Phenotyping Alfalfa (Medicago sativa L.) Root Structure Architecture via Integrating Confident Machine Learning with ResNet-18
Brandon J. Weihs, Zhou Tang, Zezhong Tian, D. Jo Heuschele, Aftab Siddique, Thomas H Terrill, Zhou Zhang, Larry M. York, Zhiwu Zhang, Zhanyou Xu
Abstract
ResNet-18 DNN prediction accuracies of alfalfa RSA image labels are increased when CL and RL are employed. By increasing the dataset to reduce overfitting while concurrently finding and correcting image label errors, it is demonstrated here that accuracy increases by as much as ~11% to 13% can be achieved with semi-automated, computer-assisted preprocessing and data cleaning (CL/RL).
Topics & Concepts
Medicago sativaRoot (linguistics)ArchitectureResidual neural networkComputer scienceArtificial intelligenceBiologyNatural language processingBotanyDeep learningGeographyLinguisticsPhilosophyArchaeologySmart Agriculture and AIData Mining Algorithms and ApplicationsGene expression and cancer classification