Trapanese, Lucia (2024) High-tech Farming: Study and Application of Machine Learning Techniques for Improving Production Efficiency in Livestock. [Tesi di dottorato]
![[thumbnail of PhDThesis_Lucia_Trapanese_12_12_Fedoa.pdf]](https://www.fedoa.unina.it/style/images/fileicons/other.png "PhDThesis_Lucia_Trapanese_12_12_Fedoa.pdf") |
Documento PDF
PhDThesis_Lucia_Trapanese_12_12_Fedoa.pdf Visibile a [TBR] Amministratori dell'archivio Download (4MB) | Richiedi una copia |
| Tipologia del documento: | Tesi di dottorato |
|---|---|
| Lingua: | English |
| Titolo: | High-tech Farming: Study and Application of Machine Learning Techniques for Improving Production Efficiency in Livestock |
| Autori: | Autore Email Trapanese, Lucia lucia.trapanese2@unina.it |
| Data: | 12 Dicembre 2024 |
| Numero di pagine: | 113 |
| Istituzione: | Università degli Studi di Napoli Federico II |
| Dipartimento: | Biologia |
| Dottorato: | Intelligenza artificiale Area Agrifood e ambiente |
| Ciclo di dottorato: | 37 |
| Coordinatore del Corso di dottorato: | nome email Loreto, Francesco francesco.loreto@unina.it |
| Tutor: | nome email Pasquino, Nicola [non definito] Salzano, Angela [non definito] |
| Data: | 12 Dicembre 2024 |
| Numero di pagine: | 113 |
| Parole chiave: | Precision Livestock Farming, Dairy, Machine Learning, Milk |
| Settori scientifico-disciplinari del MIUR: | Area 07 - Scienze agrarie e veterinarie > AGR/19 - Zootecnica speciale Area 09 - Ingegneria industriale e dell'informazione > ING-INF/03 - Telecomunicazioni |
| Informazioni aggiuntive: | Dichiaro di appartenere al 37°ciclo di dottorato |
| Depositato il: | 27 Ott 2025 15:12 |
| Ultima modifica: | 12 Ago 2026 05:38 |
| URI: | https://www.fedoa.unina.it/id/eprint/16534 |
Abstract
The livestock sector faces numerous challenges, including the need to mitigate greenhouse gas emissions and meet the increasing demand for animal-based foods. To address these issues, modernization of breeding techniques is essential for enhancing the overall efficiency of production systems. Additionally, recent trends indicate that consumers are increasingly choosing products based on factors such as raw material quality, animal welfare, and the healthiness of processed foods. Achieving these objectives requires a multi-level approach. Since the 1970s, farmers, veterinarians, and technicians have recognized the benefits of adopting an automated and data-driven approach to improve production and enhance their quality of life. One of the early innovations was the use of individual electronic milk meters for cows, which automatically measured milk yield. The introduction of automatic milking systems in the 2000s further revolutionized the dairy sector, alongside the development of specific devices for recognizing oestrus, animal behaviour and diseases. This progress coincided with significant advancements in engineering, making sensors, devices, and computational units more powerful and affordable. Moreover, the rise of artificial intelligence techniques around 2000 contributed to the widespread dissemination of knowledge in the field. Finally, in 2014, Berckmans defined PLF as the continuous automated real-time monitoring of livestock production, reproduction, health, welfare, and environmental impact (Berckmans, 2014). With the PLF approach, it is now possible to continuously monitor the environment, barn conditions, animal Behaviour, welfare, and production levels.
Downloads
Downloads per month over past year
Actions (login required)
 |
Modifica documento |
