检索结果-内蒙古大学图书馆

24th International Conference on Algorithms and Architectures for Parallel processing, ICA3PP 2024

作者： Xu, Xiaofeng Zhang, Weisha Huang, Yuanyuan Lu, Hongyu Lu, Jiazhong School of Cybersecurity Xin Gu Industrial College Chengdu University of Information Technology Chengdu610225 China Advanced Cryptography and System Security Key Laboratory of Sichuan Province Chengdu610225 China SUGON Industrial Control and Security Center Chengdu610225 China School of Foreign Languages University of Electronic Science and Technology of China Chengdu611731 China

ISBN: (纸本)9789819615247

The detection of fake news is not confined to a single domain, and due to domain transfer, the reliance on detection methods specific to a single domain becomes inadequate when dealing with multi-domain issues. When a multi-domain detection occurs, labels from one domain focus exclusively on the news characteristics of that particular domain, ignoring the possibility that part of the news may include functions from more than one domain. To address these challenges, we propose a multi-domain fake news detection model based on fuzzy rules, incorporating a fuzzy mechanism and an optimization module for fuzzy association rules. In this model, we first introduce a fuzzy mechanism that applies fuzzy processing to domains through neural networks, constructing fuzzy domain labels for each news domain. Subsequently, we incorporate fuzzy association rules to extract a broader range of sample features, thereby enhancing detection effectiveness. Experiments conducted on a fake news dataset demonstrate that our model achieves commendable detection performance with a relatively low training cost, reaching an F1 score of over 97.13% for sample detection. This model successfully overcomes the limitations of single-domain detection in fake news identification and improves the precision of feature extraction through fuzzy rules, showing superior performance in handling multi-domain fake news detection. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： fake news detection fuzzy rules multi-domain social media

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Domain Adaptation Using Attention Network and New Loss Function

Journal of Network Intelligence

引用

Journal of Network Intelligence 2022年第3期7卷 704-718页

作者： Zhao, Li-Quan Zhou, Si-Ying Teng, Zi-Ming Jiang, Zi-Cong Jia, Yan-Fei Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education Northeast Electric Power University Jilin132012 China College of information and communication Jilin University Changchun130012 China Graduate school of Information Science and Electrical Engineering Kyushu University Fukuoka819-0395 Japan School of Electrical and Information Engineering Beihua University Jilin132013 China

An unsupervised domain adaptation method is proposed based on the step-wise adaptive feature norm method to improve transfer learning accuracy. The feature extraction network consists of channel attention and spatial attention modules, which en-hance feature extraction ability. To reduce the influence of dimension change on channel weight, a convolution layer with the same kernel size is used to replace the fully connected layer in the bottleneck layer used in the common channel attention module. In addition, a smooth loss function is also proposed. The curve of the proposed function is smoother than the L2 function that is the least square error function. The proposed function’s gradient changes more slowly than the L2 function. The proposed function is used as the activate function of classification prediction regression to reduce the risk of gradient explosion. Compared with a selection of existing methods (Resnet50, conditional domain adversarial networks method, deep adaptive network method, joint adaptation network method, domain adaptation neural network method, and stepwise adaptive feature norm method), the proposed transfer learning method has the highest accuracy than other methods on different datasets for all tasks. © 2022 Taiwan Ubiquitous information CO LTD. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Vision-Based Autonomous Landing of a Quadrotor UAV on a Double-Layered Nested Landing Marker

Vision-Based Autonomous Landing of a Quadrotor UAV on a Doub...

引用

International Conference on Guidance, Navigation and control, ICGNC 2022

作者： Mu, Lingxia Zhang, Yuan Xin, Jing Zhang, Youmin School of Automation and Information Engineering Xi’an University of Technology Xi’an710048 China Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi’an University of Technology Xi’an710048 China Department of Mechanical and Industrial Engineering Concordia University MontrealH3G 1M8 Canada

ISBN: (纸本)9789811966125

This paper focuses on the vision-based autonomous landing mission of a quadrotor unmanned aerial vehicle (UAV). A double-layered nested Aruco landing marker is designed which can adapt to the situation that the field of sight of airborne camera changes as the UAV’s altitude decreases during the landing. Then, considering that the landing marker might be obstructed in certain situation, traditional Aruco detection method cannot effectively recognize marker. A YOLOv4 deep learning algorithm is used for marker detection. In addition, to address the problem of false detection in some test results, normalized Wasserstein distance is used to replace the non-maximum suppression to deal with redundant frames. The UAV’s relative location to the marker is then calculated and landing mission is finally achieved by the image-based visual servoing strategy. The simulation on Gazebo demonstrates that the designed marker is effective for the UAV landing mission and the revised YOLOv4 detection algorithm can increase detection results accuracy. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

Aβ-Aggregation-Generated Blue Autofluorescence Illuminates Senile Plaques as well as Complex Blood and Vascular Pathologies in Alzheimer’s Disease

引用

Neuroscience Bulletin 2024年第8期40卷 1115-1126页

作者： Hualin Fu Jilong Li Chunlei Zhang Peng Du Guo Gao Qiqi Ge Xinping Guan Daxiang Cui Institute of Nano Biomedicine and Engineering School of Sensing Science and EngineeringSchool of Electronic Information and Electrical EngineeringShanghai Jiao Tong UniversityShanghai 200240China Institute of Marine Equipment Shanghai Jiao Tong UniversityShanghai 200240China National Center for Translational Medicine Shanghai Jiao Tong UniversityShanghai 200240China Department of Colorectal Surgery School of MedicineXinhua HospitalShanghai Jiao Tong UniversityShanghai 200092China Department of Automation Shanghai Jiao Tong UniversityShanghai 200240China The Key Laboratory of System Control and Information Processing Ministry of EducationShanghai 200240China

Senile plaque blue autofluorescence was discovered around 40 years ago,however,its impact on Alzheimer’s disease(AD)pathology has not been fully *** analyzed senile plaques with immunohistochemistry and fluorescence imaging on AD brain sections and also Aβ aggregation in *** DAPI or Hoechst staining,the nuclear blue fluorescence could only be correctly assigned after subtracting the blue plaque *** flower-like structures wrapping dense-core blue fluorescence formed by cathepsin D staining could not be considered central-nucleated neurons with defective lysosomes since there was no nuclear staining in the plaque core when the blue autofluorescence was *** Aβ self-oligomers and Aβ/hemoglobin heterocomplexes generated blue *** Aβ amyloid blue autofluorescence not only labels senile plaques but also illustrates red cell aggregation,hemolysis,cerebral amyloid angiopathy,vascular plaques,vascular adhesions,and *** summary,we conclude that Aβ-aggregation-generated blue autofluorescence is an excellent multi-amyloidosis marker in Alzheimer’s disease.

关键词： Senile plaque Blue autofluorescence Aβ Amyloid aggregation Hemoglobin Cathepsin D.Microaneurysm Alzheimer's disease

来源：评论

学校读者我要写书评

暂无评论

Prediction of Distributed Photovoltaic Accommodation Capability Based on Ridge Regression 9th

Prediction of Distributed Photovoltaic Accommodation Capabil...

引用

9th Purple Mountain Form on Smart Grid Protection and control, PMF 2024

作者： Ji, Xingquan Zhang, Bowen Zhang, Yumin Sun, Pengkai Zhang, Xiaofeng Liu, Wei dong Shandong University of Science and Technology Qingdao266590 China Key Laboratory of Power System Intelligent Dispatch and Control Shandong University Jinan250061 China Information and Communication Company State Grid Shandong Electric Power Company Jinan250013 China Qingdao Yihe Electric Group Co. Ltd. Qingdao266510 China

ISBN: (纸本)9789819616701

A prediction method of distributed photovoltaic accommodation capability is proposed based on ridge regression. First, the factors influencing the distributed photovoltaic accommodation capacity are analyzed, and the concept of the contribution degree of distributed photovoltaic accommodation is introduced. The gray relation analysis method is used to evaluate the correlation between different factors and distributed photovoltaic accommodation, and a model of factors affecting distributed photovoltaic accommodation is constructed. Then, a prediction model of distributed photovoltaic accommodation capability is established based on ridge regression. The factors with high photovoltaic accommodation contribution degrees are incorporated in the prediction model. The mapping relationship between the driving factors of distributed photovoltaic accommodation and the prediction model is derived, then the development strategies for future photovoltaic accommodation capacity are formulated. Finally, simulation is performed on the SPSSPRO platform, and the results show that the proposed method can predict the distributed photovoltaic accommodation capability accurately and provide strategic suggestions for improving future photovoltaic accommodation capacity. © State Grid Electric Power 2025.

关键词： Photovoltaics

来源：评论

学校读者我要写书评

暂无评论

Dynamic Fault Detection Based on Variational Bayesian Mixture Probabilistic Principal Component Analysis 11

Dynamic Fault Detection Based on Variational Bayesian Mixtur...

引用

11th IEEE Data Driven control and Learning systems Conference, DDCLS 2022

作者： Huang, Chenghong Chai, Yi Wei, Chihang Zhu, Zheren Chongqing University College of automation Chongqing400044 China Hangzhou Normal University School of Information Science and Technology Hangzhou311121 China Institute of Industrial Process Control College of Control Science and Engineering Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou310027 China

ISBN: (数字)9781665496759

ISBN: (纸本)9781665496759

It is essential to achieve real-time fault detection of the industrial process to reduce the occurrence of accidents during the industrial process. However, there are some problems in the actual monitoring process, such as the instability of sensor measurement, losing packet while transferring data, which causes problems like missing data and outliers while sampling from actual monitoring data. In addition, the monitoring data are interrelated in time series. Thus, a fault detection method based on DMPPCA model is proposed in this study. DMPPCA can not only consider the above problems at the same time, but also determine the dimension of latent variables automatically. Finally, the effect of proposed DMPPCA model was validated by a three-phase flow facility. © 2022 IEEE.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

LHMap-loc: Cross-Modal Monocular Localization Using LiDAR Point Cloud Heat Map

LHMap-loc: Cross-Modal Monocular Localization Using LiDAR Po...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Xinrui Wu Jianbo Xu Puyuan Hu Guangming Wang Hesheng Wang Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai China Department of Engineering University of Cambridge Cambridge U.K

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Localization using a monocular camera in the pre-built LiDAR point cloud map has drawn increasing attention in the field of autonomous driving and mobile robotics. However, there are still many challenges (e.g. difficulties of map storage, poor localization robustness in large scenes) in accurately and efficiently implementing cross-modal localization. To solve these problems, a novel pipeline termed LHMap-loc is proposed, which achieves accurate and efficient monocular localization in LiDAR maps. Firstly, feature encoding is carried out on the original LiDAR point cloud map by generating offline heat point clouds, by which the size of the original LiDAR map is compressed. Then, an end-to-end online pose regression network is designed based on optical flow estimation and spatial attention to achieve real-time monocular visual localization in a pre-built map. In addition, a series of experiments have been conducted to prove the effectiveness of the proposed method. Our code is available at: https://***/IRMVLab/LHMap-loc.

关键词： Location awareness Point cloud compression Visualization Laser radar Accuracy Robot vision systems Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Heuristic Task Allocation Method for Heterogeneous Lunar Robots under Dynamic Resource Cost

Heuristic Task Allocation Method for Heterogeneous Lunar Rob...

引用

2024 IAF Space Operations Symposium at the 75th International Astronautical Congress, IAC 2024

作者： Xu, Rui Zhou, Junhui Li, Zhaoyu Zhu, Shengying Pan, Bo Zhao, Zhijun Yu, Dengyun School of Aerospace Engineering Beijing Institute of Technology Beijing100081 China Key Laboratory of Autonomous Navigation and Control for Deep Space Exploration Ministry of Industry and Information Technology Beijing100081 China Beijing Institute of Spacecraft System Engineering Beijing100094 China China Aerospace Science and Technology Corporation Beijing100048 China

ISBN: (纸本)9798331312183

China, in collaboration with multiple countries, is preparing to construct a long-term, independently operated international lunar research station on the surface of the moon in the coming years. The construction of an unmanned lunar research station requires the collaboration of diverse and heterogeneous lunar robots to successfully carry out missions. Task allocation for heterogeneous lunar robots is a crucial technical requirement, focusing on constructing evaluation matrix, designing optimization objective functions, and developing algorithms for optimization matching. The state changes during the execution of tasks by robots result in different resource costs for completing other task goals compared to the initial resource costs. Therefore, one of the major challenges in task allocation for multi-robot systems is effectively managing dynamic resource costs during the construction of evaluation matrix (and subsequent optimization based on the matrix). However, the current approach tends to calculate static cost without considering cost changes during task execution, which deviates from standard engineering practices. Instead, the primary contribution of this paper lies in designing a heuristic algorithm capable of optimizing task allocation outcomes while accounting for the dynamic changes in resource costs incurred during goal achievement. In this paper, we propose a heuristic task allocation method for heterogeneous lunar robots under dynamic resource cost. Given a multi-robot cooperative task, our method firstly constructs a task allocation model based on robotic capability and task resource consumption. Next, based on relaxation planning graph, the resource cost for each lunar rover to complete all task goals is calculated, and the cost of transitioning between different goal states is estimated (to efficiently update the resource cost of completing each goal as the lunar rover's state changes). Subsequently, the evaluation matrix is constructed. Then, a heu

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

Transfer learning with a spatiotemporal graph convolution network for city flowprediction

引用

Frontiers of information Technology & Electronic Engineering 2025年第1期26卷 79-92页

作者： Binkun LIU Yu KANG Yang CAO Yunbo ZHAO Zhenyi XU Department of Automation University of Science and Technology of ChinaHefei 230026China Key Laboratory of System Control and Information Processing Ministry of EducationShanghai 200240China Institute of Artificial Intelligence Hefei Comprehensive National Science CenterHefei 230088China Institute of Advanced Technology University of Science and Technology of ChinaHefei 230088China

Recently,deep learning based city flow prediction has been extensively used in the establishment of *** methods are data-hungry,making them unscalable to areas lacking *** transfer learningcan use data-rich source domains to assist target domain cities in city flow prediction,the performance of existingmethods cannot meet the needs of actual use,because the long-distance road network connectivity is *** this problem,we propose a transfer learning method based on spatiotemporal graph convolution,in which weconstruct a co-occurrence space between the source and target domains,and then align the mapping of the sourceand target domains’data in this space,to achieve the transfer learning of the source city flow prediction modelon the target ***,a dynamic spatiotemporal graph convolution module along with a temporalencoder is devised to simultaneously capture the concurrent spatiotemporal features,which implies the inherentrelationship among the road network structures,human travel habits,and city bike ***,these concurrentfeatures are leveraged as cross-city invariant representations and nonlinearly spanned to a co-occurrence *** domain features are thereby aligned with the source domain features in the co-occurrence space by using aMahalanobis distance loss,to achieve cross-city bike flow *** proposed method is evaluated on the publicbike flow datasets in Chicago,New York,and Washington in 2015,and significantly outperforms state-of-the-arttechniques.

关键词： Transfer learning City flow prediction Spatiotemporal graph convolution

来源：评论

学校读者我要写书评

暂无评论

S2KAN-SLAM: Elastic Neural LiDAR SLAM with SDF Submaps and Kolmogorov-Arnold Networks

引用

IEEE Transactions on Circuits and systems for Video Technology 2025年

作者： Wang, Zhong Zhang, Lin Wang, Hesheng Shanghai Jiao Tong University State Key Laboratory of Avionics Integration and Aviation System-of-Systems Synthesis Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Shanghai200240 China Tongji University School of Computer Science and Technology National Pilot Software Engineering School with Chinese Characteristics Shanghai201804 China

Traditional LiDAR SLAM approaches prioritize localization over mapping, yet high-precision dense maps are essential for numerous applications involving intelligent agents. Recent advancements have introduced methods leveraging neural fields to enhance mapping capabilities;however, these approaches still face several limitations. Firstly, concerning scene representation, they typically employ neural fields with high-dimensional features and multi-layer perceptron decoders utilizing non-continuous activation functions. This results in low learning efficiency and challenges in capturing high-frequency signals. Secondly, in terms of scene organization, these methods often treat the entire scene as a singular neural field, leading to inefficiencies, inflexibility, and difficulties in rectifying accumulated errors when mapping large-scale environments over extended periods. To tackle the first issue, we propose a lightweight continuous SDF regression approach by encoding the scene in single-valued embeddings and decoding SDF values from a Kolmogorov-Arnold Network. By minimizing discrepancies in measuring range, sampling distance, and decoded SDF values, we facilitate iterative frame-to-model tracking and bundle adjustment neural mapping. To mitigate the second challenge, we propose structuring the whole scene into multiple neural SDF submaps. By establishing node-node, node-submap, and loop closure constraints into a global pose graph, the system can create dense neural maps with global consistency across large-scale scenes. Experimental evaluations in both real-world and simulated settings indicate that our system achieves superior mapping completeness and accuracy, enhanced learning efficiency, reduced memory consumption, and greater flexibility compared to its counterparts. © 2025 IEEE.

关键词： Mapping

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：