检索结果-内蒙古大学图书馆

Rockburst Intensity Grade Prediction Model Based on Batch Gradient Descent and Multi-Scale Residual Deep Neural Network

引用

Computer Systems Science & Engineering 2023年第11期47卷 1987-2006页

作者： Yu Zhang Mingkui Zhang Jitao Li Guangshu Chen School of Electrical and Information Engineering Beijing University of Civil Engineering and ArchitectureBeijing100044China Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing University of Civil Engineering and ArchitectureBeijing100044China State Key Laboratory for GeoMechanics and Deep Underground Engineering China University of Mining&TechnologyBeijing100083China

Rockburst is a phenomenon in which free surfaces are formed during excavation,which subsequently causes the sudden release of energy in the construction of mines and *** rockburst only peels off rock slices without ejection,while severe rockburst causes casualties and property *** frequency and degree of rockburst damage increases with the excavation ***,rockburst is the leading engineering geological hazard in the excavation process,and thus the prediction of its intensity grade is of great significance to the development of geotechnical ***,the prediction of rockburst intensity grade is one problem that needs to be solved *** comprehensively considering the occurrence mechanism of rockburst,this paper selects the stress index(σθ/σc),brittleness index(σ_(c)/σ_(t)),and rock elastic energy index(Wet)as the rockburst evaluation indexes through the Spearman coefficient *** overcomes the low accuracy problem of a single evaluation index prediction *** this,the BGD-MSR-DNN rockburst intensity grade prediction model based on batch gradient descent and a multi-scale residual deep neural network is *** batch gradient descent(BGD)module is used to replace the gradient descent algorithm,which effectively improves the efficiency of the network and reduces the model training ***,the multi-scale residual(MSR)module solves the problem of network degradation when there are too many hidden layers of the deep neural network(DNN),thus improving the model prediction *** experimental results reveal the BGDMSR-DNN model accuracy to reach 97.1%,outperforming other comparable ***,actual projects such as Qinling Tunnel and Daxiangling Tunnel,reached an accuracy of 100%.The model can be applied in mines and tunnel engineering to realize the accurate and rapid prediction of rockburst intensity grade.

关键词： Rockburst prediction rockburst intensity grade deep neural network batch gradient descent multi-scale residual

来源：评论

学校读者我要写书评

暂无评论

End-to-end global segmentation of PolSAR images with data augmentation

End-to-end global segmentation of PolSAR images with data au...

引用

IET International Radar Conference (IRC 2023)

作者： Zehua Wang Zezhong Wang Xiaolan Qiu Zhe Zhang Key Laboratory of Intelligent Aerospace Big Data Application Technology Suzhou People's Republic of China

ISBN: (数字)9781837240982

Deep neural networks have demonstrated impressive performance in PolSAR image classification. However, the lack of labelled data and the complexity of land boundaries hindering the mode's ability to achieve high-quality classification results. In order to address these inherent challenges, this paper introduces an augmentation method designed to maximize the utility of available labelled data. Furthermore, we present an end-to-end PolSAR image classification network, which we refer to as PolSARMixer. Our experimental results indicate that our proposed methodology significantly streamlines the classification process for PolSAR images when compared to traditional methods. Moreover, our proposed network exhibits superior performance in terms of classification accuracy and efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

key Clues Guided Video Character Social Relationship Recognition Enhanced by LLM

Key Clues Guided Video Character Social Relationship Recogni...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Dong, Wenlong Zhu, Qing Mao, Qirong School of Computer Science and Communication Engineering Jiangsu University China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications Provincial Key Laboratory of Computational Intelligence and New Technologies in Low-Altitude Digital Agriculture Zhenjiang China

ISBN: (纸本)9798350368741

Video Character Social Relationship Recognition (VCSRR) requires a comprehensive consideration about spatio-temporal and multi-modal clues in videos. Most existing methods mainly focus on integrating multi-modal clues and modeling interactions among characters. However, they fail to discover key clues in the complex video data or fully understand the clues related to social relationships. In this article, we propose a novel Large Language Model Enhanced key Clues Selection (LEKCS) framework to address the aforementioned issues. The core of LE-KCS is to mine multi-scale key clues from the perspectives of time, space and multi-modality, then transfer the knowledge about social relationships of the Large Language Model to VCSRR for understanding the selected clues. We evaluated LEKCS on the MovieGraphs dataset and the experimental results indicate that our proposed LE-KCS achieves state-of-the-art performance. © 2025 IEEE.

关键词： large language model Social relationship recognition video understanding

来源：评论

学校读者我要写书评

暂无评论

Look Around Before Locating: Considering Content and Structure Information for Visual Grounding 39

Look Around Before Locating: Considering Content and Structu...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zheng, Shiyi Zhao, Peizhi Zheng, Zhilong He, Peihang Cheng, Haonan Cai, Yi Huang, Qingbao School of Electrical Engineering Guangxi University Nanning China State Key Laboratory of Media Convergence and Communication Communication University of China Beijing China Key Laboratory of Big Data and Intelligent Robot of Ministry of Education SCUT Guangzhou China Guangxi Key Laboratory of Multimedia Communications and Network Technology Nanning China

ISBN: (纸本)157735897X

As a long-term challenge and fundamental requirement in vision and language tasks, visual grounding aims to localize a target referred by a natural language query. The regional annotations form a superficial correlation between the subject of expression and some common visual entities, which hinder models from comprehending the linguistic content and structure. However, current one-stage methods struggle to uniformly model the visual and linguistic structure due to the structural gap between continuous image patches and discrete text tokens. In this paper, we propose a semi-structured reasoning framework for visual grounding to gradually comprehend the linguistic content and structure. Specifically, we devise a cross-modal content alignment module to effectively align unlabeled contextual information into a stable semantic space corrected by token-level prior knowledge obtained with CLIP. A multi-branch modulated localization module is also established to obtain modulation grounding by linguistic structure. Through a soft split mechanism, our method can destructure the expression into a fixed semi-structure (i.e., subject and context) while ensuring the completeness of linguistic content. Our method is thus capable of building a semi-structured reasoning system to effectively comprehend the linguistic content and structure by content alignment and structure modulated grounding. Experimental results on five widely-used datasets validate the performance improvements of our proposed method. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Improving Classroom Quality by Analyzing Student Behaviors Through Computer Vision 4

Improving Classroom Quality by Analyzing Student Behaviors T...

引用

4th International Conference on Information Science and Education, ICISE-IE 2023

作者： Chen, Xiaopan Li, Boyuan Zhu, Xiaoke Zhang, Tao School of Computer and Information Engineering Henan University Kaifeng China Henan Engineering Research Center of Intelligent Technology Henan University Kaifeng China Henan University Henan Key Laboratory of Big Data Analysis and Processing Kaifeng China

ISBN: (纸本)9798350394610

This paper aims to enhance the efficiency of teaching and learning by leveraging computer vision technology for automated analysis of student behavior in the classroom. We propose a feature-enhanced method for recognizing student behavior, which integrates an Upsampling module (UPS) and a convolutional block layer (CBL) module into the YOLOv5 model. This innovative approach significantly improves the detection and feature extraction capabilities for student targets, effectively addressing challenges associated with small-sized targets and lowresolution images. Through algorithm optimization, it achieves a balance in sample diversity, enhancing the model's adaptability and generalizability in complex classroom environments. Building upon these technological advancements, we have developed a Classroom Student Posture Perception System (CSP2S). This system integrates functions for data collection, student behavior detection, and result visualization. The CSP2S operates in realtime by capturing and analyzing students' behavioral dynamics while providing teachers with immediate feedback. Experimental results demonstrate that this system substantially reduces teachers' workload in student assessment, offering significant potential to improve teaching effectiveness. These robust technical advancements provide strong support for future applications in real educational environments. © 2023 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Malicious URL Recognition Based on Multi-feature Fusion and Machine Learning 41

Malicious URL Recognition Based on Multi-feature Fusion and ...

引用

第41届中国控制会议

作者： Changyou Ma Aimin Wu Wenzhuo Ma Ke Chen Yun Liu Xiaoning Liang Data Recovery Key Laboratory of Sichuan Province Neijiang Normal University College of Big Data & Intelligent Engineering Chongqing College of International Business and Economics College of Artificial Intelligence Southwest University XLY Salvationdata Technology INC.

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

With the rapid development of the Internet,malicious web pages including phishing,spamming and malware are gradually increasing,resulting in endangering network *** address this challenging issue,a novel malicious URL recognition method based on multi-feature fusion and machine learning is *** specifically,three classic features(URL,HTML and JavaScript code features) and two presented effective features(HTTP request and Text features) are first extracted from URL ***,several machine learning models are adopted to train binary classification model with the selected discriminant ***,we use ten-fold cross-validation accuracy to evaluate the performance of different classification *** results verify that the selected features are conductive for malicious URLs detection and the random forest model trained using the presented hybrid feature set performs better than other classification techniques.

关键词： Malicious URL detection multi-feature fusion machine learning features

来源：评论

学校读者我要写书评

暂无评论

Oriented Object Detection in Aerial Images with Double Midpoint Vectors 9

Oriented Object Detection in Aerial Images with Double Midpo...

引用

9th International Conference on Computer and Communications, ICCC 2023

作者： Zhu, Xiaoke Hu, Qi Chen, Xiaopan Yuan, Caihong Li, Minghao Henan University School of Computer and Information Engineering Kaifeng China Henan University Henan Engineering Research Center of Intelligent Technology and Application China Henan University Henan Key Laboratory of Big Data Analysis and Processing Kaifeng China

ISBN: (纸本)9798350317251

In recent years, oriented object detection technology has made significant progress. Most oriented object detectors represent oriented bounding boxes by adding additional angle information to the horizontal bounding box representation, which leads to serious angle periodicity issues. To address these issues, this paper proposes double midpoint vectors (DMvectors) to represent oriented objects. For any oriented bounding box, we align the center point with the origin in the Cartesian coordinate system, and evenly distribute the midpoints of the box edges across the four quadrants. We use the midpoint of the first and second quadrants, as well as the width and height of the box, to represent the oriented bounding box. DMvectors solve the periodic problem of angles by implicitly including angle information in vectors. To demonstrate the effectiveness of our proposed method, we conducted extensive experiments on two common remote sensing datasets (DOTA and HRSC2016), and our method achieved competitive results. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Semisupervised Domain Adaptation for Wafer Map Defect Recognition via Cross-Alignment Network

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Wang, Yiru Wu, Peng Fang, Senlin Cao, Bozhan Wu, Xinyu Lu, Xu Yi, Zhengkun Chinese Acad Sci Guangdong Prov Key Lab Robot & Intelligent Syst Shenzhen Inst Adv Technol Shenzhen 518055 Peoples R China Univ Chinese Acad Sci Shenzhen Inst Adv Technol Beijing 100049 Peoples R China City Univ Macau Fac Data Sci Macau Peoples R China Xinyang Agr & Forestry Univ Sch Informat Engn Xinyang 464400 Peoples R China Shenzhen Inst Artificial Intelligence & Robot Soc SIAT Branch Shenzhen 518055 Peoples R China Guangdong Polytech Normal Univ Sch Comp Sci Guangzhou 510665 Peoples R China Guangdong Prov Key Lab Intellectual Property & Big Guangzhou 510665 Peoples R China

Wafer map defect recognition is a crucial step in semiconductor manufacturing and measurement. Semisupervised domain adaptation (SSDA) aims to leverage abundant labeled data in the source domain to achieve accurate classification in the target domain with limited labeled data, effectively addressing the challenge of insufficient labels in wafer map datasets. However, a significant obstacle lies in the label mismatch among wafer map datasets, a problem that most current SSDA methods struggle to mitigate. To solve this problem, this article proposes a new SSDA algorithm named cross-alignment network (CAN). CAN decouples the feature subspace and label space using different encoders and classifiers. To facilitate knowledge transfer between the source and target domains, we propose cross-alignment learning (CAL). CAL consists of sample-wise cross-alignment and class-wise cross-alignment, designed to ensure the consistency of encoders' outputs and facilitate the formation of robust clusters. We also integrate consistency regularization to enforce uniformity in outputs across different views of a sample. Additionally, we introduce a dynamic threshold strategy that tailors thresholds for each class based on its learning effect, thereby enhancing the model's efficiency and data utilization. Empirically, our method outperforms the current state-of-the-art SSDA methods on public wafer map datasets. Furthermore, detailed experiments are conducted to verify the effectiveness of each component in CAN.

关键词： Deep learning Production Semiconductor device modeling Training Knowledge transfer data models Classification algorithms Accuracy Training data Service robots Defect recognition domain alignment label mismatch semiconductor manufacturing semisupervised domain adaptation (SSDA) wafer map

来源：评论

学校读者我要写书评

暂无评论

Task Offloading Scheduling and Privacy Protection Optimization in Vehicular Edge Computing Based on Double Deep Q-Network 18th

Task Offloading Scheduling and Privacy Protection Optimizat...

引用

18th China Conference on Wireless Sensor Networks, CWSN 2024

作者： Weifeng, Lu Saijun, Yang Jia, Xu Lijie, Xu Lingyun, Jiang Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and Telecommunications Xianlin Street Jiangsu Nanjing210023 China

ISBN: (纸本)9789819621859

As the applications and services within vehicular networking systems become increasingly diverse, vehicles with limited computing resources face challenges in handling these computationally intensive and latency-sensitive tasks. In this paper, we propose an improved Task Offloading Scheduling Strategy based on a Double Deep Q-Network (TOSDDQN) for a dynamic multi-vehicle, multi-edge unit task offloading environment in vehicular networking. This strategy designs communication models and computational models aimed at minimizing the total system overhead in processing tasks. To further protect the privacy of vehicle users, a Distributed Training Algorithm based on Federated Learning (DTAFL) is proposed. Comparative experimental results indicate that, compared to three other task offloading schemes, our approach reduces the average system overhead in processing tasks by 11%–36%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

A Framework based on Deep Neural Network for Ranking-oriented Software Defect Prediction 23

A Framework based on Deep Neural Network for Ranking-oriente...

引用

23rd IEEE International Conference on Software Quality, Reliability, and Security, QRS 2023

作者： Dai, Jiapeng Yang, Xiaoxing Huang, Bingding Lu, Xiaofen Shenzhen Technology University College of Big Data and Internet Shenzhen518118 China Southern University of Science and Technology Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Shenzhen518055 China

ISBN: (纸本)9798350319583

Software systems are getting larger and more complex than ever before. In order to improve software reliability, software defect prediction is applied to assist developers in bug discovery. The ranking-oriented software defect prediction aims to rank software modules according to the predicted defect counts. However, existing ranking-oriented defect prediction models are constructed based on traditional hand-crafted features, which might overlook the rich syntactic information buried inside the source codes. In this paper, we propose a universal deep learning-based framework called United Deep Network for ranking-oriented software defect prediction. This framework utilizes deep neural networks to automatically generate features from source code with the syntactic and structural information preserved, and it can combine extracted features with traditional hand-crafted features in order to take advantage of both kinds of features to construct prediction models. Experimental results over 29 sets of data show the good performance of the proposed framework for building ranking-oriented defect prediction models. © 2023 IEEE.

关键词： Deep neural networks

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：