检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Wu, Yirui Xia, Yuhang Li, Hao Yuan, Lixin Chen, Junyang Liu, Jun Lu, Tong Wan, Shaohua Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China College of Computer Science and Software Engineering Shenzhen University Shenzhen China School of Computing and Communication Lancaster University Lancaster United Kingdom National Key Lab for Novel Software Technology Nanjing University Nanjing China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Shenzhen China

ISBN: (纸本)157735897X

Incremental few-shot semantic segmentation (IFSS) expands segmentation capacity of the trained model to segment new-class images with few samples. However, semantic meanings may shift from background to object class or vice versa during incremental learning. Moreover, new-class samples often lack representative attribute features when the new class greatly differs from the pre-learned old class. In this paper, we propose a causal framework to discuss the cause of semantic shift and incompleteness in IFSS, and we deconfound the revealed causal effects from two aspects. First, we propose a Causal Intervention Module (CIM) to resist semantic shift. CIM progressively and adaptively updates prototypes of old class, and removes the confounder in an intervention manner. Second, a Prototype Refinement Module (PRM) is proposed to complete the missing semantics. In PRM, knowledge gained from the episode learning scheme assists in fusing features of new-class and old-class prototypes. Experiments on both PASCAL-VOC 2012 and ADE20k benchmarks demonstrate the outstanding performance of our method. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

An Exploratory data Analysis and Visualizations of Underprivileged Communities Diabetes dataset for Public Good

An Exploratory Data Analysis and Visualizations of Underpriv...

引用

IEEE WIC ACM International Conference on Web Intelligence (WI)

作者： Majdi Owda Amani Yousef Owda Maria Fasli Faculty of Data Science UNESCO Chair in Data Science for Sustainable Development Arab American University Ramallah West Bank Palestine Deprtment of Natural Engineering and Technology Sciences Faculty of Graduate Studies Arab American University Ramallah West Bank Palestine University of Essex School of Computer Science and Electronic Engineering Institute for Analytics and Data Science Colchester UK

Exploratory data analysis and visualization are essential tools for discovering patterns, highlighting anomalies, and discovering insights from datasets. In addition, visualizations tend to provide information in a way that is more accessible for the audience to understand and comprehend. Underprivileged communities will need an easier way to comprehend issues, challenges, and threats such as avoiding diseases. The use of exploratory data analysis and visualizations of diabetes datasets can be used as a means to make this topic easier to understand for underprivileged communities. A methodology has been developed to explore a dataset collection of diabetes patients. The dataset was obtained from the Palestinian community medical center (first-hand dataset), then the dataset was prepared and cleaned, and all rows with missing values or wrong values were dropped and removed, then an exploratory data analysis with a large number of data visualizations was produced, and last, a sample of the produced visualizations have been used to conduct a social acceptance experiment to educate an underprivileged population in the Palestinian community about the risks of diabetes. The result of the experiment was excellent and very promising in which participants understood the contents in a much easier way and provided very positive feedback on utilizing visualizations of diabetes datasets for public awareness and good.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transmission Line Routing Based on Multi-Source Geographic Information and Improved Grey Wolf Algorithm 5

Transmission Line Routing Based on Multi-Source Geographic I...

引用

5th International Conference on Machine Learning and computer Application, ICMLCA 2024

作者： Yang, Shu Xia, Yudong Zhu, Lankang Chen, Hao Cui, Li Pan, Wenwu Li, Ali He, Liang Jiaxing Hengchuang Electric Power Design and Research Institute Co. Ltd Jiaxing Hengchuang Jiaxing China School of Computer Science and Technology Xinjiang University Urumqi China Tsinghua University Center for Information Science and Technology Department of Electronic Engineering and Beijing National Research Beijing China

ISBN: (纸本)9798331530334

The design and selection of transmission lines are crucial for the security, economy and reliability of power systems. Traditional planning methods mainly rely on field visits and empirical judgment of grid researchers and have many limitations. This paper proposes a transmission line path planning method using multi-source geographic information and the improved grey wolf algorithm to reduce some costs. We utilize the geographic information system (GIS) for data processing and apply triangular fuzzy number hierarchical analysis to assess cost weights. By incorporating crossover and mutation operators, we enhance the grey wolf algorithm for optimized path planning. A local area in Jiaxing City, Zhejiang Province, is used for case study, which demonstrates that our method reduces costs compared to traditional grey wolf optimization to a certain extent. The results indicate that our approach offers a more reasonable path planning solution. © 2024 IEEE.

关键词： Power transmission lines

来源：评论

学校读者我要写书评

暂无评论

Towards Fair Federated Learning via Unbiased Feature Aggregation

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： He, Zeqing Wang, Zhibo Dong, Xiaowei Sun, Peng Ren, Ju Ren, Kui Zhejiang University State Key Laboratory of Blockchain and Data Security China Institute of Blockchain and Data Security Hangzhou310027 China Wuhan University School of Cyber Science and Engineering Wuhan430072 China Hunan University College of Computer Science and Electronic Engineering Changsha410082 China Tsinghua University Department of Computer Science and Technology Beijing100084 China Zhongguancun Laboratory Beijing100094 China

Federated learning (FL) is a distributed machine learning framework that enables multiple clients to collaboratively train models without raw data exchange. Prior studies on FL mainly focus on optimizing learning performance, enhancing privacy preservation, and improving attack resilience. However, little work studies how to mitigate the unfairness of federated trained models while unfair models would make discriminatory decisions toward certain groups or populations (e.g., favoring males over females), leading to serious ethical concerns. Thus, it is crucial to mitigate model unfairness in FL, yet challenging as this requires centralized access to each data point's fairness-sensitive information (e.g., race, gender), which is prohibited in FL. In this work, we propose a novel fair FL framework FedUFA, where the server can aggregate clients' learned knowledge in an unbiased manner, to obtain fair and high-usability federated trained models. Specifically, to unearth the bias in clients' local data and account for potentially heterogeneous local models, we propose a knowledge distillation-based FL scheme, where clients' knowledge of learned features on a public dataset is amalgamated to the server for aggregation. We train an unbiased feature mapper at the server to remove fairness-sensitive latent features and extract fair representations from clients' submitted raw features. In particular, we design an adversarial training method to train the mapper, which involves a predictor aiming to maximize the prediction accuracy on the FL task and a discriminator intending to help identify fairness-sensitive features. Extensive experiments on real-world datasets demonstrate the effectiveness of FedUFA. © 2025 IEEE. All rights reserved,

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing IoMT Security Using Large Multimodal Models

引用

IEEE Network 2025年

作者： Jiao, Yan Razaq, Mian Muaz Peng, Limei Ho, Pin-Han University of Electronic Science and Technology of China Shenzhen Institute for Advanced Study Guangdong China Kyungpook National University School of Computer Science and Engineering Daegu41566 Korea Republic of

This paper explores the potential of Large Multi-modal Models (LMMs) in enhancing the security of Internet of Medical Things (IoMT) networks. As IoMT systems become more complex and generate vast amounts of sensitive data, traditional security measures are increasingly insufficient to address evolving cyber threats. The ability of LMMs to process and integrate diverse data types, such as sensor data, audio, and video, offers a powerful approach to detecting and mitigating security risks in real time. By focusing on key applications like anomaly detection through traffic prediction and improving Physical Layer Security (PLS), this work demonstrates how LMMs can significantly enhance the resilience of IoMT networks against a wide range of cyber threats. The integration of multimodal data enables more accurate traffic predictions and allows adaptive responses to emerging security challenges. Additionally, LMMs contribute to strengthening PLS by identifying vulnerabilities in communication channels and optimizing resource allocation. Through dynamic data fusion techniques, LMMs ensure that IoMT systems can respond to threats in real-time, while maintaining high security and minimizing impact on system performance. © 1986-2012 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Object Detection Method for Bank Operation and Maintenance Scenarios 5

A Lightweight Object Detection Method for Bank Operation and...

引用

5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022

作者： Xue, Junmin Rao, Yunbo Wu, Jiangang Gou, Haosong Liu, Yong Yang, Yang University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu China Data Center of Postal Savings Bank of China Beijing China Chengdu Aerospace Science and Industry Big Data Research Institute Corporation Limited Chengdu China Sichuan Institute of Computer Sciences Chengdu China

ISBN: (数字)9781665499163

ISBN: (纸本)9781665499163

Due to the complex background of bank operation and maintenance scenarios, it is extremely difficult to detect and analyze the object of operation and maintenance scenarios. The traditional target detection algorithms, such as F-RCNN, are not suitable for object detection. We propose a lightweight object detection method for bank operation and maintenance scenarios based on deep learning. The proposed method highlights two improvements based on Yolov5. The first adjustment of it is this method constructs a new convolution method and a new activation function. Also, we use the multi-scale output strategy of Feature Pyramid Networks (FPN) to develop a new lightweight feature extraction algorithm. These changes we made are based on the real-life situation, such as bank operation and maintenance scenarios. Experiments have been carried out on the same data set with multiple object detection algorithms, and the experimental results show that the proposed method reduces the complexity of the activation function. Meanwhile, the module is flexible, and can be easily applied to other similar business scenario detection models. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Catalyzing Random Access at Physical Layer for Internet of Things:An Intelligence Enabled User Signature Code Acquisition Approach

引用

China Communications 2021年第10期18卷 181-192页

作者： Xiaojie Fang Xinyu Yin Xuejun Sha Jinghui Qiu Hongli Zhang School of Electronic and Information Engineering Harbin Institute of TechnologyHarbin 1500001China Science and Technology on Communication Networks Laboratory Shijiazhuang 050050China School of Computer Science and Technology Harbin Institute of TechnologyHarbin 150001China

Exploiting random access for the underlying connectivity provisioning has great potential to incorporate massive machine-type communication(MTC)devices in an Internet of Things(Io T)***,massive access attempts from versatile MTC devices may bring congestion to the IIo T network,thereby hindering service increasing of IIo T *** this paper,an intelligence enabled physical(PHY-)layer user signature code acquisition(USCA)algorithm is proposed to overcome the random access congestion problem with reduced signaling and control *** the proposed scheme,the detector aims at approximating the optimal observation on both active user detection and user data reception by iteratively learning and predicting the convergence of the user signature codes that are in *** crossentropy based low-complexity iterative updating rule is present to guarantee that the proposed USCA algorithm is computational feasible.A closed-form bit error rate(BER)performance analysis is carried out to show the efficiency of the proposed intelligence USCA *** results confirm that the proposed USCA algorithm provides an inherent tradeoff between performance and complexity and allows the detector achieves an approximate optimal performance with a reasonable computational complexity.

关键词： Internet of Things(IoT) artificial intelligence physical layer cross-entropy random access

来源：评论

学校读者我要写书评

暂无评论

Pedestrian Detection Method Based on Improved YOLOv5s for Densely Occluded Scenarios 3

Pedestrian Detection Method Based on Improved YOLOv5s for De...

引用

3rd International Conference on Big data, Information and computer Network, BDICN 2024

作者： Pan, Rongting Qin, Guofeng Zhu, Yongjian Mi, Peiwen Li, Ming College of Electronic and Information Engineering Guangxi Normal University Guilin541004 China Teachers College for Vocational and Technical Education Guangxi Normal University Guilin541004 China School of Computer Science and Information Engineering Shanghai Institute of Technology Shanghai201418 China

ISBN: (纸本)9798350363821

In response to the issues of low accuracy and high false negatives in real-Time detection of densely occluded pedestrians, a pedestrian detection method based on improved YOLOv5s is proposed. This method involves replacing the Centralized-Comprehensive Convolution Block (C3) module in the backbone network with the DenseBlock module to enhance the model's feature extraction capabilities for small targets. The Efficient Intersection over Union (EIoU) loss function was used instead of the Complete Intersection over Union (CIoU) loss function to improve the model's ability to accurately locate densely occluded targets. Based on the feature pyramid structure, the Adaptive Spatial Feature Fusion (ASFF) module was introduced, enhancing the network's feature extraction capability. The introduction of the multi-head self-Attention (MHSA) mechanism has enhanced the model's adaptability. The experimental results indicate that the improved YOLOv5s algorithm achieves mAP0.5 and mAP0.5:0.95 of 78.6% and 48.7%, respectively, on the CrowdHuman dataset. This represents an improvement of 2.0% and 2.2% compared to the initial YOLOv5s. The detection time is 11.4ms, showing good robustness for detecting targets of different sizes and meeting real-Time requirements. © 2024 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Spiking transformer with experts mixture 24

Spiking transformer with experts mixture

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Zhaokun Zhou Yijie Lu Yanhao Jia Kaiwei Che Jun Niu Liwei Huang Xinyu Shi Yuesheng Zhu Guoqi Li Zhaofei Yu Li Yuan School of Electronic and Computer Engineering Shenzhen Graduate School Peking University and Peng Cheng Laboratory School of Electronic and Computer Engineering Shenzhen Graduate School Peking University College of Computing and Data Science Nanyang Technological University and Deep NeuroCognition Lab I2R and CFAR Agency for Science Technology and Research School of Computer Science Peking University and Peng Cheng Laboratory Institute for Artificial Intelligence Peking University and School of Computer Science Peking University Institute of Automation Chinese Academy of Sciences and Peng Cheng Laboratory

ISBN: (纸本)9798331314385

Spiking Neural Networks (SNNs) provide a sparse spike-driven mechanism which is believed to be critical for energy-efficient deep learning. Mixture-of-Experts (MoE), on the other side, aligns with the brain mechanism of distributed and sparse processing, resulting in an efficient way of enhancing model capacity and conditional computation. In this work, we consider how to incorporate SNNs' spike-driven and MoE's conditional computation into a unified framework. However, MoE uses softmax to get the dense conditional weights for each expert and TopK to hard-sparsify the network, which does not fit the properties of SNNs. To address this issue, we reformulate MoE in SNNs and introduce the Spiking Experts Mixture Mechanism (SEMM) from the perspective of sparse spiking activation. Both the experts and the router output spiking sequences, and their element-wise operation makes SEMM computation spike-driven and dynamic sparse-conditional. By developing SEMM into Spiking Transformer, the Experts Mixture Spiking Attention (EMSA) and the Experts Mixture Spiking Perceptron (EMSP) are proposed, which performs routing allocation for head-wise and channel-wise spiking experts, respectively. Experiments show that SEMM realizes sparse conditional computation and obtains a stable improvement on neuromorphic and static datasets with approximate computational overhead based on the Spiking Transformer baselines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Method for Processing Graph Degeneracy in Dynamic Geometry Based on Domain Design

引用

Journal of computer science & Technology 2021年第4期36卷 910-921页

作者： Hao Guan Yong-Sheng Rao Jing-Zhong Zhang Sheng Cao Xiao-Lin Qin Institute of Computing Science and Technology Guangzhou UniversityGuangzhou 510006China Chengdu Institute of Computer Applications Chinese Academy of SciencesChengdu 610041China University of Chinese Academy of Sciences Beijing 100049China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu 61173China

A dynamic geometry system,as an important application in the field of geometric constraint solving,is widely used in elementary mathematics education;moreover,the dynamic geometry system is also a fundamental environment for automated theorem proving in *** a geometric constraint solving process,a situation involving a critical point is often encountered,and geometric element degeneracy may occur at this ***,the degeneracy situation must be substantively focused on during the learning and exploration ***,many degeneracy situations cannot be completely presented even by the well-known dynamic geometry *** this paper,the mechanisms causing the degeneracy of a geometric element are analyzed,and relevant definitions and formalized descriptions for the problem are provided according to the relevant modern Euclidean geometry *** solve the problem,the data structure is optimized,and a domain model design for the geometric element and the constraint relationships thereof in the dynamic geometry system are formed;furthermore,an update algorithm for the element is proposed based on the novel domain *** addition,instances show that the proposed domain model and the update algorithm can effectively cope with the geometric element degeneracy situations in the geometric constraint solving process,thereby achieving unification of the dynamic geometry drawing and the geometric intuition of the user.

关键词： dynamic geometry critical point degeneracy domain model

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：