检索结果-内蒙古大学图书馆

Cluster-CAM: Cluster-weighted visual interpretation of CNNs' decision in classification

NEURAL NETWORKS 2024年 178卷 106473页

作者： Feng, Zhenpeng Ji, Hongbing Dakovic, Milos Cui, Xiyang Zhu, Mingzhe Stankovic, Ljubisa Xidian Univ Sch Elect Engn Xian Peoples R China Xidian Univ Sch Elect Engn Kunshan Innovat Inst Xian Peoples R China Univ Montenegro Fac Elect Engn Podgorica Montenegro

Despite the tremendous success of convolutional neural networks (CNNs) in computer vision, the mechanism of CNNs still lacks clear interpretation. Currently, class activation mapping (CAM), a famous visualization technique to interpret CNN's decision, has drawn increasing attention. Gradient -based CAMs are efficient, while the performance is heavily affected by gradient vanishing and exploding. In contrast, gradient -free CAMs can avoid computing gradients to produce more understandable results. However, they are quite time-consuming because hundreds of forward interference per image are required. In this paper, we proposed Cluster -CAM, an effective and efficient gradient -free CNN interpretation algorithm. Cluster -CAM can significantly reduce the times of forward propagation by splitting the feature maps into clusters. Furthermore, we propose an artful strategy to forge a cognition -base map and cognition -scissors from clustered feature maps. The final salience heatmap will be produced by merging the above cognition maps. Qualitative results conspicuously show that Cluster -CAM can produce heatmaps where the highlighted regions match the human's cognition more precisely than existing CAMs. The quantitative evaluation further demonstrates the superiority of Cluster -CAM in both effectiveness and efficiency.

关键词： Explainable artificial intelligence Class activation mapping clustering algorithm Image classification

来源：评论

学校读者我要写书评

暂无评论

Detection of Rotated Objects Using the Improved YOLOv5 algorithm 3

Detection of Rotated Objects Using the Improved YOLOv5 Algor...

引用

3rd International Conference on Electronics and Communication;Network and Computer Technology (ECNCT)

作者： Tang Wudi Xuan, Huang Hu, Wei Dong, Li Anhui Univ Inst Phys Sci & Informat Technol Hefei 230601 Anhui Peoples R China Chinese Acad Sci CAS Hefei Inst Technol Innovat Engn Hefei Inst Phys Sci Hefei 230031 Anhui Peoples R China

ISBN: (数字)9781510652118

ISBN: (纸本)9781510652118;9781510652101

Common object detection algorithms have too many backgrounds, duplicated boxes, and a high miss ratio in detecting rotated objects, which limit their applications on the industrial site. To address these problems, this paper proposed an improved YOLOv5 to detect rotated objects. First, this paper used the K-means clustering algorithm to develop clustering analysis for trained datasets to confirm more proper anchor boxes to reduce the training time. Then this paper transferred the angle issue to a classification problem. This paper also learned angles in the original loss function combined with the circular smooth label (CSL) algorithm, thus avoiding the periodicity of angle regression. Last, this paper selected one from different detection results of an object to increase the accuracy of the detection results. The experiment showed that the proposed algorithm had a higher detection precision than other methods in the public dataset DOTA. When the proposed algorithm detected rotated objects in the dataset collected on the industrial site, its mAP reached 94.35%. This value was 8.20% higher than that of YOLOv5, satisfying the detection requirement on the industrial site.

关键词： YOLO YOLOv5 clustering algorithm object detection

来源：评论

学校读者我要写书评

暂无评论

Study on Optimization of Data-Driven Anomaly Detection

Study on Optimization of Data-Driven Anomaly Detection

引用

International Conference on Data Science and Its Applications (ICoDSA)

作者： Zhou, Yiqing Liao, Rui Chen, Yongjia Nanfang Coll Guangzhou Peoples R China

ISBN: (数字)9781665486651

ISBN: (纸本)9781665486651

In the paper, according to the original data and the value of the sensor at different moments, the box diagram method is used to process the data, and divides the normal value and outliers. The two types of outliers were distinguished based on the persistence of the outliers in the longitudinal time of the data and the linkage of the lateral sensors, and the clustering algorithm was used to reclassify the data. Then, persistence and linkage were calculated within each class, dividing the sum of persistence and linkage by the result of the maximum number of possible anomalies as the risk coefficient, and then defining a threshold to distinguish between risk-specific and non-risk anomalies. Later, a comprehensive evaluation model of anomaly degree was established through quantitative score, principal component analysis and 0,1 planning. Finally, this quantitative evaluation method is evaluated objectively.

关键词： box graph clustering algorithm principal component analysis method 0,1 planning data exception

来源：评论

学校读者我要写书评

暂无评论

Identifying and Resolving Conflicts in Requirements by Stakeholders: A clustering Approach 16

Identifying and Resolving Conflicts in Requirements by Stake...

引用

16th International Conference on Evaluation of Novel Approaches to Software Engineering (ENASE)

作者： Gambo, Ishaya Taveter, Kuldar Univ Tartu Inst Comp Sci Tartu Estonia Obafemi Awolowo Univ Dept Comp Sci & Engn Ife Nigeria

ISBN: (纸本)9789897585081

Conflicts in requirements are genuine analysis and design problems that require appropriate methods to reconcile different views, goals, and expectations by stakeholders. The research question addressed in this paper is how can conflicts in requirements elicited from different stakeholders be solved to avoid failure of the resulting software-intensive system? We propose a framework for conflict identification and resolution based on expert-based and clustering techniques for conflict resolution. The research method is a mixture of quantitative and qualitative methods by employing clustering and expert-based techniques for conflict resolution. The results demonstrate two essential features of conflict resolution in requirements engineering: (i) the ability to cater for a large volume of requirements in a multi-stakeholder setting;and (ii) the ability to effectively make precise decisions for minimizing conflicts between prioritized sets of requirements expressed by the stakeholders. The framework and the interactive system have been validated in analyzing requirements for a pharmacy information system. The contributions of the paper are an expert-based framework for resolving conflicts and an interactive system that empirically proves the adequacy of the framework. The main threat to validity is that the developed framework is yet to be validated in other problem domains.

关键词： Conflict Resolution Requirements Engineering clustering algorithm Delphi Method

来源：评论

学校读者我要写书评

暂无评论

Contrastive learning via swapped cluster assignments for bearing fault diagnosis

引用

MEASUREMENT SCIENCE AND TECHNOLOGY 2024年第1期35卷 015023-015023页

作者： Wang, Kai Liu, Chun Chen, Hongtian Xiu, Xianchao Shanghai Univ Inst Artificial Intelligence Sch Future Technol Shanghai 200444 Peoples R China Shanghai Univ Sch Mechatron Engn & Automat Shanghai 200444 Peoples R China Shanghai Univ Inst Artificial Intelligence Shanghai 200444 Peoples R China Shanghai Jiao Tong Univ Dept Automat Shanghai 200240 Peoples R China

In industrial scenarios, machinery and equipment operate in environments with many uncontrollable factors. These factors have a significant impact on vibration signals. For instance, differences in rotational speeds can make the collected data inconsistent. As a result, the tags collected from industrial environments are untrustworthy. It is impossible to know how many types of vibration signals are included in the dataset. In this paper, we propose a self-supervised pre-training method for bearing fault diagnosis called contrastive learning via swapped cluster assignments (CLSCA). Technically, CLSCA is based on momentum contrast (MoCo) and uses an unsupervised clustering algorithm to replace the classification of positive and negative samples in MoCo. By autonomously extracting representations from unlabelled datasets and then generating pseudo-labels using a clustering algorithm, CLSCA is able to learn in a self-supervised manner. When the value of the clustering center is in the appropriate range, the classification accuracy of CLSCA is improved by about 4% compared to MoCo.

关键词： intelligent fault diagnosis contrastive learning data augmentation clustering algorithm dataset availability

来源：评论

学校读者我要写书评

暂无评论

Digital twin-enabled hybrid deep evolutionary framework for smart building sustainable infrastructure management

引用

SUSTAINABLE ENERGY TECHNOLOGIES AND ASSESSMENTS 2024年 65卷

作者： Xu, Yunbo Zhang, Jiachao Qin, Heyu Zhou, Hao Yang, Zikai Henan Univ Engn Coll Civil Engn Zhengzhou 451191 Peoples R China

Combining services has become a major challenge in the use of service-based technology in smart building. The composition of services has numerous problems, specifically the quality of service (QoS), becoming increasingly difficult as dynamic environments change. The other concern is selecting services with a higher level of reliability based on trust value. A number of metaheuristic algorithms are employed to reduce the NP-hard complexity of service composition. Thus, the study adopts a hybrid gray wolf with cuckoo search optimization (HGWCSO) algorithm to achieve its objectives. The trust challenge is additionally addressed by using a trust-driven clustering algorithm using deep convolutional neural network (CNN) and k-means. The synergy between k-means and CNNs can result in improved clustering accuracy and better representation of underlying patterns in the data. According to the outcomes, the suggested algorithm is more effective in small-scale problems than the gray wolf optimization and particle swarm optimization algorithms. As the search space is clustered and reduced, response times are enhanced;it is also easier to select trusted services. The outcomes on the large-scale digital twin of smart building indicate that the suggested approach outperforms the average outcomes of similar studies in terms of computational time.

关键词： clustering algorithm Smart building service composition Convolutional neural network Digital twin Cloud computing

来源：评论

学校读者我要写书评

暂无评论

A novel patent technology characterization method based on heterogeneous network message passing algorithm and patent classification system

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年 256卷

作者： Chang, Zhi-Xing Guo, Wei Wang, Lei Fu, Zhong-Lin Ma, Jian Zhang, Guan-Wei Wang, Zi-Liang Tianjin Univ Key Lab Mech Theory & Equipment Design Minist Educ Tianjin Peoples R China Tianjin Renai Coll Tianjin Peoples R China

Patents are widely recognized as important data for generating innovation. Accurate and rational characterizing patent technology content is a prerequisite for applying innovation generation algorithms. Existing research widely employs classification codes that annotate the technology content of patents to represent patents. However, the oversight of technology similarity information within patent classification systems results in deficiencies in the accuracy and effectiveness of their representations. To fill this research gap, we analyze the hierarchical structure of patent classification systems to extract the technology similarity information embedded within them. Then, we propose a novel patent technology characterization method based on the heterogeneous network message passing algorithm, which integrates the technology similarity information in the classification code co-occurrence information and the patent classification system to obtain a more accurate patent characterization. Subsequently, several evaluation experiments were conducted to compare our method with typical existing methods. The results demonstrate that our method outperforms these methods in accuracy and effectiveness. Finally, we conducted a case study to validate the reliability and practicality of our approach. In summary, our method exhibited superior performance, thereby providing robust support for innovation generation methods based on patent characterization, with high application value and extension prospects.

关键词： Heterogeneous network Message-passing algorithm Technology topic clustering algorithm Patent characterization

来源：评论

学校读者我要写书评

暂无评论

Research on Fabric Defect Detection algorithm Based on Lightweight YOLOv7-Tiny

引用

JOURNAL OF NATURAL FIBERS 2024年第1期21卷

作者： Li, Tang Shunqi, Mei Yishan, Shi Shi, Zhou Quan, Zheng Jiang, Hongkai Qiao, Xu Zhiming, Zhang Wuhan Text Univ Hubei Digital Text Equipment Key Lab Wuhan Peoples R China Jianhu Lab Adv Text Technol Innovat Ctr Shaoxing Peoples R China Zhejiang Tianxiong Ind Technol Co Ltd Shenzhen Zhejiang Peoples R China Chinese Univ Hongkong Hongkong Peoples R China Wuhan Text Univ Coll Mech Engn & Automat 1 Sunshine Ave Wuhan 430200 Hubei Peoples R China

The current advanced neural network models are expanding in size and complexity to achieve improved detection accuracy. This study designs a lightweight fabric defect detection algorithm based on YOLOv7-tiny, called YOLOv7-tiny-MGCK. Its objectives are to improve the performance of fabric defect detection against complex backgrounds and to find a balance between the algorithm's lightweight nature and its accuracy. The algorithm utilizes the Mish activation function, known for its superior nonlinear performance capability and smoother curve, enabling the neural network to manage more complex challenges. The Ghost convolution module is also incorporated to reduce computation and model parameters. The lightweight upsampling technique CARAFE facilitates the flexible extraction of deep features, coupled with their integration with shallow features. In addition, an improved K-Means clustering algorithm, KMMP, is employed to select appropriate anchor box for fabric defects. The experimental results show: a reduction in the number of parameters by 45.5% and computational volume by 41.0%, along with increases in precision by 3.9%, recall by 7.0%, and mAP by 3.0%. These results indicated that the improved algorithm achieves a more effective balance between detection performance and the requirement for a lightweight solution.

关键词： Neural network fabric defect detection activation function Ghost module upsampling clustering algorithm (sic)(sic)(sic)(sic) (sic)(sic)(sic)(sic)(sic)(sic) (sic)(sic)(sic)(sic) (sic)(sic)(sic) (sic)(sic)(sic) (sic)(sic)(sic)(sic)

来源：评论

学校读者我要写书评

暂无评论

OPTIMIZATION APPROACH FOR WIND FARM CABLE LAYOUT BASED ON ITERATIVE SELF-ORGANIZING DATA ANALYSIS TECHNIQUE algorithm AND SWAP SEQUENCE BASED PARTICLE SWARM algorithmS

OPTIMIZATION APPROACH FOR WIND FARM CABLE LAYOUT BASED ON IT...

引用

67th ASME Turbomachinery Technical Conference and Exposition (Turbo Expo) on Road Mapping the Future of Propulsion and Power

作者： Yu Deqi Li Ming Shanghai Elect Grp Co Ltd PG EPC Shanghai Peoples R China Dalian Univ Technol Dalian Peoples R China

ISBN: (纸本)9780791886137

In the fast evolving and increasingly competitive wind energy market, to minimize initial capex and maximize production profits are essential when designing a wind farm. The electrical cable accounts for around 10% of the total capex, reasonable layout of cable connections might induce significant reduction of electrical and construction cost. In this paper, the Fuzzy C-means (FCM) clustering algorithm is adopted to determine the location of the substation(s) and the ISODATA (Iterative Self-Organizing Data Analysis Technique algorithm) is employed to divide the wind farm into finite sub-domains, effectively reducing the complexity of the NP-hard (Non-deterministic polynomial-time hard) problem of cable layout optimization. The optimal cable layout in each sub-domain is obtained through the swap sequence based particle swarm optimization (SSPSO) and practical electrical constraints, while the objective function is to minimize the total cable costs, including material cost and cable laying cost. Current study highlights both applicability of clustering algorithm and particle swarm optimization to the cable layout problem in wind farm.

关键词： wind farm clustering algorithm particle swarm optimization electrical cable layout optimization

来源：评论

学校读者我要写书评

暂无评论

REBench: Microbenchmarking Framework for Relation Extraction Systems 21st

REBench: Microbenchmarking Framework for Relation Extraction...

引用

21st International Semantic Web Conference (ISWC)

作者： Ali, Manzoor Saleem, Muhammad Ngomo, Axel-Cyrille Ngonga Univ Paderborn Dept Comp Sci DICE Grp Paderborn Germany Univ Leipzig AKSW Res Grp Leipzig Germany

ISBN: (纸本)9783031194320;9783031194337

In recent years, several relation extractions (RE) models have been developed to extract knowledge from natural language texts. Accordingly, several benchmark datasets have been proposed to evaluate these models. These RE datasets consisted of natural language sentences with a fixed number of relations from a particular domain. Albeit useful for general-purpose RE benchmarking, they do not allow the generation of customized microbenchmarks according to user-specified criteria for a specific use case. Microbenchmarks are key to testing the individual functionalities of a system and hence pinpoint component-based insights. This article proposes REBench, a framework for microbenchmarking RE systems, which can select customized relation samples from existing RE datasets from diverse domains. The framework is flexible enough to choose relation samples of different sizes and according to the user-defined criteria on essential features to be considered for RE benchmarking. We used various clustering algorithms to generate microbenchmarks. We evaluated the state-of-the-art RE systems using different RE benchmarking samples. The evaluation results show that specialized microbenchmarking is crucial for identifying the limitations of various RE models and their components.

关键词： Microbenchmark Relation extraction clustering algorithm

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：