期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到3,816篇文章
< 1 2 … 191 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
ACSF-ED: Adaptive Cross-Scale Fusion Encoder-Decoder for Spatio-Temporal Action Detection 认领 引用
1
作者 Wenju Wang Zehua Gu +2 位作者 Bang Tang Sen Wang Jianfei Hao 《Computers, Materials & Continua》 SCIE EI 2025年第2期2389-2414,共26页
Current spatio-temporal action detection methods lack sufficient capabilities in extracting and comprehending spatio-temporal information. This paper introduces an end-to-end Adaptive Cross-Scale Fusion Encoder-Decode... Current spatio-temporal action detection methods lack sufficient capabilities in extracting and comprehending spatio-temporal information. This paper introduces an end-to-end Adaptive Cross-Scale Fusion Encoder-Decoder (ACSF-ED) network to predict the action and locate the object efficiently. In the Adaptive Cross-Scale Fusion Spatio-Temporal Encoder (ACSF ST-Encoder), the Asymptotic Cross-scale Feature-fusion Module (ACCFM) is designed to address the issue of information degradation caused by the propagation of high-level semantic information, thereby extracting high-quality multi-scale features to provide superior features for subsequent spatio-temporal information modeling. Within the Shared-Head Decoder structure, a shared classification and regression detection head is constructed. A multi-constraint loss function composed of one-to-one, one-to-many, and contrastive denoising losses is designed to address the problem of insufficient constraint force in predicting results with traditional methods. This loss function enhances the accuracy of model classification predictions and improves the proximity of regression position predictions to ground truth objects. The proposed method model is evaluated on the popular dataset UCF101-24 and JHMDB-21. Experimental results demonstrate that the proposed method achieves an accuracy of 81.52% on the Frame-mAP metric, surpassing current existing methods. 展开更多
关键词 Spatio-temporal action detection encoder-decoder cross-scale fusion multi-constraint loss function
暂未订购 下载PDF
A Road Extraction Method for Remote Sensing Image Based on Encoder-Decoder Network 认领 引用 被引量：31
2
作者 Hao HE Shuyang WANG +2 位作者 Shicheng WANG Dongfang YANG Xing LIU 《Journal of Geodesy and Geoinformation Science》 2020年第2期16-25,共10页
According to the characteristics of the road features,an Encoder-Decoder deep semantic segmentation network is designed for the road extraction of remote sensing images.Firstly,as the features of the road target are r... According to the characteristics of the road features,an Encoder-Decoder deep semantic segmentation network is designed for the road extraction of remote sensing images.Firstly,as the features of the road target are rich in local details and simple in semantic features,an Encoder-Decoder network with shallow layers and high resolution is designed to improve the ability to represent detail information.Secondly,as the road area is a small proportion in remote sensing images,the cross-entropy loss function is improved,which solves the imbalance between positive and negative samples in the training process.Experiments on large road extraction datasets show that the proposed method gets the recall rate 83.9%,precision 82.5%and F1-score 82.9%,which can extract the road targets in remote sensing images completely and accurately.The Encoder-Decoder network designed in this paper performs well in the road extraction task and needs less artificial participation,so it has a good application prospect. 展开更多
关键词 remote sensing road extraction deep learning semantic segmentation Encoder-Decoder network
暂未订购 下载PDF
Rethinking the Encoder-decoder Structure in Medical Image Segmentation from Releasing Decoder Structure 认领 引用 被引量：1
3
作者 Jiajia Ni Wei Mu +1 位作者 An Pan Zhengming Chen 《Journal of Bionic Engineering》 SCIE EI CSCD 2024年第3期1511-1521,共11页
Medical image segmentation has witnessed rapid advancements with the emergence of encoder-decoder based methods.In the encoder-decoder structure,the primary goal of the decoding phase is not only to restore feature ma... Medical image segmentation has witnessed rapid advancements with the emergence of encoder-decoder based methods.In the encoder-decoder structure,the primary goal of the decoding phase is not only to restore feature map resolution,but also to mitigate the loss of feature information incurred during the encoding phase.However,this approach gives rise to a challenge:multiple up-sampling operations in the decoder segment result in the loss of feature information.To address this challenge,we propose a novel network that removes the decoding structure to reduce feature information loss(CBL-Net).In particular,we introduce a Parallel Pooling Module(PPM)to counteract the feature information loss stemming from conventional and pooling operations during the encoding stage.Furthermore,we incorporate a Multiplexed Dilation Convolution(MDC)module to expand the network's receptive field.Also,although we have removed the decoding stage,we still need to recover the feature map resolution.Therefore,we introduced the Global Feature Recovery(GFR)module.It uses attention mechanism for the image feature map resolution recovery,which can effectively reduce the loss of feature information.We conduct extensive experimental evaluations on three publicly available medical image segmentation datasets:DRIVE,CHASEDB and MoNuSeg datasets.Experimental results show that our proposed network outperforms state-of-the-art methods in medical image segmentation.In addition,it achieves higher efficiency than the current network of coding and decoding structures by eliminating the decoding component. 展开更多
关键词 Medical image segmentation Encoder-decoder architecture Attention mechanisms Releasing decoder architecture Neural network
Underwater Acoustic Signal Noise Reduction Based on a Fully Convolutional Encoder-Decoder Neural Network 认领 引用
4
作者 SONG Yongqiang CHU Qian +2 位作者 LIU Feng WANG Tao SHEN Tongsheng 《Journal of Ocean University of China》 SCIE CAS CSCD 2023年第6期1487-1496,共10页
Noise reduction analysis of signals is essential for modern underwater acoustic detection systems.The traditional noise reduction techniques gradually lose efficacy because the target signal is masked by biological an... Noise reduction analysis of signals is essential for modern underwater acoustic detection systems.The traditional noise reduction techniques gradually lose efficacy because the target signal is masked by biological and natural noise in the marine environ-ment.The feature extraction method combining time-frequency spectrograms and deep learning can effectively achieve the separation of noise and target signals.A fully convolutional encoder-decoder neural network(FCEDN)is proposed to address the issue of noise reduc-tion in underwater acoustic signals.The time-domain waveform map of underwater acoustic signals is converted into a wavelet low-frequency analysis recording spectrogram during the denoising process to preserve as many underwater acoustic signal characteristics as possible.The FCEDN is built to learn the spectrogram mapping between noise and target signals that can be learned at each time level.The transposed convolution transforms are introduced,which can transform the spectrogram features of the signals into listenable audio files.After evaluating the systems on the ShipsEar Dataset,the proposed method can increase SNR and SI-SNR by 10.02 and 9.5dB,re-spectively. 展开更多
关键词 deep learning convolutional encoder-decoder neural network wavelet low-frequency analysis recording spectrogram
暂未订购 下载PDF
Classification of Arrhythmia Based on Convolutional Neural Networks and Encoder-Decoder Model 认领 引用
5
作者 Jian Liu Xiaodong Xia +2 位作者 Chunyang Han Jiao Hui Jim Feng 《Computers, Materials & Continua》 SCIE EI 2022年第10期265-278,共14页
As a common and high-risk type of disease,heart disease seriously threatens people’s health.At the same time,in the era of the Internet of Thing(IoT),smart medical device has strong practical significance for medical... As a common and high-risk type of disease,heart disease seriously threatens people’s health.At the same time,in the era of the Internet of Thing(IoT),smart medical device has strong practical significance for medical workers and patients because of its ability to assist in the diagnosis of diseases.Therefore,the research of real-time diagnosis and classification algorithms for arrhythmia can help to improve the diagnostic efficiency of diseases.In this paper,we design an automatic arrhythmia classification algorithm model based on Convolutional Neural Network(CNN)and Encoder-Decoder model.The model uses Long Short-Term Memory(LSTM)to consider the influence of time series features on classification results.Simultaneously,it is trained and tested by the MIT-BIH arrhythmia database.Besides,Generative Adversarial Networks(GAN)is adopted as a method of data equalization for solving data imbalance problem.The simulation results show that for the inter-patient arrhythmia classification,the hybrid model combining CNN and Encoder-Decoder model has the best classification accuracy,of which the accuracy can reach 94.05%.Especially,it has a better advantage for the classification effect of supraventricular ectopic beats(class S)and fusion beats(class F). 展开更多
关键词 Electroencephalography convolutional neural network long short-term memory encoder-decoder model generative adversarial network
暂未订购 下载PDF
Robust Cultivated Land Extraction Using Encoder-Decoder 认领 引用
6
作者 Aziguli Wulamu Jingyue Sang +1 位作者 Dezheng Zhang and Zuxian Shi 《Journal of New Media》 2020年第4期149-155,共7页
Cultivated land extraction is essential for sustainable development and agriculture.In this paper,the network we propose is based on the encoder-decoder structure,which extracts the semantic segmentation neural networ... Cultivated land extraction is essential for sustainable development and agriculture.In this paper,the network we propose is based on the encoder-decoder structure,which extracts the semantic segmentation neural network of cultivated land from satellite images and uses it for agricultural automation solutions.The encoder consists of two part:the first is the modified Xception,it can used as the feature extraction network,and the second is the atrous convolution,it can used to expand the receptive field and the context information to extract richer feature information.The decoder part uses the conventional upsampling operation to restore the original resolution.In addition,we use the combination of BCE and Loves-hinge as a loss function to optimize the Intersection over Union(IoU).Experimental results show that the proposed network structure can solve the problem of cultivated land extraction in Yinchuan City. 展开更多
关键词 Semantic segmentation encoder-decoder cultivated land extraction atrous convolution
暂未订购 下载PDF
Encoder-Decoder Based LSTM Model to Advance User QoE in 360-Degree Video 认领 引用
7
作者 Muhammad Usman Younus Rabia Shafi +4 位作者 Ammar Rafiq Muhammad Rizwan Anjum Sharjeel Afridi Abdul Aleem Jamali Zulfiqar Ali Arain 《Computers, Materials & Continua》 SCIE EI 2022年第5期2617-2631,共15页
The development of multimedia content has resulted in a massiveincrease in network traffic for video streaming. It demands such types ofsolutions that can be addressed to obtain the user’s Quality-of-Experience(QoE).... The development of multimedia content has resulted in a massiveincrease in network traffic for video streaming. It demands such types ofsolutions that can be addressed to obtain the user’s Quality-of-Experience(QoE). 360-degree videos have already taken up the user’s behavior by storm.However, the users only focus on the part of 360-degree videos, known as aviewport. Despite the immense hype, 360-degree videos convey a loathsomeside effect about viewport prediction, making viewers feel uncomfortablebecause user viewport needs to be pre-fetched in advance. Ideally, we canminimize the bandwidth consumption if we know what the user motionin advance. Looking into the problem definition, we propose an EncoderDecoder based Long-Short Term Memory (LSTM) model to more accuratelycapture the non-linear relationship between past and future viewport positions. This model takes the transforming data instead of taking the direct inputto predict the future user movement. Then, this prediction model is combinedwith a rate adaptation approach that assigns the bitrates to various tiles for360-degree video frames under a given network capacity. Hence, our proposedwork aims to facilitate improved system performance when QoE parametersare jointly optimized. Some experiments were carried out and compared withexisting work to prove the performance of the proposed model. Last but notleast, the experiments implementation of our proposed work provides highuser’s QoE than its competitors. 展开更多
关键词 Encoder-decoder based lSTM 360-degree video streaming LSTM QoE viewport prediction
暂未订购 下载PDF
The epidemiology and outcomes of adult cancer patients with suspected neutropenic fever in the emergency department 认领 引用
8
作者 Shi Yeow Lee Rex Pui Kin Lam +6 位作者 Siu Chung Leung Yan Yiu Yu Tat Chi Tsang Rock Yuk Yan Leung ChungYan Joanne Leung Michael Chun Kai Lau Timothy Hudson Rainer 《World Journal of Emergency Medicine》 SCIE CAS CSCD 2026年第3期258-261,共4页
Neutropenic fever(NF)is an oncologic emergency associated with significant mortality and healthcare burden in patients with hematologic and solid organ malignancies.Cancer patients with fever often present to the emer... Neutropenic fever(NF)is an oncologic emergency associated with significant mortality and healthcare burden in patients with hematologic and solid organ malignancies.Cancer patients with fever often present to the emergency department(ED).The American Society of Clinical Oncology and the European Society for Medical Oncology recommend administering the first dose of empirical antibiotics to patients with NF within 1 h of ED triage. 展开更多
关键词 epidemiology adult cancer patients outcomes emergency department ed neutropenic fever hematologic solid organ malignanciescancer neutropenic fever nf emergency department
暂未订购 下载PDF
血清CITED2、BMAL1、NSUN3水平与脓毒症并发急性肾损伤患者病情的相关性及对预后的影响 认领 引用 被引量：1
9
作者 陈曼宁 李璐 +3 位作者 刘睿 黎璞 彭细娟 高雅 《疑难病杂志》 CAS 2026年第3期291-297,共7页
目的分析血清富含ED尾的CBP/p300相互作用反式激活因子2(CITED2)、脑-肌肉芳烃受体核转录因子样蛋白-1(BMAL1)、NOP2/Sun RNA甲基转移酶3(NSUN3)水平与脓毒症并发急性肾损伤(AKI)患者病情的相关性及对预后不良的影响。方法选取2023年2月... 目的分析血清富含ED尾的CBP/p300相互作用反式激活因子2(CITED2)、脑-肌肉芳烃受体核转录因子样蛋白-1(BMAL1)、NOP2/Sun RNA甲基转移酶3(NSUN3)水平与脓毒症并发急性肾损伤(AKI)患者病情的相关性及对预后不良的影响。方法选取2023年2月—2025年3月空军军医大学唐都医院重症医学科收治的脓毒症并发AKI患者123例作为脓毒症AKI组,脓毒症并发AKI患者根据AKI分期标准分为Ⅰ期45例、Ⅱ期40例、Ⅲ期38例,根据治疗28 d的生存情况分为生存亚组81例与死亡亚组42例,另选取同期医院收治的单纯脓毒症患者115例作为脓毒症组、健康志愿者123例作为健康对照组。采用ELISA法检测血清CITED2水平,qRT-PCR法检测血清BMAL1、NSUN3 mRNA表达;Pearson相关性分析变量间关系;多因素Cox分析影响脓毒症并发AKI患者预后不良的因素;受试者工作特征(ROC)曲线分析脓毒症并发AKI患者预后不良的预测价值。结果健康对照组、脓毒症组、脓毒症AKI组血清CITED2、NSUN3 mRNA水平依次升高,血清BMAL1 mRNA水平依次降低(F/P=544.535/<0.001、728.950/<0.001、478.098/<0.001);Ⅰ期、Ⅱ期、Ⅲ期脓毒症AKI患者血清CITED2、NSUN3 mRNA水平依次升高,血清BMAL1 mRNA水平依次降低(F/P=33.532/<0.001、22.012/<0.001、72.544/<0.001);死亡亚组血清CITED2、NSUN3 mRNA高于生存亚组,血清BMAL1 mRNA水平低于生存亚组(t/P=7.514/<0.001、7.639/<0.001、8.095/<0.001);脓毒症AKI患者血清CITED2、NSUN3 mRNA分别与APACHEⅡ评分、SOFA评分呈正相关(CITED2:r/P=0.512/<0.001、0.508/<0.001;NSUN3 mRNA:0.506/<0.001、0.513/<0.001),血清BMAL1 mRNA与APACHEⅡ评分、SOFA评分呈负相关(r/P=-0.527/<0.001、-0.519/<0.001);APACHEⅡ评分高、SOFA评分高、CITED2高、NSUN3 mRNA高是脓毒症AKI患者预后不良的独立危险因素[HR(95%CI)=2.078(1.353~3.192)、2.343(1.458~3.765)、2.436(1.763~3.366)、2.651(1.777~3.954)],BMAL1 mRNA高是独立保护因素[HR(95%CI)=0.314(0.172~0.572)];血清CITED2、BMAL1 mRNA、NSUN3 mRNA单独及三者联合预测脓毒症AKI患者预后不良的曲线下面积(AUC)分别为0.794、0.814、0.810、0.916,三者联合优于各自单独预测价值(Z/P=2.780/0.005、2.084/0.037、2.435/0.015)。结论脓毒症并发AKI患者血清CITED2、NSUN3 mRNA水平升高,BMAL1 mRNA水平下降,三者与病情程度、预后不良有关,可作为潜在的脓毒症并发AKI患者28 d内死亡的生物指标。 展开更多
关键词 脓毒症 急性肾损伤 富含ED尾的CBP/p300相互作用反式激活因子2 脑-肌肉芳烃受体核转录因子样蛋白-1 NOP2/Sun RNA甲基转移酶3 病情程度 预后
暂未订购 下载PDF
Comment on:Patient experiences with laparoscopic incisions under enhanced recovery after surgery protocols 认领 引用
10
作者 Haseeb Safdar Ali 《Laparoscopic, Endoscopic and Robotic Surgery》 2026年第1期56-57,共2页
We found the qualitative study by Xu et al.on how patients feel about laparoscopic incisions under enhanced recovery after surgery(ERAS)protocols to be very interesting.1 Xu et al.carried out a qualitative study on pa... We found the qualitative study by Xu et al.on how patients feel about laparoscopic incisions under enhanced recovery after surgery(ERAS)protocols to be very interesting.1 Xu et al.carried out a qualitative study on patient experience with laparoscopic incisions under an ERAS protocol to highlight the problem of psychosocial and aesthetic concerns,which are often overlooked when planning surgical operations.This study,which involved semistructured interviews with sixteen people,aimed to narrow perioperative education and the decision-making process for incision site selection,thus making the processes more focused on patient priorities.The study is based on a timely but under-researched subject area;however,it is possible to outline four possible areas of improvement that would allow the study to be more transparent and,at the same time,more applicable to clinical practice. 展开更多
关键词 laparoscopic incisions patient experience qualitative study narrow perioperative ed enhanced recovery surgery ERAS psychosocial concerns semistructured interviews
暂未订购 下载PDF
Action-Aware Encoder-Decoder Network for Pedestrian Trajectory Prediction 认领 引用
11
作者 傅家威 赵旭 《Journal of Shanghai Jiaotong university(Science)》 EI 2023年第1期20-27,共8页
Accurate pedestrian trajectory predictions are critical in self-driving systems,as they are fundamental to the response-and decision-making of ego vehicles.In this study,we focus on the problem of predicting the futur... Accurate pedestrian trajectory predictions are critical in self-driving systems,as they are fundamental to the response-and decision-making of ego vehicles.In this study,we focus on the problem of predicting the future trajectory of pedestrians from a first-person perspective.Most existing trajectory prediction methods from the first-person view copy the bird’s-eye view,neglecting the differences between the two.To this end,we clarify the differences between the two views and highlight the importance of action-aware trajectory prediction in the first-person view.We propose a new action-aware network based on an encoder-decoder framework with an action prediction and a goal estimation branch at the end of the encoder.In the decoder part,bidirectional long short-term memory(Bi-LSTM)blocks are adopted to generate the ultimate prediction of pedestrians’future trajectories.Our method was evaluated on a public dataset and achieved a competitive performance,compared with other approaches.An ablation study demonstrates the effectiveness of the action prediction branch. 展开更多
关键词 pedestrian trajectory prediction first-person view action prediction encoder-decoder bidirectional long short-term memory(Bi-LSTM)
暂未订购 下载PDF
基于SEDS的星载业务描述工具设计 认领 引用
12
作者 张梁 吕良庆 何睿 《计算机工程与设计》 北大核心 2026年第3期817-824,共8页
为解决星载业务的即插即用问题,对航天器星载接口业务电子数据单(SEDS)和欧空局包应用标准(PUS)进行了研究,提出了一种专注于星载业务层面的接口信息及其关系的描述方法。基于该方法,设计了模板生成工具、文件生成工具和格式转换工具,... 为解决星载业务的即插即用问题,对航天器星载接口业务电子数据单(SEDS)和欧空局包应用标准(PUS)进行了研究,提出了一种专注于星载业务层面的接口信息及其关系的描述方法。基于该方法,设计了模板生成工具、文件生成工具和格式转换工具,供用户实现对星载业务的设计定义。以星载事件表业务为例,对工具链开展了实例验证,实验结果验证了其可行性和有效性。本文提出的星载业务描述方法及其工具链系统实现为业务数据的标准化描述和处理提供了支持,能够提升星载信息系统的即插即用能力。 展开更多
关键词 空间数据系统 即插即用 电子数据单 工具链 包应用标准 星载业务 可扩展标记语言
暂未订购 下载PDF
实现三大突破! 重庆青山EDS0-2.0 首台样机成功下线 认领 引用
13
《变频器世界》 2026年第4期76-76,共1页
近日,重庆青山EDS0-2.0首台样机成功下线,标志着公司在60-100kW小型电驱领域的集成开发迈出关键一步。随着新能源汽车市场持续下沉,A0级及以下车型对电驱系统的小型化、轻量化、高集成度和低成本提出了挑战。EDS0-2.0项目组基于小型化... 近日,重庆青山EDS0-2.0首台样机成功下线,标志着公司在60-100kW小型电驱领域的集成开发迈出关键一步。随着新能源汽车市场持续下沉,A0级及以下车型对电驱系统的小型化、轻量化、高集成度和低成本提出了挑战。EDS0-2.0项目组基于小型化、轻量化、平台化、低成本的需求导向,历时3个月高效完成需求分析、集成设计与样机试制,全力攻坚小型电驱在整车布置中的空间难题,以“青山速度”展现了技术响应能力与研发实力。 展开更多
关键词 小型电驱 新能源汽车 EDS0-2.0
暂未订购 下载PDF
Optimizing land cover planning for carbon neutrality:Policy insights from scenario-based vegetation carbon sink assessment in the Guangdong-Hong Kong-Macao Greater Bay Area,China 认领 引用
14
作者 WEN Youyue CHEN Zhichao +1 位作者 CAI Saoman YANG Jian 《Regional Sustainability》 CAS CSCD 2026年第4期37-56,共20页
Mitigating national climate change requires achieving carbon neutrality,necessitating innovative land cover strategies that reconcile economic development with enhanced carbon sinks,particularly in rapidly urbanizing ... Mitigating national climate change requires achieving carbon neutrality,necessitating innovative land cover strategies that reconcile economic development with enhanced carbon sinks,particularly in rapidly urbanizing megaregions such as the Guangdong-Hong Kong-Macao Greater Bay Area(GBA)in China.This study developed a novel assessment framework that integrates Multi-Objective Programming(MOP)land cover simulations with a Carbon Neutrality Effect(CNE)matrix and a neighborhood proxy method.This framework provides a quantitative evaluation of vegetation carbon sink dynamics resulting from land cover transitions during 2020-2060 under four scenarios:economic development first(ED),carbon neutrality first(EC),sustainable development(EDC),and natural development(EN).Model validation achieved high accuracy(Kappa coefficient=0.77,Overall Accuracy(OA)=0.84).Projected land cover changes revealed distinct transition patterns.Specifically,under the ED and EN scenarios,land cover changes will dominate by the expansion of urban area at the losses of grassland and crop land;under the EC scenario,the new forested land is primarily from crop land and grassland;and under the EDC scenario,urban area and forested land will achieve simultaneous expansion.Moreover,this study found the net vegetation carbon losses of 51.43×1010and 274.54×1010g C under the ED and EN scenarios,respectively,undermining carbon neutrality.In contrast,there will be a significant net carbon gain(64.52×1010g C)under the EC scenario.Crucially,the EDC scenario demonstrates a viable balance,minimizing vegetation carbon loss(7.00×1010g C)while substantially enhancing both socioeconomic benefit(1.34×1012CNY/a)and vegetation carbon sink benefit(0.15×1012CNY/a).This study underscores the critical role of optimized land cover planning in fostering synergistic economic growth and carbon neutrality.The findings provide actionable insights for the implementation of‘Dual Carbon’strategy in the GBA and serve as a valuable reference for sustainable land management in climate-vulnerable coastal megacities worldwide. 展开更多
关键词 Multi-Objective Programming(MOP) Carbon neutrality effect(CNE) matrix Economic development first(ED) Carbon neutrality first(EC) Sustainable development(EDC) Natural development(EN) Guangdong-Hong Kong-Macao Greater Bay Area(GBA)
暂未订购 下载PDF
美盈森获得“ED油墨印刷固化装置”专利授权 认领 引用
15
作者 乔羽 《广东印刷》 2026年第3期5-5,共1页
天眼查APP数据显示,美盈森集团股份有限公司新获得一项专利授权,专利名为“ED油墨印刷固化装置”,专利申请号为CN202520995103.X,授权日为2026年5月12日。专利摘要显示:本专利属于印刷技术领域,公开了一种ED油墨印刷固化装置,包括机体... 天眼查APP数据显示,美盈森集团股份有限公司新获得一项专利授权,专利名为“ED油墨印刷固化装置”,专利申请号为CN202520995103.X,授权日为2026年5月12日。专利摘要显示:本专利属于印刷技术领域,公开了一种ED油墨印刷固化装置,包括机体、惰性气体生成装置、电子束发生器、惰性气体喷射装置以及控制系统。 展开更多
关键词 美盈森集团股份有限公司 ED油墨印刷固化装置 专利授权
暂未订购 下载PDF
基于encoder-decoder框架的城镇污水厂出水水质预测 认领 引用 被引量：6
16
作者 史红伟 陈祺 +1 位作者 王云龙 李鹏程 《中国农村水利水电》 北大核心 2023年第11期93-99,共7页
由于污水厂的出水水质指标繁多、污水处理过程中反应复杂、时序非线性程度高,基于机理模型的预测方法无法取得理想效果。针对此问题,提出基于深度学习的污水厂出水水质预测方法,并以吉林省某污水厂监测水质为来源数据,利用多种结合encod... 由于污水厂的出水水质指标繁多、污水处理过程中反应复杂、时序非线性程度高,基于机理模型的预测方法无法取得理想效果。针对此问题,提出基于深度学习的污水厂出水水质预测方法,并以吉林省某污水厂监测水质为来源数据,利用多种结合encoder-decoder结构的神经网络预测水质。结果显示,所提结构对LSTM和GRU网络预测能力都有一定提升,对长期预测能力提升更加显著,ED-GRU模型效果最佳,短期预测中的4个出水水质指标均方根误差(RMSE)为0.7551、0.2197、0.0734、0.3146,拟合优度(R2)为0.9013、0.9332、0.9167、0.9532,可以预测出水质局部变化,而长期预测中的4个指标RMSE为1.7204、1.7689、0.4478、0.8316,R2为0.4849、0.5507、0.4502、0.7595,可以预测出水质变化趋势,与顺序结构相比,短期预测RMSE降低10%以上,R2增加2%以上,长期预测RMSE降低25%以上,R2增加15%以上。研究结果表明,基于encoder-decoder结构的神经网络可以对污水厂出水水质进行准确预测,为污水处理工艺改进提供技术支撑。 展开更多
关键词 污水厂出水 encoder-decoder 多指标水质预测 GRU模型
暂未订购 下载PDF
耦合Encoder-Decoder的LSTM径流预报模型研究 认领 引用 被引量：16
17
作者 林康聆 陈华 +3 位作者 陈清勇 罗宇轩 刘峰 陈杰 《武汉大学学报（工学版）》 CAS CSCD 北大核心 2022年第8期755-761,共7页
将长短期记忆神经网络(long short-term memory neural network,LSTM)与Encoder-Decoder结构耦合应用为LSTM-ED模型,并与LSTM人工智能径流预报模型进行比较。通过在闽江建溪流域进行应用,结果表明,相较于LSTM,LSTM-ED在检验期整体和各... 将长短期记忆神经网络(long short-term memory neural network,LSTM)与Encoder-Decoder结构耦合应用为LSTM-ED模型,并与LSTM人工智能径流预报模型进行比较。通过在闽江建溪流域进行应用,结果表明,相较于LSTM,LSTM-ED在检验期整体和各预见期具有更高的精度和稳定性,且对于典型洪水的预报洪峰误差更小,其独有的语义向量可以保持水文信息的连续性,预报径流过程不易受降雨波动干扰。2个模型的预报能力都与流域最大汇流时间密切相关,当预见期小于流域最大汇流时间时,2个模型都有很好的预报能力;当预见期大于流域最大汇流时间时,模型预报能力显著变差;当预见期远大于流域最大汇流时间时,2个模型都失去预报可靠性。 展开更多
关键词 径流预报 Encoder-Decoder结构 长短期记忆神经网络 深度学习 人工神经网络
暂未订购 下载PDF
基于时空特征融合的Encoder-Decoder多步4D短期航迹预测 认领 引用 被引量：5
18
作者 石庆研 张泽中 韩萍 《信号处理》 CSCD 北大核心 2023年第11期2037-2048,共12页
航迹预测在确保空中交通安全、高效运行中扮演着至关重要的角色。所预测的航迹信息是航迹优化、冲突告警等决策工具的输入,而预测准确性取决于模型对航迹序列特征的提取能力。航迹序列数据是具有丰富时空特征的多维时间序列,其中每个变... 航迹预测在确保空中交通安全、高效运行中扮演着至关重要的角色。所预测的航迹信息是航迹优化、冲突告警等决策工具的输入,而预测准确性取决于模型对航迹序列特征的提取能力。航迹序列数据是具有丰富时空特征的多维时间序列,其中每个变量都呈现出长短期的时间变化模式,并且这些变量之间还存在着相互依赖的空间信息。为了充分提取这种时空特征,本文提出了基于融合时空特征的编码器-解码器(Spatio-Temporal EncoderDecoder,STED)航迹预测模型。在Encoder中使用门控循环单元(Gated Recurrent Unit,GRU)、卷积神经网络(Convolutional Neural Network,CNN)和注意力机制(Attention,AT)构成的双通道网络来分别提取航迹时空特征,Decoder对时空特征进行拼接融合,并利用GRU对融合特征进行学习和递归输出,实现对未来多步航迹信息的预测。利用真实的航迹数据对算法性能进行验证,实验结果表明,所提STED网络模型能够在未来10 min预测范围内进行高精度的短期航迹预测,相比于LSTM、CNN-LSTM和AT-LSTM等数据驱动航迹预测模型具有更高的精度。此外,STED网络模型预测一个航迹点平均耗时为0.002 s,具有良好的实时性。 展开更多
关键词 4D航迹预测 时空特征 Encoder-Decoder 门控循环单元
暂未订购 下载PDF
基于注意力机制的Encoder-Decoder光伏发电预测模型 认领 引用 被引量：12
19
作者 宋良才 索贵龙 +2 位作者 胡军涛 窦艳梅 崔志永 《计算机与现代化》 2020年第9期112-117,共6页
影响光伏发电系统出力的天气因素具有很大的波动性和不连续性,因此需要创建合适的预测模型来对光伏出力特性进行精准预测,从而保证电网系统的有效运行。本文通过最大信息系数选择合适的历史光伏发电数据,将其作为特征之一进行输入数据重... 影响光伏发电系统出力的天气因素具有很大的波动性和不连续性,因此需要创建合适的预测模型来对光伏出力特性进行精准预测,从而保证电网系统的有效运行。本文通过最大信息系数选择合适的历史光伏发电数据,将其作为特征之一进行输入数据重构,并在由LSTM神经元构建的Encoder-Decoder模型上引入注意力机制,最终得到结合注意力机制的Encoder-Decoder光伏发电预测模型。经实际光伏电厂算例分析,验证了所提模型在光伏发电预测方面的准确性和适用性。 展开更多
关键词 光伏发电 最大信息系数 长短期记忆神经网络 Encoder-Decoder框架 注意力机制
暂未订购 下载PDF
利用Encoder-Decoder框架的深度学习网络实现绕射波分离及成像 认领 引用 被引量：5
20
作者 马铭 包乾宗 《石油地球物理勘探》 EI CSCD 北大核心 2023年第1期56-64,共9页
利用单纯绕射波场实现地下地质异常体的识别具有坚实的理论基础,对应的实施方法得到了广泛研究,且有效地应用于实际勘探。但现有技术在微小尺度异常体成像方面收效甚微,相关研究多数以射线传播理论为基础,对于影响绕射波分离成像精度的... 利用单纯绕射波场实现地下地质异常体的识别具有坚实的理论基础,对应的实施方法得到了广泛研究,且有效地应用于实际勘探。但现有技术在微小尺度异常体成像方面收效甚微,相关研究多数以射线传播理论为基础,对于影响绕射波分离成像精度的因素分析并不完备。相较于反射波,由于存在不连续构造而产生的绕射波能量微弱并且相互干涉,同时环境干扰使得绕射波进一步湮没。因此,更高精度的波场分离及单独成像是现阶段基于绕射波超高分辨率处理、解释的重点研究方向。为此,首先针对地球物理勘探中地质异常体的准确定位,以携带高分辨率信息的绕射波为研究对象,系统分析在不同尺度、不同物性参数的异常体情况下绕射波的能量大小及形态特征,掌握绕射波与其他类型波叠加的具体形式;然后根据相应特征性质提出基于深度学习技术的绕射波分离成像方法,即利用Encoder-Decoder框架的空洞卷积网络捕获绕射波场特征,从而实现绕射波分离,基于速度连续性原则构建单纯绕射波场的偏移速度模型并完成最终成像。数据测试表明,该方法最终可满足微小地质异常体高精度识别的需求。 展开更多
关键词 绕射波分离成像 深度神经网络 Encoder-Decoder框架 方差最大范数
暂未订购 下载PDF
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 2 … 191 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈