首页|Researcher from Federal Rural University of Pernambuco Reports Details of New St udies and Findings in the Area of Machine Learning (UAV-Based Classification of Intercropped Forage Cactus: A Comparison of RGB and Multispectral Sample Spaces ...)
Researcher from Federal Rural University of Pernambuco Reports Details of New St udies and Findings in the Area of Machine Learning (UAV-Based Classification of Intercropped Forage Cactus: A Comparison of RGB and Multispectral Sample Spaces ...)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Investigators discuss new findings in artificial intelligence. According to news reporting originating from Recife, Brazil, by Ne wsRx correspondents, research stated, "Precision agriculture requires accurate m ethods for classifying crops and soil cover in agricultural production areas." Financial supporters for this research include Cnpq; Facepe; Ministry of Integra tion And Regional Development; Capes-print/ufrpe; Foundation For Science And Tec hnology, I.P.. The news editors obtained a quote from the research from Federal Rural Universit y of Pernambuco: "The study aims to evaluate three machine learning-based classi fiers to identify intercropped forage cactus cultivation in irrigated areas usin g Unmanned Aerial Vehicles (UAV). It conducted a comparative analysis between mu ltispectral and visible Red-Green-Blue (RGB) sampling, followed by the efficienc y analysis of Gaussian Mixture Model (GMM), K-Nearest Neighbors (KNN), and Rando m Forest (RF) algorithms. The classification targets included exposed soil, mulc hing soil cover, developed and undeveloped forage cactus, moringa, and gliricidi a in the Brazilian semiarid. The results indicated that the KNN and RF algorithm s outperformed other methods, showing no significant differences according to th e kappa index for both Multispectral and RGB sample spaces. In contrast, the GMM showed lower performance, with kappa index values of 0.82 and 0.78, compared to RF 0.86 and 0.82, and KNN 0.86 and 0.82. The KNN and RF algorithms performed we ll, with individual accuracy rates above 85% for both sample space s."
Federal Rural University of PernambucoRecifeBrazilSouth AmericaAlgorithmsCyborgsEmerging TechnologiesMachi ne Learning
NETL
NSTL
