检索结果-内蒙古大学图书馆

IEEE International Conference on Networking, Sensing and Control

作者： Hongyun Wang Leilei Shi ZiXuan Han Lu Liu Xiang Sun Furqan Aziz School of Computer Science and communication Engineering Jiangsu University China Department of Computer Science University of Exeter Exeter UK School of Computing and Mathematical Sciences University of Leicester UK

ISBN: (数字)9798350365221

ISBN: (纸本)9798350365238

In current online education, Knowledge Tracing (KT) technology plays a pivotal role, in monitoring and updating students' evolving knowledge states throughout their educational journey. Previous knowledge tracing models like DKT and DKVMN, have made some progress in personalised learning. However, they fall short in fully capturing the dynamic changes in the learning process, including forgetting behaviour and individual learning gains. To address these issues, this paper introduces a novel knowledge tracing model named dynamic forgetting and enhanced gain mechanisms (DF-EGM), which builds on Deep-Irt. The model initially utilises a CART decision tree classifier to extract pre-classification labels by analyzing response times and learning abilities. Subsequently, the model incorporates forgetting factors and personalised learning gains. It introduces attempt counts and time intervals to simulate knowledge forgetting. and the realization of personalised learning gains is achieved through a deeply refined knowledge gain module. This module models the perceived difficulty of exercises by students and dynamically adjusts learning gains based on their answer performance and current knowledge state. Experiments on public datasets indicate that the DF-EGM model can more accurately track students' knowledge states.

关键词： Knowledge engineering Analytical models Education Sensors Time factors Decision trees Monitoring

来源：评论

学校读者我要写书评

暂无评论

QoE-aware Multicast-Unicast Transmission Scheme For Multi-UAV Assisted Virtual Reality Live Streaming Systems

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Chen, Xin Ren, Xueqi Jiao, Libo Dai, Xin Dong, Zhe Min, Geyong School of Computer Science Beijing Information Science and Technology University Beijing China The Department of Computer Science University of Exeter ExeterEX4 4QF United Kingdom

The growing complexity of the sixth-generation (6G) wireless networks has positioned artificial intelligence (AI) as a critical tool for radio resource management (RRM). However, the opacity of AI learning models undermines their trustworthiness, robustness, and interpretability, significantly impeding their application in network resource management for 6G scenarios. Establishing reliable edge intelligence (EI) is crucial for the future of various domains, particularly in virtual reality (VR). By leveraging EI, VR applications can better meet user demands, enhancing service experiences and reliability. The 360-degree video characteristics challenge existing VR transmission networks. We propose a unmanned aerial vehicle (UAV)-assisted joint multicast-unicast system to optimize user QoE by jointly optimizing UAV trajectories, user associations, quality requests, user pairing, and power allocation. To address this optimization problem, we first decompose it into inter-frame and intra-frame components, and propose a twin delayed deep deterministic policy gradient (TD3)based algorithm to tackle the inter-frame problem. After solving the inter-frame problem, we utilize the quantum particle swarm optimization (QPSO) algorithm and matching theory to address the intra-frame problem. Simulation results demonstrate that our proposed algorithm, significantly improves the QoE for users. © 2025 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

CLOG-CD: Curriculum Learning Based on Oscillating Granularity of Class Decomposed Medical Image Classification

引用

IEEE Transactions on Emerging Topics in Computing 2025年

作者： Abbas, Asmaa Gaber, Mohamed Medhat Abdelsamea, Mohammed M. Birmingham City University School of Computing and Digital Technology Birmingham United Kingdom University of Exeter computer science department Exeter United Kingdom

Curriculum learning strategies have been proven to be effective in various applications and have gained significant interest in the field of machine learning. It has the ability to improve the final model's performance and accelerate the training process. However, in the medical imaging domain, data irregularities can make the recognition task more challenging and usually result in misclassification between the different classes in the dataset. Class-decomposition approaches have shown promising results in solving such a problem by learning the boundaries within the classes of the data set. In this paper, we present a novel convolutional neural network (CNN) training method based on the curriculum learning strategy and the class decomposition approach, which we call CLOG-CD, to improve the performance of medical image classification. We evaluated our method on four different imbalanced medical image datasets, such as Chest X-ray (CXR), brain tumour, digital knee X-ray, and histopathology colorectal cancer (CRC). CLOG-CD utilises the learnt weights from the decomposition granularity of the classes, and the training is accomplished from descending to ascending order (i.e., anti-curriculum technique). We also investigated the classification performance of our proposed method based on different acceleration factors and pace function curricula. We used two pre-trained networks, ResNet-50 and DenseNet-121, as the backbone for CLOG-CD. The results with ResNet-50 show that CLOG-CD has the ability to improve classification performance with an accuracy of 96.08% for the CXR dataset, 96.91% for the brain tumour dataset, 79.76% for the digital knee X-ray, and 99.17% for the CRC dataset, compared to other training strategies. In addition, with DenseNet-121, CLOG-CD has achieved 94.86%, 94.63%, 76.19%, and 99.45% for CXR, brain tumour, digital knee X-ray, and CRC datasets, respectively © 2013 IEEE.

关键词： Functional neuroimaging

来源：评论

学校读者我要写书评

暂无评论

Porous ceria materials for efficient direct conversion of carbon dioxide and methanol to dimethyl carbonate

引用

Materials Advances 2024年第16期5卷 6605-6617页

作者： Yang, Zhuxian Zheng, Justin Tay Lu, Xinhuan Lin, Monica Mengdie Cai, Dongming Wang, Yankun Yu, Wen-Yueh Zhu, Yanqiu Xia, Yongde Department of Engineering Faculty of Environment Science and Economy University of Exeter ExeterEX4 4QF United Kingdom Department of Chemical Engineering National Taiwan University No. 1 Sec. 4 Roosevelt Rd Taipei106335 Taiwan School of Chemical Engineering Hubei University 368 Youyi Dadao Wuchang Qu Hubei Province Wuhan430062 China Hubei Key Laboratory of Energy Storage and Power Battery School of Mathematics Physics and Optoelectronics Engineering Hubei University of Automotive Technology Shiyan442002 China

Ceria (CeO2) is widely considered as a superior catalytic material for the direct conversion of carbon dioxide (CO2) and methanol into dimethyl carbonate (DMC). Developing porous structures is a versatile way to increase the surface area, to create defects, and to improve the mass transfer of the resulting materials, consequently enhancing their catalytic performance. However, most of the reported preparation methods of porous CeO2 involve complex hydrothermal (100-120 °C) or refluxing (95-140 °C) processes followed by calcination at temperatures of 500-650 °C. In this work, we report a simple and low temperature approach to prepare porous CeO2, which involves mixing the raw materials at room temperature, followed by drying and then calcining at 450 °C. A DMC formation rate of 14.8 mmol g−1 h−1 is achieved for one of the obtained porous CeO2, which is much higher than those of the most reported CeO2 (0.51-11 mmol g−1 h−1). Further studies show that the DMC formation rate has a positive link to the parameters following the order: the CO2 uptake amount at 25 °C, the amount of weak acidity, the Ce3+ concentration, the amount of weak basicity, and the BET surface area of the CeO2 catalysts in this study. In addition, there seems to be an optimum oxygen vacancy concentration of the CeO2 samples for the DMC formation rate. This study provides a simple strategy for the preparation of a porous CeO2 material as a highly efficient catalyst for the catalytic conversion of CO2, which can not only mitigate the greenhouse gas CO2, but also turn it into value-added and versatile chemical DMC. © 2024 RSC.

关键词： Cerium oxide

来源：评论

学校读者我要写书评

暂无评论

The Recovery of PGMs from Spent Automotive Exhaust Catalysts by Lead Slag

引用

Journal of Wuhan university of Technology(Materials science) 2025年第3期40卷 871-879页

作者： YAN Jisen ZHANG Liao MAO Shuaidong WANG Zihan PENG Yinli XIE Fang HUA Xijin ZHANG Baojing Henan Province Engineering Research Center of Additive Manufacturing Aeronautical Materials Nanyang Institute of TechnologyNanyang 473004China Nanyang Key Laboratory of Additive Manufacturing Technology and Equipment Nanyang Institute of Technolo-gyNanyang 473004China Northern Engineering&Technology Corporation MCCDalian 116600China Department of Engineer-ing University of ExeterExeterEX44QFUK School of Materials Science and Physics China University of Mining and TechnologyXuzhou 221116China

This paper presented a novel and environmentally friendly approach for recovering platinum group metals(PGMs)from spent automotive exhaust *** study employed lead slag and waste graphite electrodes as raw materials,incorporating CaO as an additive to fine-tune the slag's viscosity and *** reducing FeO in the lead slag using waste graphite electrodes,pure Fe was obtained,effectively trapping the PGMs from the exhausted *** study explored the effects of reductant addition,trapping duration,slag basicity,and trapping temperature on the recovery rate of *** results indicated that a maximum recovery rate of 97.86%was achieved when the reductant was added at 1.5 times the theoretical amount,with a trapping duration of 60 minutes,a slag basicity of 0.7,and a trapping temperature of 1600℃.This research offered a greener pathway for the recovery of PGMs from spent automotive exhaust catalysts.

关键词： PGMs lead slag recovery spent automotive exhaust catalysts

来源：评论

学校读者我要写书评

暂无评论

Causes of Differences in the Tropical Pacific SST Warming Pattern Projected by CMIP6 Models

引用

Advances in Atmospheric sciences 2025年第6期42卷 1077-1091页

作者： Jun YING Matthew COLLINS Robin CHADWICK Shangfeng CHEN Xiaoming HU Tao LIAN Shangmin LONG State Key Laboratory of Satellite Ocean Environment Dynamics Second Institute of OceanographyMinistry of Natural ResourcesHangzhouChina Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai) ZhuhaiChina Department of Mathematics and Statistics University of ExeterExeterUnited Kingdom Met Office Hadley Centre ExeterUnited Kingdom Center for Monsoon System Research Institute of Atmospheric PhysicsChinese Academy of SciencesBeijingChina School of Atmospheric Sciences Sun Yat-sen UniversityZhuhaiChina School of Oceanography Shanghai Jiao Tong UniversityShanghaiChina Key Laboratory of Marine Hazards Forecasting Ministry of Natural ResourcesHohai UniversityNanjingChina College of Oceanography Hohai UniversityNanjingChina

The inter-model difference in the tropical Pacific SST warming pattern is a big stumbling block for reliable projections of global climate change. Here by conducting an inter-model Empirical Orthogonal Function(EOF) analysis as well as an ocean mixed-layer heat budget, we find that the first two modes of inter-model difference in the SST warming pattern projected by 30 CMIP6 models, explaining more than three-quarters of the total inter-model variance, are both tied to different cloud–radiation feedbacks. The EOF1 mode that captures the different magnitudes of El Ni?o-like warming as well as the largest inter-model variance in the far eastern equatorial Pacific, is likely driven by highly diverse cloud–radiation feedbacks in the east and, to a lesser extent, by differing changes in the oceanic vertical temperature gradient. The EOF2 mode that mainly represents the different magnitudes of SST warming in the western equatorial Pacific, is associated with differing levels of negative cloud–radiation feedback over the central equatorial Pacific through a dynamic air–sea coupled process involving both the Bjerknes feedback and the wind–evaporation–SST *** in isolation the robust common model bias of a weak negative cloud–radiation feedback over the central equatorial Pacific, the projected SST warming in the western equatorial Pacific is likely to be smaller than the multi-model ensemble mean, thereby presenting a more weakeened zonal SST gradient than expected, implying the potential for more severe climate extremes under global warming.

关键词： SST warming pattern inter-model difference cloud–radiation feedback

来源：评论

学校读者我要写书评

暂无评论

NOMA-Based WPT-MEC Network System Cost Efficient Units Minimization 8

NOMA-Based WPT-MEC Network System Cost Efficient Units Minim...

引用

8th IEEE International Conference on computer and Communications, ICCC 2022

作者： Zhu, Wenwu Chen, Xin Jiao, Libo Min, Geyong Wang, Yijie School of Computer Science Beijing Information Science & Technology University University of Exeter Beijing China

ISBN: (纸本)9781665450515

With the progress of the Internet of Things (loT) and 5G communication technology, the rapid development of the loT not only brings convenience to people's lives, but also brings problems such as insufficient computing power and environmen-tal pollution. On the one hand, Mobile Edge Computing (MEC) can coordinate the computing power of local and MEC servers, reduce computing latency and power consumption, and provide faster response for users. On the other hand, wireless power transmission (WPT) technology can effectively solve the pollution problem caused by traditional energy supply. On this basis, it is of great practical significance to study the architecture of the loT that combines MEC with WPT. In order to minimize the unit cost (UC) of WPT-MEC system, this paper proposes a computing offload a nd resource scheduling problem involving multiple users and a single server. We first describe t he problem a s a Mixed Integer Nonlinear Programming Problem(MINLP). Then, we propose an improved algorithm TRSA based on simulated annealing (SA) algorithm to obtain the optimal computing offload and resource allocation strategy to minimize the U C of the system. A large number of simulation results show that TRSA algorithm can significantly reduce the UC of WPT-MEC system in different scenarios compared with other baseline methods. © 2022 IEEE.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

STCIN: Spatial-Temporal Cross Interaction Networks for Urban Anomaly Prediction 25

STCIN: Spatial-Temporal Cross Interaction Networks for Urban...

引用

25th IEEE International Conference on computer Supported Cooperative Work in Design, CSCWD 2022

作者： Zhang, Xu Tang, Haina Wu, Yulei Chen, Xuewen University of Chinese Academy of Sciences School of Artificial Intelligence Beijing China University of Exeter Department of Computer Science Exeter United Kingdom

ISBN: (纸本)9781665405270

Urban anomaly adversely affects the quality of human life and even the security of urban residents. Effective prediction of urban anomalies is crucial to public safety, traffic management, urban planning, etc. However, the region division, the complex spatial-temporal correlations, and the cross interaction of multiple dynamics make this difficult. In this paper, urban anomaly data collected by crowdsourcing is used to perform anomaly prediction together with external factors. To this end, a Spatial-Temporal Cross Interaction Networks (STCIN) model is proposed, with a novel urban graph construction method and a new mechanism to build the spatial-temporal correlation between regions with multiple dynamics. STCIN is able to exploit both current region features and historical urban information for urban anomaly prediction. Experimental results validate the superiority of the proposed method in comparison with five related works on four real-world datasets. Using the dataset of Street Condition, STCIN can increase the F1-score of anomaly prediction by 5.7% comparing with the state-of-the-art WaveNet (Graph wavenet for deep spatial-temporal graph modeling). © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Launch and Recovery of Traditional VTOL UAVs by Quiescent Period Prediction (QPP);the development of QPP for All Weather Operations (AWOPS) 79

Launch and Recovery of Traditional VTOL UAVs by Quiescent Pe...

引用

79th Vertical Flight Society Annual Forum and Technology Display, FORUM 2023

作者： Ferrier, Bernard Taylor, Robert Kish, John P. Belmont, M.R. Christmas, J.T. Dynamic Interface Lab. Syntek Technologies Inc. FairfaxVA United States Royal Navy Portsmouth United Kingdom In-Service Class Desk PMA-266 MQ-8 Fire Scout Patuxent RiverMD United States School of Engineering University of Exeter Devon Exeter United Kingdom Department of Computer Science University of Exeter Devon Exeter United Kingdom

ISBN: (纸本)9781713874799

The most challenging tasks in the deployment of ship-based VTOL Uninhabited Air System (UAS) are the vehicle launch and recovery, and deck handling operational performance on smaller ship platforms all whilst maintain deck tempo. This is owing to the random nature of seaway created deck motion coupled with ship structure disturbed air wake patterns. For most of the traditional VTOL UASs, the precise measurement of these environmental data is essential for air vehicle safe launch and recovery events. Physics limits the speed by which the deck can be raised from rest to a dangerous position. It is helpful to identify the quieter, more quiescent periods in deck motion. However, the time needed to setup and land UASs are often longer than these quiescent windows may persist, assuming a quiescent window can be identified in the first place. Without precise measurement of deck motion or sufficient advanced notice of the onset of quieter motions, cycle after cycle of ship's motions whilst the vehicle attempts stabilize for recovery. The aim of Quiescent Period Prediction (QPP) is to provide ship motion conditions and motion predictions with sufficient forecasted time (over a minute) to launch, recover and complete other motion sensitive tasks regardless of the seaway. The fundamental concept is to measure remote sea surface profiles to predict the future wave forces acting upon a vessel. QPP operates within a federated architecture system containing measurement instruments such as a Wave Radar system used to map remote sea surfaces several hundred meters in advance of the ship. This enables the computation of future wave forces acting on the vessel. This article describes the development of the QPP System concentrating on test procedures, timely seaway mapping and ship motion characteristics to complete specific motion sensitive task. The objective is to expand ship operating deck limits to approximately Sea State 6+. Copyright © 2023 by the Vertical Flight Society. All ri

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Power Allocation and Client Selection For Privacy-Preserving Federated Learning in IoMT

Power Allocation and Client Selection For Privacy-Preserving...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Liu, Jingyuan Chang, Zheng Wang, Kai Min, Geyong University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu China University of Jyväskylä Faculty of Information Technology P.O. Box 35 JyväskyläFIN-40014 Finland Sichuan Provincial People's Hospital Department of Acute Care Surgery Chengdu China University of Exeter Department of Computer Science ExeterEX4 4QF United Kingdom

ISBN: (纸本)9798350351255

In recent years, the Internet of Medical Things (IoMT) has significantly boosted the healthcare industry. In the IoMT, federated learning (FL) can be applied, which can increase the utilization of patient data while protecting patient privacy. This work proposes a cutting-edge framework that combines differential privacy (DP) with FL and utilizes game theory to optimize power allocation and client selection in IoMT environments. Utilizing a Stackelberg game model, we orchestrate power allocation strategies among IoMT devices to enhance communication efficiency while meeting stringent privacy standards. We propose non-uniform and uniform pricing strategies based on the availability of network state information. Then, we derive the optimal interference price and power for the IoMT devices using nonlinear programming and convex optimization. In addition, our approach integrates DP to protect patients' data, carefully balancing between privacy and the accuracy of the learning model. The conducted simulations show that our proposed method is effective in terms of communication efficiency, privacy preservation and FL performance. © 2024 IEEE.

关键词： Federated 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：