期刊文献+
共找到407,332篇文章
< 1 2 250 >
每页显示 20 50 100
Clinical information prompt-driven retinal fundus image for brain health evaluation
1
作者 Nuo Tong Ying Hui +10 位作者 Shui-Ping Gou Ling-Xi Chen Xiang-Hong Wang Shuo-Hua Chen Jing Li Xiao-Shuai Li Yun-Tao Wu Shou-Ling Wu Zhen-Chang Wang Jing Sun Han Lv 《Military Medical Research》 2026年第1期43-57,共15页
Background:Brain volume measurement serves as a critical approach for assessing brain health status.Considering the close biological connection between the eyes and brain,this study aims to investigate the feasibility... Background:Brain volume measurement serves as a critical approach for assessing brain health status.Considering the close biological connection between the eyes and brain,this study aims to investigate the feasibility of estimating brain volume through retinal fundus imaging integrated with clinical metadata,and to offer a cost-effective approach for assessing brain health.Methods:Based on clinical information,retinal fundus images,and neuroimaging data derived from a multicenter,population-based cohort study,the Kai Luan Study,we proposed a cross-modal correlation representation(CMCR)network to elucidate the intricate co-degenerative relationships between the eyes and brain for 755 subjects.Specifically,individual clinical information,which has been followed up for as long as 12 years,was encoded as a prompt to enhance the accuracy of brain volume estimation.Independent internal validation and external validation were performed to assess the robustness of the proposed model.Root mean square error(RMSE),peak signal-tonoise ratio(PSNR),and structural similarity index measure(SSIM)metrics were employed to quantitatively evaluate the quality of synthetic brain images derived from retinal imaging data.Results:The proposed framework yielded average RMSE,PSNR,and SSIM values of 98.23,35.78 d B,and 0.64,respectively,which significantly outperformed 5 other methods:multi-channel Variational Autoencoder(mcVAE),Pixelto-Pixel(Pixel2pixel),transformer-based U-Net(Trans UNet),multi-scale transformer network(MT-Net),and residual vision transformer(ResViT).The two-(2D)and three-dimensional(3D)visualization results showed that the shape and texture of the synthetic brain images generated by the proposed method most closely resembled those of actual brain images.Thus,the CMCR framework accurately captured the latent structural correlations between the fundus and the brain.The average difference between predicted and actual brain volumes was 61.36 cm~3,with a relative error of 4.54%.When all of the clinical information(including age and sex,daily habits,cardiovascular factors,metabolic factors,and inflammatory factors)was encoded,the difference was decreased to 53.89 cm~3,with a relative error of 3.98%.Based on the synthesized brain magnetic resonance images from retinal fundus images,the volumes of brain tissues could be estimated with high accuracy.Conclusion:This study provides an innovative,accurate,and cost-effective approach to characterize brain health status through readily accessible retinal fundus images. 展开更多
关键词 Retinal fundus image brain volume brain health Magnetic resonance imaging Deep learning Eye and brain connection
原文传递
Informer-LSTM融合算法在蓝莓基质温湿度预测中的研究与应用
2
作者 胡玲艳 陈鹏宇 +6 位作者 郭占俊 徐国辉 秦山 付康 盖荣丽 汪祖民 张雨萌 《郑州大学学报(理学版)》 北大核心 2026年第1期78-86,共9页
为了精准预测温室蓝莓基质的温湿度变化趋势,提出一种融合Informer-LSTM算法的温湿度预测方法。以温室蓝莓现场环境数据为研究对象,使用LSTM算法捕捉时间序列数据中的依赖关系并与自注意力机制相结合,使模型在聚焦自注意力特征的同时兼... 为了精准预测温室蓝莓基质的温湿度变化趋势,提出一种融合Informer-LSTM算法的温湿度预测方法。以温室蓝莓现场环境数据为研究对象,使用LSTM算法捕捉时间序列数据中的依赖关系并与自注意力机制相结合,使模型在聚焦自注意力特征的同时兼顾LSTM特征,以增强其长期记忆力。在生成初步预测序列后,再应用LSTM算法修正模型的短期注意力,提高模型的反应速度。实验结果显示,Informer-LSTM预测模型在预测准确率、鲁棒性和响应速度等方面都有显著的优势。当温度湿度等时序输入数据发生明显变化时,模型能快速捕获短期内输入数据的动态模式变化。该模型在智慧温室管理中,对辅助人工决策及实现智能化控制具有较高实际价值。 展开更多
关键词 智慧农业 温室蓝莓 informer模型 LSTM模型 温湿度预测
在线阅读 下载PDF
基于改进Informer的商业建筑短期用电负荷多步预测
3
作者 周璇 李可昕 +3 位作者 郭子轩 俞祝良 闫军威 蔡盼盼 《华南理工大学学报(自然科学版)》 北大核心 2026年第1期42-52,共11页
商业建筑短期用电负荷多步预测是城市有序用电和虚拟电厂调度的关键环节。商业建筑用电负荷时间序列具有强随机性、非平稳、非线性等特点,针对传统的迭代式多步用电负荷预测方法存在误差累积效应影响预测精度的问题,提出一种基于频率增... 商业建筑短期用电负荷多步预测是城市有序用电和虚拟电厂调度的关键环节。商业建筑用电负荷时间序列具有强随机性、非平稳、非线性等特点,针对传统的迭代式多步用电负荷预测方法存在误差累积效应影响预测精度的问题,提出一种基于频率增强通道注意力机制(FECAM)—麻雀优化算法(SSA)—Informer的短期用电负荷多步预测方法。该方法在Informer编码器输出时域特征的基础上,采用FECAM对各特征通道间的频率依赖性进行自适应建模,进一步提取多维输入序列的频域特征,生成式解码器利用融合的时、频域信息直接输出未来多步用电负荷序列。此外,由于改进Informer超参数设置缺乏理论依据,使用SSA寻优学习率、批处理大小、全连接维度和失活率的最佳组合。以广州某商业建筑全年用电负荷数据作为实际算例,结果表明,与其他深度学习模型相比,所提模型在不同预测步长(48、96、288、480、672步)下的预测精度显著提升,具有更优的短期用电负荷多步预测性能。 展开更多
关键词 商业建筑用电负荷预测 频率增强通道注意力机制 informER 麻雀优化算法
在线阅读 下载PDF
基于TCN-Informer的长短期多变量时间序列预测
4
作者 李德权 江涛 《科学技术与工程》 北大核心 2026年第4期1549-1557,共9页
为了解决时间序列预测长期和短期依赖关系的难题,同时捕捉长期趋势和短期动态,并对多变量时间序列中变量间复杂的相互依赖关系进行建模,提出了一种基于时间卷积网络(temporal convolutional network,TCN)的预测方法。首先,采用TCN来有... 为了解决时间序列预测长期和短期依赖关系的难题,同时捕捉长期趋势和短期动态,并对多变量时间序列中变量间复杂的相互依赖关系进行建模,提出了一种基于时间卷积网络(temporal convolutional network,TCN)的预测方法。首先,采用TCN来有效捕捉序列变量在时间尺度上的特征,同时将压缩-激励模块(squeeze-and-excitation block,SE_Block)应用于TCN的输出。该模块通过增强多变量的表示,有效解决短期依赖性问题,并提高模型捕捉关键短期信息的能力。其次,引入Informer模型来增强长期序列处理能力,不仅有效解决了长期序列预测中的计算效率问题,还增强了模型对全局时间依赖关系的建模能力。最后,在设备状态监测(ETTm1)、交通流量(Traffic)和电力负荷(Electricity)三个数据集上将所提方法与现有的时间序列模型进行实验验证并比较。结果表明:所提出的方法在长期和短期时间序列预测中的误差率较低,能够有效提高多变量时间序列中长期和短期预测性能。 展开更多
关键词 长短期时间序列 多变量时间序列 informER 时间卷积网络(TCN) 特征提取
在线阅读 下载PDF
基于Informer模型的智能洪水预报方法研究
5
作者 董付强 万喆 +3 位作者 王丽娟 蔡金华 万俊 罗永钦 《人民长江》 北大核心 2026年第1期53-63,共11页
洪水预报精度和预见期是做好水库洪水预警和调度的关键,在洪水预报中应用人工智能模型可有效提高洪水预报精度。应用K-means聚类分析法对潘口水库流域进行了科学划分,然后采用Informer深度学习模型进行洪水预报,并与传统LSTM模型进行了... 洪水预报精度和预见期是做好水库洪水预警和调度的关键,在洪水预报中应用人工智能模型可有效提高洪水预报精度。应用K-means聚类分析法对潘口水库流域进行了科学划分,然后采用Informer深度学习模型进行洪水预报,并与传统LSTM模型进行了对比研究,最后基于Informer模型设计了4种预报方案分析上游水库对潘口水库洪水预报精度的影响。结果表明:(1) Informer模型的预报性能优于LSTM模型;(2)优化后的Informer模型,训练集和测试集总体纳什系数为0.892,洪水总量误差为6.64%,洪水峰值误差为7.69%,洪量误差及洪峰误差平均值均达到甲级标准;(3)基于Informer模型的2023年和2024年堵河流域潘口水库实际检验预报纳什系数均值为0.878和0.827,洪量误差及洪峰误差合格率均达100%,均满足甲级要求。基于深度学习Informer模型的智能洪水预报不仅可提高洪量和洪峰的预测精度,而且具有较强的实际应用潜力,可为水库洪水预报预警及防灾减灾提供决策依据。 展开更多
关键词 智能洪水预报 深度学习模型 informer模型 LSTM模型 潘口水库 堵河
在线阅读 下载PDF
基于改进Informer模型的无人机姿态估计方法
6
作者 肖蘅 包乃源 +1 位作者 周文 杨亚婷 《现代电子技术》 北大核心 2026年第4期57-63,共7页
传统无人机姿态估计方法由于传感器精度不高和设备成本限制,难以满足复杂环境中的精确需求。为此,提出一种基于改进Informer模型的无人机姿态估计方法,引入多尺度时间注意力机制和动态时间规整(DTW)损失函数,提升模型在长序列数据处理... 传统无人机姿态估计方法由于传感器精度不高和设备成本限制,难以满足复杂环境中的精确需求。为此,提出一种基于改进Informer模型的无人机姿态估计方法,引入多尺度时间注意力机制和动态时间规整(DTW)损失函数,提升模型在长序列数据处理和动态飞行数据适应方面的能力。此外,采用遗传算法对模型超参数进行优化,显著提高了复杂飞行数据处理的准确性和鲁棒性。基于苏黎世大学机器人实验室发布的UZH-FPV竞赛数据集,将改进后的Informer模型与LSTM、GRU和DNN模型进行了实验对比。结果表明,改进Informer模型在无人机的俯仰角、滚转角和偏航角估计方面均显著优于其他对比模型。 展开更多
关键词 无人机姿态估计 informer模型 多尺度时间注意力机制 动态时间规整损失函数 遗传算法优化 长序列数据处理
在线阅读 下载PDF
基于XGBoost-LSTM-Informer的硫磺价格预测研究
7
作者 张新生 李慧敏 《中国物价》 2026年第1期12-18,共7页
针对以硫磺为代表的大宗商品价格呈现非线性、非规律波动的特点,本研究创新性地提出XGBoost-LSTM-Informer深度学习组合模型。该模型的核心优势在于有效结合LSTM捕捉短期依赖的能力与Informer捕捉长期依赖的优势。本文以硫磺价格多因素... 针对以硫磺为代表的大宗商品价格呈现非线性、非规律波动的特点,本研究创新性地提出XGBoost-LSTM-Informer深度学习组合模型。该模型的核心优势在于有效结合LSTM捕捉短期依赖的能力与Informer捕捉长期依赖的优势。本文以硫磺价格多因素预测为案例,首先采用独立森林法对原始数据进行预处理,并结合皮尔逊相关系数法与XGBoost重要性对影响因素进行双重筛选。随后将融合后的数据集分别并行输入LSTM和Informer进行训练,并利用Optuna进行超参数调优,通过迭代训练输出模型最优预测结果。多组对比实验与消融实验表明,XGBoost-LSTM-Informer模型在预测精度上显著优于基准模型,既能准确反映硫磺价格整体波动趋势,也能及时捕捉局部价格波动细节。基于实验结果,本文从加强硫磺数据挖掘、引入模型辅助风险管理、构建硫磺价格预测体系三方面提出建议,为提升硫磺市场价格监测与风险管控能力提供理论支撑。 展开更多
关键词 长短期记忆神经网络 informer模型 多因素价格预测 硫磺价格 影响因素
原文传递
基于改进Informed-RRT^(*)算法的无人机三维路径规划
8
作者 张森 庞岩 周福亮 《系统工程与电子技术》 北大核心 2026年第2期660-668,共9页
为满足无人机(unmanned aerial vehicle,UAV)的三维路径规划需求,针对基于启发信息的快速扩展随机树(informed rapidly-exploring random tree,Informed-RRT^(*))算法初始可行路径较长、优化效率低的问题,本文采用动态人工势场来引导树... 为满足无人机(unmanned aerial vehicle,UAV)的三维路径规划需求,针对基于启发信息的快速扩展随机树(informed rapidly-exploring random tree,Informed-RRT^(*))算法初始可行路径较长、优化效率低的问题,本文采用动态人工势场来引导树的生长,降低初始路径的长度;将采样区域限制在分层椭球中,根据障碍物疏密调整采样概率;使用前馈神经网络和遗传算法优化重连区域半径,以降低运行时间。仿真结果显示,在障碍物稀疏和密集环境中,改进算法得到的路径质量相较于Informed-RRT^(*)算法以及A^(*)算法更优,验证了本文算法在无人机三维路径规划中的实用性。 展开更多
关键词 路径规划 无人机 informed-RRT^(*) 动态人工势场
在线阅读 下载PDF
基于Informer-SAO-LSTM的刀具磨损预测
9
作者 李昂 马俊燕 唐源斌 《组合机床与自动化加工技术》 北大核心 2026年第1期151-155,161,共6页
在产品加工过程中,准确预测刀具的磨损值既能避免过早更换造成的成本浪费,又可防止过度磨损影响加工精度,从而最大化发挥刀具寿命的价值。为了解决这个问题,提出了一种基于Informer、SAO与LSTM结合的深度学习网络模型,用于刀具磨损预测... 在产品加工过程中,准确预测刀具的磨损值既能避免过早更换造成的成本浪费,又可防止过度磨损影响加工精度,从而最大化发挥刀具寿命的价值。为了解决这个问题,提出了一种基于Informer、SAO与LSTM结合的深度学习网络模型,用于刀具磨损预测。Informer具有高效的编码器结构和稀疏自注意力机制,而LSTM网络具有较强的时间序列建模能力,通过SAO算法对超参数的调整,可以更准确高效地捕捉刀具磨损过程中长期的依赖关系,从而提取更有效的特征,提升了模型在处理长序列数据时的效率和准确性。使用PHM2010数据集进行对比实验,实验结果表明所提出的Informer-SAO-LSTM模型在MAE、RMSE等多项指标上均表现出色,最后设计了实验进行验证,进一步说明了所提出的方法比对比模型的预测准确率更高,泛化能力更好。 展开更多
关键词 LSTM informER SAO 刀具磨损 深度学习 时间序列预测
在线阅读 下载PDF
基于FDBO+Informer-ECANet的齿轮箱故障诊断分析
10
作者 李婷婷 贾东 《机械传动》 北大核心 2026年第3期161-171,共11页
【目的】基于智能优化算法与深度神经网络的齿轮箱故障诊断方法逐渐成为研究热点,但仍然存在较多问题。为了解决强噪声环境下齿轮故障特征提取难、诊断准确率低的问题,提出一种基于融合增强型蜣螂优化(Fusion-enhanced Dung Beetle Opti... 【目的】基于智能优化算法与深度神经网络的齿轮箱故障诊断方法逐渐成为研究热点,但仍然存在较多问题。为了解决强噪声环境下齿轮故障特征提取难、诊断准确率低的问题,提出一种基于融合增强型蜣螂优化(Fusion-enhanced Dung Beetle Optimization,FDBO)算法、Informer模型和通道注意力机制(Efficient Channel Attention Network,ECANet)模块的齿轮箱故障诊断方法。【方法】首先,针对现有蜣螂优化(Dung Beetle Optimization,DBO)算法全局搜索能力不足、易陷入局部最优等问题,引入融合Fuch混沌映射兼逆反向学习策略、自适应步长策略与凸透镜成像反转策略集成、随机差异变异策略,提高算法的全局搜索能力;其次,基于Informer模型出色的长时间序列处理能力,高效提取出序列数据中的全局特征与局部特征;尤其针对包含长时间依赖关系的故障信号,该模型可展现出极高的分类性能;再次,在Informer模型的编辑器中引入ECANet模块,对Informer提取的特征进行通道级的自适应校准,提高模型对重要特征的关注度,以增强特征表达能力、减少噪声干扰;最后,通过FDBO算法对Informer-ECANet模型多个超参数进行寻优,确定最优参数组合,以增强模型的诊断能力和泛化性能。【结果】试验结果表明,在无噪声条件下,所提模型准确率达100%;在加入-6 dB的高斯白噪声下准确率仍达到94.4%,验证了所提模型的优越性,为齿轮箱故障诊断提供了一种新型有效的智能方法。 展开更多
关键词 融合增强型蜣螂优化算法 informer模型 ECANet模块 随机差异变异策略
在线阅读 下载PDF
基于小波卷积与Informer模型相结合的短期电力负荷预测
11
作者 谢雄峰 谭剑中 +2 位作者 何东 岳汉文 彭彪 《湖南电力》 2026年第1期98-106,共9页
随着风电、光伏等可再生能源大规模接入电网,电力系统运行的不确定性和波动性显著增强,负荷序列特征提取困难,导致短期电力负荷预测精度难以提升。针对此问题,提出一种基于小波卷积和Informer模型相结合的短期电力负荷预测模型,采用改... 随着风电、光伏等可再生能源大规模接入电网,电力系统运行的不确定性和波动性显著增强,负荷序列特征提取困难,导致短期电力负荷预测精度难以提升。针对此问题,提出一种基于小波卷积和Informer模型相结合的短期电力负荷预测模型,采用改进的变分模态分解(variational mode decomposition,VMD),对数据分解降噪后输入小波卷积模块进行多级小波卷积,实现对复杂时间序列的多尺度特征提取及降低序列复杂度,从而提高预测精度。为验证模型的有效性,进行多组实验,结果表明,所提模型平均绝对百分比误差为1.893 1%,与单独使用Informer模型或仅使用GSWOA-VMD-Informer的方法相比降低了1.059 4个百分点和0.504 8个百分点,验证了该模型的有效性。 展开更多
关键词 时间序列预测 变分模态分解(VMD) 小波卷积(WTC) informer模型
在线阅读 下载PDF
基于深度时间序列模型xLSTM-Informer的矿压数据预测方法研究
12
作者 王永胜 崔志瀛 +2 位作者 赵亮 董文哲 赵文广 《煤炭与化工》 2026年第1期25-31,共7页
针对矿压时序数据强非线性与长程依赖特性导致的预测难题,本文提出一种融合扩展长短期记忆网络(xLSTM)与长序列预测模型(Informer)的xLSTM-Infomer预测方法。较于传统单一模型,该模型利用xLSTM精细捕捉局部动态特征的能力,并结合Informe... 针对矿压时序数据强非线性与长程依赖特性导致的预测难题,本文提出一种融合扩展长短期记忆网络(xLSTM)与长序列预测模型(Informer)的xLSTM-Infomer预测方法。较于传统单一模型,该模型利用xLSTM精细捕捉局部动态特征的能力,并结合Informer全局长程依赖高效建模的特性,实现了对矿压演化规律的长期预测。为验证模型的预测能力,本文以新疆硫磺沟煤矿的倾斜厚煤层工作面为背景,对工作面矿压数据进行预测,实验结果表明,与LSTM、Informer等基准模型相比,本文所建立的模型预测性能有较高提升,不同部位预测结果的决定系数R^(2)均在93%以上,最高的R^(2)达到了98.21%,且较于对比模型在MAE与RMSE的指标上也均处于最低水平,同时模型在复杂工况下也能表现出较高的预测精度,这为实现智能矿压监测与灾害预警提供了可靠的技术支撑。 展开更多
关键词 矿压预测 深度学习 informER xLSTM 混合模型 智能矿山
在线阅读 下载PDF
Neuroinflammation strokes the brain:A double-edged sword in ischemic stroke 被引量:1
13
作者 Giorgia Lombardozzi Vanessa Castelli +2 位作者 Chiara Giorgi Annamaria Cimini Michele d’Angelo 《Neural Regeneration Research》 2026年第5期1715-1722,共8页
Stroke is a major cause of death and disability worldwide.It is characterized by a highly interconnected and multiphasic neuropathological cascade of events,in which an intense and protracted inflammatory response pla... Stroke is a major cause of death and disability worldwide.It is characterized by a highly interconnected and multiphasic neuropathological cascade of events,in which an intense and protracted inflammatory response plays a crucial role in worsening brain injury.Neuroinflammation,a key player in the pathophysiology of stroke,has a dual role.In the acute phase of stroke,neuroinflammation exacerbates brain injury,contributing to neuronal damage and blood–brain barrier disruption.This aspect of neuroinflammation is associated with poor neurological outcomes.Conversely,in the recovery phase following stroke,neuroinflammation facilitates brain repair processes,including neurogenesis,angiogenesis,and synaptic plasticity.The transition of neuroinflammation from a harmful to a reparative role is not well understood.Therefore,this review seeks to explore the mechanisms underlying this transition,with the goal of informing the development of therapeutic interventions that are both time-and context-specific.This review aims to elucidate the complex and dual role of neuroinflammation in stroke,highlighting the main actors,biomarkers of the disease,and potential therapeutic approaches. 展开更多
关键词 brain repair euinflammation inflammation ISCHEMIA mechanisms MICROGLIA oxidative stress stroke therapeutic approaches
暂未订购
Microglial polarization pathways and therapeutic drugs targeting activated microglia in traumatic brain injury 被引量:3
14
作者 Liping Shi Shuyi Liu +2 位作者 Jialing Chen Hong Wang Zhengbo Wang 《Neural Regeneration Research》 2026年第1期39-56,共18页
Traumatic brain injury can be categorized into primary and secondary injuries.Secondary injuries are the main cause of disability following traumatic brain injury,which involves a complex multicellular cascade.Microgl... Traumatic brain injury can be categorized into primary and secondary injuries.Secondary injuries are the main cause of disability following traumatic brain injury,which involves a complex multicellular cascade.Microglia play an important role in secondary injury and can be activated in response to traumatic brain injury.In this article,we review the origin and classification of microglia as well as the dynamic changes of microglia in traumatic brain injury.We also clarify the microglial polarization pathways and the therapeutic drugs targeting activated microglia.We found that regulating the signaling pathways involved in pro-inflammatory and anti-inflammatory microglia,such as the Toll-like receptor 4/nuclear factor-kappa B,mitogen-activated protein kinase,Janus kinase/signal transducer and activator of transcription,phosphoinositide 3-kinase/protein kinase B,Notch,and high mobility group box 1 pathways,can alleviate the inflammatory response triggered by microglia in traumatic brain injury,thereby exerting neuroprotective effects.We also reviewed the strategies developed on the basis of these pathways,such as drug and cell replacement therapies.Drugs that modulate inflammatory factors,such as rosuvastatin,have been shown to promote the polarization of antiinflammatory microglia and reduce the inflammatory response caused by traumatic brain injury.Mesenchymal stem cells possess anti-inflammatory properties,and clinical studies have confirmed their significant efficacy and safety in patients with traumatic brain injury.Additionally,advancements in mesenchymal stem cell-delivery methods—such as combinations of novel biomaterials,genetic engineering,and mesenchymal stem cell exosome therapy—have greatly enhanced the efficiency and therapeutic effects of mesenchymal stem cells in animal models.However,numerous challenges in the application of drug and mesenchymal stem cell treatment strategies remain to be addressed.In the future,new technologies,such as single-cell RNA sequencing and transcriptome analysis,can facilitate further experimental studies.Moreover,research involving non-human primates can help translate these treatment strategies to clinical practice. 展开更多
关键词 animal model anti-inflammatory drug cell replacement strategy central nervous system mesenchymal stem cell MICROGLIA NEUROINFLAMMATION non-human primate signaling pathway traumatic brain injury
暂未订购
耦合图相似日和Informer的光伏出力预测
15
作者 刘晨晨 周宇慈 +4 位作者 潘张榕 李薇 沈春明 薛松 郭军红 《科学技术与工程》 北大核心 2026年第2期642-654,共13页
为了充分捕捉待预测日局部变化特征,提高光伏出力预测准确性,提出了基于结构相似性算法(structural similarity,SSIM)的图相似日与高效长时间序列预测模型(Informer)结合的光伏发电预测模型。以云南岩淜光伏电站为案例,首先利用日气象... 为了充分捕捉待预测日局部变化特征,提高光伏出力预测准确性,提出了基于结构相似性算法(structural similarity,SSIM)的图相似日与高效长时间序列预测模型(Informer)结合的光伏发电预测模型。以云南岩淜光伏电站为案例,首先利用日气象数据所构成的向量转换为格拉姆矩阵再将矩阵转换为日气象像素图,然后采用SSIM算法进行待预测日的相似日筛选。在此基础上,完成和光伏出力气象要素筛选,再利用Informer构建光伏出力预测模型,最终输出各时间段出力的预测结果。结果表明:图相似日方法可以很好地识别出待预测日的相似日,构建的Informer光伏出力预测模型在不同天气下都具有很好的预测性能。相对于传统预测方法,晴日下的均方根误差为0.66,日准确率分别提高了1.63%~3.92%。 展开更多
关键词 图相似日 SSIM算法 informer模型 光伏预测
在线阅读 下载PDF
Effect of nurse-led informational video on cesarean section-induced anxiety,satisfaction,and recovery among the patients admitted at tertiary care hospital,Uttarakhand:A quasi-experimental study
16
作者 Prerna MISHRA Anupama BAHADUR +1 位作者 Maneesh SHARMA Prasuna JELLY 《Journal of Integrative Nursing》 2025年第3期155-161,共7页
Objective:The objective of this study is to determine the effect of nurse-led instructional video(NLIV)on anxiety,satisfaction,and recovery among mothers admitted for cesarean section(CS).Materials and Methods:A quasi... Objective:The objective of this study is to determine the effect of nurse-led instructional video(NLIV)on anxiety,satisfaction,and recovery among mothers admitted for cesarean section(CS).Materials and Methods:A quasi-experimental design was carried out on the mothers scheduled for CS.Eighty participants were selected by a purposive sampling technique,which were divided(40 participants in each group)into an experimental group and a control group.Nurse-led informational video(NLIV)was shown to the experimental group,and routine care was provided for the control group.Modified hospital anxiety scale(HADS),scale for measuring maternal satisfaction in cesarean birth,and obstetric quality of recovery following cesarean delivery were used to assess anxiety,satisfaction,and recovery.Results:Both the experimental and control groups showed significant reductions in anxiety by the first postintervention day(P<0.001),with the experimental group experiencing a greater mean reduction(mean difference[MD]=4.37)than the control group(MD=3.35)but the intergroup difference was not statistically significant(P>0.05).The experimental group reported significantly higher satisfaction scores(175.55±9.42)on the 3rd postoperative day compared to the control group(151.93±14.89;P<0.001).Similarly,the experimental group’s recovery scores(79.90±6.24)were considerably higher than those of the control group(62.45±15.18;P<0.001).On the 3rd postintervention day,satisfaction was significantly associated with age(P<0.001),and recovery with gravidity(P<0.05).Conclusions:NLIV can be used in the preoperative period to reduce anxiety related to CS and to improve satisfaction and recovery after the CS. 展开更多
关键词 ANXIETY cesarean section nurse-led informational video RECOVERY SATISFACTION
暂未订购
NLRP3 inflammasome and gut microbiota–brain axis:A new perspective on white matter injury after intracerebral hemorrhage 被引量:1
17
作者 Xiaoxi Cai Xinhong Cai +4 位作者 Quanhua Xie Xueqi Xiao Tong Li Tian Zhou Haitao Sun 《Neural Regeneration Research》 2026年第1期62-80,共19页
Intracerebral hemorrhage is the most dangerous subtype of stroke,characterized by high mortality and morbidity rates,and frequently leads to significant secondary white matter injury.In recent decades,studies have rev... Intracerebral hemorrhage is the most dangerous subtype of stroke,characterized by high mortality and morbidity rates,and frequently leads to significant secondary white matter injury.In recent decades,studies have revealed that gut microbiota can communicate bidirectionally with the brain through the gut microbiota–brain axis.This axis indicates that gut microbiota is closely related to the development and prognosis of intracerebral hemorrhage and its associated secondary white matter injury.The NACHT,LRR,and pyrin domain-containing protein 3(NLRP3)inflammasome plays a crucial role in this context.This review summarizes the dysbiosis of gut microbiota following intracerebral hemorrhage and explores the mechanisms by which this imbalance may promote the activation of the NLRP3 inflammasome.These mechanisms include metabolic pathways(involving short-chain fatty acids,lipopolysaccharides,lactic acid,bile acids,trimethylamine-N-oxide,and tryptophan),neural pathways(such as the vagus nerve and sympathetic nerve),and immune pathways(involving microglia and T cells).We then discuss the relationship between the activated NLRP3 inflammasome and secondary white matter injury after intracerebral hemorrhage.The activation of the NLRP3 inflammasome can exacerbate secondary white matter injury by disrupting the blood–brain barrier,inducing neuroinflammation,and interfering with nerve regeneration.Finally,we outline potential treatment strategies for intracerebral hemorrhage and its secondary white matter injury.Our review highlights the critical role of the gut microbiota–brain axis and the NLRP3 inflammasome in white matter injury following intracerebral hemorrhage,paving the way for exploring potential therapeutic approaches. 展开更多
关键词 gut microbiota gut microbiota–brain axis immune intracerebral hemorrhage NEUROINFLAMMATION NLRP3 protein stroke THERAPEUTICS white matter injury
暂未订购
Informed consent competency assessment for brain-computer interface clinical research and application in psychiatric disorders:A systematic review
18
作者 Jia-Yue Si Zi-Yan Lin +8 位作者 Di-Ga Gan Xin-Yang Zhang Yan-Nan Liu Yu-Xin Hu Yan-Ping Bao Xue-Qin Wang Hong-Qiang Sun Xin Yu Lin Lu 《World Journal of Psychiatry》 2025年第8期404-423,共20页
BACKGROUND Brain-computer interface(BCI)technology is rapidly advancing in psychiatry.Informed consent competency(ICC)assessment among psychiatric patients is a pivotal concern in clinical research.AIM To analyze the ... BACKGROUND Brain-computer interface(BCI)technology is rapidly advancing in psychiatry.Informed consent competency(ICC)assessment among psychiatric patients is a pivotal concern in clinical research.AIM To analyze the assessment of ICC and form a framework with multi-dimensional elements involved in ICC of BCI clinical research among psychiatric disorders.METHODS A systematic review of studies regarding ICC assessments of BCI clinical research in patients with six kinds of psychiatric disorders was conducted.A systematic literature search was performed using PubMed,ScienceDirect,and Web of Science.Peer-reviewed articles and full-text studies were included in the analysis.There were no date restrictions,and all studies published up to February 27,2025,were included.RESULTS A total of 103 studies were selected for this review.Fifty-eight studies included ICC factors,and forty-five were classified in ICC related ethical issues of BCI research in six kinds of psychiatric disorders.Executive function impairment is widely recognized as the most significant factor impacting ICC,and processing speed deficits are observed in schizophrenia,mood disorders,and Alzheimer’s disease.Memory dysfunction,particularly episodic and working memory,contributes to compromised ICC.Five core ethical issues in BCI research should be addressed:BCI specificity,vulnerability,autonomy,dynamic ICC,comprehensiveness,and uncertainty.CONCLUSION A Five-Dimensional evaluative framework,including clinical,ethical,sociocultural,legal,and procedural dimensions,is constructed and proposed for future ICC research in BCI clinical research involving psychiatric disorders. 展开更多
关键词 informed consent competency brain-computer interface Psychiatric disorders Decision-making capacity MacArthur Competence Assessment Tool
暂未订购
Brain Age Detection of Alzheimer’s Disease Magnetic Resonance Images Based on Mutual Information—Support Vector Regression
19
作者 LIU Yuchuan LI Hao +4 位作者 TANG Yulong LIANG Dujuan TAN Jia FU Yue LI Yongming 《Journal of Shanghai Jiaotong university(Science)》 2025年第1期130-135,共6页
Brain age is an effective biomarker for diagnosing Alzheimer’s disease(AD).Aimed at the issue that the existing brain age detection methods are inconsistent with the biological hypothesis that AD is the accelerated a... Brain age is an effective biomarker for diagnosing Alzheimer’s disease(AD).Aimed at the issue that the existing brain age detection methods are inconsistent with the biological hypothesis that AD is the accelerated aging of the brain,a mutual information—support vector regression(MI-SVR)brain age prediction model is proposed.First,the age deviation is introduced according to the biological hypothesis of AD.Second,fitness function is designed based on mutual information criterion.Third,support vector regression and fitness function are used to obtain the predicted brain age and fitness value of the subjects,respectively.The optimal age deviation is obtained by maximizing the fitness value.Finally,the proposed method is compared with some existing brain age detection methods.Experimental results show that the brain age obtained by the proposed method has better separability,can better reflect the accelerated aging of AD,and is more helpful for improving the diagnostic accuracy of AD. 展开更多
关键词 brain age Alzheimer’s disease(AD) mutual information-support vector regression(MI-SVR) age deviation
原文传递
Adipose tissue-brain crosstalk in comorbid obesity and traumatic brain injury:Insights into mechanisms
20
作者 Susan C.Burke Bogdan A.Stoica Rebecca J.Henry 《Neural Regeneration Research》 2026年第5期1989-1990,共2页
Obese individuals who subsequently sustain a traumatic brain injury(TBI)exhibit worsened outcomes including longer periods of rehabilitation(Eagle et al.,2023).In obese individuals,prolonged symptomology is associated... Obese individuals who subsequently sustain a traumatic brain injury(TBI)exhibit worsened outcomes including longer periods of rehabilitation(Eagle et al.,2023).In obese individuals,prolonged symptomology is associated with increased levels of circulato ry pro-inflammatory marke rs up to 1 year postTBI(Eagle et al.,2023). 展开更多
关键词 pro inflammatory markers comorbid obesity adipose tissue rehabilitation outcomes traumatic brain injury tbi exhibit traumatic brain injury brain crosstalk
暂未订购
上一页 1 2 250 下一页 到第
使用帮助 返回顶部