Andmebaasi logo

Sirvi Autor "Banhazi, T." järgi

Nüüd näidatakse 1 - 2 2
  • Pisipilt
    Kirje
    Sub-clinical respiratory infection identified on farms by monitoring weight changes of pigs with the Weight-Detect instrument
    (Estonian University of Life Sciences, 2025) Banhazi, T.; Dunn, M.; Banhazi, A.; Reixach, J.; Ramon-Perez, A.; Llonch, P.; Maselyne, J.
    The essential task of growth rate monitoring of pigs is usually undertaken on farms using electronic scales, but new technologies are now available to continuously monitor the weight of pigs. One of these systems (Weight-Detect, WD, PLF Agritech, Brisbane, Australia) has been introduced on a commercial pig farm in Spain as part of the EU funded aWISH project to (1) assess the applicability of the technology and (2) use this information to assess the general welfare status of pigs. The WD unit was installed in early 2024 and manual weight recordings were undertaken periodically using an electronic scale to validate the WD system. In terms of absolute values, the manual measurements indicated that the WD system was able to predict the average pen weight of the pigs with 1.7% (2.0 kg) precision. More importantly, this case study demonstrated that the WD unit was able to detect weight reduction in pigs six days before the clinical signs of a respiratory disease infection were noticed. According to the WD measurements the study pigs achieved an average daily gain (ADG) of 882 g d-1 between the 20/03/24 and 16/04/2024. However, between the 17/4/2024 and 30/04/2024 their ADG dropped dramatically to 286 g d-1. The animals were diagnosed with respiratory disease on the 22/04/24, six days after the dramatic reduction in ADG was recorded by the WD system. This period of ADG stagnation has caused an approximate 14-day delay in reaching the desired slaughter weight, (approx. 130 kg), potentially creating significant financial losses for the producer. After the 1/05/24 pigs recovered and achieved an ADG of 645 g d-1 until their last recorded weighing day on the 20/5/24. These results highlight the WD system’s ability to alert livestock managers about impending health problems before clinical signs appear, so appropriate mitigation measures can be implemented to reduce the negative impacts on welfare and production performance.
  • Pisipilt
    Kirje
    Using machine learning techniques to assess the technology adoption readiness levels of livestock producers
    (Estonian University of Life Sciences, 2025) Mallinger, K.; Corpaci, L.; Goldenits, G.; Neubauer, T.; Tikász, I.E.; Banhazi, T.
    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.