Machine learning applied to agriculture optimises processes and land use, analyses harvest data and improves the precision of agricultural machinery. And that's just the beginning.
Jerome Treboux, a doctoral student at the Institute of Information Systems at the HES-SO Valais-Wallis in Sierre (Switzerland), presented his work in this field at this year's GIoTS conference, which was held virtually.
His paper "Towards Retraining of Machine Learning Algorithms: An Efficiency Analysis Applied to Smart Agriculture" compares the efficiency of machine learning algorithms to detect an object in an image. The experimental set-up shows that a properly tuned Random Forest is equal to or better than the Deep Learning approach and increases the speed of the relearning process by a factor of about 400.