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： Zhao, Dan Wang, Jiaxing Shan, Wei College of Physics and Electronic Information Huaibei Normal University China Anhui Provincial Key Laboratory of Intelligent Computing and Application Huaibei China

ISBN: (纸本)9798331528911

In view of the complex structure of YOLOv8n model and the large amount of parameters and calculations of the existing kiwifruit detection algorithm, it is difficult to deploy in the terminal. This paper proposes a lightweight kiwifruit detection algorithm model Faster-YOLOv8n based on YOLOv8n. That is, all C2f modules in the YOLOv8n model are merged with the FasterNet lightweight network structure to form a new C2f-Faster module to reduce the consumption of computing resources. The experimental results show that the average detection accuracy mAP of the Faster-YOLOv8n algorithm on the self-made kiwifruit dataset collected in this paper is 96.9 %. Compared with the YOLOv8n algorithm, the model size is reduced by 32 %,the calculation amount is reduced by 22.2 %, the parameter quantity is reduced by 29.6 %, and the detection speed is increased by 26.7 %.Therefore, the detection method proposed in this paper reduces the consumption of computing resources and provides a theoretical reference for the lightweight detection of kiwifruit. © 2024 IEEE.

关键词： Macroinvertebrates

来源：评论

学校读者我要写书评

暂无评论

A Method for Fast Feature Selection Utilizing Cross-Similarity within the Context of Fuzzy Relations

引用

Computers, Materials & Continua 2025年第4期83卷 1195-1218页

作者： Wenchang Yu Xiaoqin Ma Zheqing Zhang Qinli Zhang School of Big Data and Artificial Intelligence Chizhou UniversityChizhou247000China Anhui Education Big Data Intelligent Perception and Application Engineering Research Center Anhui Provincial Joint Construction Key Laboratory of Intelligent Education Equipment and TechnologyChizhou247000China

Feature selection methods rooted in rough sets confront two notable limitations:their high computa-tional complexity and sensitivity to noise,rendering them impractical for managing large-scale and noisy *** primary issue stems from these methods’undue reliance on all *** overcome these challenges,we introduce the concept of cross-similarity grounded in a robust fuzzy relation and design a rapid and robust feature selection ***,we construct a robust fuzzy relation by introducing a truncation ***,based on this fuzzy relation,we propose the concept of cross-similarity,which emphasizes the sample-to-sample similarity relations that uniquely determine feature importance,rather than considering all such relations *** studying the manifestations and properties of cross-similarity across different fuzzy granularities,we propose a forward greedy feature selection algorithm that leverages cross-similarity as the foundation for information *** algorithm significantly reduces the time complexity from O(m2n2)to O(mn2).Experimental findings reveal that the average runtime of five state-of-the-art comparison algorithms is roughly 3.7 times longer than our algorithm,while our algorithm achieves an average accuracy that surpasses those of the five comparison algorithms by approximately 3.52%.This underscores the effectiveness of our *** paper paves the way for applying feature selection algorithms grounded in fuzzy rough sets to large-scale gene datasets.

关键词： Fuzzy rough sets feature selection cross-similarity fuzzy relations

来源：评论

学校读者我要写书评

暂无评论

Research on intelligent traffic pedestrian detection algorithm based on improved YOLOv8 24

Research on intelligent traffic pedestrian detection algorit...

引用

2024 2nd International Conference on Internet of Things and Cloud computing Technology, IoTCCT 2024

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

ISBN: (纸本)9798400710148

Aiming at the problem that the pedestrian detection effect of illumination change, occlusion and different postures is not good in intelligent traffic scene, an optimized YOLOv8 is proposed to enhance its pedestrian detection ability. Based on YOLOv8, Coordinate Attention (CoordAtt) is introduced into the backbone network to enhance the sensitivity of the model to pedestrian location information and improve the detection accuracy. On the public test benchmark of Caltech Pedestrian Dataset, compared with the baseline algorithm, the proposed algorithm improves mAP0.5 by 1.3%, mAP0.5: 0.95 by 0.3%, and LAMR by 1.8%. Compared with the popular algorithm, mAP0.5 and mAP0.5: 0.95 are as high as 0.875 and 0.543 respectively, and LAMR is as low as 0.286, which is better than the popular algorithm. The algorithm has been tested to show that the accuracy of excellent performance detection has been significantly improved, and the phenomenon of missed detection has been greatly reduced, which can serve the intelligent transportation more effectively and reduce the potential safety hazards caused by missed detection. © 2024 Copyright held by the owner/author(s).

关键词： CoordAtt

来源：评论

学校读者我要写书评

暂无评论

Research on intelligent Traffic Pedestrian Detection Algorithm Based on Improved YOLOv8 5

Research on Intelligent Traffic Pedestrian Detection Algorit...

引用

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

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

Research on Kiwifruit Detection Algorithm Based on Faster-YOLOv8n

Research on Kiwifruit Detection Algorithm Based on Faster-YO...

引用

Artificial Intelligence and Computer Engineering (ICAICE), International Conference on

作者： Dan Zhao Jiaxing Wang Wei Shan College of Physics and Electronic Information Huaibei Normal University Anhui Provincial Key Laboratory of Intelligent Computing and Application Huaibei China

ISBN: (数字)9798331528911

ISBN: (纸本)9798331528928

关键词： YOLO Accuracy Image recognition Fuses Computational modeling Production Detection algorithms Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

A Privacy Preservation Method for Attributed Social Network Based on Negative Representation of Information

引用

Computer Modeling in Engineering & Sciences 2024年第7期140卷 1045-1075页

作者： Hao Jiang Yuerong Liao Dongdong Zhao Wenjian Luo Xingyi Zhang Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and TechnologyAnhui UniversityHefei230601China Chongqing Research Institute School of Computer Science and Artificial IntelligenceWuhan University of TechnologyWuhan430070China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies School of Computer Science and TechnologyHarbin Institute of TechnologyShenzhen518055China

Due to the presence of a large amount of personal sensitive information in social networks,privacy preservation issues in social networks have attracted the attention of many *** by the self-nonself discrimination paradigmin the biological immune system,the negative representation of information indicates features such as simplicity and efficiency,which is very suitable for preserving social network ***,we suggest a method to preserve the topology privacy and node attribute privacy of attribute social networks,called ***,a negative survey-based method is developed to disturb the relationship between nodes in the social network so that the topology structure can be kept ***,a negative database-based method is proposed to hide node attributes,so that the privacy of node attributes can be preserved while supporting the similarity estimation between different node attributes,which is crucial to the analysis of social *** evaluate the performance of the AttNetNRI,empirical studies have been conducted on various attribute social networks and compared with several state-of-the-art methods tailored to preserve the privacy of social *** experimental results show the superiority of the developed method in preserving the privacy of attribute social networks and demonstrate the effectiveness of the topology disturbing and attribute hiding *** experimental results show the superiority of the developed methods in preserving the privacy of attribute social networks and demonstrate the effectiveness of the topological interference and attribute-hiding components.

关键词： Attributed social network topology privacy node attribute privacy negative representation of information negative survey negative database

来源：评论

学校读者我要写书评

暂无评论

Representing Multiview Time-Series Graph Structures for Multivariate Long-Term Time-Series Forecasting

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 2651-2662页

作者： Wang, Zehao Fan, Jin Wu, Huifeng Sun, Danfeng Wu, Jia Hangzhou Dianzi University Department of Computer Science and Technology Hangzhou310018 China Zhejiang Provincial Key Laboratory of Industrial Internet in Discrete Industries Hangzhou310018 China Zhejiang Normal University Laboratory of Intelligent Education Technology and Application of Zhejiang Province Hangzhou310018 China Macquarie University School of Computing SydneyNSW2113 Australia

Multivariate long-term time-series forecasting tasks are very challenging tasks in many real-world application areas. Recently, researchers focus on designing robust and effective methods, and have made considerable progress. However, there are several issues with existing models that need to be overcome. First, the lack of a relationship structure between multivariate variables needs to be addressed. Second, most models only have a weak ability to capture local dynamic changes across the entire long-term time-series. Third, current models suffer from high computational complexity and unsatisfactory accuracy. To figure out the abovementioned issues, we propose an effective and efficient method called multiview time-series graph structure representation (MTGSR). MTGSR uses GCNs to construct topological relationships in the multivariate time-series from three different perspectives: time, dimension, and crossing segments. Variation trends in different dimensions are extracted through a difference operation to construct topological maps that reflect the correlations between different dimensions. To capture the dynamically changing characteristics of fluctuation correlations between adjacent local sequences, MTGSR constructs a cross graph by calculating correlation coefficients between adjacent local sequences. Extensive experiments show that MTGSR reduces errors by 17.41% over the state of the art. In addition, memory use is decreased by 66.52% and the running time is reduced by 78.09%. © 2020 IEEE.

关键词： Forecasting

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

Lightweight Small Target Detection Algorithm for UAV Infrare...

引用

Artificial Intelligence and Computer Engineering (ICAICE), International Conference on

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

ISBN: (数字)9798331528911

ISBN: (纸本)9798331528928

关键词： Training Accuracy Convolution Atmospheric modeling Object detection Benchmark testing Autonomous aerial vehicles Real-time systems Complexity theory Satellite images

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：