检索结果-内蒙古大学图书馆

22nd ACM Conference on Embedded Networked Sensor systems, SenSys 2024

作者： Weng, Yuxuan Wu, Guoquan Zheng, Tianyue Yang, Yanbing Luo, Jun Department of Computer Science and Engineering Southern University of Science and Technology China Smart City Center Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology China College of Computer Science Sichuan University China College of Computing and Data Science Nanyang Technological University Singapore Singapore

ISBN: (纸本)9798400706974

Radio-Frequency (RF)-based Human Activity Recognition (HAR) rises as a promising solution for applications unamenable to techniques requiring computer visions. However, the scarcity of labeled RF data due to their non-interpretable nature poses a significant obstacle. Thanks to the recent breakthrough of foundation models (FMs), extracting deep semantic insights from unlabeled visual data become viable, yet these vision-based FMs fall short when applied to small RF datasets. To bridge this gap, we introduce FM-Fi, an innovative cross-modal framework engineered to translate the knowledge of vision-based FMs for enhancing RF-based HAR systems. FM-Fi involves a novel cross-modal contrastive knowledge distillation mechanism, enabling an RF encoder to inherit the interpretative power of FMs for achieving zero-shot learning. It also employs the intrinsic capabilities of FM and RF to remove extraneous features for better alignment between the two modalities. The framework is further refined through metric-based few-shot learning techniques, aiming to boost the performance for predefined HAR tasks. Comprehensive evaluations evidently indicate that FM-Fi rivals the effectiveness of vision-based methodologies, and the evaluation results provide empirical validation of FM-Fi's generalizability across various environments. © 2024 Copyright is held by the owner/author(s).

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Socialized Learning: A Survey of the Paradigm Shift for Edge Intelligence in Networked systems

引用

IEEE Communications Surveys and Tutorials 2024年第3期27卷 2085-2128页

作者： Wang, Xiaofei Zhao, Yunfeng Qiu, Chao Hu, Qinghua Leung, Victor C. M. Tianjin University College of Intelligence and Computing Tianjin300072 China Shenzhen518000 China Shenzhen MSU-BIT University Artificial Intelligence Research Institute Shenzhen518172 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China The University of British Columbia Department of Electrical and Computer Engineering VancouverV6T 1Z4 Canada

Amidst the robust impetus from artificial intelligence (AI) and big data, edge intelligence (EI) has emerged as a nascent computing paradigm, synthesizing AI with edge computing (EC) to become an exemplary solution for unleashing the full potential of AI services. Nonetheless, challenges in communication costs, resource allocation, privacy, and security continue to constrain its proficiency in supporting services with diverse requirements. In response to these issues, this paper introduces socialized learning (SL) as a promising solution, further propelling the advancement of EI. SL is a learning paradigm predicated on social principles and behaviors, aimed at amplifying the collaborative capacity and collective intelligence of agents within the EI system. SL not only enhances the system's adaptability but also optimizes communication, and networking processes, essential for distributed intelligence across diverse devices and platforms. Therefore, a combination of SL and EI may greatly facilitate the development of collaborative intelligence in the future network. This paper presents the findings of a literature review on the integration of EI and SL, summarizing the latest achievements in existing research on EI and SL. Subsequently, we delve comprehensively into the limitations of EI and how it could benefit from SL. Special emphasis is placed on the communication challenges and networking strategies and other aspects within these systems, underlining the role of optimized network solutions in improving system efficiency. Based on these discussions, we elaborate in detail on three integrated components: socialized architecture, socialized training, and socialized inference, analyzing their strengths and weaknesses. Finally, we identify some possible future applications of combining SL and EI, discuss open problems and suggest some future research, with the hope of arousing the research community's interest in this emerging and exciting interdisciplinary field. © 1

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Deepfake Image Verification using DCNN with MobileNetV2 3

Deepfake Image Verification using DCNN with MobileNetV2

引用

3rd IEEE Delhi Section Flagship Conference, DELCON 2024

作者： Pujari, Jeevana Jyothi Bikku, Thulasi Prasanna, Kamepalli S. L. Kocherlakota, Sarvani Gupta, Nancy Anitha, Raju School of Computer Science and Engineering Vellore Institute of Technology Department of Database Systems Tamil Nadu Vellore India Amrita School of Computing Amaravati Amrita Vishwa Vidyapeetham Andhra Pradesh Amaravati India Amrita School of Business Amrita Vishwa Vidyapeetham Department of Business Andhra Pradesh Amaravati India School of Computer Science and Engineering Vellore Institute of Technology Department of Computer Science Core Tamil Nadu Vellore India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Guntur India

ISBN: (纸本)9798331518592

In this contemporary era we find so many things happening around us. They may or may not be rational, but we accept them and go on the path they show without knowing who is behind all that. This all is done by communication channels that make use of Artificial Intelligence to come up with content that looks as if some human being has done but it is a few lines of code that generate that content called Deepfake. This technology has been a boon for entertainment, fiction, art, etc. From our study, we found that there is research that found a deep fake image detection machine. This machine can adequately detect any changes made in the image. This has helped us go a bit closer to our goal by giving us creative ideas that ensure more authenticity and integrity of media. We can achieve our goal by using various fields of Deep Learning and computer Vision. DCNNs and MobileNetV2 have strong object detection identification and classification abilities and are perfect tools to help us get rid of the deepfake menace. Since technology is rapidly changing it brings new challenges with it. So, to cope with the ongoing challenges our system would have self-learning abilities and would effectively handle any deepfake methods and strategies. This system would serve as a mother to many other advanced deepfake detection systems that safeguard our visual media. Our target is to build a flexible, easy-to-use system that can effectively work in different environments and in collaboration with other software applications. These models would dominate deepfake expansion with 99% accuracy. Thus, our work would play a great role in protecting our data and help provide a safe and secure environment for every user. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Review of Algorithms's Complexities on Different Valued Sorted and Unsorted Data

A Review of Algorithms's Complexities on Different Valued So...

引用

2023 International Conference on IT and Industrial Technologies, ICIT 2023

作者： Shabbir, Attia Majeed, Asad Iftikhar, Mahnoor Ali, Raja Hashim Arshad, Usama Shabbir, Muhammad Zeeshan Zeeshan Ijaz, Ali Ali, Nisar Aftab, Ali Gik Institute of Engg. Sciences & Technology Faculty of Computer Science & Engineering Topi Pakistan University of Europe for Applied Sciences Dept. of Technology & Software Engineering Berlin Germany Department of Electrical Engineering Lahore Pakistan University of Regina Faculty of Electronic Systems Engineering Regina Canada

ISBN: (纸本)9798350315974

Sorting and searching are critical processes for effecttive data analysis. In this paper, we evaluate the performance of various sorting and searching algorithms and compare their time and space complexities on both sorted and unsorted data. The algorithms we analyzed include six common sorting algorithms (insertion, radix, bucket, merge, bubble, and quick sort) and three search algorithms (linear, binary, and jump search). The results of our study provide insights into the best algorithms to use for different input sizes and types of data. It was found that for small input sizes, all algorithms perform similarly, but for larger input sizes, insertion and radix sorts are better for time complexity while bubble sort is better for space complexity. Additionally, jump search outperformed linear and binary search algorithms in both time and space complexity. Besides, difference between time and space complexity of sorted and unsorted data was significant. © 2023 IEEE.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

TMRE:Novel Algorithm for Computing Daily Reference Evapotranspiration Using Transformer-Based Models

引用

computers, Materials & Continua 2025年第5期83卷 2851-2864页

作者： Bushra Tayyaba Muhammad Usman Ghani Khan Talha Waheed Shaha Al-Otaibi Tanzila Saba National Center of Artificial Intelligence(NCAI) Al Khwarizmi Institute of Computer Sciences(KICS)Lahore54890Pakistan Department of Computer Science University of Engineering and Technology LahoreLahore54890Pakistan Artificial Intelligence&Data Analytics Lab Prince Sultan UniversityRiyadh11586Saudi Arabia Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia

Reference Evapotranspiration(ETo)iswidely used to assess totalwater loss between land and atmosphere due to its importance in maintaining the atmospheric water balance,especially in agricultural and environmental *** estimation of ETo is challenging due to its dependency onmultiple climatic variables,including temperature,humidity,and solar radiation,making it a complexmultivariate time-series *** machine learning and deep learning models have been applied to forecast ETo,achieving moderate ***,the introduction of transformer-based architectures in time-series forecasting has opened new possibilities formore precise ETo *** this study,a novel algorithm for ETo forecasting is proposed,focusing on four transformer-based models:Vanilla Transformer,Informer,Autoformer,and FEDformer(Frequency Enhanced Decomposed Transformer),applied to an ETo dataset from the Andalusian *** novelty of the proposed algorithm lies in determining optimized window sizes based on seasonal trends and variations,which were then used with each model to enhance prediction *** custom window-sizing method allows the models to capture ETo’s unique seasonal patterns more ***,results demonstrate that the Informer model outperformed other transformer-based models,achievingmean square error(MSE)values of 0.1404 and 0.1445 for forecast windows(15,7)and(30,15),*** Vanilla Transformer also showed strong performance,closely following the *** findings suggest that the proposed optimized window-sizing approach,combined with transformer-based architectures,is highly effective for ETo *** novel strategy has the potential to be adapted in othermultivariate time-series forecasting tasks that require seasonality-sensitive approaches.

关键词： Reference evapotranspiration ETo transformer informer autoformer FEDformer timeseries forecasting self-attention

来源：评论

学校读者我要写书评

暂无评论

Multi-View Incongruity Learning for Multimodal Sarcasm Detection 31

Multi-View Incongruity Learning for Multimodal Sarcasm Detec...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Guo, Diandian Cao, Cong Yuan, Fangfang Liu, Yanbing Zeng, Guangjie Yu, Xiaoyan Peng, Hao Yu, Philip S. Institute of Information Engineering Chinese Academy of Sciences China School of Cyber Security University of Chinese Academy of Sciences China State Key Laboratory of Software Development Environment Beihang University China School of Computer Science and Technology Beijing Institute of Technology China Department of Computer Science University of Illinois Chicago United States

ISBN: (纸本)9798891761964

Multimodal sarcasm detection (MSD) is essential for various downstream tasks. Existing MSD methods tend to rely on spurious correlations. These methods often mistakenly prioritize non-essential features yet still make correct predictions, demonstrating poor generalizability beyond training environments. Regarding this phenomenon, this paper undertakes several initiatives. Firstly, we identify two primary causes that lead to the reliance of spurious correlations. Secondly, we address these challenges by proposing a novel method that integrate Multimodal Incongruities via Contrastive Learning (MICL) for multimodal sarcasm detection. Specifically, we first leverage incongruity to drive multi-view learning from three views: token-patch, entity-object, and sentiment. Then, we introduce extensive data augmentation to mitigate the biased learning of the textual modality. Additionally, we construct a test set, SPMSD, which consists potential spurious correlations to evaluate the the model's generalizability. Experimental results demonstrate the superiority of MICL on benchmark datasets, along with the analyses showcasing MICL's advancement in mitigating the effect of spurious correlation. © 2025 Association for Computational Linguistics.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

XMeta-OS: A Conceptual Framework for Unified Resource Management in Distributed Edge-Cloud Environments 1

引用

3rd International Conference on Advances in Computing Research, ACR 2025

作者： Zacharioudakis, Eleftherios Kakoulli, Elena Evripidou, Salomi Intelligent Systems Laboratory Department of Computer Science Neapolis University Pafos Pafos Cyprus National Technical University of Ukraine Igor Sikorsky Kyiv Polytechnic Institute Kyiv Ukraine Electrical Engineering and Computer Engineering and Informatics Cyprus University of Technology Limassol Cyprus

ISBN: (数字)9783031876479

ISBN: (纸本)9783031876462

This paper introduces XMeta-OS, a meta-operating system specially designed with Linux as its foundation to unify and optimize resource management for the distributed edge-cloud when dynamic use of GPU resources is possible. This approach offer a new GPU abstraction layer and dynamic edge-cloud allocation model that offer enhanced flexibility and resource utilization over existing systems like Kubernetes and OpenStack. By using likely sensitive data, the model applied cloud-pushed deployment model. XMeta-OS manages computer resources in real-time. Therefore, fulfilling high performance various needs. It allocates CPU and GPU in real-time to workloads requiring massive parallel processing, such as machine learning, scientific simulations, real-time data analytics, and transportation tasks. Fabrication in the laboratory of an edge-cloud environment can help to assess the scalability, fault tolerance and efficiency of the system. It showcases the overall architectural design of XMeta-OS. Changes to the kernel and security solutions for safe and effective distribution are suggested. This article presents the design of the XMeta-OS. The future of XMeta-OS entails usage and testing with which we see latency, energy, computation and other such measurements in labs. XMeta-OS is a solution to cost performance, emerging application, large-scale edge-cloud deployments, and distributed GPU-enabled infrastructures. Meta-Operating System in Edge-Cloud Continuum for dynamic resource management of GPU. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Cluster computing

来源：评论

学校读者我要写书评

暂无评论

Autoencoder and Teaching-learning-based Optimizer for Mobile Edge Computing System Optimization Problems

Autoencoder and Teaching-learning-based Optimizer for Mobile...

引用

2023 IEEE International Conference on systems, Man, and Cybernetics, SMC 2023

作者： Xu, Dian Zhou, Mengchu Yuan, Haitao Institute of Systems Engineering Macau University of Science and Technology Macao China New Jersey Institute of Technology Department of Electrical and Computer Engineering Newark United States School of Automation Science and Electrical Engineering Beihang University Beijing China

ISBN: (纸本)9798350337020

By using an autoencoder as a dimension reduction tool, an Autoencoder-embedded Teaching-Learning Based Optimization (ATLBO) has been proved to be effective in solving high-dimensional computationally expensive problems through several widely used function problems. However, the following two crucial issues have not been resolved, 1) ATLBO should be verified by solving real-life optimization problems;and 2) how autoencoder parameters and structures impact AEO's performance. In this work, ATLBO is verified by an energy consumption minimization problem (ECM) in mobile edge computing systems. To design an effective autoencoder for ATLBO, this work proposes a parameter tuning optimization strategy for autoencoders. By using the proposed Autoencoder Parameter Tuning (APT) strategy, ATLBO can enjoy higher robustness than those without it. The experimental results show that it is three to six times better than state-of-the-art methods in solving ECM. We consider the strategy-induced overhead and take the execution time as the primary criterion to evaluate them. In addition, the experimental results show that, against the conventional wisdom that higher-accuracy auto encoders bring higher system performance, lower-accuracy ones can actually assist ATLBO in locating the best solutions. This work promotes a novel application of autoencoders in optimization theory and practice. © 2023 IEEE.

关键词： autoencoder Autoencoder-embedded teaching-learning based optimization (ATLBO) High-dimensional expensive problems (HEPs) Mobile edge computing systems

来源：评论

学校读者我要写书评

暂无评论

Hybrid Technique for Constructing Footprint Extraction System from Satellite Imaginary 2

Hybrid Technique for Constructing Footprint Extraction Syste...

引用

2nd IEEE International Conference on Networking and Communications, ICNWC 2024

作者： Raghavendran, N. Menaga, P. Prabu, V. Vignesh Manimaran, V. Robinson, Y. Harold Ramanan, K. Francis Xavier Engineering College Department of Computer Science and Engineering Tamil Nadu Tirunelveli India Rajalakshmi Engineering College Department Of Computer Science & Business Systems Tamil Nadu Chennai India Bannari Amman Institute of Technology Department of Civil Engineering Tamil Nadu India National Engineering College Department of Information Technology Tamil Nadu Kovilpatti India NPR College of Engineering and Technology Natham Department of Computer Science and Engineering Tamil Nadu Dindigul India

ISBN: (纸本)9798350365269

The building extraction of the footprint from the satellite imagination has been a research problem that needs to be solved efficiently. The hybrid semantic segmentation framework is used to increase the footprint extraction system as the Inria Aerial Image Labeling Dataset is involved in improving the extraction of the footprint, the proposed technique is framed with the CGAN model and Mask RCNN for utilizing the instance segmentation which manages the data augmentation and semantic segmentation process. The performance evaluation shows that the proposed technique has an improved F1 score and accuracy as the effect of every functionality for the footprint extraction has been analyzed subsequently. © 2024 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of vehicle type recognition system based on language large model

Design and implementation of vehicle type recognition system...

引用

Internet of Things, Automation and Artificial Intelligence (IoTAAI), International Conference on

作者： Xiang Liu Yikuan Zhang Computer Science Department Software Engineering Institute of GuangZhou Guangzhou China Department of Electronics Software Engineering Institute of GuangZhou Guangzhou China

ISBN: (数字)9798350386974

ISBN: (纸本)9798350386981

Using large language model to generate vehicle type recognition algorithm can reduce the burden of developers and realize the rapid development of projects. In this paper, LangChain large model interface provided by Baidu Qianfan large-scale platform is used to realize the auxiliary development of vehicle type recognition. With the support of large model, the training and testing model of vehicle type recognition is constructed by using deep learning method, and the fine-grained vehicle image classification and recognition system is realized. At present, the ResNet50 Enhance MEAL2 model is used for classification recognition, supporting 1748 types of vehicle classification and recognition. In the Car-Dataset of vehicle data, the Accuracy of the training set is about 95.9%, and the Accuracy of the test set is about 84.3%. The backbone network can support Googlenet. ResNet [18, 34, 50], Inception_v3, Mobilenet_v2 and other common models. The use of language large model in this project improves the efficiency of development.

关键词： Training Image recognition Accuracy Large language models Web and internet services Neural networks Internet of Things Testing Residual neural networks Image classification

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：