检索结果-内蒙古大学图书馆

Effective ensemble learning approach for SST field prediction using attention-based PredRNN

Frontiers of Computer Science 2023年第1期17卷 143-155页

作者： Baiyou QIAO Zhongqiang WU Ling MA Yicheng Zhou Yunjiao SUN School of Computer Science and Engineering Northeastern UniversityShenyang 110169China Key Laboratory of Intelligent Computing in Medical Image Ministry of EducationNortheastern UniversityShenyang 110169China

Accurate prediction of sea surface temperature (SST) is extremely important for forecasting oceanic environmental events and for ocean studies. However, the existing SST prediction methods do not consider the seasonal periodicity and abnormal fluctuation characteristics of SST or the importance of historical SST data from different times;thus, these methods suffer from low prediction accuracy. To solve this problem, we comprehensively consider the effects of seasonal periodicity and abnormal fluctuation characteristics of SST data, as well as the influence of historical data in different periods, on prediction accuracy. We propose a novel ensemble learning approach that combines the Predictive Recurrent Neural Network(PredRNN) network and an attention mechanism for effective SST field prediction. In this approach, the XGBoost model is used to learn the long-period fluctuation law of SST and to extract seasonal periodic features from SST data. The exponential smoothing method is used to mitigate the impact of severely abnormal SST fluctuations and extract the a priori features of SST data. The outputs of the two aforementioned models and the original SST data are stacked and used as inputs for the next model, the PredRNN network. PredRNN is the most recently developed spatiotemporal deep learning network, which simulates both spatial and temporal representations and is capable of transferring memory across layers and time steps. Therefore, we used it to extract the spatiotemporal correlations of SST data and predict future SSTs. Finally, an attention mechanism is added to capture the importance of different historical SST data, weigh the output of each step of the PredRNN network, and improve the prediction accuracy. The experimental results on two ocean datasets confirm that the proposed approach achieves higher training efficiency and prediction accuracy than the existing SST field prediction approaches do.

关键词： SST prediction ensemble learning XGBoost PredRNN attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Edge-Enhanced Cascaded MRF for SAR image Segmentation

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Liu, Mengmeng Shang, Ronghua Liu, Kang Feng, Jie Wang, Chao Xu, Songhua Li, Yangyang Xidian University Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Shaanxi Xi’an710071 China Xidian University School of Computer Science and Technology Shaanxi Xi’an710071 China Research Center for Data Hub and Security Zhejiang Lab Hangzhou311100 China The Second Affiliated Hospital of Xi’an Jiaotong University Department of Health Management Institute of Medical Artificial Intelligence Xi’an710004 China

Markov random fields (MRFs) effectively capture local contextual information by modeling the spatial dependencies between pixels, which helps highlight details and enhances segmentation smoothness. To fully exploit MRF for synthetic aperture radar (SAR) image segmentation, we propose a novel edge-enhanced cascaded MRF (ECMRF) approach. Specifically, we introduce multiple edge-constrained filters to emphasize SAR image boundaries and provide relatively clean features. Building on this, we present a cascaded MRF framework that sequentially integrates region-level and pixel-level segmentations with feature perturbation and fusion to generate the final segmentation output. The framework comprises four key components: 1) a region-level MRF (RMRF), regulated by edge features, to achieve precise region segmentation;2) a pixel-level MRF (PMRF) with selective label smoothing to refine edges and reduce noise clusters;3) equal-channel feature perturbation (EC-FP) to increase feature diversity;and 4) a random probability-based feature fusion (RP-FF) scheme to merge the input features. The experimental results demonstrate that our ECMRF outperforms six state-of-the-art comparable methods, underscoring its competitive performance. © 1980-2012 IEEE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Eco-friendly, mechanically robust, weather-resistant and rapidly cured polyurea elastomer synthesized by vat photopolymerization 3D printing

引用

Composites Part A: Applied Science and Manufacturing 2025年 196卷

作者： Yu, Yin Xu, Lisheng Liu, Siqi Gu, Gege Chen, Yufeng Yuan, Haochen Kuan, Hsu-Chiang Liu, Jianbang Meng, Qingshi Ma, Jun College of Medicine and Bioinformatics Engineering Northeastern University Shenyang110819 China College of Information Science and Engineering Northeastern University Shenyang110004 China Key Laboratory of Medical Image Computing Ministry of Education Shenyang110169 China College of Civil Aviation Shenyang Aerospace University Shenyang110136 China College of Aerospace Engineering Shenyang Aerospace University Shenyang110136 China UniSA STEM and Future Industries Institute University of South Australia Mawson Lakes5095 Australia

Vat photopolymerization (VP) 3D printing is increasingly employed for efficient elastomer production. However, the printed elastomers often exhibit unsatisfactory mechanical properties, and the process involves harmful volatile substances. Polyurea elastomers, which have a fast reaction rate and high viscosity during synthesis, pose challenges for solvent-free or diluent-free VP 3D printing. This study developed an eco-friendly, mechanically robust and rapidly cured polyurea elastomer by VP 3D printing. The synthesis rate and viscosity of polyurea prepolymer were reduced by controlling the reaction time and stirring speed for reactions without solvent and diluent. Novel urea-acryl resins were designed by employing two acrylic monomers. The mechanical properties of the UV-cured polyurea elastomer were further enhanced through graphene incorporation. The polyurea/graphene nanocomposite at an optimal graphene loading of 0.10 wt% exhibited tensile strength of 12.9 MPa, and elongation at break of 399.2 %. These values correspond to increments of 76.7 % and 66.8 %, respectively, over the neat DLP polyurea elastomer. Moreover, these photocured elastomers exhibited excellent recyclability and weather resistance. The innovative synthesis strategy offers a solution to the mechanical limitations of photocured resins while minimizing environmental impact. © 2025 The Authors

关键词： Tensile strength

来源：评论

学校读者我要写书评

暂无评论

A Progressive Peak-Finding and Weak Peak-Preserving LM Algorithm for Isotope Separation in Miniature Mass Spectrometers

引用

Rapid Communications in Mass Spectrometry 2025年第17期39卷 e10073页

作者： Zhiwei Wang Ang Li Wei Xu Dayu Li School of Computer Science and Engineering Northeastern University Shenyang China Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education Northeastern University Shenyang China School of Medical Technology Beijing Institute of Technology Beijing China

Rationale In recent years, performance enhancement strategies for miniature mass spectrometers through signal processing techniques have garnered significant attention, primarily due to their advantage of not changing their mechanical structure. Gaussian decomposition, as a signal processing approach, has shown considerable potential in the field of overlapping peak identification. Method In this study, a novel PPWP-LM (progressive peak-finding and weak peak-preserving Levenberg-Marquardt) algorithm integrating Gaussian decomposition techniques is proposed for use in miniature ion trap mass spectrometers for aliased peak separation. Result The feasibility of the algorithm was verified using simulation data, and the anti-noise performance of the PPWP-LM algorithm was verified under different signal-to-noise ratios. The analytical capability of the algorithm was further evaluated using samples at different concentrations and different scanning speeds, and the results showed that the algorithm maintained stable performance and was adaptable under high-speed scanning conditions. In addition, aliased signal separation was successfully demonstrated by mixing samples, and the results show that it is suitable for rapid analysis in the field and meets the requirements of practical applications. Conclusion Through optimized strategies including a progressive search, pseudo-peak removal, and weak peak protection, the algorithm successfully achieves isotope separation under high-speed scanning conditions in miniature ion trap mass spectrometers, significantly enhancing their analytical efficiency and performance.

关键词： Gaussian decomposition isotope separation miniature ion trap mass spectrometer parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Stfi: Structure-Aware and Time-Frequency Domain Interaction Network for Deformable medical image Registration

SSRN

引用

SSRN 2025年

作者： Hu, Rui Wang, Nian Zhang, Yuxin Li, Teng Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Electrical Engineering and Automation Anhui University Hefei230601 China Advanced Imaging Research Center University of Texas Southwestern Medical Center 5323 Harry Hines Blvd Dallas75390 United States School of Cyber Science and Engineering Southeast University No.2 Southeast University Road Nanjing211189 China

Deformable image registration is crucial in medical image analysis. Recently, unsupervised methods using intensity matching have shown promising results without labeled data. However, these methods still face challenges: (1) They often encounter local optima when handling anatomical structures with significant variations in intensity distribution;(2) Time domain convolution in decoders leads to loss of high-frequency fine features, limiting the effectiveness of generating fine deformation vector fields. To address these issues, we propose a novel structure-aware and time-frequency domain interaction (STFI) network. STFI integrates a structure-aware frequency domain loss and a time-frequency domain interaction module. The former leverages principal structural information from the weighted phase spectrum to guide the registration process, thereby reducing the risk of local optima. The latter processes and amalgamates information from both the time and frequency domains, effectively preserving high-frequency details. The efficacy and adaptability of our approach have been demonstrated on two types of data, offering a new perspective on exploiting time-frequency domain information for medical image registration. © 2025, The Authors. All rights reserved.

关键词： image registration

来源：评论

学校读者我要写书评

暂无评论

Delving into Invisible Semantics for Generalized One-shot Neural Human Rendering

引用

IEEE Transactions on Visualization and Computer Graphics 2025年

作者： Lin, Yihong Xu, Xuemiao Zhang, Huaidong Xu, Cheng Li, Weijie Xie, Yi Qin, Jing He, Shengfeng South China University of Technology Guangdong China Guangdong Engineering Center for Large Model and GenAI Technology State Key Laboratory of Subtropical Building and Urban Science Ministry of Education Key Laboratory of Big Data and Intelligent Robot Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information China South China University of Technology China Hong Kong Polytechnic University Centre for Smart Health Hong Kong CAS-Hong Kong Joint Laboratory for Multimodal Medical Molecular Imaging Hong Kong Singapore Management University School of Computing and Information Systems Singapore

Traditional human neural radiance fields often overlook crucial body semantics, resulting in ambiguous reconstructions, particularly in occluded regions. To address this problem, we propose the Super-Semantic Disentangled Neural Renderer (SSD-NeRF), which employs rich regional semantic priors to enhance human rendering accuracy. This approach initiates with a Visible-Invisible Semantic Propagation module, ensuring coherent semantic assignment to occluded parts based on visible body segments. Furthermore, a Region-Wise Texture Propagation module independently extends textures from visible to occluded areas within semantic regions, thereby avoiding irrelevant texture mixtures and preserving semantic consistency. Additionally, a view-aware curricular learning approach is integrated to bolster the model's robustness and output quality across different viewpoints. Extensive evaluations confirm that SSD-NeRF surpasses leading methods, particularly in generating quality and structurally semantic reconstructions of unseen or occluded views and poses. © 2025 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Decoupled Doubly Contrastive Learning for Cross Domain Facial Action Unit Detection

arXiv

引用

arXiv 2025年

作者： Li, Yong Liu, Menglin Cui, Zhen Ding, Yi Zong, Yuan Zheng, Wenming Shan, Shiguang Guan, Cuntai School of Computer Science and Engineering The Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Nanjing210096 China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China School of Artificial Intelligence Beijing Normal University Beijing100875 China Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China School of Computer Science and Engineering Nanyang Technological University 50 Nanyang Avenue Singapore639798 Singapore Key Laboratory of Child Development and Learning Science of Ministry of Education School of Biological Science and Medical Engineering Nanjing210096 China

Despite the impressive performance of current vision-based facial action unit (AU) detection approaches, they are heavily susceptible to the variations across different domains and the cross-domain AU detection methods are under-explored. In response to this challenge, we propose a decoupled doubly contrastive adaptation (D2CA) approach to learn a purified AU representation that is semantically aligned for the source and target domains. Specifically, we decompose latent representations into AU-relevant and AU-irrelevant components, with the objective of exclusively facilitating adaptation within the AU-relevant subspace. To achieve the feature decoupling, D2CA is trained to disentangle AU and domain factors by assessing the quality of synthesized faces in cross-domain scenarios when either AU or domain attributes are modified. To further strengthen feature decoupling, particularly in scenarios with limited AU data diversity, D2CA employs a doubly contrastive learning mechanism comprising image and feature-level contrastive learning to ensure the quality of synthesized faces and mitigate feature ambiguities. This new framework leads to an automatically learned, dedicated separation of AU-relevant and domain-relevant factors, and it enables intuitive, scale-specific control of the cross-domain facial image synthesis. Extensive experiments demonstrate the efficacy of D2CA in successfully decoupling AU and domain factors, yielding visually pleasing cross-domain synthesized facial images. Meanwhile, D2CA consistently outperforms state-of-the-art cross-domain AU detection approaches, achieving an average F1 score improvement of 6%-14% across various cross-domain scenarios. © 2025, CC BY-NC-SA.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Classifying Uncertain and Evolving Data Streams with Distributed Extreme Learning Machine

引用

Journal of Computer Science & Technology 2015年第4期30卷 874-887页

作者：韩东红张昕王国仁 College of Information Science and Engineering Northeastern University Shenyang 110819 China Key Laboratory of Medical Image Computing ( NEU) Ministry of Education Shenyang 110819 China

Conventional classification algorithms are not well suited for the inherent uncertainty, potential concept drift, volume, and velocity of streaming data. Specialized algorithms are needed to obtain efficient and accurate classifiers for uncertain data streams. In this paper, we first introduce Distributed Extreme Learning Machine （DELM）, an optimization of ELM for large matrix operations over large datasets. We then present Weighted Ensemble Classifier Based on Distributed ELM （WE-DELM）, an online and one-pass algorithm for efficiently classifying uncertain streaming data with concept drift. A probability world model is built to transform uncertain streaming data into certain streaming data. Base classifiers are learned using DELM. The weights of the base classifiers are updated dynamically according to classification results. WE-DELM improves both the efficiency in learning the model and the accuracy in performing classification. Experimental results show that WE-DELM achieves better performance on different evaluation criteria, including efficiency, accuracy, and speedup.

关键词： uncertain data stream classification extreme learning machine distributed computing concept drift

来源：评论

学校读者我要写书评

暂无评论

Semantic movie summarization based on string of IE-Role Nets

引用

Computational Visual Media 2015年第2期1卷 129-141页

作者： Wen Qu Yifei Zhang Daling Wang Shi Feng Ge Yu School of Information Science and Engineering Northeastern University Key Laboratory of Medical Image Computing(Northeastern University) Ministry of Education

Roles, their emotion, and interactions between them are three key elements for semantic content understanding of movies. In this paper, we proposed a novel movie summarization method to capture the semantic content in movies based on a string of IE-Role Nets. An IE-Role Net(interaction and emotion rolenet) models the emotion and interactions of roles in a shot of the movie. The whole movie is represented as a string of IE-Role Nets. Summarization of a movie is transformed into finding an optimal substring with user-specified summarization *** substring mining is conducted to find an optimal substring of the whole movie. We have conducted objective and subjective experiments on our method. Experimental results show the ability of our method to capture the semantic content of movies.

关键词： movie summarization content analysis movie understanding

来源：评论

学校读者我要写书评

暂无评论

Research on light field capturing and reconstruction algorithm based on wavelet base

引用

Journal of Information and Computational Science 2012年第16期9卷 4997-5004页

作者： Jiang, Huiyan Fang, Di Gao, Rui Software College of Northeastern University Shenyang China Key Laboratory of Medical Image Computing of Ministry of Education Shenyang China

In this paper, we propose a novel coded aperture and two associated algorithm for making up the defect of traditional aperture such as the depth of scene, quality and the limitation of dimension. In sampling, combining with the sampling characteristics of traditional aperture and the properties of wavelet transform, we design a coded aperture achieving multi-angle reuse acquisition of light field. Then we project the captured light field data to double tree discrete wavelet domain. For reconstruction, we propose to use the sparse characteristics of light field combine with the redundancy in both spatial and angle domain. Experimental results demonstrate the efficiency and quality of the proposed methods. © 2012 Binary Information Press.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：