Results 41 to 50 of about 5,179,681 (193)
Zhejiang Daxue xuebao. Lixue ban, 2022 近年来，机器学习等人工智能技术被应用于蛋白质工程，其在蛋白质结构、功能预测、催化活性等研究中具有独特优势。在未知蛋白质结构的情况下，将蛋白质序列和功能特性与机器学习相结合，基于序列-活性关系（innovative sequence-activity relationship，ISAR）算法，将蛋白质氨基酸序列数字化，用快速傅里叶变换（fast four transform，FFT）进行预处理，再进行偏最小二乘回归建模，可在数据集较少情况下拟合得到最佳模型。通过机器学习对紫色球杆菌视紫红质 ...
JIALili(郏丽丽) +1 more
doaj +1 more source
Microstructure Engineering Toward High Cost‐Effective Nd–Fe–B Sintered Magnets: A Review
Rare Metals, Volume 45, Issue 7, July 2026.ABSTRACT Nd–Fe–B sintered magnets, critical for enhancing electromechanical conversion efficiency and operational stability in wind turbines and electric vehicle drives, are prized for their outstanding coercivity, high remanence, and superior maximum energy product.
Dongmin Zhang +5 more
wiley +1 more source
Rare Metals, Volume 45, Issue 7, July 2026.ABSTRACT Developing advanced electrocatalysts for urea synthesis is pivotal to alleviating environmental burdens as well as advancing sustainability in the industrial and agricultural sectors, yet untargeted catalyst screening still suffers from the notorious drawbacks of being time‐consuming, labor‐intensive, and inefficient.
Xinyuan Yang +8 more
wiley +1 more source
Methods in Ecology and Evolution, Volume 17, Issue 7, Page 2123-2134, July 2026.Abstract Elliptic Fourier analysis (EFA) is often employed in geometric morphometrics (GM), but the normalization of elliptic Fourier descriptor (EFD) has persistently posed challenges for obtaining unique and comparable results, especially in the application of outline‐based GM methods, which limits the implementation in automated analysis of numerous,
Hui Wu +6 more
wiley +1 more source
智能科学与技术学报, 2021 鉴别图像中的真伪人脸是一个长期具有挑战性的问题。当合成的伪造人脸十分逼真时，机器识别难分真假，甚至肉眼也难以区分。基于监督学习的真伪人脸识别建模往往需要大量的标签样本，模型的性能严重依赖样本的规模。提出一种基于半监督学习的人脸识别反欺骗方法，以减少对大量标签样本的依赖。该方法利用图像修复模型来学习人脸图像潜在的数据分布。在训练过程中，少量标签样本周期性地提供有监督信号来训练分类器，以区分真伪人脸。该方法可用于不同场景的伪造人脸，如基于摄像头拍摄的人脸或生成对抗网络生成的人脸。在NUAA ...
李莉, 曾伟良, 黄永慧, 孙为军
doaj
Classifier of silicon content in hot metal based on support vector machines(基于支持向量机的高炉铁水硅含量多类别分类)
Zhejiang Daxue xuebao. Lixue ban, 2007 支持向量机是基于统计学习理论发展而来的一种机器学习算法，本文介绍了非线性软间隔分类机、最小二乘分类机和加权最小二乘分类机的算法.以山东莱钢1号高炉在线采集数据作为应用案例，使用C-均值算法对[Si]做聚类分析将其分成5类，改进M-ary分类方法实现对铁水硅质量分数[Si]的多类别分类，并对各分类机的性能作出评价.
JIANLing(渐令) +2 more
doaj +1 more source
Intelligent Material Framework for Data Mining and Performance Prediction of Invar Alloy
Rare Metals, Volume 45, Issue 6, June 2026.ABSTRACT Invar alloys exhibit a low coefficient of thermal expansion (CTE) over a wide temperature range and are regarded as critical materials for precision engineering and aerospace applications. In this work, an integrated OLR‐IMF (an intelligent material framework based on optical character recognition [OCR], large language models [LLMs], and ...
Tongbo Jiang +11 more
wiley +1 more source
基于半监督学习的断路器弹簧机构机械特性监测及状态评估技术研究
Gaoya dianqi, 2022 针对断路器弹簧机构机械特性监测及状态识别系统普遍存在监测类型不全、特征值提取单一、判断标准太过绝对等问题，文中提出了基于小波及半监督学习的多特征分析的断路器弹簧操动机构机械状态识别新方法。通过感知元件对分合闸线圈电流、动触头位移等信号进行采集，采用小波算法对信号进行滤波处理，分析断路器弹簧操动机构的分合闸线圈电流、动触头位移等信号与断路器异常状态之间的对应关系，提取特征值，建立半监督学习多分类网络模型，实现断路器弹簧操动机构故障的机械特性监测及状态识别。实验结果验证了此方法具有较高的诊断正确率 ...
彭跃辉 +3 more
doaj
Rare Metals, Volume 45, Issue 5, May 2026.ABSTRACT With excellent castability and dimensional stability, Zn alloys are widely used in the automotive and electronic industries. However, the inherent trade‐off between strength and ductility remains a key bottleneck limiting their application in high‐performance fields.
Jianxing Zhou +11 more
wiley +1 more source
Rare Metals, Volume 45, Issue 4, April 2026.ABSTRACT Nickel‐based superalloys (Ni‐based superalloys) have attracted extensive attention in laser additive manufacturing (LAM) due to their capability to directly fabricate complex and high‐performance structural components. However, the rapid melting and solidification inherent to LAM result in intense thermal cycling, which induces high residual ...
Tianxiang Lin +9 more
wiley +1 more source