Trigonometric-Euclidean-Smoother Interpolator (TESI) for continuous time-series and non-time-series data augmentation for deep neural network applications in agriculture

Biomass estimation, fertilisation, and crop production reflect crop yield potential. The prediction of these variables allows the selection of crop cultivars with high yield potential. Deep neural networks (DNNs) can predict such crop variables. However, DNNs are data greedy algorithms that overfit/...

Full description

Bibliographic Details
Main Authors: Derraz, Radhwane, Muharam, Farrah Melissa, Jaafar, Noraini Ahmad, Yap, Ng Keng
Format: Article
Published: Elsevier 2023
Online Access:http://psasir.upm.edu.my/id/eprint/108355/
_version_ 1848865139358433280
author Derraz, Radhwane
Muharam, Farrah Melissa
Jaafar, Noraini Ahmad
Yap, Ng Keng
author_facet Derraz, Radhwane
Muharam, Farrah Melissa
Jaafar, Noraini Ahmad
Yap, Ng Keng
author_sort Derraz, Radhwane
building UPM Institutional Repository
collection Online Access
description Biomass estimation, fertilisation, and crop production reflect crop yield potential. The prediction of these variables allows the selection of crop cultivars with high yield potential. Deep neural networks (DNNs) can predict such crop variables. However, DNNs are data greedy algorithms that overfit/underfit on small-size datasets. Additionally, the collection of big data is expensive and laborious. Therefore, providing synthetic big data is preferable. This study aims to: (i) develop a trigonometric-Euclidean-smoother interpolation (TESI) for continuous time-series and non-time-series data augmentation to prevent DNNs from under/overfitting; (ii) compare the TESI performance to the tabular variational autoencoder (TVAE) and the conditional tabular generative adversarial network (CTGAN); and (iii) compare the DNN performance before and after data augmentation. Two time-series datasets, oil palm production and rice.
first_indexed 2025-11-15T13:59:57Z
format Article
id upm-108355
institution Universiti Putra Malaysia
institution_category Local University
last_indexed 2025-11-15T13:59:57Z
publishDate 2023
publisher Elsevier
recordtype eprints
repository_type Digital Repository
spelling upm-1083552024-10-23T06:39:47Z http://psasir.upm.edu.my/id/eprint/108355/ Trigonometric-Euclidean-Smoother Interpolator (TESI) for continuous time-series and non-time-series data augmentation for deep neural network applications in agriculture Derraz, Radhwane Muharam, Farrah Melissa Jaafar, Noraini Ahmad Yap, Ng Keng Biomass estimation, fertilisation, and crop production reflect crop yield potential. The prediction of these variables allows the selection of crop cultivars with high yield potential. Deep neural networks (DNNs) can predict such crop variables. However, DNNs are data greedy algorithms that overfit/underfit on small-size datasets. Additionally, the collection of big data is expensive and laborious. Therefore, providing synthetic big data is preferable. This study aims to: (i) develop a trigonometric-Euclidean-smoother interpolation (TESI) for continuous time-series and non-time-series data augmentation to prevent DNNs from under/overfitting; (ii) compare the TESI performance to the tabular variational autoencoder (TVAE) and the conditional tabular generative adversarial network (CTGAN); and (iii) compare the DNN performance before and after data augmentation. Two time-series datasets, oil palm production and rice. Elsevier 2023-03 Article PeerReviewed Derraz, Radhwane and Muharam, Farrah Melissa and Jaafar, Noraini Ahmad and Yap, Ng Keng (2023) Trigonometric-Euclidean-Smoother Interpolator (TESI) for continuous time-series and non-time-series data augmentation for deep neural network applications in agriculture. Computers and Electronics in Agriculture, 206. pp. 1-17. ISSN 0168-1699; eISSN: 1872-7107 https://www.sciencedirect.com/science/article/abs/pii/S0168169923000340?via%3Dihub 10.1016/j.compag.2023.107646
spellingShingle Derraz, Radhwane
Muharam, Farrah Melissa
Jaafar, Noraini Ahmad
Yap, Ng Keng
Trigonometric-Euclidean-Smoother Interpolator (TESI) for continuous time-series and non-time-series data augmentation for deep neural network applications in agriculture
title Trigonometric-Euclidean-Smoother Interpolator (TESI) for continuous time-series and non-time-series data augmentation for deep neural network applications in agriculture
title_full Trigonometric-Euclidean-Smoother Interpolator (TESI) for continuous time-series and non-time-series data augmentation for deep neural network applications in agriculture
title_fullStr Trigonometric-Euclidean-Smoother Interpolator (TESI) for continuous time-series and non-time-series data augmentation for deep neural network applications in agriculture
title_full_unstemmed Trigonometric-Euclidean-Smoother Interpolator (TESI) for continuous time-series and non-time-series data augmentation for deep neural network applications in agriculture
title_short Trigonometric-Euclidean-Smoother Interpolator (TESI) for continuous time-series and non-time-series data augmentation for deep neural network applications in agriculture
title_sort trigonometric-euclidean-smoother interpolator (tesi) for continuous time-series and non-time-series data augmentation for deep neural network applications in agriculture
url http://psasir.upm.edu.my/id/eprint/108355/
http://psasir.upm.edu.my/id/eprint/108355/
http://psasir.upm.edu.my/id/eprint/108355/