Home > Research > Publications & Outputs > Actively Semi-Supervised Deep Rule-based Classi...

Electronic data

  • Actively_Deep_Rule_based_Classifier_Applied_to_Adverse_Driving_Scenarios

    Rights statement: ©2020 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

    Accepted author manuscript, 480 KB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

View graph of relations

Actively Semi-Supervised Deep Rule-based Classifier Applied to Adverse Driving Scenarios

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

Actively Semi-Supervised Deep Rule-based Classifier Applied to Adverse Driving Scenarios. / Almeida Soares, Eduardo; Angelov, Plamen Parvanov; Costa, Bruno Sielly Jales et al.
2019 International Joint Conference on Neural Networks (IJCNN). IEEE, 2019. p. 1-8.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Almeida Soares, E, Angelov, PP, Costa, BSJ & Castro, M 2019, Actively Semi-Supervised Deep Rule-based Classifier Applied to Adverse Driving Scenarios. in 2019 International Joint Conference on Neural Networks (IJCNN). IEEE, pp. 1-8, 2019 IEEE International Joint Conference on Neural Networks, Budapest, Hungary, 14/07/19. https://doi.org/10.1109/IJCNN.2019.8851842

APA

Vancouver

Almeida Soares E, Angelov PP, Costa BSJ, Castro M. Actively Semi-Supervised Deep Rule-based Classifier Applied to Adverse Driving Scenarios. In 2019 International Joint Conference on Neural Networks (IJCNN). IEEE. 2019. p. 1-8 Epub 2019 Jul 14. doi: 10.1109/IJCNN.2019.8851842

Author

Bibtex

@inproceedings{1b6bdbecbc9343599a6307b28035832e,
title = "Actively Semi-Supervised Deep Rule-based Classifier Applied to Adverse Driving Scenarios",
abstract = "This paper presents an actively semi-supervised multi-layer neuro-fuzzy modeling method, ASSDRB, to classify different lighting conditions for driving scenes. ASSDRB is composed of a massively parallel ensemble of AnYa type 0-order fuzzy rules. It uses a recursive learning algorithm to update its structure when new data items are provided and, therefore, is able to cope with nonstationarities. Different lighting conditions for driving situations are considered in the analysis, which is used by self-driving cars as a safety mechanism. Differently from mainstream Deep Neural Networks approaches, the ASSDRB is able to learn from unseen data. Experiments on different lighting conditions for driving scenes, demonstrated that the deep neuro-fuzzy modeling is an efficient framework for these challenging classification tasks. Classification accuracy is higher than those produced by alternative machine learning methods. The number of algebraic calculations for the present method are significantly smaller and, therefore, the method is significantly faster than common Deep Neural Networks approaches. Moreover, DRB produced transparent AnYa fuzzy rules, which are human interpretable. ",
author = "{Almeida Soares}, Eduardo and Angelov, {Plamen Parvanov} and Costa, {Bruno Sielly Jales} and Marcos Castro",
note = "{\textcopyright}2020 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. ; 2019 IEEE International Joint Conference on Neural Networks, IJCNN 19 ; Conference date: 14-07-2019 Through 19-07-2019",
year = "2019",
month = sep,
day = "30",
doi = "10.1109/IJCNN.2019.8851842",
language = "English",
isbn = "9781728119861",
pages = "1--8",
booktitle = "2019 International Joint Conference on Neural Networks (IJCNN)",
publisher = "IEEE",
url = "https://www.ijcnn.org/",

}

RIS

TY - GEN

T1 - Actively Semi-Supervised Deep Rule-based Classifier Applied to Adverse Driving Scenarios

AU - Almeida Soares, Eduardo

AU - Angelov, Plamen Parvanov

AU - Costa, Bruno Sielly Jales

AU - Castro, Marcos

N1 - ©2020 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

PY - 2019/9/30

Y1 - 2019/9/30

N2 - This paper presents an actively semi-supervised multi-layer neuro-fuzzy modeling method, ASSDRB, to classify different lighting conditions for driving scenes. ASSDRB is composed of a massively parallel ensemble of AnYa type 0-order fuzzy rules. It uses a recursive learning algorithm to update its structure when new data items are provided and, therefore, is able to cope with nonstationarities. Different lighting conditions for driving situations are considered in the analysis, which is used by self-driving cars as a safety mechanism. Differently from mainstream Deep Neural Networks approaches, the ASSDRB is able to learn from unseen data. Experiments on different lighting conditions for driving scenes, demonstrated that the deep neuro-fuzzy modeling is an efficient framework for these challenging classification tasks. Classification accuracy is higher than those produced by alternative machine learning methods. The number of algebraic calculations for the present method are significantly smaller and, therefore, the method is significantly faster than common Deep Neural Networks approaches. Moreover, DRB produced transparent AnYa fuzzy rules, which are human interpretable.

AB - This paper presents an actively semi-supervised multi-layer neuro-fuzzy modeling method, ASSDRB, to classify different lighting conditions for driving scenes. ASSDRB is composed of a massively parallel ensemble of AnYa type 0-order fuzzy rules. It uses a recursive learning algorithm to update its structure when new data items are provided and, therefore, is able to cope with nonstationarities. Different lighting conditions for driving situations are considered in the analysis, which is used by self-driving cars as a safety mechanism. Differently from mainstream Deep Neural Networks approaches, the ASSDRB is able to learn from unseen data. Experiments on different lighting conditions for driving scenes, demonstrated that the deep neuro-fuzzy modeling is an efficient framework for these challenging classification tasks. Classification accuracy is higher than those produced by alternative machine learning methods. The number of algebraic calculations for the present method are significantly smaller and, therefore, the method is significantly faster than common Deep Neural Networks approaches. Moreover, DRB produced transparent AnYa fuzzy rules, which are human interpretable.

U2 - 10.1109/IJCNN.2019.8851842

DO - 10.1109/IJCNN.2019.8851842

M3 - Conference contribution/Paper

SN - 9781728119861

SP - 1

EP - 8

BT - 2019 International Joint Conference on Neural Networks (IJCNN)

PB - IEEE

T2 - 2019 IEEE International Joint Conference on Neural Networks

Y2 - 14 July 2019 through 19 July 2019

ER -