检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第11期5卷 5771-5785页

作者： Li, Jinbo Liu, Peng Chen, Long Pedrycz, Witold Ding, Weiping Nantong University School of Artificial Intelligence and Computer Science Nantong226019 China China Unicom Research Institute Beijing100048 China Henan University International Business School Zhengzhou47500 China University of Macau Department of Computer and Information Science 999078 China University of Alberta Department of Electrical and Computer Engineering EdmontonAB T6R 2V4 Canada City University of Macau Faculty of Data Science 999078 China

The integration of different learning paradigms has long been a focus of machine learning research, aimed at overcoming the inherent limitations of individual methods. Fuzzy rule-based models excel in interpretability and have seen widespread application across diverse fields. However, they face challenges such as complex design specifications and scalability issues with large datasets. The fusion of different techniques and strategies, particularly gradient boosting, with fuzzy rule-based models offers a robust solution to these challenges. This article proposes an integrated fusion framework that merges the strengths of both paradigms to enhance model performance and interpretability. At each iteration, a fuzzy rule-based model is constructed and controlled by a dynamic factor to optimize its contribution to the overall ensemble. This control factor serves multiple purposes: it prevents model dominance, encourages diversity, acts as a regularization parameter, and provides a mechanism for dynamic tuning based on model performance, thus mitigating the risk of overfitting. Additionally, the framework incorporates a sample-based correction mechanism that allows for adaptive adjustments based on feedback from a validation set. Experimental results substantiate the efficacy of the presented gradient-boosting framework for fuzzy rule-based models, demonstrating performance enhancement, especially in terms of mitigating overfitting and complexity typically associated with many rules. By leveraging an optimal factor to govern the contribution of each model, the framework improves performance, maintains interpretability, and simplifies the maintenance and update of the models. © 2024 IEEE.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Generative Multimodal data Augmentation for Low-Resource Multimodal Named Entity Recognition 24

Generative Multimodal Data Augmentation for Low-Resource Mul...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Li, Ziyan Yu, Jianfei Yang, Jia Wang, Wenya Yang, Li Xia, Rui School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China College of Computing and Data Science Nanyang Technological University Singapore Wee Kim Wee School of Communication and Information Nanyang Technological University Singapore

ISBN: (纸本)9798400706868

As an important task in multimodal information extraction, Multimodal Named Entity Recognition (MNER) has recently attracted considerable attention. One key challenge of MNER lies in the lack of sufficient fine-grained annotated data, especially in low-resource scenarios. Although data augmentation is a widely used technique to tackle the above issue, it is challenging to simultaneously generate synthetic text-image pairs and their corresponding high-quality entity annotations. In this work, we propose a novel Generative Multimodal data Augmentation (GMDA) framework for MNER, which contains two stages: Multimodal Text Generation and Multimodal Image Generation. Specifically, we first transform each annotated sentence into a linearized labeled sequence, and then train a Label-aware Multimodal Large Language Model (LMLLM) to generate the labeled sequence based on a label-aware prompt and its associated image. We further employ a Stable Diffusion model to generate the synthetic images that are semantically related to these sentences. Experimental results on three benchmark datasets demonstrate the effectiveness of the proposed GMDA framework, which consistently boosts the performance of several competitive methods for two subtasks of MNER in both full-supervision and low-resource settings. The low-resource dataset and source code are released at https://***/NUSTM/GMDA. © 2024 ACM.

关键词： data augmentation

来源：评论

学校读者我要写书评

暂无评论

Design of Provably Secure Authentication Protocol for Edge-Centric Maritime Transportation System

引用

IEEE Transactions on Intelligent Transportation Systems 2023年第12期24卷 14536-14545页

作者： Mahmood, Khalid Shamshad, Salman Ayub, Muhammad Faizan Ghaffar, Zahid Khan, Muhammad Khurram Das, Ashok Kumar National Yunlin University of Science and Technology Graduate School of Intelligent Data Science Douliu64002 Taiwan The University of Lahore Department of Software Engineering Lahore54590 Pakistan University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu610054 China National Yunlin University of Science and Technology Department of Computer Science and Information Engineering Douliu64002 Taiwan King Saud University Center of Excellence in Information Assurance Riyadh11653 Saudi Arabia International Institute of Information Technology Center for Security Theory and Algorithmic Research Hyderabad500032 India

The epidemic growth of the Internet of Things (IoT) objects have revolutionized Maritime Transportation Systems (MTS). Though, it becomes challenging for the centralized cloud-centric framework to fulfil the application requirements such as low latency and power utilization. The introduction of the distributed edge-centric framework has recently helped the IoT-enabled MTS to meet these requirements by manipulating the tasks at the edge of the networks. Despite the fact that MTS leverages mobile subscribers by overcoming inherent cloud computing limitations, data security and user privacy requirements in establishing the MTS setup are still non-trivial challenges. In this article, we develop a key agreement solution for mobile users to realize mutual authentication in a single round. Our protocol offers user anonymity to maintain user privacy, and it can prevent physical attacks by physically unclonable functions. Initially, the security analysis is conferred to substantiate our protocol's security persistence or strength. Later, its performance correlation is observed under the assumption of diverse metrics in a predefined empirical setup. The meticulous performance correlation endorses the precedence of our protocol over specified related protocols. © 2000-2011 IEEE.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

Improved Particle Swarm Algorithm Using Multiple Strategies 1

引用

14th International Symposium on Intelligence Computation and Applications, ISICA 2023

作者： Yi, Yunfei Wang, Zhiyong Shi, Yunying School of Big Data and Computer Hechi University Guangxi Yizhou546300 China College of Computer Science and Engineering Guangxi Normal University Guangxi Guilin541001 China

ISBN: (数字)9789819743933

ISBN: (纸本)9789819743926

In order to address the issues of premature convergence and low search efficiency in the basic particle swarm algorithm, this paper analyzes the improved particle swarm optimization algorithms proposed by previous researchers. Based on this analysis, a modified algorithm for particle swarm optimization is proposed. The enhanced algorithm adjusts the inertia weight parameter in a nonlinear manner and dynamically changes the self-learning factor using chaos, allowing it to continuously change during iterations and achieve better optimization results. Additionally, to prevent the algorithm from getting trapped in local optima, a mutation operation is introduced into the improved algorithm. Finally, several classical test functions are used to conduct experiments, and the results are compared with the improved particle swarm optimization algorithms described in related literature. The experimental results demonstrate that the newly proposed algorithm achieves a certain degree of improvement in optimization accuracy compared to the basic particle swarm algorithm. This indicates that the modified algorithm effectively avoids premature convergence and possesses high search efficiency. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Extended Finite State Machine based Fault Tolerance in WSN 7

Extended Finite State Machine based Fault Tolerance in WSN

引用

7th International Conference on Computing Methodologies and Communication, ICCMC 2023

作者： Lekha, D. Ahsan Shariff, M. Lakshmi, S. Venkata Anwar Basha, H. Department of Computer Science and Engineering RMK College of Engineering and Technology Tamil Nadu Chennai India Department of Computer Science and Engineering Aalim Muhammed Salegh College of Engineering Tamil Nadu Chennai India Artificial Intelligence and Data Science Sri Krishna College of Engineering and Technology Tamil Nadu Coimbatore India School of Computer Science and Engineering REVA University Karnataka Bengaluru India

ISBN: (纸本)9781665464086

Wireless Sensor Network (WSN) suffers from different malware attacks. Several traditional approaches are proposed for detecting fault nodes in WSN. It is necessary to redistribute the nodes and detect the fault nodes while modifying the WSN parameters. Faults can occur in the nodes interrupting the continuous communication process of the nodes in the WSN. The main reason for a fault is also the induction of the energy drain in a node to the maximum possible level, failure of links in communicating nodes due to bandwidth constraints, and attacks induced by the malicious nodes. To solve this problems, Extended Finite State Machine based Fault Tolerance (EFSM_FT) in the WSN is used to detect the fault sensor nodes in the WSN. In this approach, called the finite state machine (FSM), state prompted is modified while a set of situations are true. Every node can be absolutely to be faulty or not establishing on the sensor node states. Using sensor energy, drop rate, forward sensor rate, sensor obtained rate, bandwidth, and transmission delay, this method finds the node with the fault. As a result, this approach accurately detects the faulty nodes in the WSN. The simulation outcomes illustrate the proposed method has a better fault detection ratio and minimizes the false negative ratio in the WSN. © 2023 IEEE.

关键词： Finite automata

来源：评论

学校读者我要写书评

暂无评论

Text Sentiment Analysis of Film Reviews Using Bi-LSTM and GRU 4

Text Sentiment Analysis of Film Reviews Using Bi-LSTM and GR...

引用

4th International Conference on Electronics and Sustainable Communication Systems, ICESC 2023

作者： Mouthami, K. Yuvaraj, N. Thilaheswaran, K.K. Lokeshvar, K.J. Kpr Institute of Engineering and Technology Dept. of Computer Science Engineering Coimbatore India Kpr Institute of Engineering and Technology Dept. of Artificial Intelligence and Data Science Coimbatore India

ISBN: (纸本)9798350300093

Sentiment analysis is a vast subject to explore in natural language processing (NLP) techniques. The film reviews were analyzed and segregated into positive, neutral, and negative reviews. The proposed model examines two distinct datasets, one with multi-class labels and the other with binary-type class labels. The preprocessing is done by using the bag of words and skip-gram word2vec, variety of classifiers, including Two state Gated recurrent units (TS-GRU), was used for binary classification, and the Bidirectional Long Short-Term Memory (Bi-LSTM for the multi-class situation was implemented. Bi-LSTM was utilized in the model, in which symmetric Bi-LSTM replaces the LSTM approaches to get around the high computational cost of training the normal LSTM. The Bi-LSTM has equivalent accuracy to the LSTM while significantly reducing computational costs. Sentiment analysis offers a glimpse of how consumers feel about certain movies. This endeavor is undertaken via the study of natural language processing, in which sentiment analysis is a branch which examines how words are arranged and utilized to extract meaning from user writing. This helps to investigate further the methods for deciphering such data thanks to significant advancements in machine learning techniques;with Keras API and the Internet Movie database (IMDb) dataset, this study compares single and multi-branch CNN with Bidirectional LSTMs with different kernel sizes. GRU achieved 98.24% of accuracy, and bi-LSTM achieved 98.65% of accuracy. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Improve Accuracy in Healthcare data Analysis using Competitive Ensemble Deep Learning Model 18

Improve Accuracy in Healthcare Data Analysis using Competiti...

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Sravanthi, Jakkula Reddy, Chada Sampath Mahendar, A. Kumar, V. Ravi Buragadda, Swathi Ghantasala, G. S. Pradeep Gupta, Gaurav Vnr Vignana Jyoti Institute of Engineering and Technology Department of Information Technology Telangana India Sree Chaitanya Institute of Technological Sciences Department of Computer Science Engineering Telangana Karimnagar India Telangana Hyderabad India Ace Engineering College Department of Computer Science Engineering Ghatkesar India Lakireddy Balireddy College of Engineering Department of Computer Science Engineering Kakinada India Alliance University Department of Computer Science and Engineering Bengaluru India Shoolini University Yogananda School of Artificial Intelligence Computers and Data Sciences Solan India

ISBN: (纸本)9789380544519

This paper discusses the significance of Machine Learning (ML) and Deep Learning (DL) techniques for structured and unstructured healthcare data. As healthcare data is increasing tremendously, it is difficult to identify hidden patterns in huge amounts of data. DL handles a massive amount of clinical data and provides better outcomes. A novel competitive ensemble deep learning model has been proposed to improve the classification performance of structured data. However, dealing with unstructured data, the proposed work highlights a competitive DL model for Twitter sentiment analysis. In addition, this paper discusses the proposed Competitive Ensemble Deep Learning (CEPL) algorithm for text data. The proposed model is compared with a traditional model to evaluate the model's performance in the range of 0.2%-0.5%. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Accuracy CEPL Deep Learning Healthcare data Machine learning Methods

来源：评论

学校读者我要写书评

暂无评论

Underwater Photography Noise cancellation Using Artificial Intelligence and Deep Learning 2

Underwater Photography Noise cancellation Using Artificial I...

引用

2nd IEEE International Conference on Advances in Computing, Communication and Applied Informatics, ACCAI 2023

作者： Sanjiv, S. Kishore Harshan Kumar, R. Ranjith, R. Chandrasekar, A. Vijayakumar, K. St. Joseph's College of Engineering Artificial Intelligence and Data Science Chennai India St. Joseph's College of Engineering Computer Science and Engineering Chennai India

ISBN: (纸本)9798350315905

Cameras submerged underwater are widely used to see the ocean floor. Unmanned underwater automation, autonomous underwater vehicles, and in situ ocean sensors are common places to find them (AUVs). While being an essential sensor for keeping track of underwater landscapes, recent underwater camera sensors have several issues. Because of how light moves through water and the biological activity at the seafloor, underwater photographs are typically cluttered with scatters and noise. Over the past five years, a variety of tactics have been developed to Important facts of oceanographic study include image processing and underwater sensing. One prior challenge is light absorption with a scattering effect, which reduces the image quality in underwater conditions with respect to its ground truth. © 2023 IEEE.

关键词： Underwater photography

来源：评论

学校读者我要写书评

暂无评论

Exploring nonintrusive measurements of spatio-temporal portrait of microservices

Exploring nonintrusive measurements of spatio-temporal portr...

引用

作者： Zeng, Tao Xu, Zichen Wu, Dan Li, Xiaoling Liu, Biyong Hu, Haichuan Tan, Shuang Tan, Yusong Xu, Chenren Stewart, Christopher Zhou, Qihe Cao, Ye School of Mathematics and Computer Sciences Nanchang University Nanchang China College of Computer National University of Defense Technology Hunan China School of Computer Science Peking University Beijing China Computer Science and Engineering The Ohio State University ColumbusOH United States Faculty of Data Science City University of Macau China

As cloud native technology advances, the scale and complexity of applications built on microservice architecture continue to expand, leading to increasingly intricate differences between software within the same application. Microservice applications, offering high flexibility, are deployed in data centers as black boxes from the users' perspective, leaving them with no insight into the orchestration of cloud service providers. Consequently, users face challenges in promptly recognizing performance imbalances within their deployed applications. Meanwhile, cloud service providers may cut costs by offering a mix of qualified and unqualified services, potentially deceiving users. To enhance the understanding of microservice application organization, we propose a non-intrusive measurement framework, termed NMPI. NMPI facilitates rapid identification of microservice application defects, offering insights into cloud services and detecting fraudulent behavior in microservice-based applications. We model microservice applications using a queue analysis-based approach and filter the dominant frequency components of average response time signals by employing k-means on the fast fourier transform (FFT). Our model constructs a library of performance portraits for various software, with these portraits resembling human fingerprints that carry and mark the software's internal information. Utilizing a two-tier microservices-based application incorporating a database as a case study allows us to demonstrate the effectiveness of NMPI. Our experimental results show that NMPI can produce differentiable profiles of data service performance portraits across a diverse and extensive range of workloads, enabling the identification of software types and the analysis of performance conditions. © 2023 John Wiley & Sons, Ltd.

关键词： Fast Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

Enhancing digital security using Signa-Deep for online signature verification and identity authentication

International Journal of Systematic Innovation

引用

International Journal of Systematic Innovation 2024年第2期8卷 58-69页

作者： Ch, Ravikumar Sridevi, Mulagundla Ramchander, M. Ramesh, Vankudoth Kumar, Vadapally Praveen Department of Artificial Intelligence &Data Science Chaitanya Bharathi Institute of Technology Hyderabad 500075 India Department of Computer Science and Engineering CVR College of Engineering Hyderabad 501510 India Department of Computer Applications Chaitanya Bharathi Institute of Technology Hyderabad 500075 India Department of Emerging Technologies CVR College of Engineering Hyderabad 500039 India

In the contemporary digital realm, the utilization of online services has surged, facilitated by the seamless integration of deep learning technology, which is paramount in applications demanding precision and efficiency. A pivotal use case in this context is online handwritten signature verification, where the need for exceptional accuracy is indisputable. This paper introduces ‘Signa-Deep, ’ an innovative approach designed to address the challenge of online signature verification and the determination of an individual’s authorization status. The study explores a range of methodologies, including Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), GoogleNet, and MobileNet, to discern the authenticity of signatures and affirm the identity of the signatory. The results of our proposed method are promising, showcasing its potential to significantly enhance the security of digital transactions and identity verification processes. In summary, ‘Signa-Deep’ harnesses deep learning technology to bolster the accuracy and reliability of online signature verification, thereby contributing to the overall robustness of digital interactions and identity validation processes. © (2024), (Society of Sytematic Innovation). All rights reserved.

关键词： Authorization Status Deep Learning Digital Transactions Security Identity Authentication Online Signature Verification

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：