The graph-based representation of material structures,along with deep neural network models,often lacks locality and requires large datasets,which are seldom available in specialized materials research.To address this...The graph-based representation of material structures,along with deep neural network models,often lacks locality and requires large datasets,which are seldom available in specialized materials research.To address this challenge,we developed a more data-efficient center-environment(CE)structure representation that incorporates a predefined attention-focused mechanism.This approach was applied in a machine learning(ML)study to examine the local alloying effects on the structural stability of Nb alloys.In the CE feature model,the atomic environment type(AET)method was utilized,which effectively describes the low-symmetry physical shell structures of neighboring atoms.The optimized ML-CEAET models successfully predicted double-site substitution energies in Nb with a mean absolute error of 55.37 meV and identified Si-M pairs(where M=Ta,W,Re,and lanthanide rare-earth elements)as promising stabilizers for Nb.The ML-CE_(AET)model’s good transferability was further confirmed through accurate prediction of untrained alloying element Nb.Significantly,in cases involving small datasets,non-deep learning models with CE features outperformed deep learning models based on graph features reported in the literature.展开更多
Magnesium and its alloys have been initially applied to biliary tract surgery.Currently,few reports on the degradation behavior of magnesium in the bile environment were investigated.Thus,in-depth research on the degr...Magnesium and its alloys have been initially applied to biliary tract surgery.Currently,few reports on the degradation behavior of magnesium in the bile environment were investigated.Thus,in-depth research on the degradation behavior of Mg and its alloys in bile is beneficial to the further application of Mg in biliary tract surgery.In this study,the degradation behavior of HP-Mg(HPM)and Mg-2 wt.%Zn(MZ2)alloys in human bile and Hanks balanced salt solution(HBSS)was systematically investigated.The MZ2 alloy biliary stent was implanted into the porcine common bile duct to study the degradation behavior of MZ2 alloy in vivo,and to verify the biosafety of MZ2 alloys degradation in the bile duct.It was found that the degradation product layer formed by MZ2 alloys in bile consisted of three layers,including organic matter(fatty acid,etc.),calcium and magnesium phosphate,and Mg(OH)2/MgO,respectively from the outside to the inside.The multi-layered degradation product layer slowed down the corrosion of the Mg matrix.During the 21 days of stent implantation,the degradation rate of the MZ2 stent was about 0.83 mm/y,there was no blockage and stenosis of the tube diameter,and the bile drainage function was normal.展开更多
为提高水域鱼类资源监测的自动化程度和实时分析能力,结合YOLOv8X(You only look once version 8-extra large)目标检测模型、ByteTrack(ByteTrack:a strong baseline for multi-object tracking)算法与双频识别声呐(Dual-frequency ide...为提高水域鱼类资源监测的自动化程度和实时分析能力,结合YOLOv8X(You only look once version 8-extra large)目标检测模型、ByteTrack(ByteTrack:a strong baseline for multi-object tracking)算法与双频识别声呐(Dual-frequency identification sonar,DIDSON)数据,开发了1种快速、准确的鱼类目标识别与计数方法。实验结果表明,YOLOv8X与ByteTrack联合方法与传统的Echoview软件识别精度接近(偏差率仅为1.36%),但处理时间显著减少(单条测线从约30 min减少至约3 min),表现出较强的实时处理能力和泛化性能。同时,通过重复实验验证了该方法的稳定性,确认其在不同场景中的可靠性。本研究方法与成果为水域鱼类资源的自动化监测提供了可靠的技术支持,可广泛地应用于大范围高频次的渔业资源监测与管理工作中。展开更多
基金supported by the National Natural Science Foundation of China(Nos.52373227,52201016)the National Key Research and Development Program of China(Nos.2017YFB0702901,2017YFB0701502,2023YFB4606200)+1 种基金Shanghai Technical Service Center for Advanced Ceramics Structure Design and Precision Manufacturing,China(No.20DZ2294000)Key Program of Science and Technology of Yunnan Province,China(No.202302AB080020).
文摘The graph-based representation of material structures,along with deep neural network models,often lacks locality and requires large datasets,which are seldom available in specialized materials research.To address this challenge,we developed a more data-efficient center-environment(CE)structure representation that incorporates a predefined attention-focused mechanism.This approach was applied in a machine learning(ML)study to examine the local alloying effects on the structural stability of Nb alloys.In the CE feature model,the atomic environment type(AET)method was utilized,which effectively describes the low-symmetry physical shell structures of neighboring atoms.The optimized ML-CEAET models successfully predicted double-site substitution energies in Nb with a mean absolute error of 55.37 meV and identified Si-M pairs(where M=Ta,W,Re,and lanthanide rare-earth elements)as promising stabilizers for Nb.The ML-CE_(AET)model’s good transferability was further confirmed through accurate prediction of untrained alloying element Nb.Significantly,in cases involving small datasets,non-deep learning models with CE features outperformed deep learning models based on graph features reported in the literature.
基金supported by the Sci-ence and technology commission of Shanghai Municipal-ity(No.19441905600)the Shanghai Jiao Tong University Interdisciplinary(Biomedical Engineering)Research Fund(No.ZH2018ZDA09)+2 种基金Clinical Research Plan of SHDC(No.SHDC2020CR3036B)China Postdoctoral Science Founda-tion(No.2021M702090)Changshu Science and Technology Program(Industrial)Project(No.CG202107).
文摘Magnesium and its alloys have been initially applied to biliary tract surgery.Currently,few reports on the degradation behavior of magnesium in the bile environment were investigated.Thus,in-depth research on the degradation behavior of Mg and its alloys in bile is beneficial to the further application of Mg in biliary tract surgery.In this study,the degradation behavior of HP-Mg(HPM)and Mg-2 wt.%Zn(MZ2)alloys in human bile and Hanks balanced salt solution(HBSS)was systematically investigated.The MZ2 alloy biliary stent was implanted into the porcine common bile duct to study the degradation behavior of MZ2 alloy in vivo,and to verify the biosafety of MZ2 alloys degradation in the bile duct.It was found that the degradation product layer formed by MZ2 alloys in bile consisted of three layers,including organic matter(fatty acid,etc.),calcium and magnesium phosphate,and Mg(OH)2/MgO,respectively from the outside to the inside.The multi-layered degradation product layer slowed down the corrosion of the Mg matrix.During the 21 days of stent implantation,the degradation rate of the MZ2 stent was about 0.83 mm/y,there was no blockage and stenosis of the tube diameter,and the bile drainage function was normal.
文摘为提高水域鱼类资源监测的自动化程度和实时分析能力,结合YOLOv8X(You only look once version 8-extra large)目标检测模型、ByteTrack(ByteTrack:a strong baseline for multi-object tracking)算法与双频识别声呐(Dual-frequency identification sonar,DIDSON)数据,开发了1种快速、准确的鱼类目标识别与计数方法。实验结果表明,YOLOv8X与ByteTrack联合方法与传统的Echoview软件识别精度接近(偏差率仅为1.36%),但处理时间显著减少(单条测线从约30 min减少至约3 min),表现出较强的实时处理能力和泛化性能。同时,通过重复实验验证了该方法的稳定性,确认其在不同场景中的可靠性。本研究方法与成果为水域鱼类资源的自动化监测提供了可靠的技术支持,可广泛地应用于大范围高频次的渔业资源监测与管理工作中。
