检索结果-内蒙古大学图书馆

Annual Symposium on Logic in Computer science

作者： Jelle Hellings Marc Gyssens Jan Van Den Bussche Dirk Van Gucht Department of Computing and Software McMaster University Hamilton Canada Data Science Institute Hasselt University Diepenbeek Belgium Luddy School of Informatics Computing and Engineering Indiana University Bloomington IN USA

We consider the class of finite, rooted, unranked, unordered, node-labeled trees. Such trees are represented as structures with only the parent-child relation, in addition to any number of unary predicates for node labels. We prove that every unary first-order query over the considered class of trees is already expressible in two-variable first-order logic with counting. Somewhat to our surprise, we have not seen this result being conjectured in the extensive literature on logics for trees. Our proof is based on a global variant of local equivalence notions on nodes of trees. This variant applies to entire trees, and involves counting ancestors of locally equivalent nodes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Implementation of Topic Modeling in the Analysis of Topic Trends in SDGs Goal 6 Research

Implementation of Topic Modeling in the Analysis of Topic Tr...

引用

International Conference on Electrical Engineering and Informatics, ICEEI

作者： Fathonah Illia Rani Nooraeni Lya Hulliyyatus Suadaa Department of Statistical Computing Politeknik Statistika STIS Jakarta Indonesia Data Science Research Unit Politeknik Statistika STIS Jakarta Indonesia

SDGs Goal 6 is one of the crucial objectives within the SDGs framework, making fulfilling this goal highly significant as it determines the achievement of other SDGs. As a serious global issue, this goal can be addressed through scientific research and innovation. However, research on this goal is often not well-known, leading to a need for more connection between the academic world and practitioners in implementing available solutions. Consequently, identifying critical pathways through scientific research is essential to attain this goal effectively. One of the expedient approaches is the utilization of topic modeling, which also facilitates the analysis of research topic trends related to SDGs Goal 6. This study employs topic modeling on data sourced from SemanticScholar using the BERTopic method, which captures the comprehensive context of research articles. The research results indicate that studies focusing on SDGs Goal 6 are interconnected with other SDGs. The default BERTopic model, chosen as the optimal model, illustrates that there is a prevailing topic tendency in target 6.3 related to water quality.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Active Large Language Model-based Knowledge Distillation for Session-based Recommendation

arXiv

引用

arXiv 2024年

作者： Du, Yingpeng Sun, Zhu Wang, Ziyan Chua, Haoyan Zhang, Jie Ong, Yew-Soon College of Computing and Data Science Nanyang Technological University Singapore Information Systems Technology and Design Singapore University of Technology and Design Singapore Department of Computer Science and Engineering Yonsei University Korea Republic of

Large language models (LLMs) provide a promising way for accurate session-based recommendation (SBR), but they demand substantial computational time and memory. Knowledge distillation (KD)-based methods can alleviate these issues by transferring the knowledge to a small student, which trains a student based on the predictions of a cumbersome teacher. However, these methods encounter difficulties for LLM-based KD in SBR. 1) It is expensive to make LLMs predict for all instances in KD. 2) LLMs may make ineffective predictions for some instances in KD, e.g., incorrect predictions for hard instances or similar predictions as existing recommenders for easy instances. In this paper, we propose an active LLM-based KD method in SBR, contributing to sustainable AI. To efficiently distill knowledge from LLMs with limited cost, we propose to extract a small proportion of instances predicted by LLMs. Meanwhile, for a more effective distillation, we propose an active learning strategy to extract instances that are as effective as possible for KD from a theoretical view. Specifically, we first formulate gains based on potential effects (e.g., effective, similar, and incorrect predictions by LLMs) and difficulties (e.g., easy or hard to fit) of instances for KD. Then, we propose to maximize the minimal gains of distillation to find the optimal selection policy for active learning, which can largely avoid extracting ineffective instances in KD. Experiments on real-world datasets show that our method significantly outperforms state-of-the-art methods for SBR. Copyright © 2024, The Authors. All rights reserved.

关键词： Active learning

来源：评论

学校读者我要写书评

暂无评论

LossControl: Defending Membership Inference Attacks by Controlling the Loss

LossControl: Defending Membership Inference Attacks by Contr...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Bo Yang Hongwei Yang Renhao Lu Hui He Weizhe Zhang Haoyu He Rahul Yadav Faculty of Computing Harbin Institute of Technology Harbin China Department of Data Science and AI Faculty of Information Technology Monash University Melbourne Australia College of Computer Science and Technology Harbin Engineering University Harbin China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Machine learning models are vulnerable to membership inference attacks (MIAs), where adversaries attempt to predict whether specific samples are part of the model’s training set. Previous studies have demonstrated a strong correlation between the distinguishability of training and testing loss distributions and the model’s susceptibility to MIAs. Motivated by existing results, we propose a novel training framework called LossControl, which focuses on manipulating loss to mitigate privacy leaks. In LossControl, we first utilize Soft-label Training to replace the general learning process, which facilitates model training while improving generalization. Next, we monitor overfitting samples during the training process and prevent further loss reduction by applying our designed Loss Ascent to these samples without sacrificing model performance. Through extensive evaluations across four diverse datasets (including images, medical data, and transaction records), our method consistently outperforms defense mechanisms against state-of-the-art attacks and achieves optimal model performance in most experiments, demonstrating LossControl’s superior resilience against MIAs and its ability to strike an unparalleled balance between privacy and utility.

关键词： Training Privacy Process control Machine learning Predictive models Signal processing Speech processing Testing Resilience Overfitting

来源：评论

学校读者我要写书评

暂无评论

Network Traffic Prediction with Attention-based Spatial-Temporal Graph Network

Network Traffic Prediction with Attention-based Spatial-Temp...

引用

IEEE Workshop on High Performance Switching and Routing

作者： Yufei Peng Yingya Guo Run Hao Junda Lin Department of Computer and Data Science Fuzhou University Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University

Network traffic prediction plays a significant role in network management. Previous network traffic prediction methods mainly focus on the temporal relationship between network traffic, and used time series models to predict network traffic, ignoring the spatial information contained in traffic data. Therefore, the prediction accuracy is limited, especially in long-term prediction. To improve the prediction accuracy of the dynamic network traffic in the long term, we propose an Attention-based Spatial-Temporal Graph Network (ASTGN) model for network traffic prediction to better capture both the temporal and spatial relations between the network traffic. Specifically, in ASTGN, we exploit an encoder-decoder architecture, where the encoder encodes the input network traffic and the decoder outputs the predicted network traffic sequences, integrating the temporal and spatial information of the network traffic data through the Spatio-Temporal Embedding module. The experimental results demonstrate the superiority of our proposed method ASTGN in long-term prediction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Survey on Deep Learning for Enhanced Node Position Prediction in Vehicular Ad-Hoc Networks

A Comprehensive Survey on Deep Learning for Enhanced Node Po...

引用

Ubiquitous computing and Intelligent Information Systems (ICUIS), International Conference on

作者： B.Deena Divya Nayomi V. Jyothsna Department of Computer Science and Engineering School of Computing MOHAN BABU UNIVERSITY (Erstwhile Sree Vidyanikethan Engineering College (Autonomous)) Tirupati Andhra Pradesh India Department of Data Science School of Computing MOHAN BABU UNIVERSITY (Erstwhile Sree Vidyanikethan Engineering College (Autonomous)) Tirupati Andhra Pradesh India

ISBN: (数字)9798331529635

ISBN: (纸本)9798331529642

This research study presents a thorough examination of the application of deep learning techniques in enhancing node position prediction within Vehicular Ad-Hoc Networks (VANETs). As VANETs become increasingly integral to the development of intelligent transportation systems, accurate and efficient node position prediction emerges as a critical component for ensuring optimal network functionality, safety, and traffic management. This paper explores the performance and adaptability of multiple deep learning models in the dynamic and complicated VANET environment, such as Graph Neural Networks (GNNs), Recurrent Neural Networks (RNNs), and Convolutional Neural Networks (CNNs). We provide a detailed analysis of the existing literature, highlighting the strengths and limitations of different deep learning approaches in handling the high mobility, variable density, and recurrently changing topology of vehicular networks. Furthermore, the survey discusses the integration of contextual information, such as environmental factors and road conditions, into the prediction models, enhancing their accuracy and reliability. We also explore the implications of advanced methodologies like Transfer Learning and Federated Learning in this domain. In addition to providing insights into future research paths, the paper finishes with an assessment of the difficulties encountered in the practical application of these models, including data privacy and computing limits. The goal of this thorough investigation is to provide a roadmap for future developments in node location prediction in VANETs, making it an invaluable tool for scholars and professionals working in the subject of intelligent transportation systems.

关键词： Deep learning Surveys Accuracy Network topology Transfer learning Vehicular ad hoc networks Topology Safety Security Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

AIGC-Driven Real-Time Interactive 4D Traffic Scene Generation in Vehicular Networks

引用

IEEE Network 2025年

作者： Li, Xiaolong Deng, Ruiting Wei, Jianhao Wu, Xin Chen, Jiayuan Yi, Changyan Cai, Jun Niyato, Dusit Shen, Xuemin Hunan University of Technology and Business School of Computer Science China Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology China Concordia University Department of Electrical and Computer Engineering Montreal Canada Nanyang Technological University College of Computing and Data Science Singapore University of Waterloo Department of Electrical and Computer Engineering Canada

Real-time, interactive 4D traffic scene generation enables rapid digital twinning of traffic scenarios, improving management and decision-making in intelligent transportation systems. However, current text-to-video models, such as Sora, struggle to maintain the temporal coherence of traffic elements and interact with dynamic environments and users when generating 4D scenes. This article introduces a novel cloud-edge-terminal collaborative framework that leverages Artificial Intelligence-Generated Content (AIGC) in vehicular networks to tackle these challenges, ensuring long-term coherence and improved interactivity. The framework presents a comprehensive architecture for real-time interactive 4D scene generation, encompassing data collection, management, model pre-training, fine-tuning, and inference. We examine key design requirements and challenges, demonstrating that our microservice-based framework enables the system to generate and update 4D traffic scenes in real time, effectively responding to traffic data and user inputs. To the best of our knowledge, this is the first successful implementation of real-time, interactive 4D traffic scene generation. Performance evaluations show the superiority of our framework, powered by microservice-based code fine-tuning, over traditional frameworks. Finally, we discuss future research directions to enhance AIGC-driven 4D traffic scene generation. © 1986-2012 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Location Recommendations Based on Multi-view Learning and Attention-Enhanced Graph Networks 8th

Location Recommendations Based on Multi-view Learning and ...

引用

8th China National Conference on Big data and Social computing, BDSC 2023

作者： Chen, Junxin Lin, Kuijie Chen, Xiang Wang, Xijun Hsu, Terng-Yin School of Electronics and Information Technology Sun Yat-sen University Guangzhou511400 China Guangdong Provincial Key Laboratory of Big Data Computing The Chinese University of Hong Kong Shenzhen518000 China Department of Computer Science National Chiao Tung University Hsinchu30013 Taiwan

ISBN: (纸本)9789819939244

Personalized location recommendation plays a very important role in location-based social networks, from which both users and service providers can benefit from. In spite of the significant endeavors that have been made towards acquiring knowledge on location attributes and user inclinations, it is still faced with serious data sparsity problems. In this paper, we propose a personalized location recommendation model based on graph neural networks with multi-view learning to obtain effective representations of mobile users and locations from different heterogeneous graphs. We also design an attention-enhanced mechanism to explore the implicit interactions between mobile users and locations themselves. Conducting adequate comparative experiments on two real-world telecom datasets has demonstrated that our model achieves superior performance. Additionally, our model has been proven effective in addressing data sparsity issues. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

A Novel Pipeline for Compressing Image Buffers in Remote Education Video Conferencing using Harris Corner Detection and Pixel Map Array

A Novel Pipeline for Compressing Image Buffers in Remote Edu...

引用

International Conference on Electronics, Communication and computing Technologies (ICECCT)

作者： Gita Alekhya Paul Ansh Sharma Yashvardhan Jagnani Abhishek Saxena P Supraja Networking and Communications Department SRM Institute of Science and Technology Chennai India Computing Technologies Department SRM Institute of Science and Technology Chennai India Data Science and Business Systems Department SRM Institute of Science and Technology Chennai India

The COVID-19 pandemic has compelled educational institutions worldwide to shift to remote online education. Addressing the growing trend, an Oxford University Press report titled ‘Addressing the Deepening Digital Divide’ states that poor digital access is the most significant barrier to digital learning according to 68 percent of academicians. Students in many remote parts of India frequently have access to limited bandwidth internet, which is insufficient for the modern standards of network-hogging online video conference software solutions. This paper provides an algorithmic compression of image buffers to aid low-cost remote online video education. This compression can be done by translating the teacher's blackboard images to pixel arrays projected on a canvas on the student's dashboard while the instructor constantly communicates via real-time voice. The image is first converted to grayscale and dilated with a square kernel. Using Harris Corner Detector, probable board corners are identified and compared to a geometrical center of the points and the corners recovered by cornerSubPix. An adaptive threshold is employed, distinguishing the board's contents from the backdrop on the cropped picture based on the recovered points. The pixel-mapped array is then transmitted to the students through the webRTC real-time protocol, which includes support for two-way audio, allowing the teacher to deliver lectures. Using Canvas API on the application front-end, the array is projected onto the student's device as a dot matrix display. This paper has achieved an effective rate in the video transmission format, aiding online remote education on low-bandwidth network devices.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of A Multipurpose Healthcare Mobile App Using JAVA

Development of A Multipurpose Healthcare Mobile App Using JA...

引用

IEEE International Conference on System, Computation, Automation and Networking (ICSCAN)

作者： R K Pongiannan S. Nikkath Bushra Syed Ismail Abdul Lathif Saahil Pradhan R Brindha J Franklin Department of Computing Technologies SRM Institute of Science and Technology Kattankulathur India Data science and business systems School of computing SRM Institute of Science and Technology Kattankulathur India Department of Computational Intelligence SRM Institute of Science and Technology Kattankulathur India Department of Electrical and Electronics Engineering SRM Institute of Science and Technology Kattankulathur India

Health care has become an essential part of present human life. The preliminary requirement to select the basic information about medical facilities through a mobile app will serve the needs of the common people. This paper presents an integrated mobile app developed using JAVA. This app is user-friendly in terms of login, registration, and bookings. This caters to the facility to select information regarding doctors, medical lab facilities, pharmacy details, and health articles. This app will provide communication.

关键词：

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：