检索结果-内蒙古大学图书馆

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Wang, Zhen Lu, Yifei Wu, Wenxin Lu, Yun Wang, Hongxiang Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing China

ISBN: (纸本)9798350351255

In the actual Internet of Things (IoT) environment, the proportion of abnormal behavior is much lower than that of normal behavior, and abnormal samples are often scarce, so it is a significant challenge to train efficient network intrusion detection systems using limited labeled samples. Meanwhile, intrusion detection systems based on online learning are prone to catastrophic forgetting, which greatly reduces the performance of online models. Previous research has not comprehensively addressed these two issues. Therefore, this paper proposes a few-shot and anti-forgetting network intrusion detection system based on online meta-learning. The system uses meta-learning as the basic algorithm to efficiently utilize data to train well-performing models with very few samples, thereby addressing the problem of insufficient samples;meanwhile, by saving previous models and invoking them when necessary to combat catastrophic forgetting. The experiments on the CIC-IDS2017 and CIC-IDS2018 datasets show that our proposed detection system can maintain good performance over the long term without forgetting. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

A Multi-Modal Rumor Detection Method Based on Topic Features and Multi-Level Fusion 24

A Multi-Modal Rumor Detection Method Based on Topic Features...

引用

2024 7th International Conference on computer Information science and Artificial Intelligence, CISAI 2024

作者： Yang, Xiaolu Ge, Jike Wang, Zining Yu, Wencheng Zhang, Yifan Xiang, Hao School of Computer Science and Engineering Chongqing University of Science and Technology Chongqing China

ISBN: (纸本)9798400707254

Rumors can have a negative impact on social life, and multimodal rumors, which combine text and images, are more misleading and spread more widely than text-only rumors. Therefore, detecting multimodal rumors is particularly important. Existing multimodal rumor detection methods primarily focus on contextual information in the text and image information, neglecting other feature information, and simply concatenate features during fusion, which fails to fully utilize the multimodal information. To address these issues, we propose a multimodal rumor detection method based on topic features and multi-level fusion. First, contrastive learning is used to optimize the sentence embeddings of the pre-trained BERT model, enabling the model to learn high-quality embeddings that capture the semantics of sentences. Then, the optimized BERT model is employed to extract contextual semantic features from the text, while the LDA topic model is used to extract topic semantic features from the text. At the same time, the pre-trained ViT model is used to extract features from images, overcoming the limitation of small training samples. Next, a multi-level fusion of various features is performed to fully capture the potential relationships between different features. Finally, the obtained multimodal fused features are fed into the rumor detection module for classification. Experimental results show that our model outperforms mainstream multimodal baseline models on both Twitter and Weibo datasets, enhancing the effectiveness of multimodal rumor detection. © 2024 Copyright held by the owner/author(s).

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Knowledge Graph Completion Enhanced by Muti-Level Attention Mechanisms 3

Multi-Modal Knowledge Graph Completion Enhanced by Muti-Leve...

引用

3rd International Conference on Cloud Computing, Big Data Application and Software engineering, CBASE 2024

作者： Zhang, Tingting Wang, Yongli Liu, Dongmei School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9798331506582

Multimodel knowledge graph completion (MKGC) aims to predict missing entities in MKGs. Differing from prior Single-model knowledge graph completion efforts, MKGC leverages rich textual descriptions, images, and other multi-model information associated with entities. Traditional MKGC methods often use simple concatennation, weighted fusion, or tensor-based approaches for multi-modal information fusion, but they fail to capture the in-tra-modality and inter-modality dynamics. Moreover, traditional models like TransE and TransH, based on translational operations, struggle with complex relationships such as 1-N, N-N. To address these issue, this paper proposes a multi-modal information fusion enhanced by multi-level attention mechanism and relation-specific graph attention network method for MKGC. Firstly, obtaining text, attribute, and image embeddings of entities by leveraging pre-trained modals such as BERT and Vision Transformer. Secondly, using low-rank tensors for multimodal fusion and introducing self-attention and cross-attention blocks to capture complementary information within and across modalities respectively. Finally, constructing a multi-source node graph and a relation graph attention network is employed to capture the structural information of the graph. The ConvE modal is used as a decoder, and the performance is evaluated through link prediction tasks on real datasets. Experimental results show that new method out-performs other baselines, such as TransE, R-GCN, RSME, KG-BERT. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

SMART DRIVING LICENSING SYSTEM AND AUTHORIZATION OF AUTONOMOUS VEHICLE INTEGRATING WIRELESS SENSOR NETWORKS AND IoT

引用

Telecommunications and Radio engineering (English translation of Elektrosvyaz and Radiotekhnika) 2024年第9期83卷 69-85页

作者： Santhakumar, D. Sudhan, M.B. Prasanna, R. Manikandan, S.P. Prathaban, Banu Priya Kanna, Rajesh R. Saravanan, G. Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Department of Computer Science and Engineering SRM Institute of Science and Technology Chennai Ramapuram India Department of Electronics and Communication Engineering SRM Institute of Science and Technology Kattankulathur Chennai India Department of Electronics and Communication Engineering Sree Sastha Institute of Engineering and Technology Chennai India Department of Networking and Communications School of Computing SRM Institute of Science and Technology Kattankulathur Chennai India Department of Electronics and Communication Engineering Sri Sairam Institute of Technology Tamil Nadu Chennai India

The advent of autonomous vehicles has revolutionized the automotive industry, offering promising advancements in safety, efficiency, and mobility. To integrate these autonomous vehicles into our society seamlessly, it is imperative to establish a robust licensing system that ensures the safe operation of automated vehicles on public roads. This article presents an effective smart Driving Licensing System (SDLS), a digital framework designed to regulate the existing licensing system and authorize licensing for autonomous vehicles. Through a comprehensive assessment process, the system assesses the drivers and the autonomous vehicle’s ability to navigate various road conditions, respond to dynamic environments, and prioritize safety for passengers and other road users. SDLS integrates high-level security through facial and fingerprint verification for identity verification to preserve licensing data. Hacking and unauthorized access to autonomous vehicles is prevented by robust cybersecurity protocols. The key benefits of SDLS include automated data collection, integration of wireless sensor networks (WSN) and Internet of Things (IoT), smart application processing, real-time license checks, cybersecurity measures, automated testing, and digital certification. The proposed system offers a comprehensive approach to safely integrating autonomous vehicles into our transportation ecosystem. The autonomous vehicles are integrated with antennas at rooftops or into bumpers, depending upon the vehicle design which can be connected with the SDLS for signal communication. Furthermore, the SDLS establishes a framework for continuous monitoring and updates, enabling ongoing assessments to keep pace with evolving technology and safety standards. © 2024 by Begell House, Inc.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Network with Dual Encoder and Cross Feature Fusion for Cement Pavement Crack Detection

引用

computer Modeling in engineering & sciences 2024年第7期140卷 255-273页

作者： Zhong Qu Guoqing Mu Bin Yuan School of Computer Science and Technology Chongqing University of Posts and TelecommunicationsChongqing400065China School of Software Engineering Chongqing University of Posts and TelecommunicationsChongqing400065China

Automatic crack detection of cement pavement chiefly benefits from the rapid development of deep learning,with convolutional neural networks(CNN)playing an important role in this ***,as the performance of crack detection in cement pavement improves,the depth and width of the network structure are significantly increased,which necessitates more computing power and storage *** limitation hampers the practical implementation of crack detection models on various platforms,particularly portable devices like small mobile *** solve these problems,we propose a dual-encoder-based network architecture that focuses on extracting more comprehensive fracture feature information and combines cross-fusion modules and coordinated attention mechanisms formore efficient feature ***,we use small channel convolution to construct shallow feature extractionmodule(SFEM)to extract low-level feature information of cracks in cement pavement images,in order to obtainmore information about cracks in the shallowfeatures of *** addition,we construct large kernel atrous convolution(LKAC)to enhance crack information,which incorporates coordination attention mechanism for non-crack information filtering,and large kernel atrous convolution with different cores,using different receptive fields to extract more detailed edge and context ***,the three-stage feature map outputs from the shallow feature extraction module is cross-fused with the two-stage feature map outputs from the large kernel atrous convolution module,and the shallow feature and detailed edge feature are fully fused to obtain the final crack prediction *** evaluate our method on three public crack datasets:DeepCrack,CFD,and *** results on theDeepCrack dataset demonstrate the effectiveness of our proposed method compared to state-of-the-art crack detection methods,which achieves Precision(P)87.2%,Recall(R)87.7%,and F-score(F1)87.4%.Thanks to our lightweight cr

关键词： Shallow feature extraction module large kernel atrous convolution dual encoder lightweight network crack detection

来源：评论

学校读者我要写书评

暂无评论

Towards Maximizing Semantic Coverage for Image-Text Retrieval

Towards Maximizing Semantic Coverage for Image-Text Retrieva...

引用

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

作者： Xu, Junhao Liu, Zheng Chen, Zhumin Shen, Fei School of Computer Science and Technology Shandong University China School of Computer Science and Technology Shandong University of Finance and Economics China School of Computer Science and Engineering Nanjing University of Science and Technology China

ISBN: (纸本)9798350368741

To establish semantic associations between images and texts, existing Image-Text Retrieval (ITR) methods primarily focus on fixed-scale fragments, which only identify explicit semantic categories. Consequently, semantic coverage is constrained, leading to the omission of certain semantic associations. To enlarge the semantic coverage, we propose the Semantic Coverage-Aware Network (SCA-Net). First, explicit semantic categories are identified by SCA-Net through analyzing the semantic membership of visual and textual fragments, thereby establishing more precise explicit semantic associations. Second, implicit semantic categories are identified by SCA-Net via adaptively aggregating visual and textual fragments across various scales using a co-occurrence-aware router, thereby significantly expanding the semantic coverage and establishing complete semantic associations. Third, image-text similarity is calculated using the attention mechanism over a broader range of semantic coverage. Extensive experiments demonstrate that SCA-Net significantly enhances ITR performance compared to state-of-the-art methods by maximizing semantic coverage. © 2025 IEEE.

关键词： Co-occurrence-aware router Image-text retrieval Semantic association Semantic category Semantic coverage

来源：评论

学校读者我要写书评

暂无评论

Document Classification and Data Extraction 3

Document Classification and Data Extraction

引用

3rd IEEE World Conference on Applied Intelligence and Computing, AIC 2024

作者： Khurana, Madhav Chaturvedi, Ravi Prakash Mishra, Annu Gupta, Devika Negi, Ishika Mishra, Ambuj Sharma, Hirdesh Jemtec Department of Computer Science & Engineering Greater Noida India Sharda School of Engineering and Technology Department of Computer Science & Applications Greater Noida India Sharda School of Engineering and Technology Department of Computer Science & Engineering Greater Noida India

ISBN: (纸本)9798350384598

T- Data classification and extraction are fundamental tasks in the field of computer vision and data analysis. This abstract presents an overview of these concepts along with the utilization of Python and OpenCV, a popular computer vision library, in building data extraction tools. Data classification involves organizing data into categories or classes based on certain characteristics or features. It enables efficient data management and analysis by grouping similar data together. In the context of computer vision, data classification often involves categorizing images or videos based on their content, such as identifying objects, scenes, or patterns within them. Data extraction, on the other hand, involves retrieving specific information or features from a dataset. This process is crucial for tasks like data mining, information retrieval, and automated document processing. In computer vision applications, data extraction often entails locating and extracting relevant information from images or videos, such as text, objects, or numerical data. © 2024 IEEE.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Graph Neural Network Focused on Structural Features for Link Prediction 5

Heterogeneous Graph Neural Network Focused on Structural Fea...

引用

5th International Conference on Artificial Intelligence and computer engineering, ICAICE 2024

作者： Bai, Longjie Wang, Yongli Liu, Dongmei School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9798331528911

Heterogeneous Graph Neural Networks (HGNNs) inherit some of the mechanisms of traditional graph neural networks, and are able to focus on graph structures that contain different types of nodes and edges, effectively embedding their structural and semantic features into node representations. Little work has investigated whether these capabilities play a critical utility in the problem of link prediction for heterogeneous graphs. In this paper, we target these issues by proposing Heterogeneous Graph Neural Network Focused on Structural Features (SFH4LP). Mean value aggregation is used to simplify the computation of neighbor aggregation, while centrality coding is added to complement node representation. In order to exploit the structural information of the graph more comprehensively, the model pays deep attention to the edges and spatial relationships in the metapaths. An improved self-attention mechanism based on Transformer is proposed to explore the information implied on the metapaths and achieve high-quality fusion of features from different metapaths to generate the final node representations. Experimental results on three heterogeneous graph datasets show that the model proposed in this paper outperforms existing baseline models in terms of the effectiveness of heterogeneous graph embedding, and exhibits good performance for the link prediction task. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Prolonging The Range of Low-power Visible Light Communication Systems with M-FSK 30

Prolonging The Range of Low-power Visible Light Communicatio...

引用

30th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2024

作者： Kang, Mengyu Wu, Jiyi Li, Jacheng Zhou, Yi Zhao, Zhiwei Zhou, Yaxin University of Electronic Science and Technology of China School of Computer Science and Engineering China

ISBN: (纸本)9798331515966

Visible light communication (VLC) has become a powerful and complementary technology to radio frequency (RF) communication thanks to its unrestricted bandwidth resources and high transmission rates. However, current VLC applications are limited to the short-ranged and interference-free scenarios because of the attenuation characteristics of light and the interference of ambient light. In order to extend VLC to various IoT applications, this paper tries to prolong the communication range of VLC systems based on M-frequency shift keying (MFSK), where M denotes the modulation index. Specifically, 1) we modulate the luminous intensity of the LEDs to form sine waves instead of square waves and tune the sine wave frequency to transmit data. Compared to light intensity modulation, it can effectively resist the ambient light interference. Meanwhile, 2) we propose a demodulation method based on gradient thresholding to increase its fault tolerance in decoding. In addition, 3) we built a real VLC platform and conducted comprehensive experiments to verify the communication distance and reliability of the low-power VLC systems (with 1W/3W LEDs). The experimental results show that the proposed work successfully prolongs the communication distance to 5.8 meters with 1 W LED and to 10 meters with 3 W LED, extending the VLC range by nearly 2. 5 x compared to existing work. © 2024 IEEE.

关键词： Light interference

来源：评论

学校读者我要写书评

暂无评论

Reasonable Gradients for Online Training Algorithms in Spiking Neural Networks 27

Reasonable Gradients for Online Training Algorithms in Spiki...

引用

27th European Conference on Artificial Intelligence, ECAI 2024

作者： Xue, Lang Liu, HanWen Wang, Jing Qu, Hong School of Computer Science and Engineering University of Electronic Science and Technology of China China

ISBN: (纸本)9781643685489

Spiking neural networks (SNNs) have the potential to simulate sparse and spatio-temporal dynamics observed in biological neurons, making them promising for achieving energy-efficient artificial general intelligence. While backpropagation through time (BPTT) ensures reliable precision for training SNNs, it is hampered by high computation and storage complexity and does not conform to the instantaneous learning mechanism in brains. On the contrary, online training algorithms, which are biologically interpretable, offer low latency and memory efficiency, and are well-suited for on-chip learning applications. However, recent research exhibit a deficiency in the scientific comprehension of online gradients, which leads to certain limitations. To address this issue, we conduct an in-depth analysis of the calculation deviation in chain derivations induced by weight update and find two pivotal factors that affect the accuracy of online gradients: completeness and timeliness. To further enhance the performance of online training leveraging these findings, we propose spatio-temporal online learning (STOL), which substantially ameliorates the accuracy of the online gradients and demonstrates superior computation and memory efficiency. Our experiments on CIFAR-10, CIFAR-100, ImageNet, CIFAR10-DVS, and DVS128-Gesture datasets demonstrate that our method achieves state-of-the-art performance across most of these tasks. Besides, it shows a great improvement compared with existing online training algorithms. © 2024 The Authors.

关键词： Contrastive Learning

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：