Machine learning-assisted methods for rapid and accurate prediction of temperature field,mushy zone,and grain size were proposed for the heating−cooling combined mold(HCCM)horizontal continuous casting of C70250 alloy...Machine learning-assisted methods for rapid and accurate prediction of temperature field,mushy zone,and grain size were proposed for the heating−cooling combined mold(HCCM)horizontal continuous casting of C70250 alloy plates.First,finite element simulations of casting processes were carried out with various parameters to build a dataset.Subsequently,different machine learning algorithms were employed to achieve high precision in predicting temperature fields,mushy zone locations,mushy zone inclination angle,and billet grain size.Finally,the process parameters were quickly optimized using a strategy consisting of random generation,prediction,and screening,allowing the mushy zone to be controlled to the desired target.The optimized parameters are 1234℃for heating mold temperature,47 mm/min for casting speed,and 10 L/min for cooling water flow rate.The optimized mushy zone is located in the middle of the second heat insulation section and has an inclination angle of roughly 7°.展开更多
针对受扰移动机器人系统自触发模型预测控制(self-triggered model predictive control,STMPC)在虚假数据注入(false data injection,FDI)攻击下的安全控制问题,提出了一种基于输入重构的弹性STMPC方法。结合自触发机制非周期采样特性和...针对受扰移动机器人系统自触发模型预测控制(self-triggered model predictive control,STMPC)在虚假数据注入(false data injection,FDI)攻击下的安全控制问题,提出了一种基于输入重构的弹性STMPC方法。结合自触发机制非周期采样特性和FDI攻击模型,设计了一种基于关键数据的输入重构机制,以减弱FDI攻击对被控系统的影响。根据状态误差的最优控制问题,设计了重构参数的确定方法,以保证系统在应用重构控制输入后的控制性能。详细分析了所提出弹性STMPC算法的稳定性以及算法可行性。通过仿真和实验验证了所提出算法的有效性。展开更多
Objective To assess the short-term lag effects of climate and air pollution on hospital admissions for cardiovascular and respiratory diseases,and to develop deep learning-based models for daily hospital admission pre...Objective To assess the short-term lag effects of climate and air pollution on hospital admissions for cardiovascular and respiratory diseases,and to develop deep learning-based models for daily hospital admission prediction.Methods A multi-city study was conducted in Tokyo’s 23 wards,Osaka City,and Nagoya City.Random forest models were employed to assess the synergistic short-term lag effects(lag0,lag3,and lag7)of climate and air pollutants on hospitalization for five cardiovascular diseases(CVDs)and two respiratory diseases(RDs).Furthermore,we developed hybrid deep learning models that integrated an autoencoder(AE)with a Long Short-Term Memory network(AE+LSTM)to predict daily hospital admissions.Results On the day of exposure(lag0),air pollutants,particularly nitrogen oxides(NOx),exhibited the strongest influence on hospital admissions for CVD and RD,with pronounced effects observed for hypertension(I10–I15),ischemic heart disease(I20),arterial and capillary diseases(I70–I79),and lower respiratory infections(J20–J22 and J40–J47).At longer lags(lag3 and lag7),temperature and precipitation were more influential predictors.The AE+LSTM model outperformed the standard LSTM,improving the prediction accuracy by 32.4%for RD in Osaka and 20.94%for CVD in Nagoya.Conclusion Our findings reveal the dynamic,time-varying health risks associated with environmental exposure and demonstrate the utility of deep learnings in predicting short-term hospital admissions.This framework can inform early warning systems,enhance healthcare resource allocation,and support climate-adaptive public health strategies.展开更多
Digital modeling and autonomous control of the die forging process are significant challenges in realizing high-quality intelli-gent forging of components.Using the die forging of AA2014 aluminum alloy as a case study...Digital modeling and autonomous control of the die forging process are significant challenges in realizing high-quality intelli-gent forging of components.Using the die forging of AA2014 aluminum alloy as a case study,a machine-learning-assisted method for di-gital modeling of the forging force and autonomous control in response to forging parameter disturbances was proposed.First,finite ele-ment simulations of the forging processes were conducted under varying friction factors,die temperatures,billet temperatures,and for-ging velocities,and the sample data,including process parameters and forging force under different forging strokes,were gathered.Pre-diction models for the forging force were established using the support vector regression algorithm.The prediction error of F_(f),that is,the forging force required to fill the die cavity fully,was as low as 4.1%.To further improve the prediction accuracy of the model for the ac-tual F_(f),two rounds of iterative forging experiments were conducted using the Bayesian optimization algorithm,and the prediction error of F_(f) in the forging experiments was reduced from 6.0%to 1.5%.Finally,the prediction model of F_(f) combined with a genetic algorithm was used to establish an autonomous optimization strategy for the forging velocity at each stage of the forging stroke,when the billet and die temperatures were disturbed,which realized the autonomous control in response to disturbances.In cases of−20 or−40℃ reductions in the die and billet temperatures,forging experiments conducted with the autonomous optimization strategy maintained the measured F_(f) around the target value of 180 t,with the relative error ranging from−1.3%to+3.1%.This work provides a reference for the study of di-gital modeling and autonomous optimization control of quality factors in the forging process.展开更多
Iron oxide nanoparticles(IONPs)with intrinsic peroxidase(POD)-mimic activity have gained significant attention as nanozymes.Reducing sizes of IONPs is the mostly applied strategy to boost their enzymatic activity due ...Iron oxide nanoparticles(IONPs)with intrinsic peroxidase(POD)-mimic activity have gained significant attention as nanozymes.Reducing sizes of IONPs is the mostly applied strategy to boost their enzymatic activity due to their high specific surface areas.Herein,we synthesized a series of uniformly sized IONPs ranging from3.17 to 21.2 nm,and found that POD activity of IONPs is not monotone increased by reducing their sizes,with the optimal size of 7.82 nm rather than smaller sized 3.17 nm.The reason for this unnormal phenomenon is that electronic structure also had great influence on POD activity,especially at the ultrasmall size region.Since Fe^(2+)are with higher enzymatic activity than Fe^(3+),3.17 nm IONPs although have the largest specific surface area,are prone to be oxidized,which reduced their iron content and ratio of Fe^(2+)to Fe^(3+),and consequently decreased their POD activity.By intentionally oxidized 7.82 nm IONPs in air,POD activity was obviously reduced,illustrating electronic structure cannot be overlooked.At the larger sized region ranging from 7.82 to 21.2 nm,oxidation degree of IONPs is similar,and surface electronic structure had a negligible effect on POD activity,and therefore,POD activity is predominantly influenced by specific surface area.By using the optimized 7.82 nm IONPs,tumor growth was obviously inhibited,demonstrating their potential in cancer therapeutics.Our results reveal that the designing of nanozymes should comprehensively balance their influence of surface electronic structure and specific surface area.展开更多
Background:To understand the mitochondrial genome of the Crocidura fuliginosa in Dali region and to explore its systematic relationship with other species within the same genus.Methods:Employing high-throughput sequen...Background:To understand the mitochondrial genome of the Crocidura fuliginosa in Dali region and to explore its systematic relationship with other species within the same genus.Methods:Employing high-throughput sequencing technology in conjunction with bioinformatics software,to sequence and analyze the mitochondrial genome of this species.Utilizing complete mitochondrial genome data,the phylogenetic tree was constructed to illustrate the relationships among this species and other members of the genus.Results:Employing high-throughput sequencing technology in conjunction with bioinformatics software,to sequence and analyze the mitochondrial genome of this species.Utilizing complete mitochondrial genome data,the phylogenetic tree was constructed to illustrate the relationships among this species and other members of the genus.The results indicated that the mitochondrial genome length was 17,224 bp,and encoded 37 genes,exhibiting a significant AT bias.With the exception of the trnS1 gene,all other tRNA genes can fold into a standard clover structure,while the base composition of rRNA genes followed the order of A>T>C>G.All PCGs were stared by ATN,with the majority terminating in TAA or TAG,except for the cob gene.The codon with the highest RSCU was UUA,while the lowest was CCG.The phylogenetic relationship of C.fuliginosa with(((((C.anhuiensis,C.attenuata),C.lasiura),C.dongyangjiangensis),C.tanakae),C.sp.g ZL)had recently received strong support.Conclusion:Therefore,this study expands the mitochondrial genomics database for Crocidura,providing a solid foundation for future in-depth exploration of the classification,phylogenetic relationships,and evolution of this genus and its related species.展开更多
Objective:To explore the effect of medical and nursing integration mode on the nursing care of patients with inguinal hernia treated by tension-free repair.Methods:A total of 76 cases of inguinal hernia patients admit...Objective:To explore the effect of medical and nursing integration mode on the nursing care of patients with inguinal hernia treated by tension-free repair.Methods:A total of 76 cases of inguinal hernia patients admitted to the hospital from September 2023 to August 2024 were selected as study subjects.They were divided into 38 cases each in the control group and the observation group by using the random number table method.The patients in the control group were cared for by the traditional postoperative care mode and the patients in the observation group were given additional medical and nursing care based on the control group,and were observed and analyzed for pain relief,infection,hospital stay,and hospital costs.Results:The VAS score of patients in the observation group was(7.91±2.21)at 1d postoperation and(11.04±3.24)at 1d postoperation in the control group,which was significantly lower than that of the control group,with a statistically significant difference(P<0.05),and the VAS score of the patients at 6 months postoperation was(4.82±1.81),which was not statistically significant when compared with that of the control patients(4.79±1.45),which was not statistically different from those of the control group(P>0.05);3 cases of infection occurred in the at 3d,accounting for the total number of observation group postoperative patients(7.89%),and compared with control group with postoperative 5 cases of infection occurred in the 3 days,accounting for of the total number of patients(13.16%),the postoperative infection rate of the patients in the observation group was significantly reduced,and the difference was statistically significant(P<0.05).The number of hospitalization days as well as the hospitalization costs of the observation group were significantly lower than those of the control group,and the difference was statistically significant(P<0.05).Conclusion:The integrated model of medical care has significant advantages in the care of patients with inguinal hernia treated with tension-free repair,which can effectively alleviate early postoperative pain,reduce the rate of infection,shorten the length of hospital stay,and reduce the cost of hospitalization.展开更多
本研究利用功能磁共振成像(functional magnetic resonance imaging,fMRI)构建个体脑网络以期能够对阿尔兹海默症(Alzheimer′s disease,AD)不同病程阶段进行分类,为临床诊断早期AD提供一种辅助手段。首先构建有向脑网络,将体素葡萄糖...本研究利用功能磁共振成像(functional magnetic resonance imaging,fMRI)构建个体脑网络以期能够对阿尔兹海默症(Alzheimer′s disease,AD)不同病程阶段进行分类,为临床诊断早期AD提供一种辅助手段。首先构建有向脑网络,将体素葡萄糖代谢平均率和脑网络连接,增加节点的度作为被研究对象对应图像的特征。然后采用Wrapper式特征选择法分别验证三种特征在核主成分分析(kernel principal component analysis,KPCA)和Adaboost两种机器学习算法下诊断AD的性能,将特征融合后以同样的方法进行验证。最后,对比分析了两种预测模型在AD不同病程中的分类性能,用十折交叉验证评估预测性能。结果显示,就单特征识别能力而言,平均葡萄糖代谢率对于AD的分类性能贡献最大,在两种算法下分别达到了93.21%和92.89%的准确率,多特征融合的分类性能最佳,准确率达94%以上,AUC值为0.97。两种算法模型对AD不同分类组的预测能力都不错,虽略有差异,但相比而言,KPCA算法表现更好。本研究可为计算机辅助AD早期诊断、及时干预提供参考依据。展开更多
基金financially supported by the National Key Research and Development Program of China (No. 2023YFB3812601)the National Natural Science Foundation of China (No. 51925401)the Young Elite Scientists Sponsorship Program by CAST, China (No. 2022QNRC001)。
文摘Machine learning-assisted methods for rapid and accurate prediction of temperature field,mushy zone,and grain size were proposed for the heating−cooling combined mold(HCCM)horizontal continuous casting of C70250 alloy plates.First,finite element simulations of casting processes were carried out with various parameters to build a dataset.Subsequently,different machine learning algorithms were employed to achieve high precision in predicting temperature fields,mushy zone locations,mushy zone inclination angle,and billet grain size.Finally,the process parameters were quickly optimized using a strategy consisting of random generation,prediction,and screening,allowing the mushy zone to be controlled to the desired target.The optimized parameters are 1234℃for heating mold temperature,47 mm/min for casting speed,and 10 L/min for cooling water flow rate.The optimized mushy zone is located in the middle of the second heat insulation section and has an inclination angle of roughly 7°.
文摘针对受扰移动机器人系统自触发模型预测控制(self-triggered model predictive control,STMPC)在虚假数据注入(false data injection,FDI)攻击下的安全控制问题,提出了一种基于输入重构的弹性STMPC方法。结合自触发机制非周期采样特性和FDI攻击模型,设计了一种基于关键数据的输入重构机制,以减弱FDI攻击对被控系统的影响。根据状态误差的最优控制问题,设计了重构参数的确定方法,以保证系统在应用重构控制输入后的控制性能。详细分析了所提出弹性STMPC算法的稳定性以及算法可行性。通过仿真和实验验证了所提出算法的有效性。
基金supported by the Japan Science and Technology Agency SPRING Program(JST SPRING),Grant Number JPMJSP2108,which was partially funded by the Japan Society for the Promotion of Science(JSPS)Grant Numbers 20H03949,23K22919,23K28289the Environmental Restoration and Conservation Agency of Japan,and the Environment Research and Technology Development Fund(S-24).
文摘Objective To assess the short-term lag effects of climate and air pollution on hospital admissions for cardiovascular and respiratory diseases,and to develop deep learning-based models for daily hospital admission prediction.Methods A multi-city study was conducted in Tokyo’s 23 wards,Osaka City,and Nagoya City.Random forest models were employed to assess the synergistic short-term lag effects(lag0,lag3,and lag7)of climate and air pollutants on hospitalization for five cardiovascular diseases(CVDs)and two respiratory diseases(RDs).Furthermore,we developed hybrid deep learning models that integrated an autoencoder(AE)with a Long Short-Term Memory network(AE+LSTM)to predict daily hospital admissions.Results On the day of exposure(lag0),air pollutants,particularly nitrogen oxides(NOx),exhibited the strongest influence on hospital admissions for CVD and RD,with pronounced effects observed for hypertension(I10–I15),ischemic heart disease(I20),arterial and capillary diseases(I70–I79),and lower respiratory infections(J20–J22 and J40–J47).At longer lags(lag3 and lag7),temperature and precipitation were more influential predictors.The AE+LSTM model outperformed the standard LSTM,improving the prediction accuracy by 32.4%for RD in Osaka and 20.94%for CVD in Nagoya.Conclusion Our findings reveal the dynamic,time-varying health risks associated with environmental exposure and demonstrate the utility of deep learnings in predicting short-term hospital admissions.This framework can inform early warning systems,enhance healthcare resource allocation,and support climate-adaptive public health strategies.
基金financially supported by the National Key Research and Development Program of China(No.2022YFB3706901)the National Natural Science Foundation of China(No.52090041)the Young Elite Scientists Sponsorship Program by CAST(No.2022QNRC 001).
文摘Digital modeling and autonomous control of the die forging process are significant challenges in realizing high-quality intelli-gent forging of components.Using the die forging of AA2014 aluminum alloy as a case study,a machine-learning-assisted method for di-gital modeling of the forging force and autonomous control in response to forging parameter disturbances was proposed.First,finite ele-ment simulations of the forging processes were conducted under varying friction factors,die temperatures,billet temperatures,and for-ging velocities,and the sample data,including process parameters and forging force under different forging strokes,were gathered.Pre-diction models for the forging force were established using the support vector regression algorithm.The prediction error of F_(f),that is,the forging force required to fill the die cavity fully,was as low as 4.1%.To further improve the prediction accuracy of the model for the ac-tual F_(f),two rounds of iterative forging experiments were conducted using the Bayesian optimization algorithm,and the prediction error of F_(f) in the forging experiments was reduced from 6.0%to 1.5%.Finally,the prediction model of F_(f) combined with a genetic algorithm was used to establish an autonomous optimization strategy for the forging velocity at each stage of the forging stroke,when the billet and die temperatures were disturbed,which realized the autonomous control in response to disturbances.In cases of−20 or−40℃ reductions in the die and billet temperatures,forging experiments conducted with the autonomous optimization strategy maintained the measured F_(f) around the target value of 180 t,with the relative error ranging from−1.3%to+3.1%.This work provides a reference for the study of di-gital modeling and autonomous optimization control of quality factors in the forging process.
基金financially supported by the Natural Science Foundation of Zhejiang Province(No.LR22E010001)the National Natural Science Foundation of China(No.52073258)+1 种基金the Fundamental Research Funds for the Provincial Universities of Zhejiang(No.RF-B2022006)the R&D Program of Zhejiang University of Technology(No.KYY-HX-20190730)
文摘Iron oxide nanoparticles(IONPs)with intrinsic peroxidase(POD)-mimic activity have gained significant attention as nanozymes.Reducing sizes of IONPs is the mostly applied strategy to boost their enzymatic activity due to their high specific surface areas.Herein,we synthesized a series of uniformly sized IONPs ranging from3.17 to 21.2 nm,and found that POD activity of IONPs is not monotone increased by reducing their sizes,with the optimal size of 7.82 nm rather than smaller sized 3.17 nm.The reason for this unnormal phenomenon is that electronic structure also had great influence on POD activity,especially at the ultrasmall size region.Since Fe^(2+)are with higher enzymatic activity than Fe^(3+),3.17 nm IONPs although have the largest specific surface area,are prone to be oxidized,which reduced their iron content and ratio of Fe^(2+)to Fe^(3+),and consequently decreased their POD activity.By intentionally oxidized 7.82 nm IONPs in air,POD activity was obviously reduced,illustrating electronic structure cannot be overlooked.At the larger sized region ranging from 7.82 to 21.2 nm,oxidation degree of IONPs is similar,and surface electronic structure had a negligible effect on POD activity,and therefore,POD activity is predominantly influenced by specific surface area.By using the optimized 7.82 nm IONPs,tumor growth was obviously inhibited,demonstrating their potential in cancer therapeutics.Our results reveal that the designing of nanozymes should comprehensively balance their influence of surface electronic structure and specific surface area.
文摘Background:To understand the mitochondrial genome of the Crocidura fuliginosa in Dali region and to explore its systematic relationship with other species within the same genus.Methods:Employing high-throughput sequencing technology in conjunction with bioinformatics software,to sequence and analyze the mitochondrial genome of this species.Utilizing complete mitochondrial genome data,the phylogenetic tree was constructed to illustrate the relationships among this species and other members of the genus.Results:Employing high-throughput sequencing technology in conjunction with bioinformatics software,to sequence and analyze the mitochondrial genome of this species.Utilizing complete mitochondrial genome data,the phylogenetic tree was constructed to illustrate the relationships among this species and other members of the genus.The results indicated that the mitochondrial genome length was 17,224 bp,and encoded 37 genes,exhibiting a significant AT bias.With the exception of the trnS1 gene,all other tRNA genes can fold into a standard clover structure,while the base composition of rRNA genes followed the order of A>T>C>G.All PCGs were stared by ATN,with the majority terminating in TAA or TAG,except for the cob gene.The codon with the highest RSCU was UUA,while the lowest was CCG.The phylogenetic relationship of C.fuliginosa with(((((C.anhuiensis,C.attenuata),C.lasiura),C.dongyangjiangensis),C.tanakae),C.sp.g ZL)had recently received strong support.Conclusion:Therefore,this study expands the mitochondrial genomics database for Crocidura,providing a solid foundation for future in-depth exploration of the classification,phylogenetic relationships,and evolution of this genus and its related species.
文摘Objective:To explore the effect of medical and nursing integration mode on the nursing care of patients with inguinal hernia treated by tension-free repair.Methods:A total of 76 cases of inguinal hernia patients admitted to the hospital from September 2023 to August 2024 were selected as study subjects.They were divided into 38 cases each in the control group and the observation group by using the random number table method.The patients in the control group were cared for by the traditional postoperative care mode and the patients in the observation group were given additional medical and nursing care based on the control group,and were observed and analyzed for pain relief,infection,hospital stay,and hospital costs.Results:The VAS score of patients in the observation group was(7.91±2.21)at 1d postoperation and(11.04±3.24)at 1d postoperation in the control group,which was significantly lower than that of the control group,with a statistically significant difference(P<0.05),and the VAS score of the patients at 6 months postoperation was(4.82±1.81),which was not statistically significant when compared with that of the control patients(4.79±1.45),which was not statistically different from those of the control group(P>0.05);3 cases of infection occurred in the at 3d,accounting for the total number of observation group postoperative patients(7.89%),and compared with control group with postoperative 5 cases of infection occurred in the 3 days,accounting for of the total number of patients(13.16%),the postoperative infection rate of the patients in the observation group was significantly reduced,and the difference was statistically significant(P<0.05).The number of hospitalization days as well as the hospitalization costs of the observation group were significantly lower than those of the control group,and the difference was statistically significant(P<0.05).Conclusion:The integrated model of medical care has significant advantages in the care of patients with inguinal hernia treated with tension-free repair,which can effectively alleviate early postoperative pain,reduce the rate of infection,shorten the length of hospital stay,and reduce the cost of hospitalization.
文摘本研究利用功能磁共振成像(functional magnetic resonance imaging,fMRI)构建个体脑网络以期能够对阿尔兹海默症(Alzheimer′s disease,AD)不同病程阶段进行分类,为临床诊断早期AD提供一种辅助手段。首先构建有向脑网络,将体素葡萄糖代谢平均率和脑网络连接,增加节点的度作为被研究对象对应图像的特征。然后采用Wrapper式特征选择法分别验证三种特征在核主成分分析(kernel principal component analysis,KPCA)和Adaboost两种机器学习算法下诊断AD的性能,将特征融合后以同样的方法进行验证。最后,对比分析了两种预测模型在AD不同病程中的分类性能,用十折交叉验证评估预测性能。结果显示,就单特征识别能力而言,平均葡萄糖代谢率对于AD的分类性能贡献最大,在两种算法下分别达到了93.21%和92.89%的准确率,多特征融合的分类性能最佳,准确率达94%以上,AUC值为0.97。两种算法模型对AD不同分类组的预测能力都不错,虽略有差异,但相比而言,KPCA算法表现更好。本研究可为计算机辅助AD早期诊断、及时干预提供参考依据。
