Disjoint sampling is critical for rigorous and unbiased evaluation of state-of-the-art(SOTA)models e.g.,Attention Graph and Vision Transformer.When training,validation,and test sets overlap or share data,it introduces...Disjoint sampling is critical for rigorous and unbiased evaluation of state-of-the-art(SOTA)models e.g.,Attention Graph and Vision Transformer.When training,validation,and test sets overlap or share data,it introduces a bias that inflates performance metrics and prevents accurate assessment of a model’s true ability to generalize to new examples.This paper presents an innovative disjoint sampling approach for training SOTA models for the Hyperspectral Image Classification(HSIC).By separating training,validation,and test data without overlap,the proposed method facilitates a fairer evaluation of how well a model can classify pixels it was not exposed to during training or validation.Experiments demonstrate the approach significantly improves a model’s generalization compared to alternatives that include training and validation data in test data(A trivial approach involves testing the model on the entire Hyperspectral dataset to generate the ground truth maps.This approach produces higher accuracy but ultimately results in low generalization performance).Disjoint sampling eliminates data leakage between sets and provides reliable metrics for benchmarking progress in HSIC.Disjoint sampling is critical for advancing SOTA models and their real-world application to large-scale land mapping with Hyperspectral sensors.Overall,with the disjoint test set,the performance of the deep models achieves 96.36%accuracy on Indian Pines data,99.73%on Pavia University data,98.29%on University of Houston data,99.43%on Botswana data,and 99.88%on Salinas data.展开更多
Graph neural networks have been shown to be very effective in utilizing pairwise relationships across samples.Recently,there have been several successful proposals to generalize graph neural networks to hypergraph neu...Graph neural networks have been shown to be very effective in utilizing pairwise relationships across samples.Recently,there have been several successful proposals to generalize graph neural networks to hypergraph neural networks to exploit more com-plex relationships.In particular,the hypergraph collaborative networks yield superior results compared to other hypergraph neural net-works for various semi-supervised learning tasks.The collaborative network can provide high quality vertex embeddings and hyperedge embeddings together by formulating them as a joint optimization problem and by using their consistency in reconstructing the given hy-pergraph.In this paper,we aim to establish the algorithmic stability of the core layer of the collaborative network and provide generaliz--ation guarantees.The analysis sheds light on the design of hypergraph filters in collaborative networks,for instance,how the data and hypergraph filters should be scaled to achieve uniform stability of the learning process.Some experimental results on real-world datasets are presented to illustrate the theory.展开更多
Achieving precise and scalable solar potential estimation in urban settings is challenging due to the presence of a wide variety of obstructions.To address this issue,we developed a novel urban solar potential modelin...Achieving precise and scalable solar potential estimation in urban settings is challenging due to the presence of a wide variety of obstructions.To address this issue,we developed a novel urban solar potential modeling method based on an improved 2-phase daylight model.Utilizing a dynamic graph convolutional neural network semantic segmentation model to process urban point cloud data,our method distinguishes between different types of solar obstructions,assigning specific simulation hyperparameters accordingly.Demonstrated through experiments,our method significantly outperforms traditional models by avoiding the underestimation of shading impacts—by up to 60%for monthly solar irradiation potential and 40%for annual PV yield potential.Moreover,our method accurately accounts for complex solar transmission through tree canopies,avoiding underestimation of PV energy potential by up to 7%compared to its predecessor(Pyrano 1.0).These improvements offer substantial benefits for managing PV shading risks,configuring PV systems,and managing renewable resources,especially in urban areas with complex geometries and dynamically changing shading conditions.Our findings underscore the method’s potential to enhance decision-making in sustainable urban development and renewable energy integration.展开更多
基金the Researchers Supporting Project number(RSPD2024R848),King Saud University,Riyadh,Saudi Arabia.
文摘Disjoint sampling is critical for rigorous and unbiased evaluation of state-of-the-art(SOTA)models e.g.,Attention Graph and Vision Transformer.When training,validation,and test sets overlap or share data,it introduces a bias that inflates performance metrics and prevents accurate assessment of a model’s true ability to generalize to new examples.This paper presents an innovative disjoint sampling approach for training SOTA models for the Hyperspectral Image Classification(HSIC).By separating training,validation,and test data without overlap,the proposed method facilitates a fairer evaluation of how well a model can classify pixels it was not exposed to during training or validation.Experiments demonstrate the approach significantly improves a model’s generalization compared to alternatives that include training and validation data in test data(A trivial approach involves testing the model on the entire Hyperspectral dataset to generate the ground truth maps.This approach produces higher accuracy but ultimately results in low generalization performance).Disjoint sampling eliminates data leakage between sets and provides reliable metrics for benchmarking progress in HSIC.Disjoint sampling is critical for advancing SOTA models and their real-world application to large-scale land mapping with Hyperspectral sensors.Overall,with the disjoint test set,the performance of the deep models achieves 96.36%accuracy on Indian Pines data,99.73%on Pavia University data,98.29%on University of Houston data,99.43%on Botswana data,and 99.88%on Salinas data.
基金Ng was supported in part by Hong Kong Research Grant Council General Research Fund(GRF),China(Nos.12300218,12300519,117201020,17300021,CRF C1013-21GF,C7004-21GF and Joint NSFC-RGC NHKU76921)Wu is supported by National Natural Science Foundation of China(No.62206111)+3 种基金Young Talent Support Project of Guangzhou Association for Science and Technology,China(No.QT-2023-017)Guangzhou Basic and Applied Basic Research Foundation,China(No.2023A04J1058)Fundamental Research Funds for the Central Universities,China(No.21622326)China Postdoctoral Science Foundation(No.2022M721343).
文摘Graph neural networks have been shown to be very effective in utilizing pairwise relationships across samples.Recently,there have been several successful proposals to generalize graph neural networks to hypergraph neural networks to exploit more com-plex relationships.In particular,the hypergraph collaborative networks yield superior results compared to other hypergraph neural net-works for various semi-supervised learning tasks.The collaborative network can provide high quality vertex embeddings and hyperedge embeddings together by formulating them as a joint optimization problem and by using their consistency in reconstructing the given hy-pergraph.In this paper,we aim to establish the algorithmic stability of the core layer of the collaborative network and provide generaliz--ation guarantees.The analysis sheds light on the design of hypergraph filters in collaborative networks,for instance,how the data and hypergraph filters should be scaled to achieve uniform stability of the learning process.Some experimental results on real-world datasets are presented to illustrate the theory.
基金sponsored by the scholarship from China Scholarship Council(CSC,202107720038).
文摘Achieving precise and scalable solar potential estimation in urban settings is challenging due to the presence of a wide variety of obstructions.To address this issue,we developed a novel urban solar potential modeling method based on an improved 2-phase daylight model.Utilizing a dynamic graph convolutional neural network semantic segmentation model to process urban point cloud data,our method distinguishes between different types of solar obstructions,assigning specific simulation hyperparameters accordingly.Demonstrated through experiments,our method significantly outperforms traditional models by avoiding the underestimation of shading impacts—by up to 60%for monthly solar irradiation potential and 40%for annual PV yield potential.Moreover,our method accurately accounts for complex solar transmission through tree canopies,avoiding underestimation of PV energy potential by up to 7%compared to its predecessor(Pyrano 1.0).These improvements offer substantial benefits for managing PV shading risks,configuring PV systems,and managing renewable resources,especially in urban areas with complex geometries and dynamically changing shading conditions.Our findings underscore the method’s potential to enhance decision-making in sustainable urban development and renewable energy integration.
