检索结果-内蒙古大学图书馆

11th International Conference on Learning Representations, ICLR 2023

作者： Dong, Hanze Wang, Xi Lin, Yong Zhang, Tong Department of Mathematics HKUST Hong Kong Department of Computer Science and Engineering HKUST Hong Kong College of Information and Computer Science UMass Amherst United States

Particle-based variational inference (VI) minimizes the KL divergence between model samples and the target posterior with gradient flow estimates. With the popularity of Stein variational gradient descent (SVGD), the focus of particle-based VI algorithms has been on the properties of functions in Reproducing Kernel Hilbert Space (RKHS) to approximate the gradient flow. However, the requirement of RKHS restricts the function class and algorithmic flexibility. This paper offers a general solution to this problem by introducing a functional regularization term that encompasses the RKHS norm as a special case. This allows us to propose a new particle-based VI algorithm called preconditioned functional gradient flow (PFG). Compared to SVGD, PFG has several advantages. It has a larger function class, improved scalability in large particle-size scenarios, better adaptation to ill-conditioned distributions, and provable continuous-time convergence in KL divergence. Additionally, non-linear function classes such as neural networks can be incorporated to estimate the gradient flow. Our theory and experiments demonstrate the effectiveness of the proposed framework. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

Analyzing COVID-19 Discourse on Twitter: Text Clustering and Classification Models for Public Health Surveillance

引用

computer Systems science & Engineering 2024年第3期48卷 665-689页

作者： Pakorn Santakij Samai Srisuay Pongporn Punpeng Department of Information Technology Lampang Rajabhat UniversityLampang52100Thailand Department of Computer Science Lampang Rajabhat UniversityLampang52100Thailand

Social media has revolutionized the dissemination of real-life information,serving as a robust platform for sharing life ***,characterized by its brevity and continuous flow of posts,has emerged as a crucial source for public health surveillance,offering valuable insights into public reactions during the COVID-19 *** study aims to leverage a range of machine learning techniques to extract pivotal themes and facilitate text classification on a dataset of COVID-19 outbreak-related *** topic modeling approaches have been employed to extract pertinent themes and subsequently form a dataset for training text classification *** assessment of coherence metrics revealed that the Gibbs Sampling Dirichlet Mixture Model(GSDMM),which utilizes trigram and bag-of-words(BOW)feature extraction,outperformed Non-negative Matrix Factorization(NMF),Latent Dirichlet Allocation(LDA),and a hybrid strategy involving Bidirectional Encoder Representations from Transformers(BERT)combined with LDA and K-means to pinpoint significant themes within the *** the models assessed for text clustering,the utilization of LDA,either as a clustering model or for feature extraction combined with BERT for K-means,resulted in higher coherence scores,consistent with human ratings,signifying their *** particular,LDA,notably in conjunction with trigram representation and BOW,demonstrated superior *** underscores the suitability of LDA for conducting topic modeling,given its proficiency in capturing intricate textual *** the context of text classification,models such as Linear Support Vector Classification(LSVC),Long Short-Term Memory(LSTM),Bidirectional Long Short-Term Memory(BiLSTM),Convolutional Neural Network with BiLSTM(CNN-BiLSTM),and BERT have shown outstanding performance,achieving accuracy and weighted F1-Score scores exceeding 80%.These results significantly surpassed other models,such as Multinomial Naive Bayes(MNB),Lin

关键词： Topic modeling text classification twitter feature extraction social media

来源：评论

学校读者我要写书评

暂无评论

Authenblue: A New Authentication Protocol for the Industrial Internet of Things

引用

computers, Materials & Continua 2021年第4期67卷 1103-1119页

作者： Rachid Zagrouba Asayel AlAbdullatif Kholood AlAjaji Norah Al-Serhani Fahd Alhaidari Abdullah Almuhaideb Atta-ur-Rahman Department of Computer Information System College of Computer Science and Information Technology(CCSIT)Imam Abdulrahman Bin Faisal UniversityDammam31441Saudi Arabia Department of Computer Science College of Computer Science and Information Technology(CCSIT)Imam Abdulrahman Bin Faisal UniversityDammam31441Saudi Arabia

The Internet of Things(IoT)is where almost anything can be controlled and managed remotely by means of *** the IoT evolution led to quality of life enhancement,many of its devices are *** lack of robust key management systems,efficient identity authentication,low fault tolerance,and many other issues lead to IoT devices being easily targeted by *** this paper we propose a new authentication protocol called Authenblue that improve the authentication process of IoT devices and Coordinators of Personal Area Network(CPANs)in an Industrial IoT(IIoT)*** study proposed Authenblue protocol as a new Blockchainbased authentication *** enhance the authentication process and make it more secure,Authenblue modified the way of generating IIoT identifiers and the shared secret keys used by the IIoT devices to raise the efficiency of the authentication *** enhance the authentication protocol that other models rely on by enhancing the approach used to generate the User Identifier(UI).The UI values changed from being static values,sensors MAC addresses,to be generated values in the inception *** approach makes the process of renewing the sensor keys more secure by renewing their UI values instead of changing the secret *** this study,Authenblue has been simulated in the Network Simulator 3(NS3).Simulation results show an improved performance compared to the related work.

关键词： Authentication industrial internet of things security Authenblue blockchain NS3

来源：评论

学校读者我要写书评

暂无评论

Severity Classification of Code Smells Using Machine-Learning Methods

引用

SN computer science 2023年第5期4卷 564页

作者： Dewangan, Seema Rao, Rajwant Singh Chowdhuri, Sripriya Roy Gupta, Manjari Department of Computer Science and Information Technology Guru Ghasidas Vishwavidyalaya Chhattisgarh Bilaspur India Computer Science DST-Centre for Interdisciplinary Mathematical Sciences Institute of Science Banaras Hindu University Varanasi India

Code smell detection can be very useful for minimizing maintenance costs and improving software quality. Code smells help developers/programmers, researchers to subjectively interpret design defects in different ways. Code smells instances can have varied size, intensity or severity which needs to be focused upon as they affect the software quality accordingly. Therefore, this study aims to detect the severity of code smells from code smell datasets. The severity of code smells is significant for reporting code smell detection performance, as it permits refactoring efforts to be prioritized. Code smell severity also describes extent of effort required during software maintenance. In our work, we have considered four code smells severity datasets to detect the severity of code smell. These datasets are data class, god class, feature envy and long method code smells. This paper uses four machine-learning and three ensemble learning approaches to identify the severity of code smells. To improve the models’ performance, we used fivefold cross-validation method: Chi-square-based feature selection algorithm and parameter optimization techniques. We applied two-parameter optimization techniques, namely grid search and random search and also compared their accuracy. The conclusion of this study is that the XG Boost model obtained an accuracy of 99.12%, using the Chi-square-based feature selection technique for the long method code smell dataset. In this study, the results show that ensemble learning is best as compared to machine learning for severity detection of code smells. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Code smells Feature selection Machine learning Parameter optimization Severity of code smells

来源：评论

学校读者我要写书评

暂无评论

Effective short text classification via the fusion of hybrid features for IoT social data

引用

Digital Communications and Networks 2022年第6期8卷 942-954页

作者： Xiong Luo Zhijian Yu Zhigang Zhao Wenbing Zhao Jenq-Haur Wang School of Computer and Communication Engineering University of Science and Technology BeijingBeijing100083China Shunde Innovation School University of Science and Technology BeijingFoshan528399China Beijing Key Laboratory of Knowledge Engineering for Materials Science Beijing100083China Department of Electrical Engineering and Computer Science Cleveland State UniversityClevelandOH44115USA Department of Computer Science and Information Engineering National Taipei University of TechnologyTaipei10608China

Nowadays short texts can be widely found in various social data in relation to the 5G-enabled Internet of Things (IoT). Short text classification is a challenging task due to its sparsity and the lack of context. Previous studies mainly tackle these problems by enhancing the semantic information or the statistical information individually. However, the improvement achieved by a single type of information is limited, while fusing various information may help to improve the classification accuracy more effectively. To fuse various information for short text classification, this article proposes a feature fusion method that integrates the statistical feature and the comprehensive semantic feature together by using the weighting mechanism and deep learning models. In the proposed method, we apply Bidirectional Encoder Representations from Transformers (BERT) to generate word vectors on the sentence level automatically, and then obtain the statistical feature, the local semantic feature and the overall semantic feature using Term Frequency-Inverse Document Frequency (TF-IDF) weighting approach, Convolutional Neural Network (CNN) and Bidirectional Gate Recurrent Unit (BiGRU). Then, the fusion feature is accordingly obtained for classification. Experiments are conducted on five popular short text classification datasets and a 5G-enabled IoT social dataset and the results show that our proposed method effectively improves the classification performance.

关键词： information fusion Short text classi fication BERT Bidirectional encoder representations fr 0om transformers Deep learning Social data

来源：评论

学校读者我要写书评

暂无评论

FAQNet: Frequency-Aware Quaternion Network for Endoscopic Highlight Removal

FAQNet: Frequency-Aware Quaternion Network for Endoscopic Hi...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zhu, Dingzhou Huang, Guoheng Yuan, Xiaochen Chen, Xuhang Zhong, Guo Pun, Chi-Man Deng, Jie Guangdong University of Technology School of Computer Science and Technology China Macao Polytechnic University Faculty of Applied Sciences China Huizhou University School of Computer Science and Engineering China University of Macau Department of Computer and Information Science China Guangdong University of Foreign Studies School of Information Science and Technology China First Affiliated Hospital of Sun Yat-Sen University China

ISBN: (纸本)9798350386226

Due to the built-in light source within the endoscope, the illumination of bodily mucous can cause the formation of highlight regions due to reflection. This not only interferes with the diagnosis conducted by doctors but also poses a challenge to subsequent computer vision tasks. To tackle this issue, we introduce FAQNet, a network specifically designed for endoscopic image highlight removal. FAQNet seamlessly integrates multi-channel information leveraging quaternion convolution and spatial channel attention within our Quaternion Multi-Channel Fusion (QMCF) Module. This allows it to capture intricate details of color, texture, spatial information, and highlight characteristics within the imaged organ. Additionally, by employing frequency domain transformation and dilated convolution, the Contextual information Integration (CII) Module effectively enlarges the receptive field, organizing contextual information between highlight regions and their surrounding areas. Lastly, the PixelShuffle Upsampling (PSU) Module generates the restored image. We validate our model's performance on two benchmark datasets, demonstrating its superiority over existing highlight removal methodologies. © 2024 IEEE.

关键词： Endoscopy

来源：评论

学校读者我要写书评

暂无评论

CHIE: Generative MRC Evaluation for in-context QA with Correctness, Helpfulness, Irrelevancy, and Extraneousness Aspects 2

CHIE: Generative MRC Evaluation for in-context QA with Corre...

引用

2nd Workshop on Generalisation (Benchmarking) in NLP, GenBench 2024

作者： Phatthiyaphaibun, Wannaphong Nonesung, Surapon Limkonchotiwat, Peerat Udomcharoenchaikit, Can Sawatphol, Jitkapat Chuangsuwanich, Ekapol Nutanong, Sarana School of Information Science and Technology VISTEC Thailand Department of Computer Engineering Faculty of Engineering Chulalongkorn University Thailand

ISBN: (纸本)9798891761827

The evaluation of generative models in Machine Reading Comprehension (MRC) presents distinct difficulties, as traditional metrics like BLEU, ROUGE, METEOR, Exact Match, and F1 score often struggle to capture the nuanced and diverse responses. While embedding-based metrics such as BERTScore and BARTScore focus on semantic similarity, they still fail to fully address aspects such as recognizing additional helpful information and rewarding contextual faithfulness. Recent advances in large language model (LLM) based metrics offer more fine-grained evaluations, but challenges such as score clustering remain. This paper introduces a multi-aspect evaluation framework, CHIE, incorporating aspects of Correctness, Helpfulness, Irrelevance, and Extraneousness. Our approach, which uses binary categorical values rather than continuous rating scales, aligns well with human judgments, indicating its potential as a comprehensive and effective evaluation method. © 2024 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-Time Monitoring and Control Systems Using IoT-Integrated Wireless Sensor Networks-Leveraging Machine Learning Algorithms for Enhanced Performance and Efficiency

Real-Time Monitoring and Control Systems Using IoT-Integrate...

引用

2024 International Conference on Cybernation and Computation, CYBERCOM 2024

作者： Swaminathan, Subbiah Poongavanam, N. Arun, M. Pushparani, S. Muthukrishnan, A. Johri, Prashant Rajalakshmi Engineering College Department of Information Technology Tamil Nadu Chennai India Saveetha University Department of Computer Science and Engineering Chennai602105 India Panimalar Engineering College Department of Electronics and Communication Engineering Tamil Nadu Chennai India Meenakshi College of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai600 078 India Vel Tech Rangarajan Dr. Sagunthala R and D Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Avadi Chennai India School of Computer Application and Technology Galgotias University India

ISBN: (纸本)9798331542344

This paper introduces a developed real-Time monitoring and control system using Internet of Things (IoT) incorporated Wireless Sensor Networks (WSNs) supported by machines learning algorithms. The system focuses at meeting core issues and questions in terms of productivity, reliability and timeliness within evolving settings. The current paper contributes to the ongoing research and development in the area of IoT and WSN to enable, always-on real-Time data gathering from a variety of discrete sensors which is invaluable for various applications including industrial, environmental and smart city applications. The heart of the system is based on the idea of utilising machine learning methods to acquire and elaborate sensor signals. More specifically, the deep learning models that are used include Long Short-Term Memory (LSTM) networks as well as Reinforcement Learning (RL) algorithms for predictive analytics, as well as anomaly detection. The work also entails a comparison of the system performance based on energy consumption and other factors such as latency, packet delivery ratio and even the accuracy of the predictions made by the system. The findings suggest improved utilisation within substantial ranges;decreased energy use by 30 per cent or more. 7%, latency decrease by 33. Although achieving this was accompanied by an increased data packet loss rate to 3%, the overall packet delivery ratio was boosted to 98%. Additionally, the system established overall accuracy rate of 95% with negligible error percentage. In conclusion, this research proves the applicability of incorporating the IoT and the advanced machine learning methods in the real-Time monitoring and control systems development to overcome cases of low efficiency and reduced performance in numerous real-world applications. © 2024 IEEE.

关键词： Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

Adaptive Intrusion Detection in Cyber-Physical Systems using Reinforcement Learning-Based Autoencoders 2

Adaptive Intrusion Detection in Cyber-Physical Systems using...

引用

2nd IEEE International Conference on Integrated Intelligence and Communication Systems, ICIICS 2024

作者： Rajathi, N. Divya, S. Anitha Elavarasi, S. Saritha, G. Jeya ramya, V. Department of Information Technology Kumaraguru College of Technology Coimbatore India Department of Computer Science and Business System Bannari Amman Institute of Technology Erode India Department of Computer Science and Engineering Sona College of Technology Salem India Department of Electronics and Communication Engineering Sri Sai Ram Institute of Technology Chennai India Department of Electronics and Communication Engineering Panimalar Engineering College Chennai India

ISBN: (纸本)9798331504960

The increasing integration of Cyber-Physical Systems (CPS) in critical infrastructure presents unique challenges for ensuring robust cybersecurity. Traditional Intrusion Detection Systems (IDS) often struggle with the dynamic, complex nature of CPS environments, making adaptive solutions essential. This paper presents an Adaptive Intrusion Detection System (AIDS) that leverages Reinforcement Learning-Based Autoencoders (RL-AE) to detect and respond to cyber intrusions in CPS environments. The proposed model combines the power of autoencoders for unsupervised anomaly detection with reinforcement learning to continuously adapt and improve detection accuracy. Experimental results on benchmark CPS datasets demonstrate that the RL-AE-based IDS achieves a detection accuracy of 98.3%, a precision rate of 96.8%, and a recall rate of 97.5%, effectively minimizing false positives to 2.4%. The system also demonstrated rapid adaptability, with a convergence time of less than 50 iterations in response to new attack patterns. These results highlight the model's ability to enhance system resilience and promote secure and efficient CPS operations in industrial and critical infrastructure applications. This approach provides a scalable and flexible IDS solution, promoting secure and resilient CPS operations in real-time, high-stakes environments. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Car Lock Control System Using Radio Frequency Identification(RFID)

Car Lock Control System Using Radio Frequency Identification...

引用

2024 IEEE SmartBlock4Africa, SmartBlock4Africa 2024

作者： Izang Aaron, A. Jonathan, Erihri O. Oyerinde Emmanuel, I. Ominike, Akpovi Chukwu Esther, C. Omodara Oluwademilade, E. Micheal Goldrich, C. School of Computing and Engineering Sciences Babcock University Department of Information Technology Ogun State Ilishan-Remo Nigeria School of Information and Communication Technology Delta State Polytechnic Department of computer Science Ogwashiuku Nigeria Petroleum Training Institute Computer Science and Information Technology Department Delta State Effurun Nigeria School of Computing and Engineering Sciences Babcock University Department of Computer Science Ogun State Ilishan-Remo Nigeria

ISBN: (纸本)9798350376838

Car Lock controlled system addresses the critical issue of vehicle security by utilizing RFID technology to create a more secure, passive, and wireless vehicle access system. This innovation surpasses traditional key-based systems, offering enhanced convenience and security. The project involves the development of a digital door locking mechanism integrated with RFID for secure vehicle identification. The system's efficacy was validated through rigorous testing, showcasing its potential to significantly deter vehicle theft. Despite challenges such as signal interference, the outcomes suggest a promising future for RFID in vehicle security. The study concludes with recommendations for extending RF communication range and exploring emerging technologies for further enhancement. This research marks a significant step towards redefining vehicle security, demonstrating the feasibility and effectiveness of a radio frequency-controlled car lock system. © 2024 IEEE.

关键词： Radio frequency identification (RFID)

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：