检索结果-内蒙古大学图书馆

40th IEEE International Conference on data Engineering, ICDE 2024

作者： Niu, Yudong Li, Yuchen Karras, Panagiotis Wang, Yanhao Li, Zhao School of Computing and Information Systems Singapore Management University Singapore University of Copenhagen Department of Computer Science Copenhagen Denmark School of Data Science and Engineering East China Normal University Shanghai China Zhejiang Lab Hangzhou China

ISBN: (纸本)9798350317152

What is the widest community in which a person exercises a strong impact? Although extensive attention has been devoted to searching communities containing given individuals, the problem of finding their unique communities of influence has barely been examined. In this paper, we study the novel problem of Characteristic cOmmunity Discovery (COD) in attributed graphs. Our goal is to identify the largest community, taking into account the query attribute, in which the query node has a significant impact. The key challenge of the COD problem is that it requires evaluating the influence of the query node over a large number of hierarchically structured communities. We first propose a novel compressed COD evaluation approach to accelerate the influence estimation by eliminating redundant computations for overlapping communities. Then, we further devise a local hierarchical reclustering method to alleviate the skewness of hierarchical communities generated by global clustering for a specific query attribute. Extensive experiments confirm the effectiveness and efficiency of our solutions to COD: they find characteristic communities better than existing community search methods by several quality measures and achieve up to 25 x speedups against well-crafted baselines. © 2024 IEEE.

关键词： attributed graph characteristic community community hierarchy influence

来源：评论

学校读者我要写书评

暂无评论

Hybrid Shunted Transformer embedding UNet for remote sensing image semantic segmentation

引用

Neural Computing and Applications 2024年第25期36卷 15705-15720页

作者： Zhou, Huacong Xiao, Xiangling Li, Huihui Liu, Xiaoyong Liang, Peng School of Computer Science Guangdong Polytechnic Normal University Guangdong Guangzhou510630 China Guangdong Provincial Key Laboratory of Intellectual Property and Big Data Guangdong Polytechnic Normal University Guangdong Guangzhou510665 China School of Data Science and Engineering Guangdong Polytechnic Normal University Guangdong Guangzhou510630 China Academy of Heyuan Guangdong Polytechnic Normal University Guangdong Heyuan517099 China The Cyberspace Institute of Advanced Technology Guangzhou University Guangdong Guangzhou510006 China

With the development of deep learning, Remote Sensing Image (RSI) semantic segmentation has produced significant advances. However, due to the sparse distribution of the objects and the high similarity between classes, the task of semantic segmentation in RSI is still extremely challenging. In this paper, we propose a novel semantic segmentation framework for RSI called HST-UNet that can overcome the shortcomings of the existing models and extract and recover the global and local features of RSI, which is a hybrid semantic segmentation model with Shunted Transformer as encoder and Multi-Scale Convolutional Attention Network (MSCAN) as decoder. Then, to better fuse the information from the Encoder and the Decoder and alleviate the ambiguity, we design a Learnable Weighted Fusion (LWF) module to effectively connect to the decoder features. Extensive experiments demonstrate that the proposed HST-UNet outperforms the state-of-the-art methods, achieving F1 score/MIoU accuracy of 71.44%/83.00% on the ISPRS Vaihingen dataset and 77.36%/87.09% on ISPRS Potsdam dataset. The code will be available at https://***/HC-Zhou/HST-UNet. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Federated Learning for Edge Heterogeneous Object Detection Algorithm 18th

Federated Learning for Edge Heterogeneous Object Detection ...

引用

18th International Conference on Wireless Artificial Intelligent Computing Systems and Applications, WASA 2024

作者： Hu, Yanxin Liu, Gang Cheng, Chao School of Computer Science and Engineering Changchun University of Technology Changchun130102 China Jilin Province Data Service Industry Public Technology Research Centre Changchun130102 China

ISBN: (纸本)9783031714665

The combination of federated learning and object detection techniques allows for the use of extensive datasets. This approach creates target detection models that are robust and adaptable. It also upholds strict privacy and security protocols. However, the computational resource variance among edge nodes poses significant constraints on the scalability of detection algorithms, thereby impinging on their accuracy and operational efficiency. This discrepancy compels clients, who might otherwise engage complex models, to resort to more simplified algorithms. To navigate this challenge, we introduce a federated learning framework enriched with a knowledge distillation strategy, specifically engineered for the object detection realm. This framework intelligently selects the largest model from the pool of client-contributed models and facilitates model upload and dissemination through a knowledge transfer mechanism orchestrated at the server side. Extensive experimental validations underscore the method’s proficiency in addressing the heterogeneity of detection algorithms within a varied environment, showcasing its viability for real-world application. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis for TikTok Review Using VADER Sentiment and SVM Model 8

Sentiment Analysis for TikTok Review Using VADER Sentiment a...

引用

8th International Conference on computer science and Computational Intelligence, ICCSCI 2023

作者： Isnan, Mahmud Elwirehardja, Gregorius Natanael Pardamean, Bens Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta11480 Indonesia

TikTok, a social networking site for uploading short videos, has become one of the most popular. Despite this, not all users are happy with the app;there are criticisms and suggestions, one of which is reviewed via the TikTok app on the Google Play Store. The reviews were extracted and then used for training a sentiment analysis model. The VADER sentiment method was utilized to offer the review's initial labeling (positive, neutral, and negative). The result revealed that most reviews were classified as positive, meaning that the data were imbalanced and challenging to handle in further analysis. Therefore, Random Under-sampling (RUS) and Random Over-sampling (ROS) methods were deployed to deal with that condition. The labeled reviews were subsequently pre-processed using tools such as case folding, noise removal, normalization, and stopwords before being used for training a Support Vector Machine (SVM) model for sentiment classification. The SVM trained without resampling produced the most favorable results, with an F1-score of 0.80. © 2023 The Authors. Published by Elsevier B.V.

关键词： Google Play Store Sentiment Analysis SVM TikTok VADER Sentiment

来源：评论

学校读者我要写书评

暂无评论

Bidirectional Authentication Protocol for RFID Systems Based on Mms

引用

International Journal of Network Security 2025年第1期27卷 72-80页

作者： He, Xiao-ping Liu, Dao-wei Wu, Yang School of Data and Computer Science Guangdong Peizheng College Guangzhou510800 China Engineering College Guangzhou College of Technology and Business Guangzhou510006 China College of Information and Communication National University of Defense Technology Wuhan430010 China

data exchange between electronic tags and the reader-writer in RFID systems is based on the wireless channel. Due to the inherent openness of the wireless channel, the transmitted data information is easy to be eavesdropped by other illegal users. In order to ensure data security, an ultra-lightweight mutual authentication protocol is proposed to solve this problem. In this paper, we independently design a new encryption algorithm, namely the product module synthesis operation. This algorithm is implemented based on bit operations, which can greatly reduce the total computation burden. Using the inherent Hamming weight and anti-Hamming weight information of encrypted parameters, different synthesis operations are carried out based on their product size relationship. Through the protocol analysis, it is shown that the proposed protocol has high security performance and meets the current computational requirements of low-cost RFID systems. © (2025), (Femto Technique Co., Ltd.). All rights reserved.

关键词： Radio frequency identification (RFID)

来源：评论

学校读者我要写书评

暂无评论

Next Generation Intelligent Traffic Signal Control: Empowering Electronics Consumers with Edge-AIoT Capabilities

引用

IEEE Transactions on Consumer Electronics 2025年第1期71卷 1926-1934页

作者： Chavhan, Suresh Doswada, Rohit Gupta, Deepak Gunjal, Saymam Rodrigues, Joel J.P.C. School of Data Sciences Indian Institute of Science Education and Research Kerala Thiruvananthapuram India C-DoT Karnataka Bangalore India Dept. of Computer Science and Engineering Maharaja Agrasen Institute of Technology Delhi India Centre for Research Impact and Outcome Institute of Engineering and Technology Chitkara University Punjab India Department of Computer Science and Engineering University of Visvesvaraya College of Engineering Karnataka Bangalore India Federal University of Piaui PI Teresina Brazil

Traffic congestion has become a major issue that is being faced by the majority of road users. The increasing vehicle usage, and the lack of space and funds to construct new transport infrastructure, further complicates the issue. In this scenario, it is important to come up with an intelligent and economical solution that improves the quality of road users' service. The problem with the traffic handling framework is signal timings are fixed which is not adaptive to the density of vehicles. To address this issue we propose an Edge-Augument Artificial Intelligence of Things (AIoT) road user cooperation for traffic management. The proposed system efficiently utilizes electronic devices to learn and adapt to changing traffic conditions in real-time. By optimizing the traffic signal timings based on the actual traffic conditions, adaptive systems reduce delay, improve traffic flow, reduce fuel consumption and pollution, and improve the electronics consumers' and road users' experiences. The proposed system has been tested with real-time experiments by integrating Electronic devices like cameras, smartphones, and AGX Xavier (edge device) with Cloud (ThingSpeak). The proposed system is verified by simulating the proposed system in the SUMO traffic simulator and its reliability is concluded by comparing the waiting time, depart delay, running, and halt time with the existing traditional method. © 2025 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

LLM2Vec Sentence Embeddings Analysis in Sentiment Classification

LLM2Vec Sentence Embeddings Analysis in Sentiment Classifica...

引用

2024 IEEE International Conference on data and Software Engineering, ICoDSE 2024

作者： Henry, Matthew Martianus Heryanto, Nur Adhianti Isnan, Mahmud Kurnianingrum, Dian Ratnapuri, Chyntia Ika Pardamean, Bens Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Entrepreneurship Department Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia

ISBN: (纸本)9798331506407

Sentiment analysis is crucial method in business intelligence to extract insights, which typically begin with sentiment classification. One of the latest frameworks for generating sentence embeddings for sentiment classification is LLM2Vec, which allows Transformer decoder-based models to generate sentence embeddings for text representation. Its capability is deemed language-agnostic, which, in this study, the framework is leveraged for Tokopedia tweet sentiment analysis to prove the claim. The base decoder models used in the LLM2Vec framework were Llama 3 8B, Llama 2 7B, Sheared Llama 1.3B, and Mistral 7B. Two BERT-based models, which are the Indonesian SBERT model and IndoBERT trained with the SimCSE approach, were employed as a comparison. The generated embeddings were classified using logistic regression, SVM, and MLP Classifier. Classifiers using embedding generated by LLM2Vec with Llama 3 8B and Mistral 7B achieves on-par performance with classifiers that utilize IndoBERT SimCSE embeddings, while classifiers using embeddings generated by LLM2Vec with Llama 2 7B and Sheared Llama 1.3B achieves much lower performance. Classifiers with Indonesian SBERT embeddings achieve the highest F1 score performance. Despite slightly lower performance, this study has proven the language-agnostic capability of LLM2Vec, especially with Llama 3 8B and Mistral 7B in colloquial Bahasa Indonesia sentiment analysis, since none of the base decoders were ever trained using the Bahasa Indonesia corpus. © 2024 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Faster Local Solvers for Graph Diffusion Equations

arXiv

引用

arXiv 2024年

作者： Bai, Jiahe Zhou, Baojian Yang, Deqing Xiao, Yanghua The School of Data Science Fudan University China Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China

Efficient computation of graph diffusion equations (GDEs), such as Personalized PageRank, Katz centrality, and the Heat kernel, is crucial for clustering, training neural networks, and many other graph-related problems. Standard iterative methods require accessing the whole graph per iteration, making them time-consuming for large-scale graphs. While existing local solvers approximate diffusion vectors through heuristic local updates, they often operate sequentially and are typically designed for specific diffusion types, limiting their applicability. Given that diffusion vectors are highly localizable, as measured by the participation ratio, this paper introduces a novel framework for approximately solving GDEs using a local diffusion process. This framework reveals the suboptimality of existing local solvers. Furthermore, our approach effectively localizes standard iterative solvers by designing simple and provably sublinear time algorithms. These new local solvers are highly parallelizable, making them well-suited for implementation on GPUs. We demonstrate the effectiveness of our framework in quickly obtaining approximate diffusion vectors, achieving up to a hundred-fold speed improvement, and its applicability to large-scale dynamic graphs. Our framework could also facilitate more efficient local message-passing mechanisms for GNNs. © 2024, CC BY-NC-SA.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Kernel triplet loss for image-text retrieval

Kernel triplet loss for image-text retrieval

引用

作者： Pan, Zhengxin Wu, Fangyu Zhang, Bailing School of Computer and Data Engineering NingboTech University Ningbo China School of Computer Science and Technology Zhejiang University Hangzhou China

Triplet loss is widely used as the objective function in image-text retrieval tasks. However, as all the triplets are treated equally, triplet loss has a bottleneck problem of slow convergence and other unsatisfactory performances. In this article, we propose solutions by appropriately weighting triplets according to the relative similarities among the training samples. Specifically, we present three weighting functions to assign an appropriate weight for the selected informative triplets to accelerate the convergence. We evaluate our approach on two widely used benchmark datasets: Flickr30k and MSCOCO, with results outperforming the previous methods, which demonstrates its superiority. © 2022 John Wiley & Sons, Ltd.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Multi-head Hashing with Orthogonal Decomposition for Cross-modal Retrieval 1

引用

30th International Conference on MultiMedia Modeling, MMM 2024

作者： Liu, Wei Li, Jun Wu, Zhijian Xu, Jianhua Yang, Bo School of Computer and Electronic Information Nanjing Normal University Nanjing210023 China School of Data Science and Engineering East China Normal University Shanghai200062 China School of Artificial Intelligence Nanjing University of Information Science and Technology Nanjing210044 China

ISBN: (数字)9783031533082

ISBN: (纸本)9783031533075

Recently, cross-modal hashing has become a promising line of research in cross-modal retrieval. It not only takes advantage of complementary multiple heterogeneous data modalities for improved retrieval accuracy, but also enjoys reduced memory footprint and fast query speed due to efficient binary feature embedding. With the boom of deep learning, convolutional neural network (CNN) has become the de facto method for advanced cross-model hashing algorithm. Recent research demonstrates that dominant role of CNN is challenged by increasingly effective Transformer architectures due to their advantages of long-range modeling by relaxing local inductive bias. However, the absence of inductive bias shatters the inherent geometric structure, which inevitably leads to compromised neighborhood correlation. To alleviate this problem, in this paper, we propose a novel cross-modal hashing method termed Multi-head Hashing with Orthogonal Decomposition (MHOD) for cross-modal retrieval. More specifically, with the multi-modal Transformers used as the backbones, MHOD leverages orthogonal decomposition for decoupling local cues and global features, and further captures their intrinsic correlations through our designed multi-head hash layer. In this way, the global and local representations are simultaneously embedded into the resulting binary code, leading to a comprehensive and robust representation. Extensive experiments on popular cross-modal retrieval benchmarking datasets demonstrate the proposed MHOD method achieves advantageous performance against the other state-of-the-art cross-modal hashing approaches. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Benchmarking

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：