检索结果-内蒙古大学图书馆

Oesophageal cancer-specific mortality risk and public health insurance: Prospective cohort study from china

World Journal of Gastrointestinal Oncology 2025年第4期17卷 274-285页

作者： Xiang-Lin Wu Xiao-Sheng Li Jing-Han Cheng Lin-Xin Deng Zu-Hai Hu Jun Qi Hai-Ke Lei Chongqing Key Laboratory of Translational Research for Cancer Metastasis and Individualized Treatment Chongqing University Cancer HospitalChongqing 400030China Chongqing Cancer Multi-omics Big Data Application Engineering Research Center Chongqing University Cancer HospitalChongqing 400030China Research Center for Medicine and Social Development Chongqing Medical UniversityChongqing 400016China Department of Health Statistics School of Public HealthChongqing Medical UniversityChongqing 400016China Department of Thoracic Surgery The People’s Hospital of Changshou ChongqingChongqing 401220China

BACKGROUND Oesophageal cancer is a significant health concern worldwide,with high inci-dence and mortality *** china,the disease burden is particularly high,accounting for a substantial proportion of oesophageal cancer cases and related deaths *** To explore the relationship between the mortality rate of oesophageal cancer patients and insurance type,out-of-pocket ratio,and the joint effects of insurance type and out-of-pocket *** The χ^(2) test was used to analyze patients’demographic and clinical *** logistic regression,the Cox proportional hazard model,and the competitive risk model were used to calculate the cumulative hazard ratios(HRs)of all-cause death and oesophageal cancer-specific death among patients with different types of insurance and out-of-pocket *** Compared with patients covered by basic medical insurance for urban and rural residents,patients covered by urban employee basic medical insurance for urban workers(UEBMI)had a 23.30%increased risk of oesophageal cancer-specific death[HR=1.233,95%confidence interval(CI):1.093-1.391,P<0.005].Compared with patients in the low out-of-pocket ratio group,patients in the high out-of-pocket ratio group had a 25.80%reduction in the risk of oesophageal cancer-specific death(HR=0.742,95%CI:0.6555-0.84,P<0.005).With each 10%increase in the out-of-pocket ratio,the risk of oesophageal cancer-specific death decreased by 10.10%in patients covered by ***,the risk of oesophageal cancer-specific death increased by 26.90%in patients in the high out-of-pocket ratio *** This study reveals the relationships of the specific mortality rate of patients with oesophageal cancer with the out-of-pocket ratio and medical insurance types as well as their combined *** study provides practical suggestions and guidance for the formulation of relevant policies in this area.

关键词： Oesophageal cancer Public health Insurance Prognosis Mortality risk

来源：评论

学校读者我要写书评

暂无评论

Robust 2D Skeleton Action Recognition via Decoupling and Distilling 3D Latent Features

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Zhang, Xiangyue Jia, Yifan Zhang, Jiaxu Yang, Yijie Tu, Zhigang Wuhan University State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan430072 China Renmin Hospital of Wuhan University Department of Pain Wuhan430060 China

Human skeletons provide a compact representation for action recognition. Compared to 3D skeletons, 2D skeletons lack view-independence and depth, making them less robust for motion analysis. However, 3D skeleton data requires specialized hardware, limiting its practicality, especially in outdoor or dynamic settings. In contrast, 2D skeletons can be extracted from standard RGB videos, making them more accessible. To address this, we propose 2D3-SkelAct, a 2D skeleton-based action recognition model. It maps 2D inputs to a 3D latent space, where pose and view features are decoupled. Additionally, 2D3-SkelAct distills motion cues from 3D models, enhancing motion detail capture while keeping the benefits of 2D data. Specifically, the pipeline of our 2D3-SkelAct consists of two steps: pose-view decoupling and pose-view distilling. First, we use a spatio-temporal transformer to decouple 2D skeleton sequences into latent pose and view features, enhancing the model’s ability to learn motion dynamics. Next, these decoupled features are separately integrated into the 2D skeleton model through two cross-attention modules, allowing it to extract discriminative motion features while mitigating uncertainties in 3D viewpoint and depth. Additionally, we distill motion cues from 3D models to compensate for the limitations of 2D skeletons. Remarkably, our model can seamless integrate with various skeleton feature extractors. We validate the proposed 2D3-SkelAct through extensive experiments, demonstrating its adaptability across different model architectures as where consistent improvement achieving. When combined with advanced skeleton feature extractors, 2D3-SkelAct achieves state-of-the-art performance in 2D skeleton-based action recognition. © 1991-2012 IEEE.

关键词： Bone

来源：评论

学校读者我要写书评

暂无评论

Multi-modal sentiment recognition with residual gating network and emotion intensity attention

引用

Neural Networks 2025年 188卷 107483页

作者： Wang, Yadi Guo, Xiaoding Hou, Xianhong Miao, Zhijun Yang, Xiaojin Guo, Jinkai School of Computer and Information Engineering Henan University Kaifeng475004 China Henan Key Laboratory of Big Data Analysis and Processing Kaifeng475004 China

Multimodal emotion recognition focuses on the prediction of emotions using text, visual and acoustic modalities, and some results have been generated in this field. Previous approaches fall short in two aspects, one is the processing of complementary information among modalities, the other is how to avoid the long-term dependency and select the most important joint modal features. In this paper, we propose a new multimodal emotion recognition framework MSRG, which consists of feature extraction (FE), emotional intensity attention (EIA), time-step level fusion (TLF), utterance level fusion (ULF), and sentiment inference module (SIM). EIA is divided into adaptive multimodal linear pooling (AMLP) and joint cross-attention fusion (JCAF), where AMLP adopts the adaptive strategy of multimodal fusion to dynamically calculate the adaptive coefficients of three modalities, then performs the pooling operation to obtain joint modal features. JCAF calculates the attention weights and attention features of each modality based on cross-correlation between individual and joint features. TLF performs feature alignment fusion at the time-step level, then uses the residual gating network (RGN) to process the time-step level fused sequences. The obtained time-step level fused features are then input into two fully connected layers and an activation layer to obtain the time-step level emotion intensity. ULF fuses the three modalities’ utterance level representations by concatenating them and then inputs the obtained utterance level fused features into a fully connected layer to obtain the utterance level emotion intensity. Finally, both the time-step level emotion intensity and the utterance level emotion intensity are input into SIM to obtain the final emotion prediction results. Experiments demonstrate that MSRG achieves better prediction performance on CMU-MOSI and CMU-MOSEI datasets. © 2025 Elsevier Ltd

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

A Secure and Efficient Privacy data Aggregation Mechanism 18th

A Secure and Efficient Privacy Data Aggregation Mechanism

引用

18th International Conference on Wireless Artificial Intelligent Computing Systems and Applications, WASA 2024

作者： Ma, Wenshuo Liu, Xinru Yu, Kan Luo, Chuanwen Wang, Guopeng Liu, Xiaowu School of Artificial Intelligence and Big Data Zibo Vocational Institute Zibo China Weifang Engineering Vocational College Weifang China School of Computer Science and Engineering Macau University of Science and Technology Taipa China The Key Laboratory of Universal Wireless Communications Ministry of Education Beijing University of Posts and Telecommunications Beijing China School of Information Science and Technology Beijing Forestry University Beijing China School of Computer Science Qufu Normal University Rizhao China Zhejiang Ocean University Zhoushan China The Open University of China Beijing China

ISBN: (纸本)9783031714665

data aggregation (DA) plays an important role in conserving the limited resources and extending the network lifetime of Wireless Sensor Networks (WSNs). Privacy preservation has garnered considerable attention and is considered one of the most viable schemes to address issues such as communication eavesdropping, information leakage, and unauthorized access in WSNs employing DA. In this paper, we propose an improved Secure Privacy-preserving data Aggregation (iSECPDA) mechanism. It dynamically selects cluster heads through an enhanced Stable Election Protocol (SEP), which considers the residual energy of sensor nodes to enhance network lifetime. In our proposed SEPPDA, we integrate interference information into the sensing data and ensure data transmission privacy through a proposed slicing mechanism. Theoretical analysis and simulation experiments demonstrate that iSECPDA exhibits significant performance improvements in terms of communication overhead and privacy preservation levels. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： data aggregation

来源：评论

学校读者我要写书评

暂无评论

Priority-Based Reward Mechanism for Dual-Robot Path Planning in Dynamic Environments

引用

IEEE Access 2025年 13卷 92519-92530页

作者： Hu, Yibo Wei, Lai Guo, Xiaoyu Li, Zhenyao Wei, Yanding Fang, Qiang Zhejiang University The State Key Laboratory of Fluid Power and Mechatronic Systems School of Mechanical Engineering Hangzhou310027 China Zhejiang University Key Laboratory of Advanced Manufacturing Technology of Zhejiang Province School of Mechanical Engineering Hangzhou310027 China The Chinese University of Hong Kong School of Data Science Shenzhen518172 China

The definition of motion priority enables robot groups to handle competition and cooperation better when performing physical tasks. In this paper, we propose a priority-based step reward mechanism, which is a new reward mechanism for deep reinforcement learning of multi-robot systems and can improve collaboration between robotic arms in shared workspaces. The intention of each agent is provided to other agents, presenting a 2D map of the head that is visually consistent, with state and action representations aligned spatially. Guided by priority-based step rewards, the dual-robots are sequentially assigned high priority, enabling them to pass through complex environments in sequence. We validated our method on a path planning task where two robots collaborate to transport cubes in dynamic environments. The two robots need to consider obstacle avoidance while handing cubes to the human operator. The experimental environment includes Free space, obstacles in the middle, obstacles on both sides, and combinations of several environments. The results show that priority step rewards improve the performance of robot collaborative tasks and significantly enhance cooperative behavior. © 2013 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Droplet control and grain refinement in magnetic-assisted CMT additive manufacturing of 2319 aluminum alloy

引用

Journal of Materials Research and Technology 2025年 36卷 6790-6801页

作者： Xinge Zhang Wenquan Wang Jianyang Zheng Jingwei Liang Xiaosong Feng Hao Yi Zhihui Zhang Key Laboratory of Automobile Materials (Ministry of Education) School of Materials Science and Engineering Jilin University No. 5988 Renmin Street Changchun 130022 China Shanghai Aerospace Equipment Manufacturer Co. Ltd. Shanghai 200245 China State Key Laboratory of Mechanical Transmission for Advanced Equipment Chongqing University Chongqing 400044 China Key Laboratory of Bionic Engineering (Ministry of Education) Jilin University Changchun 130022 China

The influence of excitation current on the microstructure and mechanical properties of the formed components was analyzed, focusing on the interaction between the magnetic field, the arc, molten droplets, and the molten pool. Results showed that the application of a magnetic field significantly improved the surface quality by reducing wave-like fluctuations on the component's side, with the optimal excitation current being 3A. At this current, the surface was smooth, and the grain structure was fine and homogeneous. This magnetic field application was crucial in stabilizing the arc, reducing non-steady-state behavior in the CMT process, and enhancing molten droplet transition, which prevented splattering and promoted stronger bonds between molten droplets and remelted metal. As a result, grain refinement was achieved, and the mechanical properties, including tensile strength and elongation, were significantly improved. At 3A excitation current, the tensile strength in the additive and scanning directions reached 269 MPa and 268 MPa, respectively, with elongation values of 20.5 % and 19.5 %, showing notable improvement compared to the no-field condition. These findings suggest that applying a magnetic field in the arc-based AM process is an effective method for optimizing the surface, microstructure, and mechanical properties of the formed components.

关键词： 2319 aluminum alloy CMT arc additive manufacturing Magnetic field assist Microstructure Arc characteristics

来源：评论

学校读者我要写书评

暂无评论

Auxiliary Tasks Benefit Skeleton-based Action Recognition

Auxiliary Tasks Benefit Skeleton-based Action Recognition

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yuheng Yang Haipeng Chen College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Skeleton-based action recognition has long been a fundamental and intriguing problem in machine intelligence. This task is challenging due to pose occlusion and rapid motion, which typically results in incomplete or noisy skeleton data. State-of-the-art methods tend to learn human motion directly from these corrupted skeletons as if they were reliable. Unfortunately, this might lead to unsatisfactory results when key regions of the skeleton are occluded or disturbed. To tackle the problem, we propose a novel framework that integrates auxiliary tasks into a motion modeling network. These auxiliary tasks corrupt partial human skeletons with masking or noise and then force the network to recover the corrupted data, explicitly facilitating robust feature representation learning. We further propose supervising the auxiliary tasks with mutual information losses, mathematically ensuring feature consistency and spatial alignment between the recovered and original skeleton data. Empirically, our approach sets the new state-of-the-art performance on three benchmark datasets.

关键词： Representation learning Noise Speech recognition Benchmark testing Skeleton Mathematical models Reliability Noise measurement Speech processing Mutual information

来源：评论

学校读者我要写书评

暂无评论

Privacy-preserving and Verifiable Federated Learning with weighted average aggregation in edge computing

引用

Journal of Network and Computer Applications 2025年 240卷

作者： Niu, Shufen Kong, Weiying Chen, Lihua Zhou, Xusheng Wang, Ning College of Computer Science and Engineering Northwest Normal University Lanzhou730070 China Key Laboratory of Cryptography and Data Analytics Northwest Normal University Lanzhou730070 China

In Federated Learning (FL), clients collaborate with edge and cloud servers to train a global model without sharing raw data. However, cloud servers cannot be fully trusted due to the risk of malicious servers forging aggregation results to compromise model updates. Consequently, secure aggregation of local gradients and verification of the integrity of global parameters are crucial. While existing methods ensure the verifiability of aggregation results, few address the trade-off between verification and efficiency in edge computing. To bridge this gap, we propose a privacy-preserving and verifiable weighted averaging aggregation scheme for FL within a cloud–edge collaborative architecture. Our scheme employs a masking technique to compute the weighted gradients and data size of the clients, followed by Lagrange interpolation at the edge servers, and gradient aggregation by dual cloud servers. In this design, the two cloud servers cannot reconstruct a client's local gradients, as each only receives partial interpolation points of the Lagrange polynomial, ensuring client privacy. Additionally, the edge servers can verify the correctness of the aggregation results using cross-verification, providing an efficient method with low computational overhead, and performance evaluations show that the masking overhead is independent of the number of clients. Security analysis shows the scheme guarantees secure, efficient privacy protection and verification. © 2025 Elsevier Ltd

关键词： Lagrange multipliers

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Aerial Image Object Detector Based on Mask Information Enhancement

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Zhou, Liming Zhao, Shuai Liu, Zhehao Zhang, Wanjun Qiao, Baojun Liu, Yang Henan University Henan Key Laboratory of Big Data Analysis and Processing Henan Kaifeng China Henan University School of Computer and Information Engineering Henan Kaifeng China

Object detection in UAV imagery is highly valuable in both military and civilian domains. However, deploying conventional detectors is challenging due to limited computing resources on UAV platforms. Additionally, UAV images often contain densely arranged objects, demanding higher accuracy from detectors. In response to these challenges, we proposed the lightweight aerial object detection method based on mask feature enhancement, named BFDet. First, to enhance the feature extraction capability of the model under limited parameters, we designed the Balanced Channel Attention Layer (BCA Layer). The BCA Layer improves the extraction of high-quality channel information during feature processing. Second, to enhance model performance while minimizing parameters, we designed a feature extraction network utilizing the Efficient Feature Extraction Module (EFEM) and the Downsampling Module (DM) as its backbone. This design reduces the number of parameters while improving the extraction of discriminative features. Third, to enrich the semantic information of features, we proposed a Progressive Space Pyramid Pooling (PSPP) module, obtaining features with rich semantic information to enhance model performance. Finally, to tackle the challenge of detecting densely packed objects, we proposed a Mask Information Enhancement Module (MIEM) to obtain the fine-grained features, enhancing the model's discriminative ability in dense scenes. The proposed BFDet underwent extensive experimentation on both the Vis-Drone and UAVDT datasets. The mAP0.5 and FPS values of BFDet reach 51.4% and 33 respectively on the VisDrone dataset, and the parameter number is only 5.6M. © 1963-2012 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Enhancing diabetes complications prediction through knowledge graphs and convolutional networks

引用

engineering Applications of Artificial Intelligence 2025年 153卷

作者： Cheng, Haitao Zheng, Qunli Li, Peng Xu, He School of Computer Science Nanjing University of Posts and Telecommunications Nanjing210023 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China

Early prediction of diabetes complications is crucial for timely intervention and effective disease management. However, current deep learning approaches often lack sufficient representation of diabetes knowledge and rely on large-scale annotated data. To address this, we propose a knowledge Graphs-enhanced Diabetes Complications Prediction (KGDCP) model, which integrates a physical examination knowledge graph and an improved Diabetes knowledge Graph (DiaKG) using self-attention-based convolutional neural networks. We construct the physical examination knowledge graph based on normal reference ranges of examination indicators and enhance DiaKG through knowledge deduplication and coreference resolution, improving its accuracy and comprehensiveness. Furthermore, we employ the embeddings of these two knowledge graphs to represent examination data and diagnostic information. A token-to-token (token2token) self-attention is utilized to explore dependencies among examination indicators, and convolutional neural networks extract local features to generate representation vectors. Additionally, source-to-token (source2token) self-attention assesses dependencies between diagnostic entities and the entire entity set, with entity-to-Physical Examination (entity2PE) attention gauging entity relevance to examination data representation vectors. Our model combines these features to enhance diabetes complications prediction, outperforming traditional models in predicting cerebral infarction and peripheral neuropathy. © 2025

关键词： knowledge graph

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：