Results 1 to 10 of about 751 (153)
Zhongshan Daxue xuebao. Yixue kexue ban目的探讨基于光学相干断层扫描血管成像技术（OCTA），筛查糖尿病肾脏病（DKD）高风险人群的临床预测模型。方法本研究以567例糖尿病患者为研究对象，在逐步logistic回归分析的基础上，运用随机森林算法筛选纳入建模的指标，构建基于OCTA糖尿病肾脏病临床预测模型。通过受试者工作特征曲线评价模型区分度，通过决策曲线分析评估模型临床有效性。结果构建基于OCTA的DKD临床预测模型，ROC曲线下面积为0.878，Brier=0.11。结论本研究构建了基于OCTA结果进行糖尿病肾脏病临床预测的列线图预测模型 ...
陆丽娇 +7 more
doaj +6 more sources
全球能源互联网, 2022 电力负荷具有非线性和时序性的特点，为了深入研究各特征变量对于电力负荷预测的重要性，进而获得更高的电力负荷预测精度，提出了基于随机森林（random forest，RF）算法及长短期记忆网络（long short-term memory，LSTM）的混合负荷预测模型。首先根据时间日期因素及气候因素建立高维特征数据集作为随机森林模型的输入，通过随机森林算法筛选出重要特征量，并使其与历史负荷结合作为LSTM模型的输入，经过粒子群算法对LSTM模型进行参数寻优后得到RF-LSTM混合模型及负荷预测结果 ...
董彦军 +6 more
doaj +1 more source
全球能源互联网, 2021 电负荷和热负荷具有较强的耦合性，热负荷需求的准确预测对于预测电负荷进而让供热机组更好地进行深度调峰辅助服务报价工作具有重要作用。经多种算法对比研究表明，基于最邻近结点和随机森林的集成预测算法（KNN-RFAverage）具有很好的回归性能和较低的计算复杂度。特别是在面对热负荷存在极端波动的情况下，采用该算法进行热负荷预测可以保持鲁棒性，为有效解决连续多点热负荷预测、机组供热面积及用热习惯发生变化的问题提供了新的思路和方法。
刘培栋 +6 more
doaj +1 more source
Geological structure recognition model based on improved random forest algorithm [PDF]
, 2023 Seismic attributes are often used for structural interpretation and prediction. In order to overcome the problems of multiple solutions and uncertainty caused by single seismic attribute prediction, seismic multi-attribute fusion technology is used to ...
Huaixiu WANG, Siyi FENG, Zuiliang LIU
core +1 more source
Improved Deep Learning Model for Forecasting Short-Term Load Based on Random Forest Algorithm and Rough Set Theory [PDF]
, 2023 Accurate power load forecasting is conducive to ensuring the safe and economic operation of the power system. Aiming at the problems of low prediction accuracy and long time consuming of the current prediction algorithms, an improved deep learning (DL ...
FENG Jiahuan +6 more
core +1 more source
Journal of Diabetes, Volume 15, Issue 12, Page 1020-1028, December 2023., 2023 Highlights Childhood obesity was significantly associated with the increased risk of insulin resistance (IR). There were 12 metabolites co‐associated with childhood obesity and IR, including seven amino acid and five fatty acid metabolites. The combination of body mass index standard deviation score and key metabolites could effectively predict the ...
Wu Yan +5 more
wiley +1 more source
Journal of Diabetes, Volume 15, Issue 4, Page 338-348, April 2023., 2023 Highlights The logistic regression model consisted of seven commonly used clinical indicators (including lipid profile) and gestational diabetes mellitus subtypes, with an area under the curve (AUC) of 0.760 for the training set and 0.748 for the internal validation set.
Ning Wang +11 more
wiley +1 more source
Generalization of threats attributed to large carnivores in areas of high human–wildlife conflict
Conservation Biology, Volume 36, Issue 5, October 2022., 2022 Abstract Fear‐induced generalization of threats to noninimical stimuli is a behavioral tendency of humans to minimize exposure to potential threats. In human–carnivore conflict zones, people often generalize their fear of predation by obligate carnivores to nonobligate carnivores despite differences in species’ predation rates.
Kumar Ashish +3 more
wiley +1 more source
Analysis on Land Suitability for Maize and Rapeseed Production Based on Data Mining Method [PDF]
, 2022 [Objective] Conducting multi-crop land suitability analysis was carried out in order to provide an accurate and effective method for crop planning, land use planning, and management of agricultural production.
Lin Yan, Zhang Chen, Zhou Hua
core +1 more source
Metabonomics Analysis of Brain Stem Tissue in Rats with Primary Brain Stem Injury Caused Death [PDF]
, 2023 Objective To explore the potential biomarkers for the diagnosis of primary brain stem injury （PBSI） by using metabonomics method to observe the changes of metabolites in rats with PBSI caused death.
Qin SU, Qian-ling CHEN, Wei-bin WU, Qing-qing XIANG, Cheng-liang YANG, Dong-fang QIAO, Zhi-gang LI
core +1 more source