Comparative analysis of RNN versus IIR digital filtering to optimize resilience to dynamic perturbations in pH sensing for vertical farming
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 ne...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-12-01
|
| Series: | Agrosystems, Geosciences & Environment |
| Online Access: | https://doi.org/10.1002/agg2.70001 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850119279088762880 |
|---|---|
| author | Rolando Hinojosa‐Meza Martín Montes Rivera Paulino Vacas‐Jacques Nivia Escalante‐Garcia José Alonso Dena‐Aguilar Aldonso Becerra Sanchez Ernesto Olvera‐Gonzalez |
| author_facet | Rolando Hinojosa‐Meza Martín Montes Rivera Paulino Vacas‐Jacques Nivia Escalante‐Garcia José Alonso Dena‐Aguilar Aldonso Becerra Sanchez Ernesto Olvera‐Gonzalez |
| author_sort | Rolando Hinojosa‐Meza |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-c8defa6c354e4f13b140d681d5fe983a |
| institution | OA Journals |
| issn | 2639-6696 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | Agrosystems, Geosciences & Environment |
| spelling | doaj-art-c8defa6c354e4f13b140d681d5fe983a2025-08-20T02:35:40ZengWileyAgrosystems, Geosciences & Environment2639-66962024-12-0174n/an/a10.1002/agg2.70001Comparative analysis of RNN versus IIR digital filtering to optimize resilience to dynamic perturbations in pH sensing for vertical farmingRolando Hinojosa‐Meza0Martín Montes Rivera1Paulino Vacas‐Jacques2Nivia Escalante‐Garcia3José Alonso Dena‐Aguilar4Aldonso Becerra Sanchez5Ernesto Olvera‐Gonzalez6Laboratorio de Iluminación Artificial Tecnológico Nacional de México/IT de Pabellón de Arteaga Aguascalientes MéxicoDepartamento de Investigación y Estudios de Posgrado Universidad Politécnica de Aguascalientes Aguascalientes MéxicoLaboratorio de Iluminación Artificial Tecnológico Nacional de México/IT de Pabellón de Arteaga Aguascalientes MéxicoLaboratorio de Iluminación Artificial Tecnológico Nacional de México/IT de Pabellón de Arteaga Aguascalientes MéxicoDepartamento de Ingenierías Tecnológico Nacional de México /IT de Pabellón de Arteaga Aguascalientes MéxicoUnidad Académica de Ingeniería Eléctrica Universidad Autónoma de Zacatecas Zacatecas MéxicoLaboratorio de Iluminación Artificial Tecnológico Nacional de México/IT de Pabellón de Arteaga Aguascalientes MéxicoAbstract 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.https://doi.org/10.1002/agg2.70001 |
| spellingShingle | Rolando Hinojosa‐Meza Martín Montes Rivera Paulino Vacas‐Jacques Nivia Escalante‐Garcia José Alonso Dena‐Aguilar Aldonso Becerra Sanchez Ernesto Olvera‐Gonzalez Comparative analysis of RNN versus IIR digital filtering to optimize resilience to dynamic perturbations in pH sensing for vertical farming Agrosystems, Geosciences & Environment |
| title | Comparative analysis of RNN versus IIR digital filtering to optimize resilience to dynamic perturbations in pH sensing for vertical farming |
| title_full | Comparative analysis of RNN versus IIR digital filtering to optimize resilience to dynamic perturbations in pH sensing for vertical farming |
| title_fullStr | Comparative analysis of RNN versus IIR digital filtering to optimize resilience to dynamic perturbations in pH sensing for vertical farming |
| title_full_unstemmed | Comparative analysis of RNN versus IIR digital filtering to optimize resilience to dynamic perturbations in pH sensing for vertical farming |
| title_short | Comparative analysis of RNN versus IIR digital filtering to optimize resilience to dynamic perturbations in pH sensing for vertical farming |
| title_sort | comparative analysis of rnn versus iir digital filtering to optimize resilience to dynamic perturbations in ph sensing for vertical farming |
| url | https://doi.org/10.1002/agg2.70001 |
| work_keys_str_mv | AT rolandohinojosameza comparativeanalysisofrnnversusiirdigitalfilteringtooptimizeresiliencetodynamicperturbationsinphsensingforverticalfarming AT martinmontesrivera comparativeanalysisofrnnversusiirdigitalfilteringtooptimizeresiliencetodynamicperturbationsinphsensingforverticalfarming AT paulinovacasjacques comparativeanalysisofrnnversusiirdigitalfilteringtooptimizeresiliencetodynamicperturbationsinphsensingforverticalfarming AT niviaescalantegarcia comparativeanalysisofrnnversusiirdigitalfilteringtooptimizeresiliencetodynamicperturbationsinphsensingforverticalfarming AT josealonsodenaaguilar comparativeanalysisofrnnversusiirdigitalfilteringtooptimizeresiliencetodynamicperturbationsinphsensingforverticalfarming AT aldonsobecerrasanchez comparativeanalysisofrnnversusiirdigitalfilteringtooptimizeresiliencetodynamicperturbationsinphsensingforverticalfarming AT ernestoolveragonzalez comparativeanalysisofrnnversusiirdigitalfilteringtooptimizeresiliencetodynamicperturbationsinphsensingforverticalfarming |