检索结果-内蒙古大学图书馆

7th International Conference on Machine Learning and Natural Language Processing, MLNLP 2024

作者： Shi, Xin He, Sheng Wang, Ting Zhang, Chong Wang, Yang Zhang, Xiao School of Computer Science and Software Engineering Southwest Petroleum University Chengdu China School of Computer Science Chengdu University of Information Technology Chengdu China School of Information Engineering Mianyang Teachers College Mianyang China

ISBN: (纸本)9798350354973

In the process of realizing the Internet of Everything through the Internet of Things (IoT), the massive deployment of sensor nodes poses significant security challenges. This paper introduces a novel approach to anomaly detection. The proposed method focuses on generating secure replicas of sensor data, which are compared with real-time data to identify anomalies. This process ensures robust detection across multiple devices and terminals, a key challenge in the realization of the Internet of Everything. The model combines Long Short-Term Memory (LSTM) networks and Variational Autoencoders (VAE), leveraging their strengths in capturing temporal dependencies and learning latent feature representations from sensor data. To enhance detection accuracy in complex environments, an adaptive threshold algorithm is employed, dynamically adjusting thresholds based on real-time data's statistical properties. A crossattention mechanism is also integrated, allowing the model to effectively capture spatio-temporal relationships between sensors. Additionally, we employed a weighted smoothing algorithm to reduce noise while preserving data integrity, ensuring accurate anomaly detection even in noisy environments. Finally, we evaluated our method using the real-world dataset of the Belgian railway bridge KW51. The results indicate that our system can generate sensor data replicas with 99.02% accuracy and detect abnormal data with 99.8% precision. Based on these findings, we believe that this novel approach can effectively perform anomaly detection and provide robust support for IoT security across multiple terminals and devices. © 2024 IEEE.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Enhancing Communication Accessibility:UrSL-CNN Approach to Urdu Sign Language Translation for Hearing-Impaired Individuals

引用

computer Modeling in engineering & sciences 2024年第10期141卷 689-711页

作者： Khushal Das Fazeel Abid Jawad Rasheed Kamlish Tunc Asuroglu Shtwai Alsubai Safeeullah Soomro Department of Computer Engineering Modeling Electronics and Systems EngineeringUniversity of CalabriaRende Cosenza87036Italy Department of Information Systems University of Management and TechnologyLahore54770Pakistan Department of Computer Engineering Istanbul Sabahattin Zaim UniversityIstanbul34303Turkey Department of Software Engineering Istanbul Nisantasi UniversityIstanbul34398Turkey Department of Computer Science COMSATS University IslamabadLahore CampusLahore54700Pakistan Faculty of Medicine and Health Technology Tampere UniversityTampere33720Finland Department of Computer Science College of Computer Engineering and Sciences in Al-KharjPrince Sattam Bin Abdulaziz UniversityP.O.Box 151Al-Kharj11942Saudi Arabia Second Department of Computer Science College of Engineering and ComputingGeorge Mason UniversityFairfaxVA 4418USA

Deaf people or people facing hearing issues can communicate using sign language(SL),a visual *** works based on rich source language have been proposed;however,the work using poor resource language is still *** other SLs,the visuals of the Urdu Language are *** study presents a novel approach to translating Urdu sign language(UrSL)using the UrSL-CNN model,a convolutional neural network(CNN)architecture specifically designed for this *** existingworks that primarily focus on languageswith rich resources,this study addresses the challenge of translating a sign language with limited *** conducted experiments using two datasets containing 1500 and 78,000 images,employing a methodology comprising four modules:data collection,pre-processing,categorization,and *** enhance prediction accuracy,each sign image was transformed into a greyscale image and underwent noise *** analysis with machine learning baseline methods(support vectormachine,GaussianNaive Bayes,randomforest,and k-nearest neighbors’algorithm)on the UrSL alphabets dataset demonstrated the superiority of UrSL-CNN,achieving an accuracy of ***,our model exhibited superior performance in Precision,Recall,and F1-score *** work not only contributes to advancing sign language translation but also holds promise for improving communication accessibility for individuals with hearing impairments.

关键词： Convolutional neural networks Pakistan sign language visual language

来源：评论

学校读者我要写书评

暂无评论

HFGNN: Efficient Graph Neural Networks Using Hub-Fringe Structures 24

HFGNN: Efficient Graph Neural Networks Using Hub-Fringe Stru...

引用

24th IEEE International Conference on Data Mining, ICDM 2024

作者： Ip, Pak Lon Zhang, Shenghui Wei, Xuekai Chan, Tsz Nam Hou, Leong University of Macau SKL of Internet of Things for Smart City China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (纸本)9798331506681

Existing message passing-based and transformer-based graph neural networks (GNNs) cannot satisfy requirements for learning representative graph embeddings due to restricted receptive fields, redundant message passing, and reliance on fixed aggregations. These methods face scalability and expressivity limitations from intractable exponential growth or quadratic complexity, restricting interaction ranges and information coverage across large graphs. Motivated by the analysis of long-range graph structures, we introduce a novel Graph Neural Network called Hub-Fringe Graph Neural Network (HFGNN). Our Hub-Fringe structure, drawing inspiration from the graph indexing technique known as Hub Labeling, offers a straightforward and effective approach for learning scalable graph representations while ensuring comprehensive coverage of information. HFGNN leverages this structure to enable selective propagation of relevant embeddings through a carefully designed message function. Theoretical analysis is presented to show the expressivity and scalability of the proposed method. Empirically, HFGNN exceeds standard GNNs on tasks including classification and regression, especially for large, long-range graphs where scalability and coverage matter. Ablation studies further confirm the benefits of our hub-fringe based graph neural network, including improved expressivity and scalability. The source codes is available at https://***/nick12340/HFGNN. © 2024 IEEE.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based conditional privacy-preserving authentication scheme for vehicular ad hoc networks

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第5期14卷 6273-6286页

作者： Gong, Cheng Xiong, Ling He, Xingyu Niu, Xianhua College of Computer and Software Engineering Xihua University Sichuan Chengdu610099 China National Key Laboratory of Science and Technology Communications University of Electronic Science and Technology of China Sichuan Chengdu611731 China

Security and privacy are two challenging issues in Vehicular Ad-hoc Networks (VANETs), which have attracted widespread concern from industry and academia. However, the existing security schemes for VANETs environment have various problems, such as the unlinkability and the cross region communication,etc. To overcome these weaknesses, this paper designs a blockchain-based conditional privacy-preserving authentication scheme (BCPAS) for VANETs. The proposed scheme has the following two advantages: (1) Pseudonym ID is employed in authentication phase to ensure the real identity of vehicle is unlinkable. (2) Blockchain technology is adopted to make cross-region authentication more efficient. Compared with the most recent scheme, the computational efficiency of our scheme has improved 50% with 3 service management nodes, and 87% with 15 service management nodes in the Authentication and Member Secrets Generate Phase. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

LESS: Label-Efficient and Single-Stage Referring 3D Segmentation 38

LESS: Label-Efficient and Single-Stage Referring 3D Segmenta...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Liu, Xuexun Xu, Xiaoxu Li, Jinlong Zhang, Qiudan Wang, Xu Sebe, Nicu Ma, Lin College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China University of Trento Italy Meituan Inc. China

Referring 3D Segmentation is a visual-language task that segments all points of the specified object from a 3D point cloud described by a sentence of query. Previous works perform a two-stage paradigm, first conducting language-agnostic instance segmentation then matching with given text query. However, the semantic concepts from text query and visual cues are separately interacted during the training, and both instance and semantic labels for each object are required, which is time consuming and human-labor intensive. To mitigate these issues, we propose a novel Referring 3D Segmentation pipeline, Label-Efficient and Single-Stage, dubbed LESS, which is only under the supervision of efficient binary mask. Specifically, we design a Point-Word Cross-Modal Alignment module for aligning the fine-grained features of points and textual embedding. Query Mask Predictor module and Query-Sentence Alignment module are introduced for coarse-grained alignment between masks and query. Furthermore, we propose an area regularization loss, which coarsely reduces irrelevant background predictions on a large scale. Besides, a point-to-point contrastive loss is proposed concentrating on distinguishing points with subtly similar features. Through extensive experiments, we achieve state-of-the-art performance on ScanRefer dataset by surpassing the previous methods about 3.7% mIoU using only binary labels. Code is available at https://***/mellody11/LESS. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ensuring IoT Controller Reliability with Colored Generalized Stochastic Petri Net 28

Ensuring IoT Controller Reliability with Colored Generalized...

引用

28th International computer science and engineering Conference, ICSEC 2024

作者： Samngamnoi, Kruntarat Pomsiri, Sutinun Kamput, Apipath Dechsupa, Chanon College of Computing Khon Kaen University Intelligent Software Engineering Research Group Department of Computer Science Khon Kaen40002 Thailand

ISBN: (纸本)9798350366860

In IoT systems managing multiple devices simultaneously, errors in system controllers often undermine intended operations. Formal verification offers a method to assess system reliability. Colored Generalized Stochastic Petri Net (CGSPN), a formal language, facilitate correctness checks of such systems. This study proposes a verification approach by translating a C++-based system controller of a self-service machine into a CGSPN models and validating it using the Snoopy Tool. Mapping techniques employed to transform components in the controller into CGSPN models are provided. Results demonstrate the method's efficacy in verifying system safety properties, simulating system events, and enabling quantitative verification. © 2024 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

EOSAD: An Event-Oriented Physiological and Behavioral Social Anxiety Annotation Dataset in Virtual Reality

EOSAD: An Event-Oriented Physiological and Behavioral Social...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Hou, Qinyao Ding, Ding Yang, Jiaju Tu, Jiahang School of Computer Science and Engineering Southeast University Nanjing China Chien-Shiung Wu College Southeast University Nanjing China College of Software Engineering Southeast University Nanjing China

ISBN: (纸本)9781665410205

Social phobia is a prevalent mental health con-dition characterized by overwhelming fear on apprehension of social situations, often leading individuals to avoid such encounters. It is a very common mental disorder among adolescents and can have a significant bad effect on their social skills and well-beings if not intervened early. Existing methods to assess social anxiety level rely on self-report scales or clinical diagnosis, both of which may face challenges like subjective judgments and patient resistance. To address this, we applied Virtual Reality technology (VR) and introduced event-oriented social anxiety dataset (EOSAD) to serve for fine-grained social anxiety level detected model. A case study (N = 44) was conducted where participants wore a Vive Pro Eye HMD to experience two types of scenes and labeled their social anxiety level accordingly. During the experiment, relevant signals and social anxiety scores were collected, including (1) behavioral signals (head and eye movements) (2) physiological signals (heart rate (HR), electrodermal activity (EDA), etc.) (3) discrete social anxiety self-reported labels (4) evaluation questionnaires. We first verified the labels, and furthermore ran baseline classification experiments, where GRU model showed best accuracy: 92.84 %for binary classification. It was also found that either behavioral data or physiological signals alone could achieve satisfactory accuracies (85.64% and 91.02%) while the combined achieved slightly higher(92.84 %) © 2024 IEEE.

关键词： Eye movements

来源：评论

学校读者我要写书评

暂无评论

High Precision Method of Federated Learning Based on Cosine Similarity and Differential Privacy 15

High Precision Method of Federated Learning Based on Cosine ...

引用

2022 IEEE Congress on Cybermatics: 15th IEEE International Conferences on Internet of Things, iThings 2022, 18th IEEE International Conferences on Green Computing and Communications, GreenCom 2022, 2022 IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2022 and 8th IEEE International Conference on Smart Data, SmartData 2022

作者： Wang, Jia Li, Yazheng Ye, Ronghang Li, Jianqiang Shenzhen University College of Computer Science and Software Engineering Shenzhen China Zhengzhou University of Industrial Technology College of Computer Science and Software Engineering Zhengzhou China

ISBN: (数字)9781665454179

ISBN: (纸本)9781665454179

Federated learning has emerged as an efficient way to exploit distributed data in recent years. It allows multiple client nodes to collaboratively train an optimized machine learning model without revealing the participants' data. However, there are some shortcomings in the existing federated learning algorithms: the existence of poor quality nodes leads to undesirable effects on the overall gradient descent direction of the model. And the typical iterative training and noising way also make the privacy loss of the model reaches the privacy budget quickly. Hence, the model training may stop before convergence. In this paper, we propose a federated learning gradient adaptive aggregation method based on cosine similarity and a central node privacy protection method based on random differential privacy to solve the above-mentioned problems respectively. The proposed scheme was implemented on two public general datasets (MNIST and SVHN) and a medical dataset (UCI diabetes). Experimental results show that the federated learning adaptive method based on cosine similarity could effectively eliminate the negative influence of nodes with poor data quality on the overall model and maintain stable performance. The central node privacy protection method based on random differential privacy could also improve the performance of the training model under the same privacy budget and privacy loss threshold. © 2022 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Ensemble Graph and Device Clustering Method based on Attention Mechanism for Decomposing Monolithic to Microservices 22

Ensemble Graph and Device Clustering Method based on Attenti...

引用

22nd IEEE International Symposium on Parallel and Distributed Processing with Applications, ISPA 2024

作者： Deng, Qingyong Li, Qiuming Zuo, Qinghua Tian, Shujuan Long, Saiqin Guangxi Normal University School of Computer Science and Engineering The School of Software Guilin China Xiangtan University School of Computer Science Xiangtan China Jinan University College of Information Science and Technology Guangzhou China

ISBN: (纸本)9798331509712

Existing methods for decomposing monolithic applications into microservices in cloud environments primarily rely on the call relationships within itself. However, these methods are difficult to apply directly in resource-constrained and distributed edge network scenarios without considering the heterogeneity of the device. Therefore, this paper proposes a clustering method that ensembles graph structures and device features based on attention mechanism, which utilizes attention encoders to learn node embeddings and employs a spectral clustering algorithm to obtain decomposition results, optimizing the affinity and matching degree between microservices and devices. Experimental results demonstrate that the proposed method exhibits excellent performance in terms of functional independence, modularity, and adaptability of microservices. © 2024 IEEE.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Secure and Fast Remote Application-Based Authentication Dragonfly Using an LED Algorithm in Smart Buildings 6

Secure and Fast Remote Application-Based Authentication Drag...

引用

6th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2024

作者： Radhi, Batool Mohammed Hussain, Mohammed Abdulridha Abduljabbar, Zaid Ameen Nyangaresi, Vincent Omollo College of Education for Pure Sciences University of Basrah Department of Computer Science Basrah61004 Iraq Jaramogi Oginga Odinga University of Science and Technology Department of Computer Science and Software Engineering Bondo40601 Kenya

ISBN: (纸本)9798350344349

The proliferation of the internet of things (IoT) has led to the emergence of a wide range of intelligent devices, creating a broad domain with significant security concerns. These concerns impose a high level of security;unfortunately, IoT devices usually have limited resources in terms of little memory, low computing power, and a short battery life. Therefore, IoT application developers must use lightweight cryptographic tools to achieve a trade-off between performance and security. The storage and high computation capacity of cloud computing is often exploited to manage the vast amount of data produced by such gadgets. Some methods still suffer from attacks, and others cannot achieve low complexity. We propose a secure and low-complexity system for smart buildings in transferring data between the local server, the cloud, and users authorized by the owner. The LED encryption algorithm, which is lightweight and requires limited resources and less energy, was used to create a mobile application system characterized by confidentiality, authentication, and privacy. For further security, the owner's biometrics were used and derived as the key to decrypt data from the cloud. We have leveraged Dragonfly authentication technology to transfer data from the local server to the users. The owner can add authorized persons in the cloud database and local server to enjoy using the application. Moreover, we successfully balance security complexity and performance in our work. As a result, we achieve good results with a computation cost of 0.281 s and a communication cost of 1472 bit. © 2024 IEEE.

关键词： Authentication

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：