Results 41 to 50 of about 943 (167)

Hurricane Impacts on the Population Genetics of an Endangered Ecosystem Engineer 飓风对一种濒危生态系统工程师的种群遗传学影响

open access: yesIntegrative Conservation, Volume 4, Issue 4, Page 641-651, December 2025.
Key Largo woodrats are a small and endangered island species, whose individuals tend to occur in family groups. Isolation from mainland populations, predation, and habitat fragmentation have caused genetic drift, leading to low overall diversity. Here, we found that a major category 4 hurricane promoted genetic diversity in the Key Largo woodrat ...
Taylor Ackley   +5 more
wiley   +1 more source

An Enterprise Credit Scoring Model Based On Improved Random Forest Algorithm [PDF]

open access: yes, 2010
随着我国经济和社会的迅速发展,经济活动日益活跃,业务多元化,在经济活动起到重要作用的金融机构面临着许多风险。企业的信用风险是金融机构面临的最重要的风险之一。因此建立一个客观的、有效的、完善的企业信用评级模型是十分重要的。 企业信用评级问题的实质可以看作是智能学习算法中的分类和排序问题。现在基于人工智能如:人工神经网络(ANN)、支持向量机(SVM)等的企业信用评级模型,大多数为单分类器的模型。这些单分类模型面对噪声多、分布复杂以及数据量大的企业信用评级数据,往往难以取得很好的效果。本文引入一种稳定性高 ...
吴兢
core  

Advances in the application of 18F-FDG PET/CT radiomics for diagnosis, treatment and prognosis prediction of lymphoma [PDF]

open access: yes, 2023
Lymphoma is a highly heterogeneous hematological malignancy that can affect multiple organs throughout the body, exhibiting significant clinical variations among its subtypes.
CHENG Ran, HU Jiajia, LI Biao
core   +1 more source

Social Determinants of Sepsis Mortality in the United States: A Retrospective, Epidemiologic Analysis

open access: yesWorld Medical &Health Policy, Volume 17, Issue 4, Page 823-830, December 2025.
ABSTRACT Sepsis is a leading cause of mortality in the United States, with over 350,000 deaths annually, yet the contribution of neighborhood‐level social determinants of health (SDoH) remains underexplored. We conducted a retrospective analysis of 4.4 million hospitalized patients with sepsis, identified using ICD‐10 codes, leveraging de‐identified ...
Ahad Khaleghi Ardabili   +3 more
wiley   +1 more source

基于机器学习的厚覆盖土层建筑场地类别评价

open access: yesDizhen xuebao
针对因测量等误差对等效剪切波速计算的影响而造成的场地类别容易因单个因素稍有变化即发生的类别改变问题,从江苏省盐城地区收集了大量厚覆盖土层情况下的标准贯入值、深度、剪切波速等相关现场试验数据,利用机器学习方法进行训练建模,研究多特征值模型解决厚覆盖土层情况下场地分类问题的能力。结果表明:随机森林模型的分类精度在加入“等效变异系数”后可达97.7%,且其泛化能力以及对样本总体的判断能力均优于支持向量机模型,该模型为厚覆盖土层建筑场地类别的判断提供了一种新的方式。将二次判断结果与勘探报告结果对比 ...
Zhekai Wang, Huiming Tan, Zhibing Gao
doaj   +1 more source

Advances in the Application of Machine Learning to Microbial Structure and Quality Control of Traditional Fermented Foods [PDF]

open access: yes
The unique flavor properties and rich nutrients of traditional fermented food are closely related to its complex and variable microbial structure, which also makes it difficult to control the quality of final fermented product.
Chenwei TANG   +8 more
core   +1 more source

Vegetation dominantly shapes the elevational patterns of archaeal and protistan communities and their ecological functions in the Hengduan Mountains, Tibetan Plateau

open access: yesFunctional Ecology, Volume 39, Issue 9, Page 2327-2341, September 2025.
Read the free Plain Language Summary for this article on the Journal blog. Abstract While elevational patterns of soil bacterial and fungal communities in mountain ecosystems have been well documented, the assembly processes of soil archaeal and protistan communities, and their linkage with ecosystem multifunctionality (EMF), remain poorly understood ...
Bao‐Min Yao   +14 more
wiley   +1 more source

Tree mycorrhizal associations regulate relationships between plant and microbial communities and soil organic carbon stocks at local scales in a temperate forest

open access: yesFunctional Ecology, Volume 39, Issue 6, Page 1550-1566, June 2025.
Read the free Plain Language Summary for this article on the Journal blog. Abstract Forests store substantial amounts of soil organic carbon (SOC), but SOC stocks differ strongly between forest ecosystems dominated by arbuscular mycorrhizal (AM) or ectomycorrhizal (EcM) fungi.
Mengxu Zhang   +10 more
wiley   +1 more source

基于随机森林回归的船舶特涂维修的日能耗预测

open access: yes大数据
特殊涂装(简称特涂)维修是修船工作的核心内容,能耗的预测是船舶智能能效优化中的一项重要任务。使用随机森林回归(RFR)模型对船舶特涂维修日能耗进行分析,去除异常值、随机化和标准化数据集,然后使用RFR模型对船舶日能耗历史数据进行训练拟和,利用带交叉验证的网格搜索优化RFR模型,使用优化后的RFR模型对船舶特涂维修日能耗数据进行分析,并与其他模型进行对比实验。结果表明,优化后的RFR模型预测效果优于多种其他模型,R2值达93.25%,均方误差明显更低。
甘瑞平, 任新民, 姜军, 李鹏, 周小兵
doaj   +1 more source

Analysis of Soil Erosion Intensity Change Trajectories and Their Driving Factors in Yunnan Province Based on An Improved Stability Mapping Method [PDF]

open access: yes
[Objective] To elucidate the change trajectories of soil erosion intensity in Yunnan Province from 1990 to 2022, and analyze the types of changes and their driving factors, in order to provide a scientific foundation for effective soil erosion control ...
HUANG Bangmei   +4 more
core   +1 more source

Home - About - Disclaimer - Privacy