检索结果-内蒙古大学图书馆

Sparse Channel Estimation in Massive MIMO Systems Using Compressed Sensing and Neural Networks

Sparse Channel Estimation in Massive MIMO Systems Using Comp...

2024 IEEE International Conference on Intelligent Signal Processing and Effective Communication Technologies, INSPECT 2024

作者： Upadhyay, Deepak Sharma, Kunj Bihari Gupta, Mridul Upadhyay, Abhay Venu, Nookala Graphic Era Hill University Dept. of Computer Science and Engineering Dehradun India Graphic Era deemed to be University Dept. of Computer Science and Engineering Dehradun India ABV Indian Institute of Information Technology and Management Data Science and Quantum Computing Gwalior India

ISBN: (纸本)9798350379525

In this paper, based on compressed sensing and neural networks, we present an intelligent sparse channel estimation technique for Massive MIMO systems. We show that our approach improves considerably the estimation accuracy in terms of Mean Squared Error (MSE) and Normalized Mean Squared Error (NMSE) with respect to classical methods. We demonstrate [Figure: ] that our approach is computationally more efficient, requires less time and resources (memory/disk) compared to the existing literature but for a robustness of performance across distal or low Signal-to-Noise Ratios (SNRs). We also confirm our method exhibits fast convergence and efficiently accommodates a variety of sparsity levels. By visualizing it using heatmaps and ROC curves we show that this method is able to effectively differentiate between signal and noise, asserting our approach as a powerful tool for the contemporary set of problems present in wireless communications. © 2024 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

A Detailed Analysis of Secrecy and Performance Metrics in Hybrid RF/ FSO Communication Systems: Implications of Composite Weibull and Log-normal Fading with M Turbulent Channels

A Detailed Analysis of Secrecy and Performance Metrics in Hy...

引用

2024 IEEE International Conference on Intelligent Signal Processing and Effective Communication Technologies, INSPECT 2024

ISBN: (纸本)9798350379525

In this paper, we have analyzed the secrecy performance and system operation performance for hybrid RF/FSO systems against composite Weibull-log-normal fading channel with M turbulent channels. The performance is evaluated by carrying out extensive simulations to calculate Signal-to-Noise Ratio (SNR), Bit Error Rate (BER) and outage probability, we also re-evaluate channel capacity and secrecy capacity with respect of environmental conditions. Compared with RF only system, FSO only standalone scheme and some meaningful orthogonal-modulation multicarrier IM/DD-based schemes proposed by the literatures. Similarly, the utilization of adaptive modulation schemes improved resistance to fading and roughness in systems. The above results confirm the hybridization of both RF and FSO a comprehensive solution for dependable communication in different and even hostile surrounding conditions which set this work as reliable foundation point towards forthcoming research activity or application relevance within all range telecommunication sector. © 2024 IEEE.

关键词： Bit error rate

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning Approaches for Channel State Prediction in Heterogeneous Fading Networks

Transfer Learning Approaches for Channel State Prediction in...

引用

2024 IEEE International Conference on Intelligent Signal Processing and Effective Communication Technologies, INSPECT 2024

ISBN: (纸本)9798350379525

In this work, we leverage state-of-the-art machine learning algorithms to predict Channel State Information (CSI), for enhancing performance of wireless communication systems. The simulation and analysis stop with transfer learning to finetune, adaptive domain adaptations, multitasking (MTL) as well a few shot meta-learning models framework under different network packet loss rate scenarios. By generalizing better from one domain to another, transfer learning pushes the performance beyond what traditional methods can obtain. Further, fine-tuning also helps to align the source and target domain distributions in feature space by a partial (or full) reduction of re-stylization error. This work proposes multi-Task learning as a tool to mitigate loses in light of predicting across fading scenarios. Considering multi-task learning also provides benefits from shared learnings, so experience is pooled between the tasks which indirectly improve prediction as well and it helps in training both of these algorithms together. Moreover, the few-shot learning models prove to be highly desirable as they deliver state-of-the-art performance with minimal training data for difficult problems. These results show the potential of AI-based methods to improve CSI prediction, and have implications for improving reliability and throughput when deploying real wireless communication systems. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Design of Airborne Intelligent computing System Oriented to Intelligent Task Processing 26

Design of Airborne Intelligent Computing System Oriented to ...

引用

26th ACIS International Winter Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed computing, SNPD-Winter 2023

作者： Bai, Linting Wen, Pengcheng Xie, Jianchun Li, Yunxi Lin, Rongchao School of Computer Science Northwestern Polytechnical University Xi'an Aeronautics Computing Technique Research Institute Avic Xi'an China Xi'an Aeronautics Computing Technique Research Institute Avic Aviation Key Laboratory of Science and Technology on Airborne and Missile-borne Computer Xi'an China Xi'an Aeronautics Computing Technique Research Institute Avic Aeronautics Data and Sensor Business Unit Avic Xi'an China

ISBN: (纸本)9798350345865

The rapid development of artificial intelligence technology promotes the gradual evolution of the 'three integration' of mechanization, informatization and intelligence. The mass data characteristics of airborne mission informatization put forward higher demands on the storage, transmission and management capabilities of airborne data. The characteristics of high complexity, strong confrontation, strong real-time, and uncertainty of airborne intelligent tasks pose more challenges to the intelligent processing of airborne data. This paper analyzes the data characteristics and mission characteristics in the process of airborne intelligence missions, and proposes an airborne intelligent computing architecture for airborne data processing of intelligent missions. The composition and function of each technical layer are expounded, and several problems of airborne intelligent computing technology are analyzed. Finally, the development trend of airborne intelligent technology development is prospected. © 2023 IEEE.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Interpretable label-free self-guided subspace clustering

arXiv

引用

arXiv 2024年

作者： Kopriva, Ivica Division of Computing and Data Science Ruđer Bošković Institute Zagreb Croatia

Majority subspace clustering (SC) algorithms depend on one or more hyperparameters that need to be carefully tuned for the SC algorithms to achieve high clustering performance. Hyperparameter optimization (HPO) is often performed using grid-search, assuming that some labeled data is available. In some domains, such as medicine, this assumption does not hold true in many cases. One avenue of research focuses on developing SC algorithms that are inherently free of hyperparameters. For hyperparameters-dependent SC algorithms, one approach to label-independent HPO tuning is based on internal clustering quality metrics (if available), whose performance should ideally match that of external (label-dependent) clustering quality metrics. In this paper, we propose a novel approach to label-independent HPO that uses clustering quality metrics, such as accuracy (ACC) or normalized mutual information (NMI), that are computed based on pseudo-labels obtained from the SC algorithm across a predefined grid of hyperparameters. Assuming that ACC (or NMI) is a smooth function of hyperparameter values it is possible to select subintervals of hyperparameters. These subintervals are then iteratively further split into halves or thirds until a relative error criterion is satisfied. In principle, the hyperparameters of any SC algorithm can be tuned using the proposed method. We demonstrate this approach on several single- and multi-view SC algorithms, comparing the achieved performance with their oracle versions across six datasets representing digits, faces and objects. The proposed method typically achieves clustering performance that is 5% to 7% lower than that of the oracle versions. We also make our proposed method interpretable by visualizing subspace bases, which are estimated from the computed clustering partitions. This aids in the initial selection of the hyperparameter search *** Codes 68T10, 68U10, 68T09 © 2024, CC BY-NC-SA.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Gaussian Splatting Under Attack: Investigating Adversarial Noise in 3D Objects

arXiv

引用

arXiv 2024年

作者： Zeybey, Abdurrahman Ergezer, Mehmet Nguyen, Tommy School of Computing and Data Science Wentworth Institute of Technology BostonMA United States

3D Gaussian Splatting has advanced radiance field reconstruction, enabling high-quality view synthesis and fast rendering in 3D modeling. While adversarial attacks on object detection models are well-studied for 2D images, their impact on 3D models remains underexplored. This work introduces the Masked Iterative Fast Gradient Sign Method (M-IFGSM), designed to generate adversarial noise targeting the CLIP vision-language model. M-IFGSM specifically alters the object of interest by focusing perturbations on masked regions, degrading the performance of CLIP’s zero-shot object detection capability when applied to 3D models. Using eight objects from the Common Objects 3D (CO3D) dataset, we demonstrate that our method effectively reduces the accuracy and confidence of the model, with adversarial noise being nearly imperceptible to human observers. The top-1 accuracy in original model renders drops from 95.4% to 12.5% for train images and from 91.2% to 35.4% for test images, with confidence levels reflecting this shift from true classification to misclassification, underscoring the risks of adversarial attacks on 3D models in applications such as autonomous driving, robotics, and surveillance. The significance of this research lies in its potential to expose vulnerabilities in modern 3D vision models, including radiance fields, prompting the development of more robust defenses and security measures in critical real-world applications. © 2024, CC BY.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

Temporal Structural Probability Network for Weather Prediction

Temporal Structural Probability Network for Weather Predicti...

引用

2023 International Conference on Sustainable computing and Smart Systems, ICSCSS 2023

作者： Veeramani, R. Sathya Bama, B. Deeptha, R. Ishwarya, M.V. Karthikeyan, U. Srm Institute of Science and Technology Ramapuram Department of Information Technology Chennai India Agni College of Technology Artificial Intelligence and Data Science Department Tamil Nadu Chennai India Srm Institute of Science and Technology Kattankulathur Department of Computing Technologies Chennai India

ISBN: (纸本)9798350333602

A large number of people and assets are destroyed each year as a result of severe weather, such as cyclones, lightning, storm, or rain. Scientists are developing machine learning approaches that can help forecasters better anticipate these catastrophes by better understanding the underlying mechanisms and generating more accurate empirical models. Temporal structural probability networks have been significantly improved in this research, allowing for autonomous discovery of spatiotemporal correlations and the capacity to learn with any form. Prediction of thunderstorms in Texas and aero plane instability in the United States are the focus of the evaluations of suggested method. As part of the work discussion on how to assess the effectiveness of a machine learning algorithm in the context of severe weather, the system give a collection of instructions cultured for given machine learning techniques and talk about how to implement the proposed strategy. © 2023 IEEE.

关键词： Storms

来源：评论

学校读者我要写书评

暂无评论

OOP: Object-Oriented Programming Evaluation Benchmark for Large Language Models 62

OOP: Object-Oriented Programming Evaluation Benchmark for La...

引用

Findings of the 62nd Annual Meeting of the Association for Computational Linguistics, ACL 2024

作者： Wang, Shuai Ding, Liang Shen, Li Luo, Yong Du, Bo Tao, Dacheng Institute of Artificial Intelligence School of Computer Science Wuhan University China Hubei Luojia Laboratory Wuhan China The University of Sydney Australia School of Cyber Science and Teachnology Sun Yat-sen University China College of Computing & Data Science Nanyang Technology University Singapore

ISBN: (纸本)9798891760998

Advancing automated programming necessitates robust and comprehensive code generation benchmarks, yet current evaluation frameworks largely neglect object-oriented programming (OOP) in favour of functional programming (FP), e.g., HumanEval and MBPP. To address this, (1) our study introduces a pioneering OOP-focused benchmark, featuring 431 Python programs that encompass essential OOP concepts and features like classes and encapsulation methods. (2) We propose a novel evaluation metric, pass@o, tailored for OOP, enhancing traditional pass@k metric. (3) Our evaluation of 23 leading large language models (LLMs), including both general and code-specialized models, reveals three key insights: 1) pass@o offers a more relevant and comprehensive assessment for OOP code generation;2) Despite excelling in FP, code-specialized LLMs like WizardCoder lag in OOP compared to models like ChatGPT;3) The poor performance of all advanced LLMs on our OOP benchmark highlights a critical need for improvements in this field. Our benchmark and scripts are publicly released at: https://***/alphadl/OOP-eval. © 2024 Association for Computational Linguistics.

关键词： Object oriented programming

来源：评论

学校读者我要写书评

暂无评论

Hybrid Visual Verification 14

Hybrid Visual Verification

引用

14th International Conference on Cloud computing, data science and Engineering, Confluence 2024

作者： Bushra, S.Nikkath Syed Ismail, A. Sasigresa, P. Edwin Singh, C. Srm Institute of Scienece and Technology Department of Computing Technologies Chengalpattu Kattankulathur India Srm Institute of Scienece and Technology Department of Data Science and Business Systems Chengalpattu Kattankulathur India Veltech University Department: Computer Science and Engineering India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department: Computer Science and Engineering India

ISBN: (纸本)9798350344837

data security is becoming increasingly important as cloud computing advances. data security is the fundamental problem of all distributed computing systems. Cloud computing enables access to distributed applications and services belonging to various organizations spread across different locations. Cloud computing raises security concerns, because it shares data with distributed users via network in an open terrain. In this system, some of the most important security services like image-based security are handled by the cloud computing system. The proposed scheme takes care of several attacks like botnets, malware and guessing attacks. This scheme is contrasted withseveral established schemesand a new form of authentication is used for the purpose of storing files in a secure manner. © 2024 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

AdvIRL: Reinforcement Learning-Based Adversarial Attacks on 3D NeRF Models

arXiv

引用

arXiv 2024年

作者： Nguyen, Tommy Ergezer, Mehmet Green, Christian School of Computing and Data Science Wentworth Institute of Technology BostonMA United States

The increasing deployment of AI models in critical applications has exposed them to significant risks from adversarial attacks. While adversarial vulnerabilities in 2D vision models have been extensively studied, the threat landscape for 3D generative models, such as Neural Radiance Fields (NeRF), remains underexplored. This work introduces AdvIRL, a novel framework for crafting adversarial NeRF models using Instant Neural Graphics Primitives (Instant-NGP) and Reinforcement Learning. Unlike prior methods, AdvIRL generates adversarial noise that remains robust under diverse 3D transformations, including rotations and scaling, enabling effective black-box attacks in real-world scenarios. Our approach is validated across a wide range of scenes, from small objects (e.g., bananas) to large environments (e.g., lighthouses). Notably, targeted attacks achieved high-confidence misclassifications, such as labeling a banana as a slug and a truck as a cannon, demonstrating the practical risks posed by adversarial NeRFs. Beyond attacking, AdvIRL-generated adversarial models can serve as adversarial training data to enhance the robustness of vision systems. The implementation of AdvIRL is publicly available at https://***/TommyNguyen-cpu/AdvIRL/tree/MultiView-Clean, ensuring reproducibility and facilitating future research. © 2024, CC BY.

关键词： Adversarial machine learning

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：