检索结果-内蒙古大学图书馆

Journal of Network Intelligence 2025年第1期10卷 339-352页

作者： Cui, Xiu-Yan Hwang, David Hebei Software Institute Hebei Province University Intelligent Interconnection Equipment and Multimodal Big Data Application Technology Research and Development Center Baoding071000 China College of Engineering St. Paul University Philippines Tuguegarao3500 Philippines

Aiming at the issue that the jobs predicted by the existing job recommendation methods cannot be precisely matched with the job seekers, this paper designs a personalized intelligent job recommendation method based on deep learning in the Elas-ticsearch environment. Firstly, to deal with the data sparsity and cold start issue of traditional collaborative filtering algorithms, the similarity calculation formula of Pearson’s correlation in the algorithm is modified to enhance the accuracy of similarity calculation. Secondly, on the ground of the history of different job seekers, the keywords of job seekers are constructed in terms of various weights, and input into ElasticSearch to recall the set of jobs that are strongly related to the job seekers. Then adopting Convolutional Neural Network (CNN) to extract the text data features of job seekers and positions, and meanwhile, integrating the attention mechanism to get the auxiliary features of job seekers and positions, and finally, integrating the implicit feedback data with other at-tribute features of job seekers and positions as the input of the improved collaborative filtration algorithm, so that we can realize the intelligent recommendation of jobs for job seekers. Simulation outcome indicates that the Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE) and Root Mean Square Percentage Error (RMSPE) of the suggested method are 0.0681, 0.0519, 0.0834 and 0.0628 respectively, which are lower than those of the comparison method, and the accuracy of the recommendation is effectively enhanced. © 2025, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Imbalanced Heartbeat Classification Based on a Convseq2seq Model with Focal Loss

SSRN

引用

SSRN 2025年

作者： Yang, Ping Jiang, Yu-Peng Wang, Meng School of Economics and Management Beijing Information Science and Technology University Beijing China Software Research and Development Center Postal Savings Bank of China Beijing China Department of Mathematics and Physics Beijing Information Science and Technology University Beijing China

The electrocardiogram (ECG) serves as a crucial tool for cardiovascular disease diagnosis and arrhythmia detection. In this paper, we propose a deep learning approach named ConvSeq2Seq, which combines convolutional neural network (CNN) and sequence-to-sequence (Seq2Seq) models, for automatic ECG classification. We employ CNN to extract spatial features from ECG data, which exhibit inter-patient variations, capturing significant spatial patterns within heartbeat sequences. Subsequently, these spatial features are input into the encoder of a Seq2Seq model to capture and encode temporal dependencies among heartbeat sequences into semantic vector representations. The decoder component of the Seq2Seq model performs semantic transformations and outputs final classification results. Our method is both simple and effective, as it does not involve any form of ECG signal filtering or processing. Despite existing literature proposing enhanced ECG heartbeat classification algorithms, they often fail to achieve high performance in detecting certain abnormal heartbeat categories, particularly in imbalanced datasets. To address this challenge, we introduce an optimization step for our ConvSeq2Seq model using a novel loss function called focal loss. This function prioritizes minority heartbeat classes by increasing their loss contribution. We evaluate our proposed methodology on the public MIT-BIH arrhythmia database using the inter-patient scheme, classifying four types of abnormal and normal beats. Experimental results demonstrate that the ConvSeq2Seq model with focal loss is effective for heartbeat classification. Furthermore, compared with state-of-the-art methods, our approach not only achieves superior overall performance but also significantly improves the performance of minority categories while maintaining the strong performance of majority categories. © 2025, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Multiscale Analysis and Size Effect Discussion Investigation for the Armor Layer of Flexible Risers Based on NIAH Method

引用

Journal of Marine Science and Engineering 2025年第4期13卷 698-698页

作者： Liu, Miaoer Li, Endao Li, Fangqiu Yan, Jun Lu, Hailong Research and Development Center CNOOC Gas & Power Group Co. Ltd. Beijing100028 China State Key Laboratory of Structural Analysis Optimization and CAE Software for Industrial Equipment School of Mechanics and Aerospace Engineering Dalian University of Technology Dalian116024 China

The armor layer is one of the core components of flexible risers. It provides essential mechanical properties such as tensile strength, pressure resistance, and torsional performance, which are necessary for operation in complex marine environments. However, due to the significant disparity between the cross-sectional dimensions of the armor wires and the overall riser size, severe computational costs are often incurred when a finite element (FE) model is employed for the performance analysis of an armor layer. To address this, an asymptotic homogenization method for flexible risers is established in the present study. In this method, the armor wires, modeled as beam elements, are equivalent to an anisotropic shell structure, and the equivalent elastic properties of the armor layer are obtained with unit-cell analysis. These properties are then used for the overall analysis of the flexible riser’s armor layer response, without considering the specific characteristics of the steel wires, thereby improving the efficiency of the performance analysis. The effectiveness of the proposed method is verified in a numerical example based on a comparison with a finite element (FE) model. Moreover, the effect of the unit cell size is investigated by introducing a size factor. A significant size effect is observed, unlike in the truss-based unit cell, for which an explanation based on the stiffness coefficient is given. The proposed method offers a new technique for efficient performance analysis of the armor layer of flexible risers. © 2025 by the authors.

关键词： Marine risers

来源：评论

学校读者我要写书评

暂无评论

RobNODDI: Robust NODDI Parameter Estimation with Adaptive Sampling Under Continuous Representation 15th

RobNODDI: Robust NODDI Parameter Estimation with Adaptive S...

引用

15th International Workshop on Computational Diffusion MRI, CDMRI 2024, held in conjunction with 27th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2024

作者： Xiao, Taohui Cheng, Jian Fan, Wenxin Yang, Jing Li, Cheng Dong, Enqing Wang, Shanshan School of Mechanical Electrical and Information Engineering Shandong University Weihai264209 China State Key Laboratory of Software Development Environment Beihang University Beijing China Key Laboratory of Data Science and Intelligent Computing Institute of International Innovation Beihang University Zhejiang Hangzhou China Paul C. Lauterbur Research Center for Biomedical Imaging Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China Peng Cheng Laboratory Guangdong Shenzhen China

ISBN: (纸本)9783031869198

Neurite Orientation Dispersion and Density Imaging (NODDI) is an important imaging technology used to evaluate the microstructure of brain tissue, which is of great significance for the discovery and treatment of various neurological diseases. Current deep learning-based methods perform parameter estimation through diffusion magnetic resonance imaging (dMRI) with a small number of diffusion gradients. These methods speed up parameter estimation and improve accuracy. However, the diffusion directions used by most existing deep learning models during testing needs to be strictly consistent with the diffusion directions during training. This results in poor generalization and robustness of deep learning models in dMRI parameter estimation. In this work, we first verify that the parameter estimation performance of current mainstream methods will significantly decrease when the testing diffusion directions and the training diffusion directions are inconsistent. A robust NODDI parameter estimation method with adaptive sampling under continuous representation (RobNODDI) is proposed. Furthermore, long short-term memory (LSTM) units and fully connected layers are selected to learn continuous representation signals. To this end, we use a total of 100 subjects to conduct experiments based on the Human Connectome Project (HCP) dataset, of which 60 are used for training, 20 are used for validation, and 20 are used for testing. The test results indicate that RobNODDI improves the generalization performance and robustness of the deep learning model, enhancing the stability and flexibility of deep learning NODDI parameter estimatimation applications. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Paleolithic divergence and multiple Neolithic expansions of ancestral nomadic emperor-related paternal lineages

引用

Journal of Genetics and Genomics 2025年第4期52卷 502-512页

作者： Mengge Wang Qiuxia Sun Yuhang Feng Lan-Hai Wei Kaijun Liu Lintao Luo Yuguo Huang Kun Zhou Haibing Yuan Hongliang Lv Yu Lu Jing Cheng Shaoqing Wen Chuan-Chao Wang Renkuan Tang Fengxiao Bu Chao Liu Huijun Yuan Zhiyong Wang Guanglin He Institute of Rare Diseases Frontiers Science Center for Disease-related Molecular NetworkWest China HospitalSichuan UniversityChengduSichuan 610000China Center for Archaeological Science Sichuan UniversityChengduSichuan 610000China Anti-Drug Technology Center of Guangdong Province GuangzhouGuangdong 510230China Department of Forensic Medicine College of Basic MedicineChongqing Medical UniversityChongqing 400331China Human Genetics and Forensic Genomics Research Institute College of Basic MedicineChongqing Medical UniversityChongqing 400331China Institute of Humanities and Human Sciences Inner Mongolia Normal UniversityHohhotInner Mongolia 010022China Institute of 23Mofang Tianfu Software ParkChengduSichuan 610042China MOE Laboratory for National Development and Intelligent Governance Fudan UniversityShanghai 200433China State Key Laboratory of Cellular Stress Biology School of Life SciencesXiamen UniversityXiamenFujian 361102China

The reconstruction of demographic history using ancient and modern genomic resources reveals extensive interactions and admixture between ancient nomadic pastoralists and the social organizations of the Chinese Central ***,the extent to which Y-chromosome genetic legacies from nomadic emperor-related ancestral lineages influence the Chinese paternal gene pool remains ***,we genotype 2717 ethnolinguistically diverse samples belonging to C2a lineages,perform whole-genome sequencing on 997 representative samples,and integrate these data with ancient genomic *** reconstruct the evolutionary histories of Northern Zhou-,Qing emperor-,and pastoralist-related lineages to assess their genetic impact on modern Chinese *** reassembled fine-scale Ychromosome phylogeny identifies deep divergence and five Neolithic expansion events contributing differently to the formation of northern Chinese *** modeling indicates that the nomadic empires of the Northern Zhou and Qing dynasties genetically originated from the Mongolian *** topology and shared haplotype patterns show that three upstream ancestors of Northern Zhou(C2a1a1b1a2a1b-FGC28857),Donghu tribe(C2a1a1b1-F1756),and Qing(C2a1a3a2-F10283)emperor-related lineages expanded during the middle Neolithic,contributing significantly to genetic flow between ancient northeastern Asians and modern East ***,this study reveals limited direct contributions of Emperor Wu of Northern Zhou’s lineages to modern East Asians.

关键词： Paternal lineage Founding lineage Genetic origin Emperor lineage Y-chromosome

来源：评论

学校读者我要写书评

暂无评论

Vacancy-Type Defects in HfO2 Layers and Their Role in Amorphous-to-Crystalline Transition Studied by Monoenergetic Positron Beams

引用

IEEE Transactions on Semiconductor Manufacturing 2025年

作者： Uedono, Akira Kawakami, Kazuya Kuribara, Tatsunori Hasunuma, Ryu Harashima, Yosuke Shigeta, Yasuteru Ni, Zeyuan Yan, Ruolin Nakamura, Hideo Notake, Akira Moriya, Tsuyoshi Michishio, Koji Ishibashi, Shoji University of Tsukuba Faculty of Pure and Applied Science Tsukuba Ibaraki305-8573 Japan Nara Institute of Science and Technology Graduate School of Science and Technology Ikoma Nara630-0192 Japan Tokyo Electron Technology Solutions Ltd S-Technology Development Center Nirasaki Yamanashi650 Japan Tokyo Electron Technology Solutions Ltd Development Department1 Nirasaki Yamanashi407-0192 Japan Tokyo Electron Ltd Digital Design Center Sapporo Hokkaido060-0003 Japan Tokyo Electron Technology Solutions Ltd Software and Data Engineering Division Nirasaki Yamanashi407-0192 Japan National Institute of Advanced Industrial Science and Technology Research Institute for Measurement and Analytical Instrumentation Tsukuba Ibaraki305-8568 Japan National Institute of Advanced Industrial Science and Technology Research Center for Computational Design of Advanced Functional Materials Tsukuba Ibaraki305-8568 Japan

The annealing properties of vacancies in HfO2 layers deposited on Si substrates and their role in amorphous-to-crystalline transition were studied with monoenergetic positron beams. HfO2 layers with a thickness of 4.30 nm were fabricated by the atomic layer deposition technique. The major vacancytype defects in these layers were identified as a Hf vacancy (VHf) coupled with multiple oxygen vacancies (VOs) and larger vacancy clusters. After annealing at 500°C, the concentration of vacancy clusters started to increase, which was attributed to the agglomeration of intrinsic open spaces in the amorphous phase upon the phase transition from amorphous to monoclinic crystalline phases. The amorphous-crystalline transition started near the interface between the HfO2 layer and bottom electrodes (TiN). After the crystallization, the concentration of vacancy clusters decreased as the annealing temperature increased. © 2025 IEEE.

关键词： Hafnium oxides

来源：评论

学校读者我要写书评

暂无评论

Full-Coverage Mapping of Daily High-Resolution XCO2 across China from 2015 to 2020 by Deep Learning-Based Spatio-Temporal Fusion

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年

作者： Li, Yi Yan, Jining Zhong, Liheng Bao, De Sun, Leigang Li, Guangyu China University of Geosciences School of Computer Science Wuhan430074 China Ministry of Education Engineering Research Center of Natural Resource Information Management and Digital Twin Engineering Software Wuhan430074 China Ant Group World Financial Center Beijing100020 China Hebei Academy of Sciences Institute of Geographical Sciences Shijiazhuang050011 China Hebei Technology Innovation Center for Geographic Information Application Shijiazhuang050011 China Environmental Development Center of the Ministry of Ecology and Environment China

Carbon neutrality has become a global priority, and high spatio-temporal resolution data on the column-average dry-air mole fraction carbon dioxide (XCO2) is essential for tracking progress and guiding policy adjustments. However, satellite-derived XCO2 exhibits significant temporal and spatial gaps due to influences such as orbital dynamics and cloud cover. Additionally, the low spatial resolution of CarbonTracker (CT) is insufficient to meet the current demands for fine-scale monitoring. Current XCO2 assessment methods often rely solely on single-pixel data, overlooking the spatio-temporal correlations. In this article, we introduce a deep learning-based spatio-temporal model (DSTM) that extracts features from multiple data sources related to atmospheric transport, carbon emissions, and carbon sinks, enabling fine-scale XCO2 assessments. Additionally, XCO2 data from the Orbiting Carbon Observatory-2 (OCO-2) and CT were fused at a 0.1° spatial resolution to generate training labels with broader coverage and more samples, serving as fitting labels. Our approach produced daily, full-coverage 0.1° resolution XCO2 maps for China from 2015 to 2020, and analyzed changes in XCO2 growth trends over this period. Numerical results show that our model outperforms traditional deep learning methods. Model validation using data from four ground-based observation sites of the Total Carbon Column Observing Network (TCCON) achieved an average R2 of 0.86 and an RMSE of 2.67 ppm. The extraction and fusion of spatio-temporal features from multiple data sources provide a novel approach for reconstructing missing XCO2 data. © 1980-2012 IEEE.

关键词： Atmospheric movements

来源：评论

学校读者我要写书评

暂无评论

Solar-thermal gradient-driven evaporation for enhanced fractional crystallization

引用

Desalination 2025年 611卷

作者： Deng, Shiyuan Zhang, Wei Gao, Yuan Duan, Xiaoyang Cao, Yan Zhu, Zongqiang Hu, Chengzhi Guangxi Key Laboratory of Environmental Pollution Control Theory and Technology Guilin University of Technology Guilin541006 China Key Laboratory of Environmental Aquatic Chemistry State Key Laboratory of Regional Environment and Sustainability Research Center for Eco-Environmental Sciences Chinese Academy of Sciences Beijing100085 China University of Chinese Academy of Sciences Beijing100049 China Engineering Research Center of Watershed Protection and Green Development University of Guangxi Guilin University of Technology Guilin541006 China Beijing Xiaomi Mobile Software Co. Ltd. Beijing100085 China National Engineering Research Center of Eco-Environment in the Yangtze River Economic Belt Wuhan430010 China

Solar-driven water evaporation (SWE) offers a low-carbon approach to extracting water and salts from various water sources. However, the composition of the obtained salts is difficult to regulate due to uncontrolled ion concentration and crystallization processes, limiting further salt reutilization. Herein, we propose a solar-thermal gradient-driven evaporation strategy for fractional crystallization. The sharp thermal gradient (1.8 °C/mm) induced by an engineered solar absorber simultaneously powers salt concentration and exploits the different thermal solubility dependencies of NaCl and NaNO3, achieving spatial salt isolation. Over a broad range of NaCl/NaNO3 ratios, pure NaCl preferentially crystallizes outside the inner rings of the evaporator, while the reduced NaCl residues in the brine inside the evaporator enable NaNO3 purification at the outer edges. Additionally, through multi-stage solar fractional crystallization, 58.9 % of NaCl can be recovered as nearly pure salts (99 wt%) from a 1:1 wt% NaCl/NaNO3 wastewater. This study presents a novel strategy for advancing solar energy utilization toward resource recovery, enhancing economic viability, and promoting sustainable development. © 2025 Elsevier B.V.

关键词： Fractional crystallization Multi-stage Salt reutilization Solar evaporation Thermal gradient

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Multi-Kernel Graph Learning for Autism Prediction and Biomarker Discovery

IEEE Transactions on Computational Biology and Bioinformatic...

引用

IEEE Transactions on Computational Biology and Bioinformatics 2025年第2期22卷 842-854页

作者： Jin Liu Junbin Mao Hanhe Lin Hulin Kuang Shirui Pan Xusheng Wu Shan Xie Fei Liu Yi Pan Hunan Provincial Key Lab on Bioinformatics School of Computer Science and Engineering Central South University Changsha China Xinjiang Engineering Research Center of Big Data and Intelligent Software School of software Xinjiang University Wulumuqi China Hunan Province Key Lab on Bioinformatics School of Computer Science and Engineering Central South University Changsha China School of Science and Engineering University of Dundee Dundee U.K. School of Information and Communication Technology Griffith University Gold Coast QLD Australia Shenzhen Health Development Research and Data Management Center Shenzhen China Faculty of Computer Science and Control Engineering Shenzhen University of Advanced Technology Shenzhen China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China

Graph learning-based multi-modal integration and classification is one of the most challenging tasks for disease prediction. To effectively offset the negative impact among modalities in the process of multi-modal integration and heterogeneous information extractions from graphs, we propose a novel method called Multi-modal Multi-Kernel Graph Learning (MMKGL). To solve the problem of negative impact among modalities, we propose a multi-modal graph embedding module to construct a multi-modal graph. Different from conventional methods that manually construct static graphs for all modalities, each modality generates a separate graph by adaptive learning, where a function graph and a supervision graph are introduced for optimization during the multi-graph fusion embedding process. We then propose a multi-kernel graph learning module to extract heterogeneous information from the multi-modal graph. The information in the multi-modal graph at different levels is aggregated by convolutional kernels with different receptive field sizes, followed by generating a cross-kernel discovery tensor for disease prediction. Our method is evaluated on the benchmark Autism Brain Imaging Data Exchange (ABIDE) dataset and outperforms the state-of-the-art methods. In addition, discriminative brain regions associated with autism are identified by our model, providing guidance for the study of autism pathology.

关键词： Diseases Autism Random access memory Data mining Kernel Electronic mail Training Neuroimaging Graph convolutional networks Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Experimental study of damage to double-hull structure by underwater explosions of three charge types - blasting, shaped, and linear shaped charges

引用

International Journal of Impact Engineering 2025年 203卷

作者： Zhang, Zhifan Yang, Shuxin Zhang, Shenhe Wang, Longkan Sui, Yutong Li, Tao Zhang, Guiyong State Key Laboratory of Structural Analysis Optimization and CAE Software for Industrial Equipment School of Naval Architecture Engineering Dalian University of Technology Dalian116024 China China Ship Research and Development Academy Beijing100192 China School of Mechanical Engineering Key Laboratory of Advanced Intelligent Protective Equipment Technology Ministry of Education Hebei University of Technology Tianjin300401 China Collaborative Innovation Center for Advanced Ship and Deep-Sea Exploration Shanghai 200240 China

In recent years, due to the improvement in ship protection capabilities, near-field underwater explosions no longer pose fatal damage to ships. Since stiffened plates are typical structures in ships, studying the impact of underwater explosions with different types of explosives on ships is of great significance. This experiment investigated the damage characteristics of blasting, shaped, and linear shaped charges on the same type of stiffened plate. The experimental results indicate that linear shaped charges can create larger penetration holes on target plates, but they suffer from insufficient flight capability. In contrast, shaped charges exhibit stronger penetrating power, yet they lack sufficient damage capability against target plates. Although the penetration capability of blasting charges is inferior to the first two, its overall deflection of the plate frame exceeds that caused by shaped charges and linear shaped charges by 1.6 % and 5.7 %, respectively. To further investigate the penetration process and the load characteristics of the penetrator, a finite element model was established in this paper. The numerical results show that there is no significant difference in jet length and velocity between the two models, but the shapes of the jet tips differ, and the computational results are in good agreement with the experimental results, confirming the validity of the Arbitrary Lagrangian-Eulerian (ALE) method. © 2025 Elsevier Ltd

关键词： Underwater explosions

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：