Clinical data have shown that survival rates vary considerably among brain tumor patients,according to the type and grade of the tumor.Metabolite profiles of intact tumor tissues measured with high-resolution magic-an...Clinical data have shown that survival rates vary considerably among brain tumor patients,according to the type and grade of the tumor.Metabolite profiles of intact tumor tissues measured with high-resolution magic-angle spinning proton nuclear magnetic resonance spectroscopy (HRMAS 1H NMRS) can provide important information on tumor biology and metabolism.These metabolic fingerprints can then be used for tumor classification and grading,with great potential value for tumor diagnosis.We studied the metabolic characteristics of 30 neuroepithelial tumor biopsies,including two astrocytomas (grade I),12 astrocytomas (grade II),eight anaplastic astrocytomas (grade III),three glioblastomas (grade IV) and five medulloblastomas (grade IV) from 30 patients using HRMAS 1H NMRS.The results were correlated with pathological features using multivariate data analysis,including principal component analysis (PCA).There were significant differences in the levels of N-acetyl-aspartate (NAA),creatine,myo-inositol,glycine and lactate between tumors of different grades (P<0.05).There were also significant differences in the ratios of NAA/creatine,lactate/creatine,myo-inositol/creatine,glycine/creatine,scyllo-inositol/creatine and alanine/creatine (P<0.05).A soft independent modeling of class analogy model produced a predictive accuracy of 87% for high-grade (grade III-IV) brain tumors with a sensitivity of 87% and a specificity of 93%.HRMAS 1H NMR spectroscopy in conjunction with pattern recognition thus provides a potentially useful tool for the rapid and accurate classification of human brain tumor grades.展开更多
To solve inefficient water stress classification of spinach seedlings under complex background,this study proposed an automatic classification method for the water stress level of spinach seedlings based on the N-Mobi...To solve inefficient water stress classification of spinach seedlings under complex background,this study proposed an automatic classification method for the water stress level of spinach seedlings based on the N-MobileNetXt(NCAM+MobileNetXt)network.Firstly,this study recon-structed the Sandglass Block to effectively increase the model accuracy;secondly,this study introduced the group convolution module and a two-dimensional adaptive average pool,which can significantly compress the model parameters and enhance the model robustness separately;finally,this study innovatively proposed the Normalization-based Channel Attention Module(NCAM)to enhance the image features obviously.The experimental results showed that the classification accuracy of N-MobileNetXt model for spinach seedlings under the natural environment reached 90.35%,and the number of parameters was decreased by 66%compared with the original MobileNetXt model.The N-MobileNetXt model was superior to other net-work models such as ShuffleNet and GhostNet in terms of parameters and accuracy of identification.It can provide a theoretical basis and technical support for automatic irrigation.展开更多
Accurate and fine-scale short-term precipitation forecasting is crucial for disaster prevention,mitigation,and socioeconomic development.Currently,the direct precipitation forecasts of numerical weather prediction oft...Accurate and fine-scale short-term precipitation forecasting is crucial for disaster prevention,mitigation,and socioeconomic development.Currently,the direct precipitation forecasts of numerical weather prediction often face great challenges and correction methods are still needed to further improve the forecast accuracy.By utilizing the 500-m resolution fusion precipitation data from the Rapid-refresh Integrated Seamless Ensemble(RISE)system in the Beijing-Tianjin-Hebei(BTH)region,this study proposes a new Segmented Classification and Regression machine learning model based on the extreme gradient boosting(XGBoost)algorithm,termed SCR-XGBoost,which can be applied to correct hourly precipitation forecasts in areas with a dense network of weather stations at lead times of 4-6 h.The performance of the model is evaluated according to six metrics:the accuracy(AC),mean absolute error(MAE),root mean square error(RMSE),correlation coefficient(CC),threat score(TS),and bias score(BS).The results indicate that,although the XGBoost algorithm is almost ineffective for directly forecasting precipitation,the SCR-XGBoost model can significantly improve the forecast performance compared with the original RISE forecast,and the segmented correction method for torrential rainfall(≥20 mm h^(-1))outperforms other precipitation grades,which can effectively alleviate the problem of false alarms in the RISE system for heavy rainfall and above(≥10 mm h^(-1)).The optimization rates after applying the SCR-XGBoost model correction in precipitation forecasts can be improved by 6.49%-23.21%in terms of RMSE and MAE reduction,and the CC and AC can be greatly improved by 35.38%-84.39%.Therefore,the SCR-XGBoost algorithm,which introduces precipitation grade classification and multi-layer piecewise machine learning corrections,can significantly improve the 4-6-h precipitation forecast skill,especially for heavy rainfall.The results of this study not only provide new insights for machine learning-based precipitation forecasting,but also help improve rainfall forecasts and the level of disaster prevention and reduction in the BTH region.展开更多
Objective:To systematically evaluate the efficacy and safety of traditional Chinese medicine for regulating spleen and kidney.Methods:We developed a search strategy and then retrieved the database including CNKI,Wanfa...Objective:To systematically evaluate the efficacy and safety of traditional Chinese medicine for regulating spleen and kidney.Methods:We developed a search strategy and then retrieved the database including CNKI,Wanfang data knowledge service platform,VIP journals resource integration service platform,PubMed,Embasefor randomized controlled trial of regulating spleen and kidney traditional Chinese medicine compared with conventional western medicine in the treatment of chronic uric acid nephropathy.The search deadline was set to June 30,2020.For the included literature,we applied the cochrane collaboration network risk bias assessment tool to evaluate the methodological quality,and evaluated the level of evidence according to GRADE standards.Quantitative data was analyzed by RevMan5.3 software,and trial sequential analysis method was used to analyze its efficiency.Results:A total of 709 cases in 10 articles were included.Compared with the control group,the related traditional Chinese medicine group improved the effective rate[RR=1.45,95%CI(1.32,1.58)],reduced the level of UA[MD=-36.24,95%CI(-41.03,-31.45)],BUN[SMD=-1.27,95%CI(-1.47,-1.07)]and SCR[MD=-36.33,95%CI(-55.79,-16.87),P=0.0003],the difference between the two groups was statistically significant(P<0.05).There was no evidence that a significant adverse reaction occurred.The results of TSA analysis showed that the Chinese medicine group had definite evidence for improving the efficiency.According to the GRADE evaluation criteria,the efficiency,UA,BUN and SCR outcome indicators were extremely low-quality evidence.Conclusions:Traditional Chinese medicine for regulating spleen and kidney in the treatment of chronic uric acid nephropathy improved efficiency,reduced the level of UA,BUN,SCR.Meanwhile,the therapy was proved to be safe.Nevertheless,the conclusions need further high-quality evidence to support.展开更多
Long-distance oil and gas pipelines are important infrastructure for ensuring the security of national energy supply.There is still a certain gap between safety management requirements and systematic construction of r...Long-distance oil and gas pipelines are important infrastructure for ensuring the security of national energy supply.There is still a certain gap between safety management requirements and systematic construction of relevant regulations and standards for long-distance pipelines in China and those of EU countries.By means of literature review and standard comparison,the differences in key indicators such as design coefficient,regional grade classification.展开更多
Cataracts are the leading cause of visual impairment and blindness globally.Over the years,researchers have achieved significant progress in developing state-of-the-art machine learning techniques for automatic catara...Cataracts are the leading cause of visual impairment and blindness globally.Over the years,researchers have achieved significant progress in developing state-of-the-art machine learning techniques for automatic cataract classification and grading,aiming to prevent cataracts early and improve clinicians′diagnosis efficiency.This survey provides a comprehensive survey of recent advances in machine learning techniques for cataract classification/grading based on ophthalmic images.We summarize existing literature from two research directions:conventional machine learning methods and deep learning methods.This survey also provides insights into existing works of both merits and limitations.In addition,we discuss several challenges of automatic cataract classification/grading based on machine learning techniques and present possible solutions to these challenges for future research.展开更多
基金supported by the National Natural Science Foundation of China (Grant Nos. 20573132 and 20575074)China Postdoctoral Science Foundation (Grant No. 20090450065)State Key Laboratory of Mag-netic Resonance and Atomic and Molecular Physics (Grant No. T152805)
文摘Clinical data have shown that survival rates vary considerably among brain tumor patients,according to the type and grade of the tumor.Metabolite profiles of intact tumor tissues measured with high-resolution magic-angle spinning proton nuclear magnetic resonance spectroscopy (HRMAS 1H NMRS) can provide important information on tumor biology and metabolism.These metabolic fingerprints can then be used for tumor classification and grading,with great potential value for tumor diagnosis.We studied the metabolic characteristics of 30 neuroepithelial tumor biopsies,including two astrocytomas (grade I),12 astrocytomas (grade II),eight anaplastic astrocytomas (grade III),three glioblastomas (grade IV) and five medulloblastomas (grade IV) from 30 patients using HRMAS 1H NMRS.The results were correlated with pathological features using multivariate data analysis,including principal component analysis (PCA).There were significant differences in the levels of N-acetyl-aspartate (NAA),creatine,myo-inositol,glycine and lactate between tumors of different grades (P<0.05).There were also significant differences in the ratios of NAA/creatine,lactate/creatine,myo-inositol/creatine,glycine/creatine,scyllo-inositol/creatine and alanine/creatine (P<0.05).A soft independent modeling of class analogy model produced a predictive accuracy of 87% for high-grade (grade III-IV) brain tumors with a sensitivity of 87% and a specificity of 93%.HRMAS 1H NMR spectroscopy in conjunction with pattern recognition thus provides a potentially useful tool for the rapid and accurate classification of human brain tumor grades.
基金supported in part by the Science and Technology Development Plan Project of Changchun[Grant Number 21ZGN28]the Jilin Provincial Science and Technology Development Plan Project[Grant Number 20210101157JC]the Jilin Provincial Science and Technology Development Plan Project[Grant Number 20230202035NC].
文摘To solve inefficient water stress classification of spinach seedlings under complex background,this study proposed an automatic classification method for the water stress level of spinach seedlings based on the N-MobileNetXt(NCAM+MobileNetXt)network.Firstly,this study recon-structed the Sandglass Block to effectively increase the model accuracy;secondly,this study introduced the group convolution module and a two-dimensional adaptive average pool,which can significantly compress the model parameters and enhance the model robustness separately;finally,this study innovatively proposed the Normalization-based Channel Attention Module(NCAM)to enhance the image features obviously.The experimental results showed that the classification accuracy of N-MobileNetXt model for spinach seedlings under the natural environment reached 90.35%,and the number of parameters was decreased by 66%compared with the original MobileNetXt model.The N-MobileNetXt model was superior to other net-work models such as ShuffleNet and GhostNet in terms of parameters and accuracy of identification.It can provide a theoretical basis and technical support for automatic irrigation.
基金Supported by the National Natural Science Foundation of China(42275012)National Key Research and Development Program of China(2022YFC3004103)+1 种基金Beijing Municipal Science and Technology Project(Z221100005222012)Key Innovation Team Fund of China Meteorological Administration(CMA2022ZD07).
文摘Accurate and fine-scale short-term precipitation forecasting is crucial for disaster prevention,mitigation,and socioeconomic development.Currently,the direct precipitation forecasts of numerical weather prediction often face great challenges and correction methods are still needed to further improve the forecast accuracy.By utilizing the 500-m resolution fusion precipitation data from the Rapid-refresh Integrated Seamless Ensemble(RISE)system in the Beijing-Tianjin-Hebei(BTH)region,this study proposes a new Segmented Classification and Regression machine learning model based on the extreme gradient boosting(XGBoost)algorithm,termed SCR-XGBoost,which can be applied to correct hourly precipitation forecasts in areas with a dense network of weather stations at lead times of 4-6 h.The performance of the model is evaluated according to six metrics:the accuracy(AC),mean absolute error(MAE),root mean square error(RMSE),correlation coefficient(CC),threat score(TS),and bias score(BS).The results indicate that,although the XGBoost algorithm is almost ineffective for directly forecasting precipitation,the SCR-XGBoost model can significantly improve the forecast performance compared with the original RISE forecast,and the segmented correction method for torrential rainfall(≥20 mm h^(-1))outperforms other precipitation grades,which can effectively alleviate the problem of false alarms in the RISE system for heavy rainfall and above(≥10 mm h^(-1)).The optimization rates after applying the SCR-XGBoost model correction in precipitation forecasts can be improved by 6.49%-23.21%in terms of RMSE and MAE reduction,and the CC and AC can be greatly improved by 35.38%-84.39%.Therefore,the SCR-XGBoost algorithm,which introduces precipitation grade classification and multi-layer piecewise machine learning corrections,can significantly improve the 4-6-h precipitation forecast skill,especially for heavy rainfall.The results of this study not only provide new insights for machine learning-based precipitation forecasting,but also help improve rainfall forecasts and the level of disaster prevention and reduction in the BTH region.
基金Inheritance and innovation of traditional Chinese Medicine"Ten million"talent project(Qihuang project)(No.2019-QTL-003)。
文摘Objective:To systematically evaluate the efficacy and safety of traditional Chinese medicine for regulating spleen and kidney.Methods:We developed a search strategy and then retrieved the database including CNKI,Wanfang data knowledge service platform,VIP journals resource integration service platform,PubMed,Embasefor randomized controlled trial of regulating spleen and kidney traditional Chinese medicine compared with conventional western medicine in the treatment of chronic uric acid nephropathy.The search deadline was set to June 30,2020.For the included literature,we applied the cochrane collaboration network risk bias assessment tool to evaluate the methodological quality,and evaluated the level of evidence according to GRADE standards.Quantitative data was analyzed by RevMan5.3 software,and trial sequential analysis method was used to analyze its efficiency.Results:A total of 709 cases in 10 articles were included.Compared with the control group,the related traditional Chinese medicine group improved the effective rate[RR=1.45,95%CI(1.32,1.58)],reduced the level of UA[MD=-36.24,95%CI(-41.03,-31.45)],BUN[SMD=-1.27,95%CI(-1.47,-1.07)]and SCR[MD=-36.33,95%CI(-55.79,-16.87),P=0.0003],the difference between the two groups was statistically significant(P<0.05).There was no evidence that a significant adverse reaction occurred.The results of TSA analysis showed that the Chinese medicine group had definite evidence for improving the efficiency.According to the GRADE evaluation criteria,the efficiency,UA,BUN and SCR outcome indicators were extremely low-quality evidence.Conclusions:Traditional Chinese medicine for regulating spleen and kidney in the treatment of chronic uric acid nephropathy improved efficiency,reduced the level of UA,BUN,SCR.Meanwhile,the therapy was proved to be safe.Nevertheless,the conclusions need further high-quality evidence to support.
基金Soft Science Research Project of the Special Equipment Safety and Energy Conservation Technology Committee of the State Administration for Market Regulation“Comparative Study of Special Equipment Supervision and Inspection Modes at Home and Abroad(AJW-2024-06)”Scientific Research and Technology Development Project of National Oil and Gas Pipeline Network Group Co.,Ltd.“Benchmarking of Pressure Pipeline(Long-Distance Pipeline)Regulatory System and Research on In-Service Pipeline Safety Management Technology(J-24-D08)”。
文摘Long-distance oil and gas pipelines are important infrastructure for ensuring the security of national energy supply.There is still a certain gap between safety management requirements and systematic construction of relevant regulations and standards for long-distance pipelines in China and those of EU countries.By means of literature review and standard comparison,the differences in key indicators such as design coefficient,regional grade classification.
基金supported by National Natural Science Foundation of China(No.8210072776)Guangdong Provincial Department of Education,China(No.2020ZD ZX3043)+2 种基金Guangdong Provincial Key Laboratory,China(No.2020B121201001)Shenzhen Natural Science Fund,China(No.JCYJ20200109140820699)the Stable Support Plan Program,China(No.20200925174052004).
文摘Cataracts are the leading cause of visual impairment and blindness globally.Over the years,researchers have achieved significant progress in developing state-of-the-art machine learning techniques for automatic cataract classification and grading,aiming to prevent cataracts early and improve clinicians′diagnosis efficiency.This survey provides a comprehensive survey of recent advances in machine learning techniques for cataract classification/grading based on ophthalmic images.We summarize existing literature from two research directions:conventional machine learning methods and deep learning methods.This survey also provides insights into existing works of both merits and limitations.In addition,we discuss several challenges of automatic cataract classification/grading based on machine learning techniques and present possible solutions to these challenges for future research.
