期刊文献+
共找到15,605篇文章
< 1 2 250 >
每页显示 20 50 100
Marginalized Modern Architectural Heritage in Indonesia:The case of transformator huisje(gardu listrik)architecture of the Nederlandsche Indisch era
1
作者 Ikaputra Ikaputra Dyah Titisari Widyastuti 《Frontiers of Architectural Research》 2025年第3期596-613,共18页
This study is in order to implement the mandate of UNESCO(2003)on the documentation of architectural heritage of the modern period of the 19th-20th century,where in reality several typologies of architectural heritage... This study is in order to implement the mandate of UNESCO(2003)on the documentation of architectural heritage of the modern period of the 19th-20th century,where in reality several typologies of architectural heritage are currently in a marginalized condition.As part of the history of modern architecture in Indonesia,transformator huisje(Dutch)or“gardu listrik”(Indonesian)which still exist today,are not widely known as buildings that have important values in the past.This study aims to reveal whether transformator huisje architecture is classifled as Modern Heritage,by tracing its historical background.Architectural analysis of 61 transformator huisje was conducted to build a“genesis”—a scheme of origin—of transformator huisje which can explain how this type of architecture was formed in accordance with the values or principles of modern architecture.The study flndings show that all design features of transformator huisje as buildings for machines are strong representations of Modern Architectural Heritage in Asia,especially the Dutch East Indies(Indonesia).In conclusion,with the flnding that transformator huisje is categorized as Modern Architectural Heritage,a strategy is needed to maintain this type of architecture as evidence of modern civilization in Indonesia. 展开更多
关键词 Modern Architectural Heritage transformator huisje gardu listrik Marginal architecture Indonesia
原文传递
基于Swin-PIDNet的纸质工程制图线型识别方法
2
作者 朱文博 陈龙飞 迟玉伦 《计算机应用研究》 北大核心 2026年第1期313-320,共8页
识别纸质工程制图图像的难点主要在于线型识别,针对纸质工程制图线型规范性差、跨度长、相对于背景图像尺寸小等问题,提出一种纸质工程制图线型识别Swin-PIDNet模型。用Swin Transformer替换PIDNet主干网络,在减少下采样的同时增强了模... 识别纸质工程制图图像的难点主要在于线型识别,针对纸质工程制图线型规范性差、跨度长、相对于背景图像尺寸小等问题,提出一种纸质工程制图线型识别Swin-PIDNet模型。用Swin Transformer替换PIDNet主干网络,在减少下采样的同时增强了模型长程建模能力;提出一种逐阶段解冻的迁移学习方法,提升模型对线型识别的训练效率和精度,平滑模型训练过程;针对工程制图线型的细长特征,嵌入注意力模块EMA到PAHDC模块中,从而改善背景信息淹没线型特征信息的问题;为处理线型类别不平衡问题,将Focal loss和Dice loss通过加权结合构建Swin-PIDNet的训练损失函数。实验证明该模型的评价指标MIoU为87.02%、MPA为95.42%、F 1分数为96.57%,相较于其他模型,该模型具有较强的线型识别能力,对纸质工程制图图像识别具有理论研究意义和实际应用价值。 展开更多
关键词 PIDNet Swin Transformer 线型识别 纸质工程制图 迁移学习 混合空洞卷积
在线阅读 下载PDF
基于多方位感知深度融合检测头的目标检测算法
3
作者 包晓安 彭书友 +3 位作者 张娜 涂小妹 张庆琪 吴彪 《浙江大学学报(工学版)》 北大核心 2026年第1期32-42,共11页
针对传统目标检测头难以有效捕捉全局信息的问题,提出基于多方位感知深度融合检测头的目标检测算法.通过在检测头部分设计高效双轴窗口注意力编码器(EDWE)模块,使网络能够深度融合捕获到的全局信息与局部信息;在特征金字塔结构之后使用... 针对传统目标检测头难以有效捕捉全局信息的问题,提出基于多方位感知深度融合检测头的目标检测算法.通过在检测头部分设计高效双轴窗口注意力编码器(EDWE)模块,使网络能够深度融合捕获到的全局信息与局部信息;在特征金字塔结构之后使用重参化大核卷积(RLK)模块,减小来自主干网络的特征空间差异,增强网络对中小型数据集的适应性;引入编码器选择保留模块(ESM),选择性地累积来自EDWE模块的输出,优化反向传播.实验结果表明,在规模较大的MS-COCO2017数据集上,所提算法应用于常见模型RetinaNet、FCOS、ATSS时使AP分别提升了2.9、2.6、3.4个百分点;在规模较小的PASCAL VOC2007数据集上,所提算法使3种模型的AP分别实现了1.3、1.0和1.1个百分点的提升.通过EDWE、RLK和ESM模块的协同作用,所提算法有效提升了目标检测精度,在不同规模的数据集上均展现了显著的性能优势. 展开更多
关键词 检测头 目标检测 Transformer编码器 深度融合 大核卷积
在线阅读 下载PDF
面向视觉算法的知识蒸馏研究综述
4
作者 潘海为 于丰铭 +3 位作者 张可佳 兰海燕 孟庆宇 李哲 《计算机研究与发展》 北大核心 2026年第1期90-122,共33页
知识蒸馏作为深度学习中的关键技术,通过将大型教师模型的知识传递给较小的学生模型,实现了模型的压缩与加速。在保证性能的前提下,显著减少了计算资源和存储需求,促进了高性能模型在资源受限的边缘设备上的部署。围绕知识蒸馏的最新研... 知识蒸馏作为深度学习中的关键技术,通过将大型教师模型的知识传递给较小的学生模型,实现了模型的压缩与加速。在保证性能的前提下,显著减少了计算资源和存储需求,促进了高性能模型在资源受限的边缘设备上的部署。围绕知识蒸馏的最新研究进展进行了系统性的综述,从知识类型和师生模型架构2个角度对知识蒸馏进行分类,详细汇总了输出特征知识、中间特征知识、关系特征知识3种典型知识类型的蒸馏方法,以及卷积架构到卷积架构、卷积架构到ViT(vision Transformer)架构、ViT架构到卷积架构和ViT架构到ViT架构的蒸馏方法;探讨了离线蒸馏、在线蒸馏、自蒸馏、无数据蒸馏、多教师蒸馏和助理蒸馏的学习方式;归纳了基于蒸馏过程、知识结构、温度系数及损失函数的蒸馏优化方法,分析了对抗性技术、自动机器学习、强化学习和扩散模型对蒸馏的改进,并总结了蒸馏技术在常见应用中的实现。尽管知识蒸馏取得了显著进展,但在实际应用和理论研究中仍面临诸多挑战。最后,对这些问题进行了深入分析,并对未来发展方向提出了见解。 展开更多
关键词 知识蒸馏 模型压缩 深度学习 卷积神经网络 视觉Transformer
在线阅读 下载PDF
融合群分解与Transformer-KAN的短期风速预测
5
作者 史加荣 张思怡 《南京信息工程大学学报》 北大核心 2026年第1期60-68,共9页
针对风速固有的不稳定性,通过融合群分解(Swarm Decomposition,SWD)、Transformer和Kolmogorov-Arnold网络(KAN),提出一种SWD-Transformer-KAN预测模型.首先,利用SWD对原始风速数据进行分解,以提取关键特征.其次,针对每个被分解的子序列... 针对风速固有的不稳定性,通过融合群分解(Swarm Decomposition,SWD)、Transformer和Kolmogorov-Arnold网络(KAN),提出一种SWD-Transformer-KAN预测模型.首先,利用SWD对原始风速数据进行分解,以提取关键特征.其次,针对每个被分解的子序列,建立Transformer-KAN模型,所建模型充分利用了Transformer的时序处理能力和KAN的非线性逼近能力.最后,对所有子序列的预测结果进行叠加,得到最终的风速预测值.为了验证所提出模型的有效性,将其与其他模型进行实验对比,结果表明,SWD-Transformer-KAN模型具有最优的预测性能,其决定系数(R2)高达99.91%. 展开更多
关键词 风速预测 群分解 TRANSFORMER Kolmogorov-Arnold网络
在线阅读 下载PDF
基于动态优化细节感知网络的遥感图像分割方法
6
作者 梁书绮 王雷 +2 位作者 孙燕青 杨善良 李彬 《工程科学学报》 北大核心 2026年第1期177-189,共13页
现有的遥感图像分割模型,例如基于卷积神经网络(Convolutional neural network,CNN)和基于Transformer框架的模型,取得了巨大成功,但是还存在难以完整保留原始编码器特征图细节、动态捕捉全局上下文信息等缺点.因此,基于CNN-Transforme... 现有的遥感图像分割模型,例如基于卷积神经网络(Convolutional neural network,CNN)和基于Transformer框架的模型,取得了巨大成功,但是还存在难以完整保留原始编码器特征图细节、动态捕捉全局上下文信息等缺点.因此,基于CNN-Transformer混合框架,提出了一种全新的基于动态优化细节感知网络(Dynamic optimized detail-aware network,DODNet)的分割方法.首先,在编码器采用ResNext-50作为主干网络,提出一种多重减法感知模块(Multi-subtraction perception module,MSPM)来收集多尺度特征图之间的空间细节差异,有效减少冗余信息.然后,在解码器设计一个动态信息融合模块(Dynamic information fusion block,DIFB),它结合了全局双层路由自注意力分支和局部注意力分支,用于提高全局和局部信息的获取能力.最后,提出一种新的通道空间注意力模块—统一特征提取器(Unified feature extractor,UFE)以进一步获取语义和上下文信息.在Vaihingen、Potsdam和LoveDA三个经典公开数据集,通过对比和消融实验的定量和可视化分析表明,所提方法在F1分数、总体精度(Over accuracy,OA)和平均交并比(Mean intersection over union,mIoU)评价指标中优于十种最先进的分割方法,其中平均交并比分别达到了84.96%、87.64%和52.43%,验证了所提方法在分割具有复杂背景、内类方差大和类间方差小问题的高分辨率遥感图像的优越性能. 展开更多
关键词 遥感图像 语义分割 CNN-Transformer框架 动态Transformer 多尺度减法
在线阅读 下载PDF
基于深度学习的无人机单目标跟踪综述
7
作者 陈泷 石磊 +2 位作者 黎智辉 丁锰 潘亦伦 《计算机科学与探索》 北大核心 2026年第1期40-65,共26页
基于深度学习的无人机(UAV)单目标跟踪算法旨在从航拍视频序列中准确跟踪指定目标,已成为计算机视觉领域的研究热点。与传统地面视觉跟踪相比,无人机单目标跟踪面临着视角变化剧烈、目标尺度复杂多变、计算资源受限等独特挑战。基于网... 基于深度学习的无人机(UAV)单目标跟踪算法旨在从航拍视频序列中准确跟踪指定目标,已成为计算机视觉领域的研究热点。与传统地面视觉跟踪相比,无人机单目标跟踪面临着视角变化剧烈、目标尺度复杂多变、计算资源受限等独特挑战。基于网络架构特点,将基于深度学习的无人机单目标跟踪方法系统梳理为传统Siamese网络、CNN-Transformer混合架构和全Transformer三大技术路线,重点关注2022—2025年间的最新研究进展。创新性地提出了两个细化分类框架:针对CNN-Transformer混合架构提出模块替代、特征后融合和协同建模三分类;针对Transformer单流方法提出静态计算、混合机制和动态计算三分类。系统揭示了无人机单目标跟踪算法从追求性能最大化向性能与效率协同优化的演进趋势。通过在UAV123、DTB70、UAVDT、VisDrone2018等主流数据集上的性能对比分析,验证了不同技术路线的优势与局限性。识别当前技术面临的关键挑战并提出未来发展方向和工程部署指导。 展开更多
关键词 无人机 单目标跟踪 深度学习 Siamese网络 TRANSFORMER
在线阅读 下载PDF
基于Transformer-卷积神经网络模型实现单节点腰部康复训练动作识别任务
8
作者 余圣涵 成贤锴 +1 位作者 郑跃 杨颖 《中国组织工程研究》 北大核心 2026年第16期4125-4136,共12页
背景:惯性测量单元被广泛用于人体姿态感知与动态捕捉。深度学习已逐步替代传统规则与特征工程,广泛应用于动作识别任务。卷积神经网络在提取局部动态特征方面表现良好,Transformer则在建模长时序依赖方面展现出强大能力。目的:通过基于... 背景:惯性测量单元被广泛用于人体姿态感知与动态捕捉。深度学习已逐步替代传统规则与特征工程,广泛应用于动作识别任务。卷积神经网络在提取局部动态特征方面表现良好,Transformer则在建模长时序依赖方面展现出强大能力。目的:通过基于Transformer-卷积神经网络融合模型识别方法,实现在单惯性传感器条件下的腰部康复训练动作识别任务。方法:采集6名健康受试者佩戴单个惯性传感器条件下执行腰部康复动作的加速度与角速度数据,以动作类型为数据进行标注,制作腰部康复动作数据集。通过腰部康复动作数据集对Transformer-卷积神经网络融合模型进行训练,构建动作分类模型。通过留一交叉验证评估模型准确性,并与线性判别分析、支持向量机、多层感知、经典Transformer等模型进行性能对比。结果与结论:在5类动作识别任务中,Transformer-卷积神经网络模型准确率达96.67%,F1-score为0.9669。在单传感器输入的条件下,相较于传统模型,在识别精度与泛化能力方面具有明显优势。验证了基于单惯性测量单元数据的深度模型在腰部康复动作分类任务中的实用性,为轻量化、高部署性的居家腰部康复训练系统提供基础。 展开更多
关键词 慢性腰痛 康复训练 深度学习 TRANSFORMER 单节点惯性传感器 动作分类
暂未订购
基于DINO的海底管道掩埋状态识别算法
9
作者 谌贵军 崔学荣 《物联网技术》 2026年第1期26-29,33,共5页
浅地层剖面仪通过声波探测海底管道并生成浅剖图像,但传统人工判读效率低,现有算法在复杂背景下特征提取能力有限,难以准确判断管道掩埋状态。针对这些问题,文中提出了一种基于SK-DINO模型的检测方法,创新地结合选择性内核网络(SKNet)... 浅地层剖面仪通过声波探测海底管道并生成浅剖图像,但传统人工判读效率低,现有算法在复杂背景下特征提取能力有限,难以准确判断管道掩埋状态。针对这些问题,文中提出了一种基于SK-DINO模型的检测方法,创新地结合选择性内核网络(SKNet)和空间注意力模块(SAM),提出SK-SAM融合注意力机制,增强了目标特征提取能力。在此基础上,采用高斯误差线性单元激活函数提升模型的非线性表达能力,降低过拟合风险。实验结果表明,改进算法的mAP@0.5、AP@0.75:0.95和AR@0.5:0.95分别达到0.8995、0.3862和0.4184,显著提高了海底管道掩埋状态的识别准确率。 展开更多
关键词 图像识别 海底管道 DINO 浅地层剖面仪 注意力机制 TRANSFORMER
在线阅读 下载PDF
层级特征融合Transformer的图像分类算法
10
作者 段士玺 王博 《电子科技》 2026年第2期72-78,共7页
针对传统ViT(Vision Transformer)模型难以完成图像多层级分类问题,文中提出了基于ViT的图像分类模型层级特征融合视觉Transformer(Hierarchical Feature Fusion Vision Transformer,HICViT)。输入数据经过ViT提取模块生成多个不同层级... 针对传统ViT(Vision Transformer)模型难以完成图像多层级分类问题,文中提出了基于ViT的图像分类模型层级特征融合视觉Transformer(Hierarchical Feature Fusion Vision Transformer,HICViT)。输入数据经过ViT提取模块生成多个不同层级的特征图,每个特征图包含不同层次的抽象特征表示。基于层级标签将ViT提取的特征映射为多级特征,运用层级特征融合策略整合不同层级信息,有效增强模型的分类性能。在CIFRA-10、CIFRA-100和CUB-200-2011这3个数据集将所提模型与多种先进深度学习模型进行对比和分析。在CIFRA-10数据集,所提方法在第1层级、第2层级和第3层级的分类精度分别为99.70%、98.80%和97.80%。在CIFRA-100数据集,所提方法在第1层级、第2层级和第3层级的分类精度分别为95.23%、93.54%和90.12%。在CUB-200-2011数据集,所提方法在第1层级和第2层级的分类精度分别为98.09%和93.66%。结果表明,所提模型的分类准确率优于其他对比模型。 展开更多
关键词 深度学习 卷积神经网络 TRANSFORMER 图像分类 层级特征 特征融合 多头注意力 Vision Transformer
在线阅读 下载PDF
Time Delay Estimation of Target Echo Signal Based on Multi-bright Spot Echoes
11
作者 Ge Yu Fan Du +1 位作者 Xiukun Li Yan Li 《哈尔滨工程大学学报(英文版)》 2026年第1期312-325,共14页
Accurate time delay estimation of target echo signals is a critical component of underwater target localization.In active sonar systems,echo signal processing is vulnerable to the effects of reverberation and noise in... Accurate time delay estimation of target echo signals is a critical component of underwater target localization.In active sonar systems,echo signal processing is vulnerable to the effects of reverberation and noise in the maritime environment.This paper proposes a novel method for estimating target time delay using multi-bright spot echoes,assuming the target’s size and depth are known.Aiming to effectively enhance the extraction of geometric features from the target echoes and mitigate the impact of reverberation and noise,the proposed approach employs the fractional order Fourier transform-frequency sliced wavelet transform to extract multi-bright spot echoes.Using the highlighting model theory and the target size information,an observation matrix is constructed to represent multi-angle incident signals and obtain the theoretical scattered echo signals from different angles.Aiming to accurately estimate the target’s time delay,waveform similarity coefficients and mean square error values between the theoretical return signals and received signals are computed across various incident angles and time delays.Simulation results show that,compared to the conventional matched filter,the proposed algorithm reduces the relative error by 65.9%-91.5%at a signal-to noise ratio of-25 dB,and by 66.7%-88.9%at a signal-to-reverberation ratio of−10 dB.This algorithm provides a new approach for the precise localization of submerged targets in shallow water environments. 展开更多
关键词 Multi-bright spot echoes Time-delay estimation Target echo signal Frequency sliced wavelet transform Fractional order fourier transform
在线阅读 下载PDF
A Transformative Masterpiece--Chinese-built bridge in Tanzania boosts trade,connectivity
12
作者 DERRICK SILIMINA 《ChinAfrica》 2026年第1期42-43,共2页
In the Kigongo area of Mwanza Region,northwest Tanzania,fishmonger Neema Aisha remembers how the morning’s fresh catch would sour while she queued for the ferry,putting her business at risk.
关键词 business risk FERRY BRIDGE CONNECTIVITY TRADE fishmonger transformative
原文传递
The Sweet Success of a Rural Fruit Industry
13
作者 FAN YUQING 《China Today》 2026年第1期30-33,共4页
Zuoquan County has revitalized local villages with the fruits of their collected labor.GLOWING red apples hang heavily on branches in the orchards on the southern outskirts of Tongyu Town,Zuoquan County,Shanxi Provinc... Zuoquan County has revitalized local villages with the fruits of their collected labor.GLOWING red apples hang heavily on branches in the orchards on the southern outskirts of Tongyu Town,Zuoquan County,Shanxi Province,an area where a decade ago weeds and rocks covered a rather barren landscape. 展开更多
关键词 ORCHARDS weeds rocks rural fruit industry LABOR REVITALIZATION landscape transformation
在线阅读 下载PDF
Nanjing:From Manufacturing Base to Research Hub
14
作者 ZHAO PIAO 《China Today》 2026年第1期48-49,共2页
Nanjing’s determination to transform itself from a production base to a research center reflects China’s evolution toward higher-quality development.A refrigerator that thaws frozen meat in 10 minutes and then keeps... Nanjing’s determination to transform itself from a production base to a research center reflects China’s evolution toward higher-quality development.A refrigerator that thaws frozen meat in 10 minutes and then keeps it fresh,a cooker hood that remains clean even after 10 years without disassembling it for cleaning. 展开更多
关键词 thaws frozen meat cooker hood high quality development manufacturing RESEARCH transformation REFRIGERATOR
在线阅读 下载PDF
Cell type-dependent role of transforming growth factor-βsignaling on postnatal neural stem cell proliferation and migration
15
作者 Kierra Ware Joshua Peter +1 位作者 Lucas McClain Yu Luo 《Neural Regeneration Research》 2026年第3期1151-1161,共11页
Adult neurogenesis continuously produces new neurons critical for cognitive plasticity in adult rodents.While it is known transforming growth factor-βsignaling is important in embryonic neurogenesis,its role in postn... Adult neurogenesis continuously produces new neurons critical for cognitive plasticity in adult rodents.While it is known transforming growth factor-βsignaling is important in embryonic neurogenesis,its role in postnatal neurogenesis remains unclear.In this study,to define the precise role of transforming growth factor-βsignaling in postnatal neurogenesis at distinct stages of the neurogenic cascade both in vitro and in vivo,we developed two novel inducible and cell type-specific mouse models to specifically silence transforming growth factor-βsignaling in neural stem cells in(mGFAPcre-ALK5fl/fl-Ai9)or immature neuroblasts in(DCXcreERT2-ALK5fl/fl-Ai9).Our data showed that exogenous transforming growth factor-βtreatment led to inhibition of the proliferation of primary neural stem cells while stimulating their migration.These effects were abolished in activin-like kinase 5(ALK5)knockout primary neural stem cells.Consistent with this,inhibition of transforming growth factor-βsignaling with SB-431542 in wild-type neural stem cells stimulated proliferation while inhibited the migration of neural stem cells.Interestingly,deletion of transforming growth factor-βreceptor in neural stem cells in vivo inhibited the migration of postnatal born neurons in mGFAPcre-ALK5fl/fl-Ai9 mice,while abolishment of transforming growth factor-βsignaling in immature neuroblasts in DCXcreERT2-ALK5fl/fl-Ai9 mice did not affect the migration of these cells in the hippocampus.In summary,our data supports a dual role of transforming growth factor-βsignaling in the proliferation and migration of neural stem cells in vitro.Moreover,our data provides novel insights on cell type-specific-dependent requirements of transforming growth factor-βsignaling on neural stem cell proliferation and migration in vivo. 展开更多
关键词 adult neurogenesis DOUBLECORTIN HIPPOCAMPUS MIGRATION neural stem cells PROLIFERATION transforming growth factor-β
暂未订购
Effect of fluoride roasting on copper species transformation on chrysocolla surfaces and its role in enhanced sulfidation flotation
16
作者 Yingqiang Ma Xin Huang +5 位作者 Yafeng Fu Zhenguo Song Sen Luo Shuanglin Zheng Feng Rao Wanzhong Yin 《International Journal of Minerals,Metallurgy and Materials》 2026年第1期165-176,共12页
It is difficult to recover chrysocolla from sulfidation flotation which is closely related to the mineral surface composition.In this study,the effects of fluoride roasting on the surface composition of chrysocolla we... It is difficult to recover chrysocolla from sulfidation flotation which is closely related to the mineral surface composition.In this study,the effects of fluoride roasting on the surface composition of chrysocolla were investigated,its impact on sulfidation flotation was explored,and the mechanisms involved in both fluoride roasting and sulfidation flotation were discussed.With CaF_(2)as the roasting reagent,Na_(2)S·9H_(2)O as the sulfidation reagent,and sodium butyl xanthate(NaBX)as the collector,the results of the flotation experiments showed that fluoride roasting improved the floatability of chrysocolla,and the recovery rate increased from 16.87%to 82.74%.X-ray diffraction analysis revealed that after fluoride roasting,approximately all the Cu on the chrysocolla surface was exposed in the form of CuO,which could provide a basis for subsequent sulfidation flotation.The microscopy and elemental analyses revealed that large quantities of"pagoda-like"grains were observed on the sulfidation surface of the fluoride-roasted chrysocolla,indicating high crystallinity particles of copper sulfide.This suggests that the effect of sulfide formation on the chrysocolla surface was more pronounced.X-ray photoelectron spectroscopy revealed that fluoride roasting increased the relative contents of sulfur and copper on the surface and that both the Cu~+and polysulfide fractions on the surface of the minerals increased.This enhances the effect of sulfidation,which is conducive to flotation recovery.Therefore,fluoride roasting improved the effect of copper species transformation and sulfidation on the surface of chysocolla,promoted the adsorption of collectors,and improved the recovery of chrysocolla from sulfidation flotation. 展开更多
关键词 sulfidation flotation CHRYSOCOLLA fluoride roasting copper species transformation enhanced sulfidation
在线阅读 下载PDF
Tracking a High-Tech Transition--How technology is powering Guangdong’s manufacturing transformation
17
作者 HU FAN 《ChinAfrica》 2026年第1期30-32,共3页
The moment a media delegation from the Republic of the Congo arrived at the Othello Kitchenware Museum on 18 November 2025,they were greeted with a vivid show of Guangdong’s industrial strength.Standing before them w... The moment a media delegation from the Republic of the Congo arrived at the Othello Kitchenware Museum on 18 November 2025,they were greeted with a vivid show of Guangdong’s industrial strength.Standing before them was not a typical exhibition hall,but a building shaped like a gleaming stainless-steel cooking pot. 展开更多
关键词 othello kitchenware museum TECHNOLOGY industrial strength high tech transition guangdong manufacturing transformation
原文传递
SELECTED REMARKS OF CHINESE PRESIDENT XI JINPING
18
《ChinAfrica》 2026年第1期6-6,共1页
AI,as a strategic technology leading the new round of scientific and technological revolution and industrial transformation,is profoundly reshaping people’s work and life.Chinese President Xi Jinping called for promo... AI,as a strategic technology leading the new round of scientific and technological revolution and industrial transformation,is profoundly reshaping people’s work and life.Chinese President Xi Jinping called for promoting a healthy and orderly development of AI during the 20th group study session of the Political Bureau of the Communist Party of China(CPC)Central Committee held on 25 April 2025. 展开更多
关键词 AI scientific technological revolution healthy orderly development industrial transformation
原文传递
基于Transformer的无人机故障检测研究
19
作者 张自旺 沈剑 +3 位作者 王晓光 刘繁 曹卓 贺斌娜 《机械设计与制造工程》 2026年第1期82-86,共5页
无人机故障检测作为保障飞行安全的核心技术,当前研究多依赖于仿真实验数据,并且传统方法难以有效捕捉飞行数据中的长程时空依赖关系。针对这些挑战,提出了一种基于Transformer架构的无人机故障检测方法,通过可学习位置编码和多头自注... 无人机故障检测作为保障飞行安全的核心技术,当前研究多依赖于仿真实验数据,并且传统方法难以有效捕捉飞行数据中的长程时空依赖关系。针对这些挑战,提出了一种基于Transformer架构的无人机故障检测方法,通过可学习位置编码和多头自注意力机制,构建传感器数据的时空依赖关系;同时结合焦点损失函数缓解类别不平衡问题。实验结果表明,该方法在真实飞行数据集上准确率达95%、F1分数达94%,相比基于LSTM和随机森林的故障检测方法展现更优的综合性能,并且在实时检测模拟中具有良好的可靠性,充分验证了其在真实飞行场景中的工程适用性。 展开更多
关键词 无人机 故障检测 TRANSFORMER 焦点损失函数 实时检测模拟
在线阅读 下载PDF
Steering China’s High-Quality Growth
20
作者 《China Today》 2026年第1期16-19,共4页
Chinese President Xi Jinping has guided China through a year of resilient growth via forward-looking reforms and innovation-driven transformation that is shaping the nation’s economic trajectory for 2026 and beyond.
关键词 forward looking reforms high quality growth STEERING resilient growth innovation driven transformation
在线阅读 下载PDF
上一页 1 2 250 下一页 到第
使用帮助 返回顶部