Results 21 to 30 of about 943 (167)
广东电网遭台风泰利侵袭的输配电设备受损分析及评估 [PDF]
全球能源互联网近年来致灾台风频率呈增加趋势，以2023年影响广东电网约百万用户的第4号台风“泰利”为例，分析广东电网遭台风侵袭受灾情况，建立输配电杆塔受损预测模型，识别关键特征变量与因素，为电网防灾减灾提供支持。首先，分析台风“泰利”气象特征，具有“台前对流活跃，风力强度大，降水范围广”等特点，对输配电设备均产生一定程度破坏。其次，利用随机森林、支持向量机、梯度决策树、神经网络等4种机器学习算法建立输配电杆塔受损预测模型，并对比部分算法针对不平衡样本优化前后模型表现。算例表明，随机森林优化后提升最大 ...
侯慧 +5 more
doaj +1 more source
基于随机森林与长短时记忆神经网络的真空接触器故障诊断方法研究
Gaoya dianqi, 2022 针对真空接触器的渐发性故障识别准确率不高的现状，提出了一种基于随机森林与长短时记忆神经网络的故障诊断方法。文中分析了某型号12 kV真空接触器在机械保持工作情况下合闸线圈电流信号的故障特征，构建了两层诊断模型，在初步诊断中利用随机森林分类器，识别特征明显的突发性故障，利用长短记忆神经网络模型发掘数据时序特征的特点，识别渐发性故障，在最终诊断中利用证据融合将两者结果融合。文中提出的故障诊断模型有效解决了传统故障诊断方法对渐发性故障识别困难的不足，实验表明，该方法对渐发性故障识别准确率达到了91.1%以上 ...
袁钰林 +4 more
doaj
Threat analysis and defense methods of deep-learning-based data theft in data sandbox mode [PDF]
, 2021 The threat model of deep-learning-based data theft in data sandbox model was analyzed in detail, and the degree of damage and distinguishing characteristics of this attack were quantitatively evaluated both in the data processing stage and the model ...
Chuanyi LIU +5 more
core +1 more source
Zhongguo cuzhong zazhi, 2022 目的 建立基于机器学习的血糖异常急性缺血性卒中患者的预后预测模型，比较传统logistic模型与机器学习模型的预测效能。 方法 以中国国家卒中登记研究Ⅲ（China national stroke registration study III，CNSR-Ⅲ）血糖异常急性缺血性卒中患者为研究对象，采用病例报告表收集患者的人口学信息、既往病史、实验室检查、头颅影像学检查、卒中病因分型等临床资料。采用分层10折交叉验证划分训练集（3325例）和测试集（369例），基于随机森林、梯度提升决策树（
杨佳蕾, 陈思玎, 孟霞, 姜勇, 王拥军
doaj +1 more source
Study on debris flow susceptibility based on SPY-RF model: A case study of the upper Minjiang River Basin [PDF]
Debris flow is a high-concentration, heterogeneous, multiphase flow typically triggered by intense rainfall or snowmelt. Its complex formation and movement processes make accurate susceptibility assessment vital for disaster monitoring and mitigation ...
Fucheng XING +7 more
core +1 more source
Comparison of Three Risk Prediction Models for Carotid Atherosclerosis in Steelworkers [PDF]
, 2022 BackgroundAs a leading cause of ischemic cerebrovascular disease, carotid atherosclerosis (CAS) lowers the productivity of steelworkers. An increasing number of scholars have used machine learning to identify readily available factors to predict the risk
WANG Jiaojiao, CHEN Yuanyu, ZHENG Ziwei, YANG Yongzhong, CHEN Zhe, LI Chao, WANG Haidong, WU Jianhui, WANG Guoli
core +1 more source
Effects of Artificial Cyanobacterial Crust on Soil Wind Erosion Control in Arid Regions [PDF]
, 2023 [Objective] The influence factors of artificial cyanobacterial crust on soil threshold wind velocity and wind erosion rate, and the effects of wind erosion prevention and control were analyzed, and the feasibility of using artificial cyanobacterial crust
Gao Liqian, Huang Minghui, Zhao Yunge
core +1 more source
Construction of a machine learning-based prediction model for mitral annular calcification [PDF]
Objective To develop a risk prediction model for mitral annular calcification (MAC) using various machine learning algorithms to enable early identification and risk assessment of MAC. Methods A total of 500 patients who were hospitalized and underwent
BAI Song +5 more
core +2 more sources
Veterinary Dermatology, Volume 37, Issue 2, Page 236-246, April 2026.Canine atopic dermatitis (cAD) is a chronic condition requiring life‐long management. Accurate diagnosis can be challenging, with no reliable diagnostic test. This study aimed to generate a simple diagnostic model for cAD. This model is a relevant prototype for an app‐based tool to support general practitioners in the diagnosis of cAD alongside ...
Xavier Langon +2 more
wiley +1 more source
Outlier detection based on random forest [PDF]
, 2007 摘要: 提出一种基于随机森林方法的异常样本 (outliers)检测方法。仿真实验表明 ,与其他 2种基于 距离的异常样本检测技术相比 ,这种方法可以更好地提高模型的准确率 ,且具有较强的鲁棒性 ,在处 理大规模数据集时还能显著地减少计算时间。Abstract: It intr oduces an outliers detecti on method based on random forest . Compared with the other t wo common outliers detecti
林成德, 邱一卉
core