检索结果-内蒙古大学图书馆

3rd International Conference on Computer Vision and data Mining, ICCVDM 2022

作者： Shi, Xiangui Wang, Xiaole Chen, Tao Qian, Cong Liu, Yiming School of Big Data and Artificial Intelligence Anhui Xinhua University Hefei230088 China College of Computing and Information Technologies National University Manila Philippines

ISBN: (纸本)9781510661363

With the rapid development of advanced technologies such as artificial intelligence and Internet of Things, intelligent traffic management has been widely used. License plate recognition technology is particularly important in intelligent traffic management as the unique identification of vehicles, but due to the influence of natural environment, recognition angle, image clarity, size of license plate and other factors, the traditional license plate recognition technology is less robust and difficult to accurately identify the number plate number. In this paper, we describe a license plate recognition technique implemented by constructing Convolutional Neural Networks (CNN), which is able to recognize license plate numbers more accurately and has certain significance for further research on deep learning in the field of intelligent traffic management. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Image processing

来源：评论

学校读者我要写书评

暂无评论

Towards Stricter Black-box Integrity Verification of Deep Neural Network Models 24

Towards Stricter Black-box Integrity Verification of Deep Ne...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： He, Chaoxiang Bai, Xiaofan Ma, Xiaojing Zhu, Bin B. Hu, Pingyi Fu, Jiayun Jin, Hai Zhang, Dongmei Huazhong University of Science and Technology Hubei Wuhan China Shanghai Jiao Tong University Shanghai China Microsoft Corporation Beijing China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security School of Cyber Science and Engineering Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China

ISBN: (纸本)9798400706868

Cloud-based machine learning services offer significant advantages but also introduce the risk of tampering with cloud-deployed deep neural network (DNN) models. Black-box integrity verification (BIV) allows model owners and end-users to determine if a cloud-deployed DNN model has been tampered with by examining only the top-1 label responses. Fingerprinting generates fingerprint samples to query the model, achieving BIV with no impact on the model's accuracy. In this paper, we present BIVBench, the first comprehensive benchmark for BIV of DNN models. BIVBench covers 16 types of model modifications, providing extensive coverage of practical modification scenarios. Our analysis reveals that existing fingerprinting methods, which are typically focused on significant tampering, lack the sensitivity needed to effectively detect subtle yet common and potentially severe modifications. To address this limitation, we propose MiSentry (Model Integrity Sentry), a novel fingerprinting method that leverages meta-learning. MiSentry strategically incorporates a few subtly modified models into the meta-learning model zoo and maximizes the divergence of output predictions between the target model and the modified models in the model zoo to generate highly sensitive, generalizable, and effective fingerprint samples. Extensive evaluations using BIVBench demonstrate that MiSentry outperforms existing state-of-the-art methods overall and significantly surpasses them in detecting subtle modifications. The BIVBench and supplementary materials are available at: https://***/CGCL-codes/BIVBench. © 2024 ACM.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Remaining Useful Life Prediction of Degraded Systems Based on Multiple Performance Indicators Constructed by Multiple Features

引用

IEEE Sensors Journal 2025年第11期25卷 19613-19631页

作者： Wu, Bin Shi, Hui Zeng, Jianchao Zhang, Xiaohong Wang, Zhijian Wang, Zuolu Taiyuan University of Science and Technology School of Electronic Information Engineering Taiyuan030024 China North University of China institute for Big Data and Visual Computing Taiyuan030051 China University of Huddersfield Centre for Efficiency and Performance Engineering HuddersfieldHD1 3DH United Kingdom

The health status assessment of industrial equipment is critical to fault prediction and health management technologies. To fully reflect system degradation and accurately predict the remaining useful life (RUL) of a system, the construction of multiple performance indicators is important. Thus, a new state-space model and RUL prediction method is proposed herein based on multiple indicators, considering the three correlation relationships among features and degradation indicators. First, according to the extracted and selected feature signals, various relationships such as the correlations among multiple features, multiple features and indicators, and multiple indicators are analyzed. Then an intuitive multi-indicator state-space model is established considering the three correlations and the identified degradation patterns. On this basis, three failure modes of the system are defined according to the multi-indicator complex correlation conditions, and the corresponding probability density function of the system RUL is calculated. Finally, the PHM2012 Challenge and XJTU-SY datasets are used as examples for experimental verification. Compared with other prediction methods, the proposed method can intuitively reflect the correlation between features and indicators, to solve the problem caused by the hidden random correlation. © 2001-2012 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

TERM: Tree Ensemble Models for Interpretable Rule Mining 25th

TERM: Tree Ensemble Models for Interpretable Rule Mining

引用

25th International Conference on Web Information Systems Engineering, WISE 2024

作者： Zhu, Mengyu Li, Zhao Zhao, Jun Liu, Xiaopeng Liu, Yongning School of Information Engineering Ningxia University Yinchuan China College of Intelligence and Computing Tianjin University Tianjin China School of Economics and Management Ningxia University Yinchuan China Financial Big Data Laboratory Bank of Shizuishan Yinchuan China

ISBN: (纸本)9789819605781

Ensemble learning, particularly tree-based ensemble techniques, is acknowledged as the advanced approach to solving a wide range of challenging issues because of its exceptional performance in multiple machine learning applications. Nonetheless, even with its capacity for prediction, ensemble learning’s interpretability continues to be a problem, which restricts its use in situations where decision transparency is necessary. We suggest a novel model named TERM (Tree Ensemble Models for Interpretable Rule Mining) in order to get over this restriction and enhance the interpretability of Ensemble Tree Models. This method converts the complex binary classification decision-making process inside tree ensemble models into a series of rule lists that are globally equivalent to the decision-making process of the original model. This transformation aids in a more precise understanding and interpretation of the model’s predictive outcomes, enhancing its interpretability. Compared with existing rule extraction methods, TERM can simultaneously be applied to bagging methods and boosting methods. During the rule extraction phase, an adaptive set cover algorithm ADAPT-TA, is proposed to select rule subsets from the original rule set while avoiding local optima. Additionally, this method reduces the generalization error in the set of rules and runs faster on ensemble models involving multiple decision trees. Through comparisons with six other models, we evaluated the performance and applicability of TERM, demonstrating its outstanding accuracy and interpretability. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Contrastive Learning for Robust Android Malware Familial Classification

引用

IEEE Transactions on Dependable and Secure computing 2022年 1-14页

作者： Wu, Yueming Dou, Shihan Zou, Deqing Yang, Wei Qiang, Weizhong Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai China University of Texas at Dallas Dallas USA National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

Due to its open-source nature, Android operating system has been the main target of attackers to exploit. Malware creators always perform different code obfuscations on their apps to hide malicious activities. Features extracted from these obfuscated samples through program analysis contain many useless and disguised features, which leads to many false negatives. To address the issue, in this paper, we demonstrate that obfuscation-resilient malware family analysis can be achieved through contrastive learning. The key insight behind our analysis is that contrastive learning can be used to reduce the difference introduced by obfuscation while amplifying the difference between malware and other types of malware. Based on the proposed analysis, we design a system that can achieve robust and interpretable classification of Android malware. To achieve robust classification, we perform contrastive learning on malware samples to learn an encoder that can automatically extract robust features from malware samples. To achieve interpretable classification, we transform the function call graph of a sample into an image by centrality analysis. Then the corresponding heatmaps can be obtained by visualization techniques. These heatmaps can help users understand why the malware is classified as this family. We implement IFDroid and perform extensive evaluations on two datasets. Experimental results show that IFDroid is superior to state-of-the-art Android malware familial classification systems. Moreover, IFDroid is capable of maintaining a 98.4% F1 on classifying 69,421 obfuscated malware samples. IEEE

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Task Separation and Knowledge Sharing for Class Incremental Learning 5

Task Separation and Knowledge Sharing for Class Incremental ...

引用

5th International Conference on Intelligent computing and Human-Computer Interaction, ICHCI 2024

作者： Zhang, Jiali Qiao, Xiaoyan School of Computer Science and Technology Shandong Technology and Business University Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Immersion Technology and Evaluation Shandong Engineering Research Center Shandong Yantai China School of Mathematics and Information Science Shandong Technology and Business University Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Immersion Technology and Evaluation Shandong Engineering Research Center Shandong Yantai China

ISBN: (纸本)9798350368284

Methods based on dynamically expanding architectures can effectively mitigate catastrophic forgetting in class incremental learning (CIL), but they often overlook information sharing and integration between subnetworks, leading to performance degradation and increased parameter count and memory consumption as the network expands. To address these complex issues, we introduce a new method called Task Separation and Knowledge Sharing (TSKS), which transfers knowledge at both the logical and feature levels through Hybrid Knowledge Distillation (HKD). In logical distillation, we combine Global Knowledge Distillation (GKD) and Task Knowledge Distillation (TKD) to establish connections between tasks. To prevent the model from favoring new classes, we design an Attention- Based Feature Fusion (ABFF) mechanism to capture important features. Additionally, we introduce a Soft-Margin Auxiliary Loss (SMAL) to help the model learn new concepts. Extensive experiments show that TSKS outperforms existing models on CIFAR100 and ImageNet100, regardless of whether memory samples are used. Notably, TSKS demonstrates superior performance in memory-free settings, indicating a reduced reliance on rehearsal memory. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

DSAFF-Net:A Backbone Network Based on Mask R-CNN for Small Object Detection

引用

Computers, Materials & Continua 2023年第2期74卷 3405-3419页

作者： Jian Peng Yifang Zhao Dengyong Zhang Feng Li Arun Kumar Sangaiah Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science and TechnologyChangsha410114China School of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha410114China School of Computing Science and Engineering Vellore Institute of Technology(VIT)Vellore632014India

Recently,object detection based on convolutional neural networks(CNNs)has developed *** backbone networks for basic feature extraction are an important component of the whole detection ***,we present a new feature extraction strategy in this paper,which name is *** this strategy,we design:1)a sandwich attention feature fusion module(SAFF module).Its purpose is to enhance the semantic information of shallow features and resolution of deep features,which is beneficial to small object detection after feature fusion.2)to add a new stage called D-block to alleviate the disadvantages of decreasing spatial resolution when the pooling layer increases the receptive *** method proposed in the new stage replaces the original method of obtaining the P6 feature map and uses the result as the input of the regional proposal network(RPN).In the experimental phase,we use the new strategy to extract *** experiment takes the public dataset of Microsoft Common Objects in Context(MS COCO)object detection and the dataset of Corona Virus Disease 2019(COVID-19)image classification as the experimental object *** results show that the average recognition accuracy of COVID-19 in the classification dataset is improved to 98.163%,and small object detection in object detection tasks is improved by 4.0%.

关键词： Small object detection classification RPN MS COCO COVID-19

来源：评论

学校读者我要写书评

暂无评论

POINE2: Improving Poincaré Embeddings for Hierarchy-Aware Complex Query Reasoning over Knowledge Graphs 26

POINE2: Improving Poincaré Embeddings for Hierarchy-Aware C...

引用

26th European Conference on Artificial Intelligence, ECAI 2023

作者： Liu, Junnan Mao, Qianren Li, Jianxin Fu, Xingcheng Wang, Zheng School of Computer Science and Engineering Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing China Zhongguancun Laboratory Beijing China The School of Computing University of Leeds United Kingdom

ISBN: (纸本)9781643684369

Reasoning complex logical queries on incomplete and massive knowledge graphs (KGs) remains a significant challenge. The prevailing method for this problem is query embedding, which embeds KG units (i.e., entities and relations) and complex queries into low-dimensional space. Recent developments in the field show that embedding queries as geometric shapes is a viable means for modeling entity set and logical relationships between them. Despite being promising, current geometric-based methods face challenges in capturing hierarchical structures of complex queries, which leaves considerable room for improvement. This paper presents POINE2, a geometric-based query embedding framework based on hyperbolic geometry to handle complex queries on knowledge graphs. POINE2 maps entities and queries as geometric shapes on a Cartesian product space of Poincaré ball spaces. To capture the hierarchical structures of complex queries, we use the Poincaré radius to represent the different levels of the hierarchy, and we use the aperture of the shape to indicate semantic differences at the same level of the hierarchy. Additionally, POINE2 offers a flexible and expressive definition of logical operations. Experimental results show that POINE2 outperforms existing salient geometric-based embedding methods and significantly improves these methods on evaluation datasets. © 2023 The Authors.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Enhanced Sentiment Analysis of Medical Application using BERT and TextCNN 5

Enhanced Sentiment Analysis of Medical Application using BER...

引用

5th International Conference on Machine Learning, big data and Business Intelligence, MLBDBI 2023

作者： Shi, Wenyu Mariano, Vladimir Y. National University College of Computing and Information Technologies Manila Philippines Anhui Xinhua University School of Big Data and Artificial Intelligence Hefei Anhui230088 China

ISBN: (纸本)9798350359930

As Internet technology advances increasingly, the Internet penetration rate in every area of the world is gradually increasing, and there are more and more Internet users, and the e-commerce platform has also grown. In order to help doctors understand the patient's psychological state and supply better diagnosis and treatment., all major hospital and online medical platforms provide comment areas to display the comments made by patients with previous medical experience. By collecting and interpreting the text of published comments for sentiment analysis, users can get the real opinions of other users about doctors and hospitals, and doctors and hospitals can also see first-hand feedback from patients. However, with the accumulation of comment text, it is difficult for users to easily obtain effective information just because of massive text data, and the emotional tendency obtained by traditional analysis algorithms is relatively vague. Therefore, it is very important to quickly obtain the overall emotional orientation of the review text and accurately obtain the emotional orientation of all aspects in the review. A model integrating BERT and TextCNN is hereinto proposed to extract emotional features and analyze emotional information in the comments. The experiment results on comment dataset of medical application indicate that this approach performs well. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Research on pedestrian tracking detection based on YOLOv5 and improved DeepSORT 5

Research on pedestrian tracking detection based on YOLOv5 an...

引用

5th International Conference on Machine Learning, big data and Business Intelligence, MLBDBI 2023

作者： Wang, Yingyun Mariano, Vladimir Y. National University College of Computing and Information Technologies Manila Philippines Anhui Xinhua University School of Big Data and Artificial Intelligence Hefei Anhui230088 China

ISBN: (纸本)9798350359930

With the development and integration of big data and artificial intelligence, intelligent transportation, video surveillance, and other fields are receiving increasing attention. In the field of video surveillance, tracking targets is a challenging issue, especially in crowded environments where occlusion and false detection are prone to occur, and multi target detection frames are also prone to *** article uses the YOLOv5 algorithm as the foundation for pedestrian tracking and detection, proposes an improved metric called DeepSORT, and extracts the skeleton network part in a lightweight manner. The network is further pruned, greatly reducing the number of parameters without reducing too much performance. The experimental results demonstrate that the proposed method improves the target recognition and tracking capabilities of pedestrian tracking and detection. © 2023 IEEE.

关键词： Object detection

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：