Comparative analysis of RNN versus IIR digital filtering to optimize resilience to dynamic perturbations in pH sensing for vertical farming

IF 1.3 Q3 AGRONOMY Agrosystems, Geosciences & Environment Pub Date : 2024-11-04 DOI:10.1002/agg2.70001
Rolando Hinojosa-Meza, Martín Montes Rivera, Paulino Vacas-Jacques, Nivia Escalante-Garcia, José Alonso Dena-Aguilar, Aldonso Becerra Sanchez, Ernesto Olvera-Gonzalez
{"title":"Comparative analysis of RNN versus IIR digital filtering to optimize resilience to dynamic perturbations in pH sensing for vertical farming","authors":"Rolando Hinojosa-Meza,&nbsp;Martín Montes Rivera,&nbsp;Paulino Vacas-Jacques,&nbsp;Nivia Escalante-Garcia,&nbsp;José Alonso Dena-Aguilar,&nbsp;Aldonso Becerra Sanchez,&nbsp;Ernesto Olvera-Gonzalez","doi":"10.1002/agg2.70001","DOIUrl":null,"url":null,"abstract":"<p>Vertical farming (VF) refers to systems of agriculture where crops are grown in trays stacked vertically by exposing them to artificial light and using sensing technology to improve product quality and yield. In this work, we propose an advanced filtering scheme based on recurrent neural networks (RNNs) and deep learning to enable efficient control strategies for VF applications. We demonstrate that the best RNN model incorporates five neuron layers, with the first and second containing 90 long short-term memory neurons. The third layer implements one gated recurrent units neuron. The fourth segment incorporates one RNN network, while the output layer is designed by using a single neuron exhibiting a rectified linear activation function. By utilizing this RNN digital filter, we introduce two variations: (1) a scaled RNN model to tune the filter to the signal of interest, and (2) a moving average filter to eliminate harmonic oscillations of the output waveforms. The RNN models are contrasted with conventional digital Butterworth, Chebyshev I, Chebyshev II, and elliptic infinite impulse response (IIR) configurations. The RNN digital filtering schemes avoid introducing unwanted oscillations, which makes them more suitable for VF than their IIR counterparts. Finally, by utilizing the advanced features of scaling of the RNN model, we demonstrate that the RNN digital filter can be pH selective, as opposed to conventional IIR filters.</p>","PeriodicalId":7567,"journal":{"name":"Agrosystems, Geosciences & Environment","volume":null,"pages":null},"PeriodicalIF":1.3000,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/agg2.70001","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Agrosystems, Geosciences & Environment","FirstCategoryId":"1085","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/agg2.70001","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"AGRONOMY","Score":null,"Total":0}
引用次数: 0

Abstract

Vertical farming (VF) refers to systems of agriculture where crops are grown in trays stacked vertically by exposing them to artificial light and using sensing technology to improve product quality and yield. In this work, we propose an advanced filtering scheme based on recurrent neural networks (RNNs) and deep learning to enable efficient control strategies for VF applications. We demonstrate that the best RNN model incorporates five neuron layers, with the first and second containing 90 long short-term memory neurons. The third layer implements one gated recurrent units neuron. The fourth segment incorporates one RNN network, while the output layer is designed by using a single neuron exhibiting a rectified linear activation function. By utilizing this RNN digital filter, we introduce two variations: (1) a scaled RNN model to tune the filter to the signal of interest, and (2) a moving average filter to eliminate harmonic oscillations of the output waveforms. The RNN models are contrasted with conventional digital Butterworth, Chebyshev I, Chebyshev II, and elliptic infinite impulse response (IIR) configurations. The RNN digital filtering schemes avoid introducing unwanted oscillations, which makes them more suitable for VF than their IIR counterparts. Finally, by utilizing the advanced features of scaling of the RNN model, we demonstrate that the RNN digital filter can be pH selective, as opposed to conventional IIR filters.

Abstract Image

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
RNN 与 IIR 数字滤波的比较分析,优化垂直耕作 pH 值传感对动态扰动的适应能力
垂直耕作(VF)是指通过人工光照和传感技术将农作物种植在垂直堆叠的托盘中,以提高产品质量和产量的农业系统。在这项工作中,我们提出了一种基于递归神经网络(RNN)和深度学习的高级滤波方案,以实现针对 VF 应用的高效控制策略。我们证明,最佳 RNN 模型包含五个神经元层,其中第一层和第二层包含 90 个长短期记忆神经元。第三层实现了一个门控递归单元神经元。第四层包含一个 RNN 网络,而输出层是通过使用一个神经元来设计的,该神经元具有整流线性激活函数。通过利用这种 RNN 数字滤波器,我们引入了两种变体:(1) 缩放 RNN 模型,以根据相关信号调整滤波器;(2) 移动平均滤波器,以消除输出波形的谐波振荡。RNN 模型与传统的数字巴特沃斯、切比雪夫 I、切比雪夫 II 和椭圆无限脉冲响应 (IIR) 配置进行了对比。RNN 数字滤波方案可避免引入不必要的振荡,因此比 IIR 方案更适用于 VF。最后,通过利用 RNN 模型先进的缩放功能,我们证明了与传统的 IIR 滤波器相比,RNN 数字滤波器具有酸碱度选择性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Agrosystems, Geosciences & Environment
Agrosystems, Geosciences & Environment Agricultural and Biological Sciences-Agricultural and Biological Sciences (miscellaneous)
CiteScore
2.60
自引率
0.00%
发文量
80
审稿时长
24 weeks
期刊最新文献
Assessment of cover crop adoption and impact on weed management in Wisconsin corn-soybean cropping systems Kinetics of Cd adsorption by biochar, activated carbon, and zeolite in some calcareous soils Comparative analysis of RNN versus IIR digital filtering to optimize resilience to dynamic perturbations in pH sensing for vertical farming Soil greenhouse gas emissions under enhanced efficiency and urea nitrogen fertilizer from Australian irrigated aerobic rice production Changes in the population and diversity of plant parasitic nematodes and their effects on sugarcane growth at Wonji-Shoa Sugar Estate, Ethiopia
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1