检索结果-内蒙古大学图书馆

2023 International Conference on Control, Automation and diagnosis, ICCAd 2023

作者： Kwag, Sujin Kang, Byeongju Jang, Hyeonsoo Park, Junyeop Hwang, Yunhyoung Korea Automotive Technology Institute Department of Big Data and SW Platform R&D Gyeonggi-do Seongnam-si Korea Republic of

ISBN: (纸本)9798350347074

With the advancement on automated vehicle technology, the highly automated driving is expected to work in complicated traffic situations such as urban intersections and traffic incidents. However, the traffic incidents still remain a comprehensively challenging situation especially in the mixed traffic. To resolve this problem, a sophisticated control strategy is required to support the automated driving in these unexpected traffic situations. From this background, this study mainly focuses on developing a generalized control strategy to manage the automated vehicles driving in traffic incident situations. First, the representative scenarios are analyzed, and a generalized control strategy is elaborated based on the framework of cooperative driving automation. The proposed control strategy can be extended to more complicated situations, and it is expected to extend the operational design domain of automated vehicles. © 2023 IEEE.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Plausible Vehicle Trajectory Augmentation with Hybrid Machine Learning

引用

IEEE Access 2025年 13卷 93033-93045页

作者： Park, Junyeop Jang, Hyeonsoo Kang, Byeongju Hwang, Yunhyoung Korea Automotive Technology institute Big Data and SW platform R&D Department South Korea Jeonbuk National University Department of Mechanical Engineering South Korea Jeonbuk National University Graduate School of Mechanical-Aerospace-Electric Convergence Engineering Jeonju 54896 South Korea

In recent decades, advancements in autonomous driving technology have fundamentally transformed the automotive industry and transportation systems. Autonomous vehicles hold the potential to significantly reduce traffic accidents, improve driving convenience, and alleviate congestion. A crucial factor in achieving these outcomes is the accurate prediction of surrounding vehicle trajectories, which relies on the effective application of artificial intelligence and machine learning algorithms. However, the collection of sufficient high-quality driving data for training these models poses practical challenges, particularly in complex and unpredictable traffic scenarios. To address this issue, this paper proposes a novel data augmentation technique, integrating Chebyshev polynomial fitting with Hierarchical density-Based Spatial Clustering of Applications with Noise clustering and Gaussian mixture models to generate robust training data. This study focuses on augmenting vehicle driving datasets by automatically managing variations in time-series lengths and the clustering of driving maneuvers. This approach ultimately generates augmented data with a high degree of similarity to real-world data. Validation on the ind dataset confirms that our approach excels in expanding training datasets, yielding substantial improvements in trajectory prediction accuracy for autonomous vehicles when applied to a vanilla long short-term memory model. This study outlines the methodology and validates the effectiveness of the augmented data, offering a promising method for enhancing autonomous vehicle training frameworks. © 2013 IEEE.

关键词： Automated driving Chebyshev polynomial data augmentation Time-series data Vehicle trajectory

来源：评论

学校读者我要写书评

暂无评论

Attack and defense of deep Learning Models in the Field of Web Attack detection

arXiv

引用

arXiv 2024年

作者： Shi, Lijia dong, Shihao R&D Department of Security Technology Platform Chinatelecom Research Institute Shanghai201315 China School of Data Science and Engineering East China Normal University Shanghai200062 China

The challenge of WAd (web attack detection) is growing as hackers continuously refine their methods to evade traditional detection. deep learning models excel in handling complex unknown attacks due to their strong generalization and adaptability. However, they are vulnerable to backdoor attacks, where contextually irrelevant fragments are inserted into requests, compromising model stability. While backdoor attacks are well studied in image recognition, they are largely unexplored in WAd. This paper introduces backdoor attacks in WAd, proposing five methods and corresponding defenses. Testing on textCNN, biLSTM, and tinybert models shows an attack success rate over 87%, reducible through fine-tuning. Future research should focus on backdoor defenses in *** the code and data of this paper can be obtained at https://***/r/attackdefenceindL-7E05 Copyright © 2024, The Authors. All rights reserved.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Optimizing diagnostic Accuracy in Ultrasound Imaging Through Cloud-Enabled deep Learning Techniques 4

Optimizing Diagnostic Accuracy in Ultrasound Imaging Through...

引用

4th International Conference on Soft Computing for security Applications, ICSCSA 2024

作者： Kalpana, V. Girija, M. Tharageswari, K. Yobu, d. revathi, J. Aruna, r. Department of Computer Science and Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai India Jeppiaar University School of Engineering and Technology Chennai India Department of Computer Science and Engineering Karpagam Academy of Higher Education Coimbatore India Computer Science and Engineering Cyber Security J.J College of Engineering and Technology Tricy India Department of Mathematics Kongu Engineering College Erode India Department of Computer Science and Engineering School of Computing Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai India

ISBN: (纸本)9798331515720

This research aims to study predicting and optimizing the diagnostic accuracy by cloud-enabled deep learning techniques in ultrasound imaging for kidney disease diagnosis. The main findings are that CNN gives 92% accurate outcomes in terms of sensitivity, precision, specificity, AUC-rOC, and other terms used for predictive outcomes in the current research. The other outcomes are 88% accuracy and 91% specificity in predicting kidney diseases by using the rNN model. The other two models used for learning are transfer learning and federated learning which also provide good outcomes which are 94% accurate and 91% accurately in diagnosing with the above-said models. These learning approaches optimize or increase the accuracy rates such as 93% by the transfer learning approach and 90% accuracy outcomes by the federated learning mechanism. These above-given models have been taken based on advanced technologies that are used to predict or forecast the diseases through learning processes. The success of these learning mechanisms is explained by the reliable processes used in the learning of the models that are possible by the neural network used in the learning mechanisms. The high accuracy rates of the models show the successfulness of such clinics, who are in rural areas and are unable to meet their necessary outcome-oriented goals, then measures can be taken for running tele-clinics using the above models of learning techniques to diagnose the diseases at the correct time by 'n' number of people in rural areas. Mine is one of them working as a health worker for which measures need to be taken for finding an accurate solution that operates on cloud-enabled deep learning. This model help run family life and be able to diagnose certain conditions at desired rural clinics out of the above learning models. These tools of learning are studied on cloud-based deep learning techniques and performed well in diagnosing kidney diseases on rural tele-medicine and these learning techni

关键词： Ultrasonic imaging

来源：评论

学校读者我要写书评

暂无评论

Traceable ring signature schemes based on SM2 digital signature algorithm and its applications in the data sharing scheme

引用

Frontiers of Computer Science 2024年第2期18卷 251-253页

作者： Yongxin ZHANG Hong LEI Bin WANG Qinghao WANG Ning LU Wenbo SHI Bangdao CHEN Qiuling YUE R&D Department SSC Holding CompanyLtd.Chengmai 571924China School of Cyberspace Security(School of Cryptography) Hainan UniversityHaikou 570228China College of Computer Science and Engineering Northeastern UniversityShenyang 110819China School of Computer Science and Technology Xidian UniversityXi'an 710071China Blockchain Research Group Oxford-Hainan Blockchain Research InstituteChengmai 571924China

1 Introduction Identity privacy concerns hinder data sharing by casting doubt on the safeguarding of personal information,eroding trust,and impeding the willingness of individuals and organizations to exchange their data[1,2].The traceable ring signatures(TrSs)addresses the contradiction between identity privacy and regulation[3],no scheme has been developed thus far that is based on SM2,the Chinese cryptographic public key algorithm standard,without relying on centralized trust.

关键词： SM2 signature scheme

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Future: Exploring the Impacts and Challenges of Artificial Intelligence in Workplace Applications 3

Unveiling the Future: Exploring the Impacts and Challenges o...

引用

3rd International Conference for Advancement in technology, ICONAT 2024

作者： Pragith, S. Supriya, S. Sasikala, S. Sateesh, rayala Swamy, Hemanth Karpagam, P. Vellore Institute of Technology Department of Computer Science Engineering Vellore India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Computer Science and Engineering India Tagore Engineering College Department of ECE Chennai India MLR Institute of Technology Department of ECE Hyderabad India Motorola Solutions United States Dhanalakshmi College of Engineering Department of Cyber Security Chennai India

ISBN: (纸本)9798350354171

Unveiling the Future: Exploring the Impacts and Challenges of Artificial Intelligence in Society' embarks on a comprehensive journey through the transformative landscape shaped by Artificial Intelligence (AI). This abstract offers a nuanced examination of AI's profound implications, ranging from its disruptive potential to its ethical complexities, and the societal imperatives it underscores. delving into the evolution of AI technologies, from foundational concepts to cutting-edge innovations, the abstract elucidates their growing significance across diverse sectors including healthcare, finance, transportation, and beyond. However, amidst the promises of efficiency and innovation, ethical concerns loom large. The abstract navigates through the ethical intricacies of AI, addressing issues of bias, accountability, and the erosion of privacy. Furthermore, it ventures into the societal ramifications of AI adoption, exploring its impact on employment dynamics, socioeconomic disparities, and the fabric of human interaction. By interrogating the dual narratives of promise and peril, this abstract offers a holistic understanding of AI's role in shaping the future of society. It underscores the imperative for thoughtful governance, ethical stewardship, and inclusive decision-making to ensure that AI serves as a force for collective progress rather than exacerbating existing divides. Through its interdisciplinary lens, this abstract serves as a roadmap for stakeholders across academia, industry, and policymaking to navigate the complex terrain of AI's integration into society, ultimately paving the way for a future where AI augments human capabilities while upholding fundamental values of fairness, equity, and justice. © 2024 IEEE.

关键词： decision making

来源：评论

学校读者我要写书评

暂无评论

Novel Gender and Age Prediction from real Time Facial Images using Linear regression Algorithm 8

Novel Gender and Age Prediction from Real Time Facial Images...

引用

8th International Conference on Electronics, Communication and Aerospace technology, ICECA 2024

作者： Nalini, N. Shahila, d. Ferlin deva rosi, A. Tamilselvi, M. Giri, Jayant Sherideh, Ala'a Al Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Ece Chennai India Saveetha University Saveetha School of Engineering Department of Ece Chennai India Yeshwantrao Chavan College of Engineering Department of Mechanical Engineering Nagpur India Lovely Professional University Division of Research and Development Phagwara India Zarqa University College of Information Technology Department of Cyber Security zarqa Jordan University of Business and Technology Jeddah Saudi Arabia

ISBN: (纸本)9798350367904

The proposed novel algorithm utilizes linear regression in real-time facial image analysis for predicting both gender and age. By leveraging features extracted from facial data, the model aims to provide accurate and instantaneous predictions. The emergence of social media platforms has made the automatic classification of gender and age increasingly relevant. real-time frame processing is possible with OpenCV. The expected gender and age are provided as the output, and this frame is provided as the input. The capacity to autonomously ascertain age and gender from facial images because of its versatility in facial analysis applications. However, the current models are still behind the required accuracy level, which is required for these models to be used in real-world applications, because of the significant intraclass variance of face images (such as difference in lighting, position, scale, and occlusion). In this work, a deep learning framework uses an ensemble of residual and attentional convolutional networks to reliably determine the gender and age group of facial photographs. By employing an attention mechanism, this model can concentrate on the important and instructive aspects of the face, increasing its prediction accuracy to 90.15%. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

A Powerful Load Balancing Algorithm for Cloud Performance Evaluation 5

A Powerful Load Balancing Algorithm for Cloud Performance Ev...

引用

5th International Conference on Inventive research in Computing Applications, ICIrCA 2023

作者： Chandar, J. Praveen Chidambaranathan, C.M. Anbarasan, Anbarasa Kumar Karthikram, A. Karunya Institute of Technology and Sciences Department of Computer Science and Engineering Coimbatore India School of Computing Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Chennai India School of Information Technology and Engineering Vellore Institute of Technology Vellore India School of Computers Madanapalle Institute of Technology & Science Department of Cyber Security Madanapalle India

ISBN: (纸本)9798350321425

The energy consumption of data centers plays a significant role in the cost estimation of maintenance, performance evaluation, and environmental pollution in cloud computing. Carbon emissions are one of the major drawback of data centers in this scenario. To manage the data center temperature as well as the necessity to reduce power consumption while satisfying customer demands. This is extremely beneficial to both the data center and the environment. The data center is a collection of servers from which consumers can benefit by using their services. In this context, cloud service providers are working hard to reduce energy usage and avoid environmental contamination. This research work describes the novel algorithm for scheduling virtual machines in servers in order to consume a minimal amount of energy. The weight approximation algorithm arranges servers and virtual machines in decreasing order depending on their configuration to allocate VMs with jobs to optimize power usage. The power consumption of the server is calculated before and after VM allocation in this algorithm. To avoid CrAC modifications, the critical threshold of each server is maintained in this instance. If it exceeds the server's critical threshold, the VM is moved to another ideal server to avoid migration. In this method of VM allocation, the ordered tasks are allocated to the server using round-robin fashion. The model is simulated using cloudsim tools, and the server's performance and energy consumption are better than the random selection algorithm. © 2023 IEEE.

关键词： Virtual machine

来源：评论

学校读者我要写书评

暂无评论

Efficient detection of Generative Chinese Statements Using Feature Compression Methods

Efficient Detection of Generative Chinese Statements Using F...

引用

Mobile Internet, Cloud Computing and Information security (MICCIS), International Conference on

作者： Yiang Gao Tianrui Huang Nishui Cai dawei Yang R&D Department of Security Application Technology China Telecom Research Institute Shanghai China AIEN Institute Shanghai Ocean University Shanghai China

ISBN: (数字)9798350389906

ISBN: (纸本)9798350389913

With the explosion of big models, compliance detection of generative utterances becomes increasingly important. Currently, the detection of Chinese corpus faces the problems of 1. a small number of effective datasets and 2. poor learning effect of Chinese corpus. In this paper, we explore a chinese statement learning approach based on a small amount of data based on the COLd dataset, which proves that the small sample data can also bring a good learning effect to the model under low-dimensional features.

关键词： Cloud computing Information security Feature extraction Explosions data models Faces

来源：评论

学校读者我要写书评

暂无评论

Estimating Smart Grid Stability with Hybrid rNN+LSTM deep Learning Approach 12

Estimating Smart Grid Stability with Hybrid RNN+LSTM Deep Le...

引用

12th International Conference on Smart Grid, icSmartGrid 2024

作者： Oyucu, Saadin Sagiroglu, Seref Aksoz, Ahmet Bicer, Emre Faculty of Engineering Department of Computer Engineering Adiyaman Turkey Gazi University Artificial Intelligence and Big Data Analytics Security R&d Center Ankara Turkey Sivas Cumhuriyet University Mobilers Team Sivas Turkey Sivas University of Science and Technology Faculty of Engineering and Natural Sciences Battery Research Laboratory Sivas Turkey

ISBN: (纸本)9798350361612

Smart grids are faced with a range of challenges, such as the development of communication infrastructure, cybersecurity threats, data privacy, and the protection of user information, due to their complex structure. Another key challenge faced by smart grids is the stability issues arising from variable energy sources and consumption patterns. In these complex grid systems where energy demand and supply need to be balanced instantly, stability predictions play a significant role in foreseeing potential disruptions and optimizing energy flow. Therefore, within the scope of this study, a hybrid structure utilizing recurrent Neural Networks (rNN) and Long Short-Term Memory (LSTM) networks is employed for stability classification to predict grid stability. This hybrid model combines the ability of rNN to recognize relationships between consecutive data points with LSTM's capability to preserve long-term dependencies. The results obtained indicate that the model exhibited stable performance with accuracy rates of 98.06% and 98.02% at 50 and 100 epochs, respectively. The findings of this study contribute valuable insights to research on the management and stability of smart grids, enabling energy systems to be operated more reliably and efficiently. © 2024 IEEE.

关键词： Smart power grids

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：