Accurate fruit size estimation is crucial for plant phenotyping,as it enables precise crop management and en-hances agricultural productivity by providing essential data for growth and resource efficiency analysis.In ...Accurate fruit size estimation is crucial for plant phenotyping,as it enables precise crop management and en-hances agricultural productivity by providing essential data for growth and resource efficiency analysis.In this study,we estimated the size of on-plant oriental melons grown in a vertical cultivation system to address the challenges posed by leaf occlusion.Data augmentation was achieved using a diffusion model to generate syn-thetic leaves to cover existing fruits and create an enriched dataset.Three instance segmentation models-mask region-based convolutional neural network(CNN),Mask2Former,and detection transformer(DETR)-and six de-occlusion models derived from these architectures were implemented.These models successfully inferred both visible and occluded areas of the fruit.Notably,Amodal Mask2Former and occlusion-aware RCNN(ORCNN)achieved average precision scores of 85.92%and 85.35%,respectively.The inferred masks were used to es-timate the height and diameter of the fruit,with Amodal Mask2Former yielding a mean absolute error of 5.46 mm and 4.20 mm and a mean absolute percentage error of 4.86%and 5.33%,respectively.The results indicate enhanced performance of the transformer-based Amodal Mask2Former over CNN architectures in de-occlusion tasks and size estimation.Finally,the enhancement in de-occlusion models compared to conventional models was assessed and demonstrated across occlusion ratios ranging from 0 to 70%.However,generating synthetic datasets with occlusion ratios over 70%remains a limitation.展开更多
Social media have dramatically changed the mode of information dissemination.Various models and algorithms have been developed to model information diffusion and address the influence maximization problem in complex s...Social media have dramatically changed the mode of information dissemination.Various models and algorithms have been developed to model information diffusion and address the influence maximization problem in complex social networks.However,it appears difficult for state-of-the-art models to interpret complex and reversible real interactive networks.In this paper,we propose a novel influence diffusion model,i.e.,the Operator-Based Model(OBM),by leveraging the advantages offered from the heat diffusion based model and the agent-based model.The OBM improves the performance of simulated dissemination by considering the complex user context in the operator of the heat diffusion based model.The experiment obtains a high similarity of the OBM simulated trend to the real-world diffusion process by use of the dynamic time warping method.Furthermore,a novel influence maximization algorithm,i.e.,the Global Topical Support Greedy algorithm(GTS-Greedy algorithm),is proposed corresponding to the OBM.The experimental results demonstrate its promising performance by comparing it against other classic algorithms.展开更多
基金This work was supported by the Rural Development Administration(RDA)through the Cooperative Research Program for Agriculture Science and Technology Development[Project No.RS-2024-00440583].
文摘Accurate fruit size estimation is crucial for plant phenotyping,as it enables precise crop management and en-hances agricultural productivity by providing essential data for growth and resource efficiency analysis.In this study,we estimated the size of on-plant oriental melons grown in a vertical cultivation system to address the challenges posed by leaf occlusion.Data augmentation was achieved using a diffusion model to generate syn-thetic leaves to cover existing fruits and create an enriched dataset.Three instance segmentation models-mask region-based convolutional neural network(CNN),Mask2Former,and detection transformer(DETR)-and six de-occlusion models derived from these architectures were implemented.These models successfully inferred both visible and occluded areas of the fruit.Notably,Amodal Mask2Former and occlusion-aware RCNN(ORCNN)achieved average precision scores of 85.92%and 85.35%,respectively.The inferred masks were used to es-timate the height and diameter of the fruit,with Amodal Mask2Former yielding a mean absolute error of 5.46 mm and 4.20 mm and a mean absolute percentage error of 4.86%and 5.33%,respectively.The results indicate enhanced performance of the transformer-based Amodal Mask2Former over CNN architectures in de-occlusion tasks and size estimation.Finally,the enhancement in de-occlusion models compared to conventional models was assessed and demonstrated across occlusion ratios ranging from 0 to 70%.However,generating synthetic datasets with occlusion ratios over 70%remains a limitation.
文摘Social media have dramatically changed the mode of information dissemination.Various models and algorithms have been developed to model information diffusion and address the influence maximization problem in complex social networks.However,it appears difficult for state-of-the-art models to interpret complex and reversible real interactive networks.In this paper,we propose a novel influence diffusion model,i.e.,the Operator-Based Model(OBM),by leveraging the advantages offered from the heat diffusion based model and the agent-based model.The OBM improves the performance of simulated dissemination by considering the complex user context in the operator of the heat diffusion based model.The experiment obtains a high similarity of the OBM simulated trend to the real-world diffusion process by use of the dynamic time warping method.Furthermore,a novel influence maximization algorithm,i.e.,the Global Topical Support Greedy algorithm(GTS-Greedy algorithm),is proposed corresponding to the OBM.The experimental results demonstrate its promising performance by comparing it against other classic algorithms.
