检索结果-内蒙古大学图书馆

5th International Conference on Artificial Intelligence and Computer Engineering, ICAICE 2024

作者： Yue, Yurong Kong, Xiaoyang Pan, Rui Shan, Wei College of Physics and Electronic Information Huaibei Normal University Huaibei China Anhui Provincial Key Laboratory of Intelligent Computing and Application Huaibei China

ISBN: (纸本)9798331528911

Aiming at the problem of poor detection of long-distance pedestrians in intelligent traffic scenarios, an improved YOLOv8 pedestrian detection algorithm is proposed. Using YOLOv8 as the basic network, SPD-Conv is embedded before the C2f layer of backbone and after the Conv layer of neck as the key preprocessing step. Experimental results on the public dataset Caltech Pedestrian Dataset show that compared with the baseline algorithm, mAP0.5 is increased by 3%, mAP0.5: 0.95 is increased by 5.8%, and LAMR is reduced by 5.5%. Compared with the popular algorithm, mAP0.5 and mAP0.5: 0.95 are as high as 0.892 and 0.598, respectively, and LAMR is as low as 0.249, which is better than the popular algorithm. The results show that the algorithm achieves a significant improvement in accuracy in pedestrian detection tasks, and effectively reduces the occurrence of missed detection. It can serve intelligent transportation more effectively and reduce the potential safety hazards caused by missed detection. © 2024 IEEE.

关键词： intelligent transportation pedestrian detection spatial to deep convolution

来源：评论

学校读者我要写书评

暂无评论

Lightweight Small Target Detection Algorithm for UAV Infrared Aerial Photography Based on YOLOv8 5

Lightweight Small Target Detection Algorithm for UAV Infrare...

引用

5th International Conference on Artificial Intelligence and Computer Engineering, ICAICE 2024

作者： Li, Jinfeng Zhu, Xiaodong Shan, Wei College of Physics and Electronic Information Huaibei Normal University Huaibei China Anhui Provincial Key Laboratory of Intelligent Computing and Application Huaibei China

ISBN: (纸本)9798331528911

Aiming at the complexity of UAV infrared air target detection model,a lightweight target detection algorithm based on YOLOv8 n is proposed. By introducing a lightweight Depthwise Convolution module, the model size is reduced to facilitate deployment on mobile devices. The experimental results on the HIT-UAV dataset show that compared with the benchmark model YOLOv8n, the improved algorithm reduces the number of parameters and GFLOPs by 0.6M and 1.2G, respectively. In summary, the effectiveness of the algorithm is verified, which provides the possibility for the UAV to perform real-time target detection tasks. © 2024 IEEE.

关键词： Aerial photography

来源：评论

学校读者我要写书评

暂无评论

Extracting Variable-Depth Logical Document Hierarchy from Long Documents:Method,Evaluation,and application

引用

Journal of Computer Science & Technology 2022年第3期37卷 699-718页

作者： Rong-Yu Cao Yi-Xuan Cao Gan-Bin Zhou Ping Luo Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China WeChat Search Application Department Tencent Holdings Ltd.Beijing 100080China Peng Cheng Laboratory Shenzhen 518066China

In this paper,we study the problem of extracting variable-depth"logical document hierarchy"from long documents,namely organizing the recognized"physical document objects"into hierarchical *** discovery of logical document hierarchy is the vital step to support many downstream applications(e.g.,passage-based retrieval and high-quality information extraction).However,long documents,containing hundreds or even thousands of pages and a variable-depth hierarchy,challenge the existing *** address these challenges,we develop a framework,namely Hierarchy Extraction from Long Document(HELD),where we"sequentially"insert each physical object at the proper position on the current *** whether each possible position is proper or not can be formulated as a binary classification *** further improve its effectiveness and efficiency,we study the design variants in HELD,including traversal orders of the insertion positions,heading extraction explicitly or implicitly,tolerance to insertion errors in predecessor steps,and so *** for evaluations,we find that previous studies ignore the error that the depth of a node is correct while its path to the root is *** such mistakes may worsen the downstream applications seriously,a new measure is developed for a more careful *** empirical experiments based on thousands of long documents from Chinese financial market,English financial market and English scientific publication show that the HELD model with the"root-to-leaf"traversal order and explicit heading extraction is the best choice to achieve the tradeoff between effectiveness and efficiency with the accuracy of 0.972,6,0.729,1 and 0.957,8 in the Chinese financial,English financial and arXiv datasets,***,we show that the logical document hierarchy can be employed to significantly improve the performance of the downstream passage retrieval *** summary,we conduct a systematic study on this task in terms of methods

关键词： logical document hierarchy long documents passage retrieval

来源：评论

学校读者我要写书评

暂无评论

FedLGMatch: Federated semi-supervised learning via joint local and global pseudo labeling

引用

Knowledge-Based Systems 2025年 320卷

作者： Zhao, Qing Chu, Jielei Li, Zhaoyu Huang, Wei Luo, Zhipeng Li, Tianrui School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Chengdu611756 China China Railway Engineering Group Limited Beijing100039 China China Railway Eryuan Engineering Group Co. Ltd. Sichuan Chengdu610031 China College of Computer and Data Science Fuzhou University China

The bulk of existing Federated Learning (FL) algorithms pay attention to supervised setting and assume that clients have fully labeled data. However, it may be impractical for all clients to obtain plenty of labels due to high annotation costs. Hence, the Federated Semi-Supervised Learning (FSSL) as a promising paradigm has better prospect in many realistic applications (e.g. medical scenario). Under Labels-at-Server scenario, most pseudo labeling based FSSL approaches use only the global model to generate pseudo-labels for unlabeled data, while the local models are ignored. When the local data distribution is much more different from the central server (e.g., Non-IID setting), the generated pseudo-labels may contain much noise, thus, resulting in more serious confirmation bias. To tackle the crucial issue, a novel Federated Semi-Supervised Learning via Joint Local and Global Pseudo Labeling (FedLGMatch) framework is proposed in this paper. The prominent advantage of the proposed FedLGMatch is that it allows local models trained in the last communication round to assist global model in generating pseudo-labels, which successfully emphasizes more clean pseudo-label learning at each client. Experimental results also show that FedLGMatch achieves significant performance improvements than other state-of-the-art models on the standard benchmark datasets. © 2025 Elsevier B.V.

关键词： Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Fusion recommendation algorithm based on DeepWalk and Item-Based collaborative filtering 3

Fusion recommendation algorithm based on DeepWalk and Item-B...

引用

3rd International Conference on Computer Science and Management Technology, ICCSMT 2022

作者： Yu, Yicheng Li, Rongbin Yin, Jun Qinghai Normal University School of Computing Xi'Ning China The State Key Laboratory of Tibetan Intelligent Information Processing and Application Xi'Ning China

ISBN: (纸本)9798350320404

Collaborative filtering techniques have been applied to personalised recommendation systems in recommender systems. However, with the gradual increase in the number of platform users and goods, the user rating data on the entire project matrix is extremely sparse, resulting in the inaccuracy of the prediction results. DeepWalk, on the other hand, still performs well when the data is sparse. Therefore, DeepWalk is introduced into collaborative filtering, and a fusion recommendation algorithm based on DeepWalk and collaborative filtering is proposed to reduce the impact of cold start and sparsity on the recommendation results. Experiments show that the proposed fusion recommendation algorithm has higher recommendation accuracy when the data is sparse compared with other traditional algorithms, which improves the recommendation quality to a certain extent. © 2022 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Multi Strategy Improvement of Newton-Raphson-Based Optimizer and Engineering application 6

Multi Strategy Improvement of Newton-Raphson-Based Optimizer...

引用

6th International Conference on Machine Learning, Big Data and Business Intelligence, MLBDBI 2024

作者： Cheng, Shaogang Yin, Jun Liu, Tingting College of Computing Qinghai Normal University Xining China Qinghai Normal University The State Key Laboratory of Tibetan Intelligent Information Processing and Application Xining China

ISBN: (纸本)9798331541798

A multi strategy improved Newton- Raphson-Based Optimizer (NRBO) is proposed to address the problem of slow convergence speed in the later stage of algorithm iteration and difficulty in finding the global optimal solution when facing complex functions. Firstly, using a set of best points instead of randomly generated initial populations to evenly distribute individuals in the optimization space improves the efficiency of the algorithms global and local search. Secondly, based on the idea of differential evolution, the initial population is mutated and crossed to accelerate the iteration speed. Then, in the optimal update stage, the Levi flight strategy is introduced to enhance the algorithms ability to jump out of local optima. The effectiveness of the proposed algorithm was tested on the CEC2005 test set, and compared with other algorithms on two test sets. The results showed that the convergence speed and accuracy of the algorithm were significantly improved. Finally, the proposed algorithm was applied to two practical engineering optimization problems, and simulation results showed that the algorithm proposed in this paper has better practicality and robustness compared to other algorithms. © 2024 IEEE.

关键词： Swarm intelligence

来源：评论

学校读者我要写书评

暂无评论

Research on Infrared Pedestrian and Vehicle Detection Algorithm from the Perspective of UAV - Small target detection based on YOLOv8 24

Research on Infrared Pedestrian and Vehicle Detection Algori...

引用

3rd International Conference on Computer, Artificial Intelligence and Control Engineering, CAICE 2024

作者： Li, Jinfeng Ma, Long Zhu, Jing Yue, Yurong Zhao, Dan Shan, Wei Dong, Xuan School of Physics and Electronic Information Huaibei Normal University Anhui Provincial Key Laboratory of Intelligent Computing and Application 100 Dongshan Road Huaibei235000 China

ISBN: (纸本)9798400716942

In the infrared pedestrian and vehicle target detection task from the perspective of UAV, there are problems such as small target size and ambiguous scale features, which can easily lead to underdetection and false detection. An improved small target detection algorithm YOLOv8 was proposed. On the basis of YOLOv8, a small target detection layer is added as the fourth output layer, which can detect smaller targets. Experimental results indicate that in the HIT-UAV dataset experiment, the accuracy P, recall R and average accuracy (mAP) of the improved algorithm are 84.9%, 72.3%, 77.7% and 51.7%, respectively, which are improved by 5.7%, 6.4%, 7% and 6.1% compared with the original YOLOv8 network, respectively. The detection accuracy of small targets is improved, and the effectiveness verification of the network is improved. © 2024 ACM.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

A niching-based nondominated sorting for multimodal multiobjective optimization with local pareto fronts

引用

Applied Soft computing 2025年 179卷

作者： Qi Deng Juan Zou Shengxiang Yang Yuan Liu Fan Yu Tianbin Xie Jinhua Zheng Key Laboratory of Intelligent Computing and Information Processing Ministry of Education School of Computer Science and School of Cyberspace Science of Xiangtan University Xiangtan Hunan Province China Faculty of School of Computer Science and School of Cyberspace Science of Xiangtan University Xiangtan 411105 China School of Computer Science and Informatics De Montfort University Leicester LE1 9BH UK School of Traffic and Transport Engineering Central South University Changsha China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang 421002 China

In multimodal multiobjective optimization problems (MMOPs), there may be local Pareto optimal solutions (PSs). Finding both global PS and local PS simultaneously can provide additional options for decision makers. However, since individuals on the global Pareto front (PF) dominate individuals on the local PF, traditional multimodal multiobjective evolutionary algorithms (MMEAs) cannot effectively handle MMOPs with local PF (MMOPLs). In this paper, we improve our previous dynamic-niching-based Pareto domination (DNPD) approach to search for local Pareto optimal solutions. The new version is called niching-based non-dominated sorting (NNSL). There are two improvements to NNSL. First, the dynamic niche is changed to a fixed niche to increase the diversity of the population. Second, individuals with poor convergence in the non-dominated layer are deleted to ensure the convergence of the population. NNSL can be combined with Pareto dominance-based algorithms. We apply NNSL to solve MMOPLs (MMF_e and IDMP_e series). Experiments show that NNSL can help traditional MMEAs find global PF/PS and local PF/PS simultaneously.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Neural Tracking Control for Nonlinear Servo System with Unknown Time-Varying Parameters and Uncertainties 42

Adaptive Neural Tracking Control for Nonlinear Servo System ...

引用

42nd Chinese Control Conference, CCC 2023

作者： Zhang, Faxiang Gao, Guanbin Na, Jing Wu, Jiande Kunming University of Science and Technology Faculty of Mechanical and Electrical Engineering Yunnan International Joint Laboratory of Intelligent Control and Application of Advanced Equipment Kunming650500 China Yunnan University Yunnan Key Laboratory of Intelligent Systems and Computing Kunming650500 China

ISBN: (纸本)9789887581543

This paper solves the neural network (NN) tracking control problem for uncertain nonlinear servo system with time-varying parameters and uncertainties. To address the uncertain nonlinear function with unknown time-varying parameters (i.e., unknown nonlinear spatiotemporal function), the time-varying parameter extraction method is used to separate the time-varying parameters from uncertain nonlinear spatiotemporal function, which yields an unknown state-based boundary function. By the tools of NN and adaptive technology, an adaptive neural tracking controller is designed, which guarantees the uniformly ultimately bounded (UUB) performance of the resulting closed-loop system. The effectiveness of the designed method is verified by simulations. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Servomechanisms

来源：评论

学校读者我要写书评

暂无评论

application of Multi-Scale Linear Attention in Road Segmentation of High-Resolution Remote Sensing Images 5

Application of Multi-Scale Linear Attention in Road Segmenta...

引用

5th International Conference on Advances in Electrical Engineering and Computer applications, AEECA 2024

作者： Zhu, Shuangling Deng, Yunyun Gulinaz, Ailimujiang Ili Normal University School of Cyber Security and Information Engineering Yining China Ili Normal University Key Laboratory of Intelligent Computing Research and Application in Ili River Valley Yining China

ISBN: (纸本)9798350355253

With the rapid development of remote sensing technology, road segmentation of high-resolution remote sensing images remains a challenging task due to the complexity of road structures and the diversity of image resolutions. This study introduces a multi-scale linear attention mechanism and optimized context information extraction capabilities based on the EfficientViT model. By adopting finely tuned training and optimization strategies, including data augmentation and efficient hardware configuration, the model ensures rapid convergence and low loss in high-resolution image processing, significantly improving the efficiency and accuracy of road segmentation tasks in remote sensing images. This study demonstrates the advantages of EfficientViT in enhancing the accuracy and efficiency of road segmentation in remote sensing images. The innovative design and outstanding performance of EfficientViT provide valuable references and powerful tools for future remote sensing image analysis work. © 2024 IEEE.

关键词： Image segmentation

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：