Internet of things enabled deep learning methods using unmanned aerial vehicles enabled integrated farm management

Area of Science:

• Agricultural Technology
• Artificial Intelligence in Agriculture
• Livestock Management Systems

Background:

• Smart livestock farming utilizes digital technologies for increased profitability, efficiency, and ecological benefits.
• Precision livestock farming, focusing on individual animal monitoring, is a key advancement.
• Challenges include climate change, biodiversity loss, and the need for continuous monitoring.

Purpose of the Study:

• To introduce and evaluate the Unmanned Aerial Vehicles enabled Integrated Farm Management (UAV-IFM) system.
• To enhance smart livestock farming practices through advanced technology integration.
• To improve the assessment process for wider adoption of smart livestock farming.

Main Methods:

• Integration of Unmanned Aerial Vehicles (UAVs), robots, remote sensors, and computer imagery.
• Application of Deep Learning (DL) algorithms for data analysis and prediction.
• Development of the UAV-IFM system for comprehensive farm management.

Main Results:

• UAV-IFM provides safe and reliable livestock tracking from farm to fork.
• The system aids in detecting and containing disease outbreaks, preventing financial losses.
• Experimental analysis shows UAV-IFM outperforms traditional smart livestock farming in efficiency, performance, accuracy, and prediction.

Conclusions:

• UAV-IFM correctly forecasts and verifies smart livestock farming management.
• The system supports wider adoption of smart livestock farming by improving assessment processes.
• UAV-IFM offers growth-supportive assistance to farmers, enhancing overall farm operations.