Heben Sie Ihre Leistungen auf People@HES-SO hervor weitere Infos
PEOPLE@HES-SO - Verzeichnis der Mitarbeitenden und Kompetenzen
PEOPLE@HES-SO - Verzeichnis der Mitarbeitenden und Kompetenzen

PEOPLE@HES-SO
Verzeichnis der Mitarbeitenden und Kompetenzen

Hilfe
language
  • fr
  • en
  • de
  • fr
  • en
  • de
  • SWITCH edu-ID
  • Verwaltung
« Zurück
Dutoit Fabien

Dutoit Fabien

Professeur HES associé

Hauptkompetenzen

Applications mobiles

mHealth

eHealth

Conception de systèmes complexes

IoT Internet Of Things

Plateformes web

Confidential Computing

  • Kontakt

  • Lehre

  • Publikationen

  • Konferenzen

  • Portfolio

Hauptvertrag

Professeur HES associé

Büro: B29

Haute école d'Ingénierie et de Gestion du Canton de Vaud
Route de Cheseaux 1, 1400 Yverdon-les-Bains, CH
HEIG-VD
BSc en Informatique et systèmes de communication - Haute école d'Ingénierie et de Gestion du Canton de Vaud
  • Développement Android
  • Développement mobile avancé
  • Systèmes mobiles
  • Administration de systèmes
  • Algorithmes et structures des données
BSc HES-SO en Technique en radiologie médicale - HESAV - Haute Ecole de Santé Vaud
  • Informatisation de la santé
MSc HES-SO/UNIL en Sciences de la santé - HES-SO Master
  • Ingénierie Santé - Gestion de projet et leadership collaboratif

2024

Advanced assessment of nutrient deficiencies in greenhouse with electrophysiological signals
Wissenschaftlicher Artikel ArODES

Daniel Tran, Elena Najdenovska, Fabien Dutoit, Carrol Plummer, Nigel Wallbridge, Marco Mazza, Cédric Camps, Laura Elena Raileanu

Horticulture, Environment, and Biotechnology,  2024

Link zur Publikation

Zusammenfassung:

Nutrient deficiencies are one of the main causes of significant reductions in commercial crop production by affecting associated growth factors. Proper plant nutrition is crucial for crop quality and yield therefore, early and objective detection of nutrient deficiency is required. Recent literature has explored the real-time monitoring of plant electrical signal, called electrophysiology, applied on tomato crop cultivated in greenhouse. This sensor allows to identify the stressed state of a plant in the presence of different biotic and abiotic stressors by employing machine learning techniques. The aim of this study was to evaluate the potential of electrophysiology signal recordings acquired from tomato plants growing in a production greenhouse environment, to detect the stress of a plant triggered by the deficiency of several main nutrients. Based on a previously proposed workflow consisting of continuous acquisition of electrical signal then application of machine learning techniques, the minimum signal features was evaluated. This study presents classification models that are able to distinguish the plant’s stressed state with good accuracy, namely 78.5% for manganese, 78.1% for iron, 89.6% for nitrogen, and 78.1% for calcium deficiency, and therefore suggests a novel path to detect nutrient deficiencies at an early stage. This could constitute a novel practical tool to help and assist farmers in nutrition management.

2023

Detecting stress caused by nitrogen deficit using deep learning techniques applied on plant electrophysiological data
Wissenschaftlicher Artikel ArODES

Daniel González I Juclà, Elena Najdenovska, Fabien Dutoit, Laura Elena Raileanu

Scientific Reports,  2023, vol. 13, article no. 9633

Link zur Publikation

Zusammenfassung:

Plant electrophysiology carries a strong potential for assessing the health of a plant. Current literature for the classification of plant electrophysiology generally comprises classical methods based on signal features that portray a simplification of the raw data and introduce a high computational cost. The Deep Learning (DL) techniques automatically learn the classification targets from the input data, overcoming the need for precalculated features. However, they are scarcely explored for identifying plant stress on electrophysiological recordings. This study applies DL techniques to the raw electrophysiological data from 16 tomato plants growing in typical production conditions to detect the presence of stress caused by a nitrogen deficiency. The proposed approach predicts the stressed state with an accuracy of around 88%, which could be increased to over 96% using a combination of the obtained prediction confidences. It outperforms the current state-of-the-art with over 8% higher accuracy and a potential for a direct application in production conditions. Moreover, the proposed approach demonstrates the ability to detect the presence of stress at its early stage. Overall, the presented findings suggest new means to automatize and improve agricultural practices with the aim of sustainability.

Assessment of the universality of the electrophysiological signal acquired from tomatoes and eggplants
Wissenschaftlicher Artikel

Najdenovska Elena, Dutoit Fabien, Gil Carron, Daniel Tran, Carrol Plummer, Nigel Wallbridge, Cédric Camps, Raileanu Laura Elena

Acta Horticulturae, 2023 , no  1360, pp.  219-224

Link zur Publikation

2021

Identifying general stress in commercial tomatoes based on machine learning applied to plant electrophysiology
Wissenschaftlicher Artikel ArODES

Elena Najdenovska, Fabien Dutoit, Daniel Tran, Antoine Rochat, Basile Vu, Marco Mazza, Cédric Camps, Carrol Plummer, Nigel Wallbridge, Laura Elena Raileanu

Applied Sciences,  2021, vol. 11, no. 5640

Link zur Publikation

Zusammenfassung:

Automated monitoring of plant health is becoming a crucial component for optimizing agricultural production. Recently, several studies have shown that plant electrophysiology could be used as a tool to determine plant status related to applied stressors. However, to the best of our knowledge, there have been no studies relating electrical plant response to general stress responses as a proxy for plant health. This study models general stress of plants exposed to either biotic or abiotic stressors, namely drought, nutrient deficiencies or infestation with spider mites, using electrophysiological signals acquired from 36 plants. Moreover, in the signal processing procedure, the proposed workflow reuses information from the previous steps, therefore considerably reducing computation time regarding recent related approaches in the literature. Careful choice of the principal parameters leads to a classification of the general stress in plants with more than 80% accuracy. The main descriptive statistics measured together with the Hjorth complexity provide the most discriminative information for such classification. The presented findings open new paths to explore for improved monitoring of plant health.

Classification of plant electrophysiology signals for detection of spider mites infestation in tomatoes
Wissenschaftlicher Artikel ArODES

Elena Najdenovska, Fabien Dutoit, Daniel Tran, Carole Plummer, Nigel Wallbridge, Cédric Camps, Laura Elena Raileanu

Applied Sciences,  2021, vol. 11, no. 4, article no. 1414

Link zur Publikation

Zusammenfassung:

Herbivorous arthropods, such as spider mites, are one of the major causes of annual crop losses. They are usually hard to spot before a severe infestation takes place. When feeding, these insects cause external perturbation that triggers changes in the underlying physiological process of a plant, which are expressed by a generation of distinct variations of electrical potential. Therefore, plant electrophysiology data portray information of the plant state. Analyses involving machine learning techniques applied to plant electrical response triggered by spider mite infestation have not been previously reported. This study investigates plant electrophysiological signals recorded from 12 commercial tomatoes plants contaminated with spider mites and proposes a workflow based on Gradient Boosted Tree algorithm for an automated differentiation of the plant’s normal state from the stressed state caused by infestation. The classification model built using the signal samples recorded during daylight and employing a reduced feature subset performs with an accuracy of 80% in identifying the plant’s stressed state. Furthermore, the Hjorth complexity encloses the most relevant information for discrimination of the plant status. The obtained findings open novel access towards automated detection of insect infestation in greenhouse crops and, consequently, more optimal prevention and treatment approaches.

2019

Electrophysiological assessment of plant status outside a Faraday cage using supervised machine learning
Wissenschaftlicher Artikel ArODES

Daniel Tran, Fabien Dutoit, Elena Najdenovska, Nigel Wallbridge, Carrol Plummer, Marco Mazza, Laura Elena Raileanu, Cédric Camps

Scientific Reports,  2019, vol. 9, art. no. 17073

Link zur Publikation

Zusammenfassung:

Living organisms have evolved complex signaling networks to drive appropriate physiological processes in response to changing environmental conditions. Amongst them, electric signals are a universal method to rapidly transmit information. In animals, bioelectrical activity measurements in the heart or the brain provide information about health status. In plants, practical measurements of bioelectrical activity are in their infancy and transposition of technology used in human medicine could therefore, by analogy provide insight about the physiological status of plants. This paper reports on the development and testing of an innovative electrophysiological sensor that can be used in greenhouse production conditions, without a Faraday cage, enabling real-time electric signal measurements. The bioelectrical activity is modified in response to water stress conditions or to nycthemeral rhythm. Furthermore, the automatic classification of plant status using supervised machine learning allows detection of these physiological modifications. This sensor represents an efficient alternative agronomic tool at the service of producers for decision support or for taking preventive measures before initial visual symptoms of plant stress appear.

2024

An intelligent IoT platform as an advisory system for fruit growth
Konferenz

Dutoit Fabien, Najdenovska Elena, Campos Carvalho Cédric, Theresa Dunkel, Nathan Miéville, Robert Whittaker, Philippe Monney, Cédric Camps, Raileanu Laura Elena

EHC 2024 - Robotics, mechanization and smart horticulture symposium, 12.05.2024 - 16.05.2024, Bucarest, Roumanie

Link zur Konferenz

2023

Novel fruit growers advisory system using connected fruit dendrometer, micro-climate data and machine learning algorithms
Konferenz
Abstract

Theresa Dunkel, Najdenovska Elena, Dutoit Fabien, Robert Whittaker, Raileanu Laura Elena, Cédric Camps

Greensys 2023, 22.10.2023 - 27.10.2023, Cancún Mexique

Link zur Konferenz

Zusammenfassung:

The climate is having an increasing impact on greenhouse production. Frequent and unpredictable events lead to physiological adaptations of plants to the detriment of fruit quality. Tomatoes, for example, split or even burst in the ripening phase, often in the summer when a succession of hot periods occur and the fruit is not elastic enough to absorb the physical changes due to frequent irrigation. This causes important losses for the growers.

This project aims to implement and test a real-time connected fruit dendrometer in a soilless tomato culture, combined with a micro-climate analysis and machine learning algorithms. The objective is to detect a typical signature growing curve for tomato crop production and predict cracking event. The research has three main outcomes: (i) improve crop quality; (ii) optimize harvest timing; (iii) reduce water usage.

A field trial took place in 2022 at the research centre of Agroscope, Switzerland. The mechanical and electronic behaviour of 60 fruit dendrometers was tested in a soilless tomato greenhouse, together with the setup of a data transmission and storage system. Six micro-climatic stations allowed to study the dependence between climatic data and fruit growth. Phenological and physiological monitoring of tomato plants and fruit quality analysis allows the characterization of the different climatic environments that could affect the fruit cracking occurrence

The preliminary results revealed promising. The build fruit-growth models can predict the final fruit diameter and the best harvest time. The plants exhibit different transpiration levels and a certain texture variability in response to the different micro-environmental conditions.

Monitoring continues for generating additional data on the fruit growth behaviour. This contributes to develop precise fruit cracking model, alerting the greenhouse producers about a potential risk that may lead to losses in yield quality.

Intelligent data analysis for conceiving an advisory growth system for tomatoes using connected fruit dendrometers and micro-climate measures in a greenhouse
Konferenz

Najdenovska Elena, Dutoit Fabien, Theresa Dunkel, Robert Whittaker, Cédric Camps, Raileanu Laura Elena

12th International Conference on Data Science, Technology and Application (DATA 2023), 11.07.2023 - 13.07.2023, Rome, Italy

2022

Point-of-care device for assessing male fertility in animals through measurement of sperm concentration and motility
Konferenz ArODES

Elena Najdenovska, Fabien Dutoit, Loris Gomez Baisac, Yulia Karlova, Alexandre Karlov, Adrien Roux, Olivier Cuisenaire, Laura Elena Raileanu

Reproduction in Domestic Animals ; Proceedings of the 25th Annual Conference of the European Society for Domestic Animal Reproduction (ESDAR)

Link zur Konferenz

Assessment of the universality of the electrophysiological signal acquired from tomatoes and eggplants
Konferenz ArODES

Elena Najdenovska, Fabien Dutoit, G. Carron, Daniel Tran, Carrol Plummer, Nigel Wallbridge, Cédric Camps, Laura Elena Raileanu

ISHS Acta Horticulturae 1360

Link zur Konferenz

Zusammenfassung:

The electrical signaling system in plants represents the most efficient means for rapidly transmitting information about changes in the environment to all plant parts. Recent studies have shown that the application of machine learning techniques to the electrophysiological signal acquired on tomato plants growing under typical production conditions enables highly accurate detection of stress in plants due to either drought, nutrient deficiency, or pest attack. To better understand how specific are the acquired learnings to tomato plants only, this study aims to explore the extent of the universality of the electrophysiological signal from tomatoes and eggplants. To this end, we modeled the drought response in both tomato and eggplants individually, using recordings from 34 plants from each crop, and evaluated the performance of the classification models trained on data from one crop to the data from the other crop. Different features appear as the most discriminative for each crop. Therefore, several models were taken in this analysis, namely those trained with: i) all extracted features, ii) the most discriminative groups of features for the tomatoes, iii) the most discriminative groups of features for the eggplants, and iv) the union of the most discriminative groups of features for both crops. The obtained findings showed that the models built on data from one crop are able to predict the plant state of the other crop if they are trained with the set of features enclosing the most discriminative ones for the crop on which the model is being evaluated. Such findings imply some similarities in the electrophysiological signals acquired from these two crops with a certain level of crop specificity indicated by the dissimilarities between the discriminatory information for a specific stressor.

Plant electrophysiology for smart irrigation management of greenhouse
Konferenz ArODES

Sandra Anselmo, Gil Carron, Thomas Meacham, Elena Najdenovska, Fabien Dutoit, Laura Elena Raileanu, Nigel Wallbridge, Carrol Plummer, Cédric Camps, Daniel Tran

Proceedings of the XXXI International Horticultural Congress (IHC2022): International Symposium on Water: a Worldwide Challenge for Horticulture! Acta Horticulturae

Link zur Konferenz

Zusammenfassung:

Monitoring crop health is a daily routine for growers and farmers to manage and respond effectively and in a timely way to abiotic and biotic challenges, thus preventing crop loss and ensuring quality production. Digital technology allows remote sensing in real-time for precision agriculture. Many sensors are now deployed in the field to measure environmental factors such as weather conditions, soil conditions, insect populations, but sensors that directly target a plant’s physiological state are scarce. Recent advances in plant electrophysiology allow real-time measurement of electrical signals from plants in greenhouses under typical production conditions. Combined with machine learning techniques, electrophysiology can accurately predict physiological plant state modifications due to drought or nutrient deficiencies. Here, we have investigated the ability of an electrophysiology sensor to support real-time crop supervision and manage precision irrigation based on plant demand/needs. To address this aspect, an automated irrigation set-up has been developed and deployed in a real working environment, e.g., tomato soilless culture. Based on real-time monitoring of electrical signals, the irrigation system is turned on/off via a set of relay controllers according to a drought-prediction model applied in real-time via a single board computer, namely a Raspberry Pi. Different algorithms have been evaluated with a comparison between i) conventional greenhouse irrigation system vs. ii) electrophysiology-driven automated irrigation. We found that irrigation volumes provided to the crop by electrophysiology-driven system were similar to the control. A similar behaviour was also observed for the drainage. In addition, fruit quality parameters (°Brix, acidity, firmness) and yield were not affected. Measuring crop water status in real-time using plant electrophysiology would allow precision irrigation management and therefore improve resource management for sustainable agriculture.

System Interpreting Electrophysiology Networks in Agricultural crops : the drought case
Konferenz

Gil Carron, Najdenovska Elena, Dutoit Fabien, Mazza Marco, Raileanu Laura Elena, Nigel Wallbridge, Carrol Plummer, Cédric Camps, Daniel Tran

International Horticultural Congress 2022, 14.08.2022 - 20.08.2022, Angers, France

Link zur Konferenz

Plant Electrophysiology for Smart Greenhouse Irrigation Management
Konferenz

Sandra Anselmo, Gil Carron, Najdenovska Elena, Dutoit Fabien, Thomas Meacham, Raileanu Laura Elena, Nigel Wallbridge, Carrol Plummer, Cédric Camps, Daniel Tran

International Horticultural Congress 2022, 14.08.2022 - 20.08.2022, Angers, France

Link zur Konferenz

Point-of-Care Sperm Concentration and Motility Measurements Using a Portable Acquisition and Processing Device
Konferenz

Cuisenaire Olivier, Najdenovska Elena, Dutoit Fabien, Medwed Gregory, Gomez Baisac Loris, Yulia Karlova, Alexandre Karlov, Roux Adrien, Raileanu Laura Elena

44th International Engineering in Medicine and Biology Conference - IEEE Engineering in Medicine and Biology Society, 11.07.2022 - 15.07.2022, Glasgow, UK

Link zur Konferenz

2021

Towards a sustainable agriculture by using plant electrophysiology
Konferenz ArODES

Cédric Camps, Lilia Castro Nicolli, Fabien Dutoit, Andrzej Kurenda, Marco Mazza, Elena Najdenovska, Carrol Plumer, Laura Elena Raileanu, Silvia Schintke, Daniel Tran, Nigel Wallbridge

Proceedings of FTAL Conference 2021 - Sustainable smart cities and regions, 28-29 October 2021, Lugano, Switzerland

Link zur Konferenz

Zusammenfassung:

With the aim of providing a tool to help optimize crop yields and increase agricultural sustainability, the main purpose of this work is to design a portable sensor that is able to both acquire the plant electrical response in regular production conditions and identitfy the plant status using machine learning algorithms by exploiting the information existing in the acquired signal.

Portable tool for analyzing male fertility based on the measurement of sperm concentration and motility
Konferenz ArODES

Loris Gomez Baisac, Laetitia Nikles, Elena Najdenovska, Fabien Dutoit, Yulia Karlova, Alexandre Karlov, Olivier Cuisenaire, Laura Elena Raileanu, Adrien Roux

Proceedings of the Swiss Symposium Point-of-Care Diagnostics 2021

Link zur Konferenz

Plant electrocardiogram :
Konferenz ArODES
machine learning for smart and sustainable irrigation

Dniel Tran, Elena Najdenovska, Fabien Dutoit, Laura Elena Raileanu, Nigel Wallbridge, Carrol Plummer, Cédric Camps

Proceedings of 4th International Symposium on Horticulture in Europe, 8-11 March 2021, Virtual symposium

Link zur Konferenz

2020

Portable tool for analyzing male fertility based on the measurement of sperm concentration and motility
Konferenz ArODES

Tatiana Nogueira, Loris Gomez Baisac, Elena Najdenovska, Fabien Dutoit, Yulia Karlova, Alexandre Karlov, Olivier Cuisenaire, Laura Elena Raileanu, Adrien Roux

Swiss Symposium in Point-of-Care Diagnostics, 29 october 2020, Visp, Switzerland

Link zur Konferenz

2019

Insights of plant electrophysiology :
Konferenz ArODES
using signal processing techniques and machine learning algorithms to associate tomatoes reaction to external stimuli

Elena Najdenovksa, Fabien Dutoit, Daniel Tran, Carrol Plummer, Nigel Wallbridge, Marco Mazza, Cédric Camps, Laura Elena Raileanu

Proceedings of ROeS: 31st Conference of the International Biometric Society of the Austro-Swiss Region, 9-12 September 2019, Lausanne, Switzerland

Link zur Konferenz

Errungenschaften

2024

Apparatus and method for assessing a characteristic of a plant

 2024 ; Brevet

Collaborateurs: Raileanu Laura Elena , Dutoit Fabien , Mazza Marco

Link zur Errungenschaft

US 12,039,417 B2

Appareil et procédé pour évaluer une caractéristique d'une plante

 2024 ; Brevet

Collaborateurs: Raileanu Laura Elena , Dutoit Fabien , Mazza Marco

Link zur Errungenschaft

European Patent Office - EP 3 968 113B1

2022

Apparatus and method for assessing a characteristic of a plant

 2022 ; Brevet

Collaborateurs: Raileanu Laura Elena , Dutoit Fabien , Mazza Marco

Link zur Errungenschaft

GB 2582547 B - Granted 10.08.2022

Medien und Kommunikation
Kontaktieren Sie uns
Folgen Sie der HES-SO
linkedin instagram facebook twitter youtube rss
univ-unita.eu www.eua.be swissuniversities.ch
Rechtliche Hinweise
© 2021 - HES-SO.

HES-SO Rectorat