U-Net因其简单高效的网络结构,已成为当前医学图像分割领域中的基准模型,在多种图像分割任务中取得了良好的效果。然而,传统U-Net在细节特征提取、跨尺度信息融合以及复杂结构识别方面仍存在一定的局限性,难以充分适应医学图像中存在的...U-Net因其简单高效的网络结构,已成为当前医学图像分割领域中的基准模型,在多种图像分割任务中取得了良好的效果。然而,传统U-Net在细节特征提取、跨尺度信息融合以及复杂结构识别方面仍存在一定的局限性,难以充分适应医学图像中存在的形变、低对比度以及多样性目标等挑战。为进一步提升分割性能,该文提出一种改进模型U-KPD(U-Net with Kolmogorov-Arnold Network and ParNet-Deformable Module)。该模型在U-Net的基础上引入科尔莫哥罗夫-阿诺德网络(Kolmogorov-Arnold Network,KAN),以增强网络对图像局部与全局特征的表达能力,同时结合ParNet-Deformable模块(PD)提升模型对关键区域的自适应建模与形变结构的捕捉能力,从而提高分割的准确性与鲁棒性。通过在CVC-ClinicDB与BUSI两个具有代表性的数据集上开展充分实验验证,结果表明,U-KPD在IoU、Dice系数以及HD95多个评估指标上均优于传统U-Net及其他主流改进模型,尤其在复杂结构、形变目标的识别精度方面表现更为优异,具有良好的通用性与应用前景。展开更多
In this study,we used the Kolmogorov-Arnold networks(KAN)model based on the Kolmogorov-Arnold representation theorem for a comprehensive and fair evaluation.We compare its performance with four other powerful classifi...In this study,we used the Kolmogorov-Arnold networks(KAN)model based on the Kolmogorov-Arnold representation theorem for a comprehensive and fair evaluation.We compare its performance with four other powerful classification models across three datasets:a simple slope binary classification dataset,an imbalanced rockburst dataset,and a highly discrete liquefaction dataset.First,a thorough review of machine-learning algorithms for geohazard assessment was conducted.Subsequently,three datasets were collected from real engineering practices,and their data structures were visualized.Bayesian optimization was then used to adjust the parameters of all models across all datasets.To ensure model interpretability,a global sensitivity analysis based on Sobol indices was performed,establishing an interpretable visual analysis of the model's decision-making process.For a fair evaluation,various metrics and repeated stratified 10-fold cross-validation were employed to comprehensively analyze the predictive results of the models.The results indicate that although the KAN model,based on the RBF kernel,achieves the expected performance on the binary classification dataset,it also performs well on imbalanced and highly discrete datasets,significantly surpassing other commonly used classification models.This demonstrated the broad application potential of the KAN model in geotechnical engineering.展开更多
在车辆行驶过程中,荷电状态(State of Charge,SOC)估算高度依赖电流测量,但电流传感器故障会导致数据缺失,进而降低SOC估算精度,为此,亟需一种能够在电流数据异常或缺失情况下仍可准确估算SOC的方法。针对此问题,提出了一种基于卷积神...在车辆行驶过程中,荷电状态(State of Charge,SOC)估算高度依赖电流测量,但电流传感器故障会导致数据缺失,进而降低SOC估算精度,为此,亟需一种能够在电流数据异常或缺失情况下仍可准确估算SOC的方法。针对此问题,提出了一种基于卷积神经网络(Convolutional Neural Networks,CNN)-长短期记忆(Long Short-Term Memory,LSTM)网络-科尔莫戈洛夫-阿诺德网络(Kolmogorov-Arnold Networks,KAN)的数据驱动方法,该方法不依赖电流数据,可以作为电流传感器失效时的替代SOC估算方案。CNN-LSTM网络-KAN模型综合利用了CNN的特征提取能力、LSTM网络的时间序列建模优势和KAN的非线性分解能力,从而实现对车辆行驶过程中SOC的估算。最终CNN-LSTM网络-KAN模型通过实车行驶数据集得到了效果验证,结果表明,所提方法对SOC的预测值与SOC真实值之间的平均绝对误差(Mean Absolute Error,MAE)为0.381,均方根误差(Root Mean Square Error,RMSE)为0.467,决定系数R2为0.980。说明所提方法在电流传感器失效情况下,仍然能够有效估算车辆的SOC。展开更多
文摘U-Net因其简单高效的网络结构,已成为当前医学图像分割领域中的基准模型,在多种图像分割任务中取得了良好的效果。然而,传统U-Net在细节特征提取、跨尺度信息融合以及复杂结构识别方面仍存在一定的局限性,难以充分适应医学图像中存在的形变、低对比度以及多样性目标等挑战。为进一步提升分割性能,该文提出一种改进模型U-KPD(U-Net with Kolmogorov-Arnold Network and ParNet-Deformable Module)。该模型在U-Net的基础上引入科尔莫哥罗夫-阿诺德网络(Kolmogorov-Arnold Network,KAN),以增强网络对图像局部与全局特征的表达能力,同时结合ParNet-Deformable模块(PD)提升模型对关键区域的自适应建模与形变结构的捕捉能力,从而提高分割的准确性与鲁棒性。通过在CVC-ClinicDB与BUSI两个具有代表性的数据集上开展充分实验验证,结果表明,U-KPD在IoU、Dice系数以及HD95多个评估指标上均优于传统U-Net及其他主流改进模型,尤其在复杂结构、形变目标的识别精度方面表现更为优异,具有良好的通用性与应用前景。
基金supported by the National Natural Science Foundation of China(Grant Nos.42107214 and 42477157).
文摘In this study,we used the Kolmogorov-Arnold networks(KAN)model based on the Kolmogorov-Arnold representation theorem for a comprehensive and fair evaluation.We compare its performance with four other powerful classification models across three datasets:a simple slope binary classification dataset,an imbalanced rockburst dataset,and a highly discrete liquefaction dataset.First,a thorough review of machine-learning algorithms for geohazard assessment was conducted.Subsequently,three datasets were collected from real engineering practices,and their data structures were visualized.Bayesian optimization was then used to adjust the parameters of all models across all datasets.To ensure model interpretability,a global sensitivity analysis based on Sobol indices was performed,establishing an interpretable visual analysis of the model's decision-making process.For a fair evaluation,various metrics and repeated stratified 10-fold cross-validation were employed to comprehensively analyze the predictive results of the models.The results indicate that although the KAN model,based on the RBF kernel,achieves the expected performance on the binary classification dataset,it also performs well on imbalanced and highly discrete datasets,significantly surpassing other commonly used classification models.This demonstrated the broad application potential of the KAN model in geotechnical engineering.
