Deep learning optimisation algorithms for snatch theft detection / Nurul Farhana Mohamad Zamri ...[et al.]

Mohamad Zamri, Nurul Farhana and Md Tahir, Nooritawati and Megat Ali, Megat Syahirul Amin and Khirul Ashar, Nur Dalila (2022) Deep learning optimisation algorithms for snatch theft detection / Nurul Farhana Mohamad Zamri ...[et al.]. Journal of Electrical and Electronic Systems Research (JEESR), 20: 5. pp. 34-40. ISSN 1985-5389

Abstract

Learning algorithms related to deep learning use bells and whistles, called hyperparameters. Hence, this study conducted numerical analysis, specifically backpropagation gradients and gradient-based optimization for snatch-theft detection. Here, snatch theft images and augmented images were used to perform
the experimental study to determine the optimum hyperparameter values. Next, the value of epoch and learning rate was obtained after careful analysis based on each training option. Results achieved showed that epoch value of 20 and learning rate corresponding to 0.0001 was the optimum values. Findings from
this study can be used as a practical guide in determining the importance of the most optimum hyperparameters.

Metadata

Item Type: Article
Creators:
Creators
Email / ID Num.
Mohamad Zamri, Nurul Farhana
UNSPECIFIED
Md Tahir, Nooritawati
nooritawati@ieee.org
Megat Ali, Megat Syahirul Amin
megatsyahirul@uitm.edu.my
Khirul Ashar, Nur Dalila
nurdalila306@uitm.edu.my
Subjects: Q Science > QA Mathematics > Instruments and machines > Electronic Computers. Computer Science > Neural networks (Computer science)
T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Electronics > Detectors. Sensors. Sensor networks
T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Electronics > Applications of electronics
Divisions: Universiti Teknologi MARA, Shah Alam > College of Engineering
Journal or Publication Title: Journal of Electrical and Electronic Systems Research (JEESR)
UiTM Journal Collections: UiTM Journal > Journal of Electrical and Electronic Systems Research (JEESR)
ISSN: 1985-5389
Volume: 20
Page Range: pp. 34-40
Keywords: Deep learning neural network, image classification, optimisation, snatch theft detection
Date: April 2022
URI: https://ir.uitm.edu.my/id/eprint/63168
Edit Item
Edit Item

Download

[thumbnail of 63168.pdf] Text
63168.pdf

Download (845kB)

ID Number

63168

Indexing

Statistic

Statistic details