loading
Papers

Research.Publish.Connect.

Paper

Authors: Gabrielė Kasparavičiūtė 1 ; Malin Thelin 2 ; Peter Nordin 3 ; Per Söderstam 2 ; Christian Magnusson 2 and Mattias Almljung 2

Affiliations: 1 Chalmers University of Technology, Chalmersplatsen 4, Gothenburg, Sweden, University of Gothenburg, Rännvägen 6B, Gothenburg and Sweden ; 2 Semcon AB, Lindholmsallén 2, Gothenburg and Sweden ; 3 Chalmers University of Technology, Chalmersplatsen 4, Gothenburg, Sweden, Semcon AB, Lindholmsallén 2, Gothenburg and Sweden

ISBN: 978-989-758-384-1

Keyword(s): Encoder-decoder, Anomaly Detection, Linear Genetic Programming, Evolutionary Algorithm, Genetic Algorithm, Embedded, Self-configuring, Neural Network.

Related Ontology Subjects/Areas/Topics: Artificial Intelligence ; Computational Intelligence ; Evolutionary Computing ; Genetic Algorithms ; Informatics in Control, Automation and Robotics ; Intelligent Control Systems and Optimization ; Soft Computing

Abstract: Recent anomaly detection techniques focus on the use of neural networks and an encoder-decoder architecture. However, these techniques lead to trade offs if implemented in an embedded environment such as high heat management, power consumption and hardware costs. This paper presents two related new methods for anomaly detection within data sets gathered from an autonomous mini-vehicle with a CAN bus. The first method which to the best of our knowledge is the first use of encoder-decoder architecture for anomaly detection using linear genetic programming (LGP). Second method uses self-configuring neural network that is created using evolutionary algorithm paradigm learning both architecture and weights suitable for embedded systems. Both approaches have the following advantages: it is inexpensive regarding resource use, can be run on almost any embedded board due to linear register machine advantages in computation. The proposed methods are also faster by at least one order of magnitud e, and it includes both inference and complete training. (More)

PDF ImageFull Text

Download
CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 34.204.173.36

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Kasparavičiūtė, G.; Thelin, M.; Nordin, P.; Söderstam, P.; Magnusson, C. and Almljung, M. (2019). Online Encoder-decoder Anomaly Detection using Encoder-decoder Architecture with Novel Self-configuring Neural Networks & Pure Linear Genetic Programming for Embedded Systems.In Proceedings of the 11th International Joint Conference on Computational Intelligence - Volume 1: ECTA, (IJCCI 2019) ISBN 978-989-758-384-1, pages 163-171. DOI: 10.5220/0008064401630171

@conference{ecta19,
author={Gabrielė Kasparavičiūtė. and Malin Thelin. and Peter Nordin. and Per Söderstam. and Christian Magnusson. and Mattias Almljung.},
title={Online Encoder-decoder Anomaly Detection using Encoder-decoder Architecture with Novel Self-configuring Neural Networks & Pure Linear Genetic Programming for Embedded Systems},
booktitle={Proceedings of the 11th International Joint Conference on Computational Intelligence - Volume 1: ECTA, (IJCCI 2019)},
year={2019},
pages={163-171},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008064401630171},
isbn={978-989-758-384-1},
}

TY - CONF

JO - Proceedings of the 11th International Joint Conference on Computational Intelligence - Volume 1: ECTA, (IJCCI 2019)
TI - Online Encoder-decoder Anomaly Detection using Encoder-decoder Architecture with Novel Self-configuring Neural Networks & Pure Linear Genetic Programming for Embedded Systems
SN - 978-989-758-384-1
AU - Kasparavičiūtė, G.
AU - Thelin, M.
AU - Nordin, P.
AU - Söderstam, P.
AU - Magnusson, C.
AU - Almljung, M.
PY - 2019
SP - 163
EP - 171
DO - 10.5220/0008064401630171

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.