Data Sciences, CAMP 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/INFRKM.2018.8464769
Almisreb, Ali Abd ; Jamil, Nursuriati ; Md Din, Norashidah. / Utilizing AlexNet Deep Transfer Learning for Ear Recognition. Proceedings - 2018 4th International Conference on Information Retrieval and Knowledge Management: Diving into Data Sciences, CAMP 2018. editor / Shyamala Doraisamy ; Azreen Azman ; Dayang Nurfatimah Awg Iskandar ; Muthukkaruppan Annamalai ; Stefan Ruger ; Fakhrul Hazman Yusoff ; Nurazzah Abd. Rahman ; Alistair Moffat ; Shahrul Azman Mohd Noah. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 8-12 (Proceedings - 2018 4th International Conference on Information Retrieval and Knowledge Management: Diving into Data Sciences, CAMP 2018).
@inproceedings{dc9cb41e6dab4808be26378fac1d0e80,
title = "Utilizing AlexNet Deep Transfer Learning for Ear Recognition",
abstract = "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.",
author = "Almisreb, {Ali Abd} and Nursuriati Jamil and {Md Din}, Norashidah",
year = "2018",
month = "9",
day = "13",
doi = "10.1109/INFRKM.2018.8464769",
language = "English",
isbn = "9781538638125",
series = "Proceedings - 2018 4th International Conference on Information Retrieval and Knowledge Management: Diving into Data Sciences, CAMP 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "8--12",
editor = "Shyamala Doraisamy and Azreen Azman and Iskandar, {Dayang Nurfatimah Awg} and Muthukkaruppan Annamalai and Stefan Ruger and Yusoff, {Fakhrul Hazman} and {Abd. Rahman}, Nurazzah and Alistair Moffat and Noah, {Shahrul Azman Mohd}",
booktitle = "Proceedings - 2018 4th International Conference on Information Retrieval and Knowledge Management",
address = "United States",

}

Almisreb, AA, Jamil, N & Md Din, N 2018, Utilizing AlexNet Deep Transfer Learning for Ear Recognition. in S Doraisamy, A Azman, DNA Iskandar, M Annamalai, S Ruger, FH Yusoff, N Abd. Rahman, A Moffat & SAM Noah (eds), Proceedings - 2018 4th International Conference on Information Retrieval and Knowledge Management: Diving into Data Sciences, CAMP 2018., 8464769, Proceedings - 2018 4th International Conference on Information Retrieval and Knowledge Management: Diving into Data Sciences, CAMP 2018, Institute of Electrical and Electronics Engineers Inc., pp. 8-12, 4th International Conference on Information Retrieval and Knowledge Management: Diving into Data Sciences, CAMP 2018, Kota Kinabalu, Sabah, Malaysia, 26/03/18. https://doi.org/10.1109/INFRKM.2018.8464769

Utilizing AlexNet Deep Transfer Learning for Ear Recognition. / Almisreb, Ali Abd; Jamil, Nursuriati; Md Din, Norashidah.

Proceedings - 2018 4th International Conference on Information Retrieval and Knowledge Management: Diving into Data Sciences, CAMP 2018. ed. / Shyamala Doraisamy; Azreen Azman; Dayang Nurfatimah Awg Iskandar; Muthukkaruppan Annamalai; Stefan Ruger; Fakhrul Hazman Yusoff; Nurazzah Abd. Rahman; Alistair Moffat; Shahrul Azman Mohd Noah. Institute of Electrical and Electronics Engineers Inc., 2018. p. 8-12 8464769 (Proceedings - 2018 4th International Conference on Information Retrieval and Knowledge Management: Diving into Data Sciences, CAMP 2018).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Utilizing AlexNet Deep Transfer Learning for Ear Recognition

AU - Almisreb, Ali Abd

AU - Jamil, Nursuriati

AU - Md Din, Norashidah

PY - 2018/9/13

Y1 - 2018/9/13

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85054421529&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054421529&partnerID=8YFLogxK

U2 - 10.1109/INFRKM.2018.8464769

DO - 10.1109/INFRKM.2018.8464769

M3 - Conference contribution

SN - 9781538638125

T3 - Proceedings - 2018 4th International Conference on Information Retrieval and Knowledge Management: Diving into Data Sciences, CAMP 2018

SP - 8

EP - 12

BT - Proceedings - 2018 4th International Conference on Information Retrieval and Knowledge Management

A2 - Doraisamy, Shyamala

A2 - Azman, Azreen

A2 - Iskandar, Dayang Nurfatimah Awg

A2 - Annamalai, Muthukkaruppan

A2 - Ruger, Stefan

A2 - Yusoff, Fakhrul Hazman

A2 - Abd. Rahman, Nurazzah

A2 - Moffat, Alistair

A2 - Noah, Shahrul Azman Mohd

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Almisreb AA, Jamil N, Md Din N. Utilizing AlexNet Deep Transfer Learning for Ear Recognition. In Doraisamy S, Azman A, Iskandar DNA, Annamalai M, Ruger S, Yusoff FH, Abd. Rahman N, Moffat A, Noah SAM, editors, Proceedings - 2018 4th International Conference on Information Retrieval and Knowledge Management: Diving into Data Sciences, CAMP 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 8-12. 8464769. (Proceedings - 2018 4th International Conference on Information Retrieval and Knowledge Management: Diving into Data Sciences, CAMP 2018). https://doi.org/10.1109/INFRKM.2018.8464769