Three-dimensional(3D)single molecule localization microscopy(SMLM)plays an important role in biomedical applications,but its data processing is very complicated.Deep learning is a potential tool to solve this problem....Three-dimensional(3D)single molecule localization microscopy(SMLM)plays an important role in biomedical applications,but its data processing is very complicated.Deep learning is a potential tool to solve this problem.As the state of art 3D super-resolution localization algorithm based on deep learning,FD-DeepLoc algorithm reported recently still has a gap with the expected goal of online image processing,even though it has greatly improved the data processing throughput.In this paper,a new algorithm Lite-FD-DeepLoc is developed on the basis of FD-DeepLoc algorithm to meet the online image processing requirements of 3D SMLM.This new algorithm uses the feature compression method to reduce the parameters of the model,and combines it with pipeline programming to accelerate the inference process of the deep learning model.The simulated data processing results show that the image processing speed of Lite-FD-DeepLoc is about twice as fast as that of FD-DeepLoc with a slight decrease in localization accuracy,which can realize real-time processing of 256×256 pixels size images.The results of biological experimental data processing imply that Lite-FD-DeepLoc can successfully analyze the data based on astigmatism and saddle point engineering,and the global resolution of the reconstructed image is equivalent to or even better than FD-DeepLoc algorithm.展开更多
Correction to:J.Iron Steel Res.Int.https://doi.org/10.1007/s42243-025-01545-x The publication of this article unfortunately contained mistakes.Equation(14)was not correct.The corrected equation is given below.
As a critical component of the in situ stress state,determination of the minimum horizontal principal stress plays a significant role in both geotechnical and petroleum engineering.To this end,a gene expression progra...As a critical component of the in situ stress state,determination of the minimum horizontal principal stress plays a significant role in both geotechnical and petroleum engineering.To this end,a gene expression programming(GEP)algorithm-based model,in which the data of borehole breakout size,vertical principal stress,and rock strength characteristics are used as the inputs,is proposed to predict the minimum horizontal principal stress.Seventy-nine(79)samples with seven features are collected to construct the minimum horizontal principal stress dataset used for training models.Twenty-four(24)GEP model hyperparameter sets were configured to explore the key parameter combinations among the inputs and their potential relationships with the minimum horizontal principal stresses.Model performance was evaluated using root mean squared error(RMSE),mean absolute error(MAE),mean absolute percentage error(MAPE),and coefficient of determination(R^(2)).By comparing predictive performance and parameter composition,two models were selected from 24 GEP models that demonstrated excellent predictive performance and simpler parameter composition.Compared with prevalent models,the results indicate that the two selected GEP models have better performance on the test set(R^(2)=0.9568 and 0.9621).Additionally,the results conducted by SHapley Additive exPlanations(SHAP)sensitivity analysis and Local Interpretable Model-agnostic Explanations(LIME)demonstrate that the vertical principal stress is the most influential parameter in both GEP models.The two GEP models have simple parameter compositions as well as stable and excellent prediction performance,which is a viable method for predicting the minimum horizontal principal stresses.展开更多
基金supported by the Start-up Fund from Hainan University(No.KYQD(ZR)-20077)。
文摘Three-dimensional(3D)single molecule localization microscopy(SMLM)plays an important role in biomedical applications,but its data processing is very complicated.Deep learning is a potential tool to solve this problem.As the state of art 3D super-resolution localization algorithm based on deep learning,FD-DeepLoc algorithm reported recently still has a gap with the expected goal of online image processing,even though it has greatly improved the data processing throughput.In this paper,a new algorithm Lite-FD-DeepLoc is developed on the basis of FD-DeepLoc algorithm to meet the online image processing requirements of 3D SMLM.This new algorithm uses the feature compression method to reduce the parameters of the model,and combines it with pipeline programming to accelerate the inference process of the deep learning model.The simulated data processing results show that the image processing speed of Lite-FD-DeepLoc is about twice as fast as that of FD-DeepLoc with a slight decrease in localization accuracy,which can realize real-time processing of 256×256 pixels size images.The results of biological experimental data processing imply that Lite-FD-DeepLoc can successfully analyze the data based on astigmatism and saddle point engineering,and the global resolution of the reconstructed image is equivalent to or even better than FD-DeepLoc algorithm.
文摘Correction to:J.Iron Steel Res.Int.https://doi.org/10.1007/s42243-025-01545-x The publication of this article unfortunately contained mistakes.Equation(14)was not correct.The corrected equation is given below.
基金partially supported by the National Natural Science Foundation of China(Grant Nos.42177164 and 52474121)the Distinguished Youth Science Foundation of Hunan Province of China(Grant No.2022JJ10073).
文摘As a critical component of the in situ stress state,determination of the minimum horizontal principal stress plays a significant role in both geotechnical and petroleum engineering.To this end,a gene expression programming(GEP)algorithm-based model,in which the data of borehole breakout size,vertical principal stress,and rock strength characteristics are used as the inputs,is proposed to predict the minimum horizontal principal stress.Seventy-nine(79)samples with seven features are collected to construct the minimum horizontal principal stress dataset used for training models.Twenty-four(24)GEP model hyperparameter sets were configured to explore the key parameter combinations among the inputs and their potential relationships with the minimum horizontal principal stresses.Model performance was evaluated using root mean squared error(RMSE),mean absolute error(MAE),mean absolute percentage error(MAPE),and coefficient of determination(R^(2)).By comparing predictive performance and parameter composition,two models were selected from 24 GEP models that demonstrated excellent predictive performance and simpler parameter composition.Compared with prevalent models,the results indicate that the two selected GEP models have better performance on the test set(R^(2)=0.9568 and 0.9621).Additionally,the results conducted by SHapley Additive exPlanations(SHAP)sensitivity analysis and Local Interpretable Model-agnostic Explanations(LIME)demonstrate that the vertical principal stress is the most influential parameter in both GEP models.The two GEP models have simple parameter compositions as well as stable and excellent prediction performance,which is a viable method for predicting the minimum horizontal principal stresses.
