Tag Archives: machine learning

1147-1168 K. Mallinger, L. Corpaci, G. Goldenits, T. Neubauer, I.E. Tikász and T. Banhazi
Using machine learning techniques to assess the technology adoption readiness levels of livestock producers
Abstract |

Full text PDF (1,013 KB)

Using machine learning techniques to assess the technology adoption readiness levels of livestock producers

K. Mallinger¹²*, L. Corpaci², G. Goldenits², T. Neubauer³, I.E. Tikász⁴ and T. Banhazi⁵⁶

¹SBA Research, Complexity and Resilience Research Group, Floragasse 7/5,
AT1040 Vienna, Austria
²University of Vienna, Kolingasse 14–16, AT1090 Vienna, Austria
³TU Wien, Institute of Information Systems Engineering - Data Science, Floragasse 9-11, AT1040 Vieanna, Austria
⁴Institute of Agricultural Economics, Nonprofit Kft., Zsil u. 3–5, HU1093 Budapest, Hungary
⁵AgHiTech Kft, Kisbacom utca 1, Budapest, Hungary, 110, Budapest, Hungary
⁶Wroclaw University of Environmental and Life Sciences, Norwida Str. 25,
PL50-375 Wroclaw, Poland
*Correspondence: kmallinger@sba-research.org

Abstract:

Technology adoption in agriculture, particularly in precision livestock farming (PLF), is often hindered by a range of barriers such as high investment costs, limited infrastructure, and uncertainty regarding the reliability and integration of new systems. Understanding these barriers is crucial for promoting the uptake of innovations that enhance sustainability and productivity. This study investigates technology adoption barriers in precision livestock farming to support sustainable agricultural development. A survey of 266 farms across several European countries and Israel was conducted to assess existing infrastructure and farmers’ attitudes toward smart farming technologies. Using machine learning techniques, farmers were grouped into two clusters representing different levels of technological readiness. The study identified the most prominent factors influencing technology adoption, including the presence of smart technologies on-site, market accessibility, cost efficiency, and the ability to manage labor shortages. A Logistic Regression model further demonstrated high predictive accuracy for farmers’ technological readiness based on these characteristics. These findings provide valuable insights into the main drivers and barriers of PLF adoption and highlight the relevance of data-driven approaches for requirement analysis and targeted policy interventions. By uncovering critical user traits and adoption barriers, this study offers structured guidance for policymakers, industry stakeholders, and researchers to foster the broader adoption of precision livestock technologies.

Key words:

cluster analysis, machine learning, precision livestock farming, survey design, technological barriers

1492-1512 M. González-Palacio, JM. García-Giraldo and L. González-Palacio
Integrating AI and sustainable materials: machine learning approaches to wood structural behavior
Abstract |

Full text PDF (1 MB)

Integrating AI and sustainable materials: machine learning approaches to wood structural behavior

M. González-Palacio¹*, JM. García-Giraldo² and L. González-Palacio³

¹Universidad de Medellín, Faculty of Engineering, Department of Computer Science,
Carrera 84 #30-65, CO 050026 Medellín, Colombia
²Universidad de Medellín, Faculty of Engineering, Department of Civil Engineering,
Carrera 84 #30-65, CO 050026 Medellín, Colombia
³Universidad EAFIT, Faculty of Engineering, Department of Computer Science, Carrera 49 N° 7 Sur - 50, CO 050022 Medellín, Colombia
*magonzalez@udemedellin.edu.co

Abstract:

Wood is a potential construction material that provides a renewable source for this crucial task compared to other classical materials, such as steel or concrete, with high carbon fingerprinting levels. This suitable material minimizes energy use and adds more sustainability to ecological consciousness. Tree planting promotes the balance of the carbon dioxide ecosystem and captures and stores greenhouse gas emissions. Wood also has peculiar characteristics in terms of its structural strength and thermal insulation, optimizing energy consumption by reducing the need for cooling or heating needs. To use this material in construction, it is mandatory to study the resistance parameters like compressive, tensile, and shear strengths, enabling it for great-span structural projects. The traditional modeling strategies used for characterizing stress-strain performances usually simplify the assumptions, overpassing the complex mechanical behavior of the wood under different physical conditions. Nonetheless, previous analyses have shown that the traditional models may exhibit significant deviations from the actual resistance parameters since they can be limited in predicting non-linear and anisotropic properties inherent in wood. To address these limitations, this study proposes using machine-learning-based regressors to predict the mechanical properties of wood. Notably, we propose Multiple Linear Regression models to preserve the model’s interpretability while preserving the ability to model the linear properties in the studied scenarios. Furthermore, we use metaheuristic models based on deep learning and ensemble methods to increase the goodness of fit of the predictions. We used an experimental campaign with a widespread type of wood characterization of different parameters under tension parallel to the grain, compression parallel and perpendicular to the grain, and shear conditions. The results showed a lower root mean square error (RMSE) and a higher determination index (R²). Preliminary results demonstrated the ability of machine-learning-based modeling to obtain more accurate and reliable mechanical behavior of renewable construction materials like wood.

Key words:

artificial neural networks, machine learning, random forest, sustainable materials

134-150 T.E.A. Mattila, E. Liski, M. Väre and R.H. Rautiainen
Diminished work ability as a contributing factor for farmer’s interest in switching to organic production
Abstract |

Full text PDF (487 KB)

Diminished work ability as a contributing factor for farmer’s interest in switching to organic production

T.E.A. Mattila¹*, E. Liski¹, M. Väre¹ and R.H. Rautiainen²

¹Natural Resources Institution Finland (‘Luke’), Latokartanonkaari 9, FI-00790 Helsinki, Finland
²University of Nebraska Medical Center, Omaha, Nebraska, 68198-4388, USA
*Correspondence: tiina.mattila@luke.fi

Abstract:

Previous studies suggest organic producers have diminished work ability, but it is unclear if this is due to pre-existing conditions or work exposures in organic production itself. The current study explored whether diminished work ability is a contributing factor to the interest in switching from conventional to organic production. The study used data from 2018, Finnish farmer questionnaire, analysed by machine learning – based approach and logistic regression modelling. Nearly half (46%) of the survey respondents (n = 2,948) had a diminished work ability score. Seventeen percent (n = 501) of the respondents reported being interested in switching to organic production. Farmers with diminished work ability had greater odds (OR 1.56, 95% CI: 1.26–1.92) for showing interest in switching. Those growing horticulture and special crops (vs. cereals) (OR 0.55) and those age 55+ years (vs. less than 35) (OR 0.51) showed less interest in switching. The interest in starting or expanding organic production was higher among those who already had an organic agreement on part of their farm (OR 5.7) and those who had other business activities on the farm (OR 1.36). In summary, this study suggests that diminished work ability predicts farmer’s interest for switching to organic production. Measures to protect the health and well-being of farmers and workers during and after switching to organic production is critically important in achieving not only policy goals to increase organic production, but also good quality of life of farmers.

Key words:

agriculture, logistic regression, machine learning, social sustainability, well-being at work

507–519 S. Kodors, G. Lacis, O. Sokolova2,V. Zhukovs, I. Apeinans and T. Bartulsons
Apple scab detection using CNN and Transfer Learning
Abstract |

Full text PDF (2 MB)

Apple scab detection using CNN and Transfer Learning

S. Kodors¹*, G. Lacis², O. Sokolova2,V. Zhukovs¹, I. Apeinans¹ and T. Bartulsons²

¹Rezekne Academy of Technologies, Faculty of Engineering, Institute of Engineering, Atbrivoshanas Str. 115, LV-4601 Rezekne, Latvia
²Institute of Horticulture, Graudu Str. 1, LV-3701 Ceriņi, Krimūnu pagasts, Dobeles novads, Latvia
*Correspondence: sergejs.kodors@rta.lv

Abstract:

The goal of smart and precise horticulture is to increase yield and product quality by simultaneous reduction of pesticide application, thereby promoting the improvement of food security. The scope of this research is apple scab detection in the early stage of development using mobile phones and artificial intelligence based on convolutional neural network (CNN) applications. The research considers data acquisition and CNN training. Two datasets were collected – with images of scab infected fruits and leaves of an apple tree. However, data acquisition is a time-consuming process and scab appearance has a probability factor. Therefore, transfer learning is an appropriate training methodology. The goal of this research was to select the most suitable dataset for transfer learning for the apple scab detection domain and to evaluate the transfer learning impact comparing it with learning from scratch. The statistical analysis confirmed the positive effect of transfer learning on CNN performance with significance level 0.05.

Key words:

agriculture., artificial intelligence, deep learning, fungus, machine learning, Malus, pathogen, precise horticulture, Venturia