检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Li, Jiaxing Zhang, Xiaotong Zhang, Ke Kong, Youyong Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing School of Computer Science and Engineering Southeast University Jiangsu Province Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing China

Graph neural networks (GNNs) are powerful architectures for graph representation learning. However, GNNs based on message-passing cannot make fully use of the valuable long-range dependencies in graph-structured data. Recently, researchers have designed Transformer-based graph learning models to expand the receptive field to capture long-range dependencies between pairwise nodes. Although the preliminary performance of the graph Transformer is encouraging and even surpasses GNNs, the quadratic complexity of the self-attention leads to much longer inference time than GNNs, which limits the deployment in practical applications. To address this issue, we propose a knowledge distillation framework to transfer long-range dependencies captured by graph Transformer to GNNs. Our framework extracts knowledge from a pre-trained graph Transformer teacher and transfer it to a GNN-based student. To better transfer the long-range dependencies, we further design a long-range dependencies transfer module, in which the intermediate graph representations of the graph Transformer and GNNs are extracted as distributions. Then we minimize the distance between the two distributions, thereby achieving the long-range dependencies transfer more accurately. The proposed method can be extended to any graph Transformer and GNNs. We evaluate our proposed method on a large number of graph classification benchmark datasets with different GNN-based baselines, and the experimental results demonstrate that our method can obtain the performance close to graph Transformer with faster inference speed and smaller memory usage. © 2024, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Test-Time Training with Invariant Graph Learning for Out-of-Distribution Generalization

SSRN

引用

SSRN 2024年

作者： Pi, Li Li, Jiaxing Song, Lei Yang, Guanyu Chen, Yang Kong, Youyong Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Jiangsu Province Nanjing China

Graph Neural Networks (GNNs) frequently do not perform optimally on out-of-distribution (OOD) data. Previous research on graph OOD generalization suggests extracting invariant subgraphs, which provide crucial categorical information even under test distributions. However, this strategy is not optimal due to two issues. Firstly, there is a significant distribution shift between the test and training sets, which may result in incorrect invariant subgraphs being extracted during the test phase. Secondly, the extraction of subgraphs can lead to the loss of important structural information. To address these issues, we propose a novel two-stage training paradigm named \textbf{I}nvariant \textbf{G}raph \textbf{T}est-\textbf{T}ime \textbf{T}raining (\textbf{IGT3}), which uses the training paradigm called Test-Time Training (TTT). We also propose invariant graph recognition to learn key parts of the graph without destroying the original graph structure. In addition, we introduce a multi-level graph contrastive learning method as an auxiliary self-supervised task. To prevent TTT failure, we use the feature constraint to enhance the robustness of the training process. We conduct experiments on seven common graph classification OOD benchmark datasets. The results demonstrate that IGT3 outperforms state-of-the-art (SOTA) methods by an average of 4.2\%, confirming the effectiveness of each module. The paper code is available at https://***/r/IGT3-3281/ © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Offloading Algorithm for Edge Computing Tasks Based on Energy Optimization 8

Offloading Algorithm for Edge Computing Tasks Based on Energ...

引用

8th IEEE International Conference on Smart Cloud, SmartCloud 2023

作者： Gao, Xing Gu, Haonan Liu, Fang Hu, Wei Wuhan City College Wuhan China College of Computer Science and Technology Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China

ISBN: (纸本)9798350313505

Current research in computation offloading encompasses various aspects, including task partitioning and allocation, resource management, communication, and data management. This paper focuses on developing new algorithms and techniques to enhance the efficiency and effectiveness of the offloading process while addressing challenges arising from dynamic and heterogeneous mobile environments. Researchers are also examining the trade-off between offloading benefits like improved performance and energy efficiency, and the associated overhead costs such as communication and data management. This paper proposes an optimization strategy for computational offloading to enhance the Grey Wolf algorithm. The solution aims to quickly optimize system energy consumption while considering the arithmetic power constraint of the mobile edge computing server and time delay constraints. Simulation experiments demonstrate that the algorithm in this paper significantly outperforms the traditional Grey Wolf and PSO algorithms in terms of both performance and computational speed. ©2023 IEEE.

关键词： information management

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Multi-Trip Routing for Municipal Solid Waste Collection by Contribution-Based Adaptive Particle Swarm Optimization

引用

Complex System Modeling and Simulation 2023年第3期3卷 202-219页

作者： Xiaoning Shen Hongli Pan Zhongpei Ge Wenyan Chen Liyan Song Shuo Wang Collaborative Innovation Center of Atmospheric Environment and Equipment Technology and also with the Jiangsu Key Laboratory of Big Data Analysis TechnologySchool of AutomationNanjing University of Information Science and TechnologyNanjing 210044China School of Automation Nanjing University of Information Science and TechnologyNanjing 210044China Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation the Department of Computer Science and EngineeringSouthern University of Science and TechnologyShenzhen 518055China School of Computer Science University of BirminghamBirminghamB152TTUK

Waste collection is an important part of waste management *** costs and carbon emissions can be greatly reduced by proper vehicle ***,each vehicle can work again after achieving its capacity limit and unloading the *** this,an energy-efficient multi-trip vehicle routing model is established for municipal solid waste collection,which incorporates practical factors like the limited capacity,maximum working hours,and multiple trips of each *** both economy and environment,fixed costs,fuel costs,and carbon emission costs are minimized *** solve the formulated model effectively,contribution-based adaptive particle swarm optimization is *** strategies named greedy learning,multi-operator learning,exploring learning,and exploiting learning are specifically designed with their own searching *** assessing the contribution of each learning strategy during the process of evolution,an appropriate one is selected and assigned to each individual adaptively to improve the searching efficiency of the ***,an improved local search operator is performed on the trips with the largest number of waste sites so that both the exploiting ability and the convergence accuracy of the algorithm are *** of the proposed algorithm is tested on ten waste collection instances,which include one real-world case derived from the Green Ring Company of Jiangbei New District,Nanjing,China,and nine synthetic instances with increasing scales generated from the commonly-used capacitated vehicle routing problem benchmark *** with five state-of-the-art algorithms show that the proposed algorithm can obtain a solution with a higher accuracy for the constructed model.

关键词： municipal solid waste collection energy conservation multi-trip contribution particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

An end-to-end instance segmentation method based on improved ConvNeXt V2

引用

International Journal of Wireless and Mobile Computing 2024年第4期26卷 384-392页

作者： Wang, Wenlu Sun, Ying Xu, Manman Bai, Dongxu Huang, Li Zou, Chunlong Chen, Baojia Tang, Dalai Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education Wuhan University of Science and Technology Hubei Wuhan China Research Centre for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Hubei Wuhan China Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of Science and Technology Hubei Wuhan China College of Computer Science and Technology Wuhan University of Science and Technology Hubei Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Hubei Wuhan China College of Mechanical Engineering Hubei University of Automotive Technology Hubei Shiyan China Hubei Key Laboratory of Hydroelectric Machinery Design and Maintenance China Three Gorges University Hubei Yichang China School of Computer Information Management Inner Mongolia University of Finance and Economics Hohhot China

In order to improve the efficiency of indoor mobile robots in locating and segmenting environmental instances, an instance segmentation method based on RTMDet is proposed. Firstly, the more powerful ConvNeXt V2 is used as the backbone network of the model, which improves the performance of the existing RTMDet model. Subsequently, NAS-FPN is used as a converged network to detect the network at any given time. Finally, AdamW is used as the model optimiser, which effectively solves the problem of excessive memory occupation when updating parameters and improves the performance of the model. The proposed method obtains the highest evaluation index in all cases. After training and testing on the Cityscapes data set, the recognition accuracy reaches 65.0%. © 2024 Inderscience Enterprises Ltd.

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Speech Lie Detection Algorithm Based on Multiple Features and Adaptive Threshold

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer Science 2025年第6期52卷 2015-2021页

作者： Zheng, Shuailong Tao, Huawei Yu, Hang Xi, Ji Zhu, Chunhua Wang, Xuemei Key Laboratory for Grain Information Processing and Control Henan Key Laboratory of Grain Storage Information Intelligent Perception and Decision Making Henan University of Technology Zhengzhou450001 China Computer Information Engineering Changzhou Institute of Technology Jiangsu213000 China

The limited number of labeled samples can significantly affect the accuracy of speech lie detection systems. However, semi-supervised algorithms have been shown to effectively improve detection performance under such constraints. To address this challenge, this paper proposes a semi-supervised speech lie detection algorithm that utilizes multiple features and adaptive thresholds. First, through comparative analysis, this paper identifies 312-dimensional acoustic features and 768-dimensional self-supervised features as the key elements of lie detection. Then, these acoustic features are processed using a bidirectional long short-term memory network (Bi-LSTM), which obtains comprehensive information by analyzing acoustic statistical features in both forward and backward directions. Subsequently, this paper develops a semi-supervised feature fusion module (BSFM) to extract deeper insights from basic features and achieves adaptive feature fusion through targeted training. In addition, based on a detailed analysis of the distribution characteristics of lie detection samples, this paper proposes an improved Freematch algorithm to better utilize unlabeled data. Experimental results show that the proposed algorithm outperforms most existing methods on the self-built H-Wolf dataset and the Columbia/SRI/Colorado Corpus (CSC). © (2025), (International Association of Engineers). All Rights Reserved.

关键词： Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Intra-Guided Dual-Energy Material Decomposition Method for Dual-Source CBCT Systems 46

Intra-Guided Dual-Energy Material Decomposition Method for D...

引用

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Zhong, Xinyun Lyu, Tianling Wu, Zhan Gao, Wei Xi, Yan Zhao, Wei Zhu, Wentao Chen, Yang Zhejiang Lab Hangzhou China First-Imaging Tech. Shanghai China Beihang University Beijing China Southeast University School of Computer Science and Engineering Laboratory of Image Science and Technology Nanjing China Southeast University Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Nanjing China

ISBN: (纸本)9798350371499

Dual-energy CBCT imaging plays a crucial role in advanced imaging applications due to its ability to quantify material components. Although there are multiple established systems for dual-energy imaging, they often come with high deployment costs. This study investigates the feasibility of dual-energy material decomposition on a less expensive dual-source CBCT system. Due to the specific geometry of dual-source CBCT, cone-beam (CB) artifacts seriously degrade the material decomposition quality when the direct inversion method is adopted. In this paper, a novel dual-source intra-guided material decomposition framework is proposed to suppress CB artifacts in the material maps. Firstly, a dual-source two-pass algorithm is developed for artifact pre-correction during image reconstruction. Then, the structure of small cone-angle regions from one X-ray source is utilized to guide cone beam artifact removal in large cone-angle regions from another source. Finally, direct matrix inverse material decomposition is applied to the filtered image. Extensive experiments have been conducted on the authentic human phantom and demonstrate that the proposed framework achieves excellent performance in cone beam artifact reduction compared to other methods, and significantly enhances the quality of the material maps. © 2024 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

IoT Service Description and Composition Method with Knowledge Graph

Journal of Network Intelligence

引用

Journal of Network Intelligence 2022年第4期7卷 1047-1065页

作者： Tang, Zheng-Yi Liu, Chuan Lian, Zhi-Zhu Wang, Jin-Shui Hossain, Md. Alamgir School of Computer Science and Mathematics Fujian University of Technology Xuefu South Road Fujian Province Fuzhou City350118 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Xiyuangong Road Fujian Province Fuzhou City350121 China Key Laboratory of Hunan Province for Mobile Business Intelligence Hunan University of Technology and Business Yuelu Road Hunan Province Changsha City410205 China Department of Management Hajee Mohammad Danesh Science and Technology University Dinajpur5200 Bangladesh

Service computing techniques have achieved remarkable results in solving the cohesiveness problem of Web applications and are therefore introduced into the IoT do-main to break the trend of inlining IoT systems. However, compared with the traditional Internet, IoT has richer elements and semantic connotations, so the existing service description framework needs to be improved and extended. In this paper, we propose an ontology description framework for IoT services, design corresponding inference rules, and give a storage method for IoT services by integrating the knowledge graph technology for the strongly associated characteristics of IoT services. On this basis, an algorithm for combining IoT services based on graph planning is proposed. The experimental results show that the proposed method in this paper can provide richer entity semantics and ef-fectively improve the efficiency and success rate of IoT service composition. © The Authors.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Adaptive Monitoring Optimization Based on Deep-Q-Network for Energy Harvesting Wireless Sensor Networks 12th

Adaptive Monitoring Optimization Based on Deep-Q-Network for...

引用

12th International Conference on Mobile Networks and Management, MONAMI 2022

作者： Bao, Xuecai Bian, Peilun Tan, Wenqun Xu, Xiaohua Nie, Jugen Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing Nanchang Institute of Technology Nanchang Jiangxi330099 China Jiangxi Provincial Technology Innovation Center for Ecological Water Engineering in Poyang Lake Basin Jiangxi330029 China

ISBN: (纸本)9783031324420

In order to improve the energy efficiency of environmental monitoring for energy harvesting wireless sensor networks (EH-WSNs) in remote areas and achieve energy-neutral operation, an adaptive monitoring and energy management optimization method of EH-WSNs based on deep Q network (DQN) algorithm is proposed. In this paper, aiming at EH-WSNs with single-hop cluster structure, we first present a more realistic energy model established by combining different climate characteristics. Then, the optimization model of maximizing long-term monitoring utility is formulated based on harvested energy constraints. We use deep Q network (DQN) to learn random and dynamic solar energy harvesting process on solar-powered sensor nodes and optimize the monitored performance of EH-WSNs through the replay memory mechanism and freezing parameter mechanism. Finally, we present an adaptive monitoring optimization method based DQN to achieve the long-term utility. Through simulation verification and comparative analysis, in different rainy weather environments, the proposed optimization algorithm has greatly improved in terms of average monitoring reward, monitoring interruption rate and energy overflow rate. Moreover, it also indicates that the proposed algorithm has effective adaptation to the random and dynamic solar energy arrival. © 2023, ICST Institute for computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Energy harvesting

来源：评论

学校读者我要写书评

暂无评论

Technical note: Error analysis of material-decomposition-based effective atomic number quantification method

引用

Medical Physics 2024年第1期51卷 419-427页

作者： Chen, Li Ji, Xu Wang, Zhe Chen, Yang Laboratory of Image Science and Technology the School of Computer Science and Engineering Southeast University Nanjing China Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing Southeast University Nanjing China Beijing Engineering Research Center of Radiographic Techniques and Equipment Institute of High Energy Physics Chinese Academy of Sciences Beijing China Jinan Laboratory of Applied Nuclear Science Jinan China Ministry of Education China

Background: The effective atomic number (Zeff) is widely applied to the identification of unknown materials. One method to determine the Zeff is material-decomposition-based spectral X-ray imaging. The method relies on certain approximations of the X-ray interaction cross-sections such as empirical model coefficients. The impact of such approximations on the accuracy of Zeff quantification has not been fully investigated. Purpose: To perform an error analysis of the material-decomposition-based Zeff quantification method and propose a coefficient calibration-in-groups method to improve the modeling accuracy and reduce the Zeff quantification error. Methods: The model of the material-decomposition-based Zeff quantification method relies on the dependence of the interaction cross-sections (σPE) on the atomic number Z and corresponding coefficient, that is, (Formula presented.). In this work, all the data is from the National Institute of Standards and technology (NIST) website. First, the coefficient m is calibrated through a logarithmic fitting method to quickly determine the m values for any certain energy and Zeff ranges. Then materials including elements and common compounds with Zeff ranging from 6–20 are selected as the objects whose effective atomic numbers are to be quantified. Different combinations of basis materials are applied to decompose the object materials and their quantification errors are analyzed. With the help of error analysis, the object materials are divided into high-error and low-error groups based on the decomposition coefficient ratio (Formula presented.), which is found to have a strong correlation with error, and their coefficients are calibrated in groups. Finally, the average errors of three m selection strategies: (1) using an empirical m value of 3.94, which is also considered a standard method;(2) using a single m value, which is calibrated through the logarithmic fitting method;(3) using different m values calibrated in groups, are

关键词： Atoms

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：