检索结果-内蒙古大学图书馆

46th International Conference on Software engineering: Companion, ICSE-Companion 2024

作者： Heo, Jinseok Lee, Eunseok Department of Electrical and Computer Engineering Sungkyunkwan University Suwon Korea Republic of College of Computing and Informatics Sungkyunkwan University Suwon Korea Republic of

ISBN: (纸本)9798400705021

Existing studies solve software engineering tasks using code infilling through LLMC. They utilize context information, which refers to data near the target code of infilling, as input prompts. Although prompts are essential for infilling the target code, current studies use them without analyzing the impact of the representation and scope of context on code infilling. In this study, we analyzed how context representation and scope affect the performance of code infilling. We used XLCost, which contains code, comments, and a function comment for various programming languages. The combination of code and a function comment for context representation yielded the best code infilling performance. Furthermore, we found that the context scope is proportional to performance. Our analysis results can be applied in various tasks that involve code infilling in the future. © 2024 IEEE computer Society. All rights reserved.

关键词： Software engineering

来源：评论

学校读者我要写书评

暂无评论

Optical Intra- and Inter-Rack Switching Architecture for Scalable, Low-Latency Data Center Networks 28

Optical Intra- and Inter-Rack Switching Architecture for Sca...

引用

28th IEEE Symposium on computers and Communications, ISCC 2023

作者： Drainakis, Georgios Baziana, Peristera Bogris, Adonis School of Electrical and Computer Engineering National Technical University of Athens Athens Greece University of Thessaly Department of Informatics and Telecommunications Lamia Greece University of West Attica Department of Informatics and Computer Engineering Egaleo Greece

ISBN: (纸本)9798350300482

In this paper we propose a DC network (DCN) architecture that interconnects servers in the intra-rack and inter-rack domain, utilizing optical switching at each domain. The proposed interconnection techniques are studied as an intermediate step before migrating the entire DCN to all-optical schemes. Unlike other studies, we study the server-to-server communication across the whole DCN. For the performance evaluation we produce numerical results for throughput and end-to-end delay for three traffic classes co-existing in DCN s. The numerical analysis reveals that bandwidth utilization reaches 90% and 100% in the intra- and inter- domain respectively. Meanwhile, the maximum end-to-end delay for the highest priority packets under congested load is lower than 0.56 and 0.41 μs for the two examined intra-rack capacity scenarios of 400 and 600 Gbps respectively. A comparative study shows that our solution can effectively interconnect up to 10000 servers with lower environmental footprint and end-to-end delay than other DCN s. © 2023 IEEE.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Concierge: Towards Accuracy-Driven Bandwidth Allocation for Video Analytics Applications in Edge Network 8

Concierge: Towards Accuracy-Driven Bandwidth Allocation for ...

引用

8th IEEE International Conference on Edge Computing and Communications, EDGE 2024

作者： Huang, Yuyang Zharfan, Faishal Hendrawan, Hendrawan Gunawi, Haryadi S. Jiang, Junchen University of Chicago Department of Computer Science Chicago United States Bandung Institute of Technology School of Electrical Engineering and Informatics Bandung Indonesia

ISBN: (纸本)9798350368499

When performing inference on sensor data, edge video analytics applications may not always need high-fidelity data, since important information may not appear all the time. Consequently, each edge AI application's bandwidth demand is highly dynamic. Thus, a shared edge system should dynamically allocate more bandwidth to the applications in need to reach high accuracy at each moment. However, previous bandwidth allocators are ill-suited because they are agnostic to the timevarying impact of bandwidth on each application's *** short paper explores a new accuracy-driven approach to bandwidth allocation, which periodically re-allocates bandwidth across edge AI applications based on the sensitivity of each application's accuracy to its bandwidth share. To examine its practical benefit and technical challenges, we present a concrete accuracy-driven bandwidth allocator called ConciERGE, which exposes a simple yet efficient interface to estimate each application's sensitivity to a small change in its bandwidth *** run CONCIERGE on state-of-the-art video-analytics applications with real video streams and show its early promise in greatly improving the inference accuracy of video analytics. © 2024 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

A Graph Neural Network Based Learning Model for Urban Metro Flow Prediction 22

A Graph Neural Network Based Learning Model for Urban Metro ...

引用

22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023

作者： Drosouli, Ifigenia Voulodimos, Athanasios Mastorocostas, Paris Miaoulis, Georgios Ghazanfarpour, Djamchid Engineering University of West Attica Department of Informatics & Computer Athens Greece School of Electrical & Computer Engineering National Technical Univ. of Athens Athens Greece University of Limoges Department of Informatics Limoges France

ISBN: (纸本)9798350345346

- Abstract-Transport data with dynamic spatial-temporal dependencies elevates transportation flow forecasting to a significant issue for operational planning, managing passenger flow, and arranging for individual travel in a smart city. The task is challenging due to the composite spatial dependency on transportation networks and the non-linear temporal dynamics with mobility conditions changing over time. To address these challenges, we propose a Spatial- Temporal Graph Convolutional Recurrent Network that learns from both the spatial stations network data and time-series of historical mobility changes so as to predict urban metro flow at a future time. The model is based on Graph Convolutional Networks (GCN) and Long Short-Term Memory (LSTM) in order to further improve the estimation accuracy. Extensive experiments on a real-world dataset of Hangzhou metro system prove the effectiveness of the proposed model. © 2023 IEEE.

关键词： Graph Convolutional Networks spatial-temporal dependencies urban metro flow prediction

来源：评论

学校读者我要写书评

暂无评论

Cyber Attacks Detection using Deep Learning Methods for Resilient Operation in DC Shipboard Microgrids

Cyber Attacks Detection using Deep Learning Methods for Resi...

引用

2024 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2024

作者： Ali, Zulfiqar Hussain, Tahir Su, Chun-Lien Jurcut, Anca Delia Baloch, Shazia Sadiq, Muhammad National Kaohsiung University of Science and Technology Department of Electrical Engineering Kaohsiung city Taiwan Graduate School of Informatics and Engineering The University of Electro-Communication Department of Informatics Tokyo Japan School of Computer Science University College Dublin BelfieldDublin 4 Ireland Balochistan University of Engineering and Technology Department of Electrical Engineering Khuzdar Pakistan

ISBN: (纸本)9798350352290

Cyber resilience has become paramount as a transition of maritime systems towards digitization, particularly within DC shipboard microgrids (SMGs). Adopting innovative communication technologies can enhance the resilience of SMGs for stable operation. However, challenges like false data injection and Man-in-The-Middle attacks pose significant threats to SMG operations when integrating these technologies into ship intelligent grids. In this regard, this paper proposes a reliable deep learning (DL) method, especially an Artificial neural network (ANN) with a deep encoder-decoder architecture, for the detection of cyber-intrusions and mitigating their effects, ensuring system control and stability for resilient operation of SMG. Detecting malicious data intrusions is crucial for maintaining optimal grid conditions and preventing disruptions in load dispatch. The proposed method utilizes a fusion of current and voltage data features for comprehensive DL model training, resulting in an adequate level of detection accuracy and providing cybersecurity analysis for SMGs, addressing component-level attacks, and devising defense strategies from aspects of detection, mitigation, and prevention. Furthermore, the deep ANN is fine-tuned with optimal hyperparameters to effectively counter cyberattacks, achieving an enhanced accuracy rate of 97.51% and minimal loss of 0.101%, surpassing conventional machine learning approaches. Rigorous test scenarios are performed to validate the robustness of the proposed method, emphasizing the cyber resilience of DC SMGs for enhanced security and operational integrity. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Assessing Predictor Influence in LSTM Models for Enhanced Solar Energy Forecasting 26

Assessing Predictor Influence in LSTM Models for Enhanced So...

引用

26th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, SYNASC 2024

作者： Ciobanu, Alexandru-Adrian Bacanin, Nebojsa Sanders, Tilman Stoean, Catalin University of Craiova Department of Computer Science Craiova Romania Singidunum University Faculty of Informatics and Computing Belgrade Serbia FH Muenster Department of Electrical Engineering and Computer Science Steinfurt Germany

ISBN: (纸本)9798331532833

Accurate forecasting of solar energy production is highly important for an adequate integration of renewable energy into the power grid. This study explores the importance of various predictors for enhancing the accuracy of solar energy forecasting using two distinct Long Short-Term Memory models: one that relies solely on historical power production data and past exogenous weather data, and another that additionally incorporates future exogenous weather data. Various settings are tried to improve the results and relatively similar parameters are used by both, yielding more accurate results for the model that also uses information from the future. The results also demonstrate that predictor importance varies significantly between the two models. These findings suggest that different models benefit from distinct predictor combinations and incorporating exogenous data can significantly enhance forecasting performance. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Analysis of selected dielectric parameters of insulating liquids 23

Analysis of selected dielectric parameters of insulating liq...

引用

23rd International Scientific Conference on Electric Power engineering, EPE 2023

作者： Pluzek, Aleksandra Nagi, Lukasz Koziol, Michal Zygarlicka, Malgorzata Opole University of Technology Faculty of Electrical Engineering Automatic Control and Informatics Department of Electrical Power and Renewable Energy Opole Poland Opole University of Technology Faculty of Electrical Engineering Automatic Control and Informatics Department of Computer Science Opole Poland

ISBN: (纸本)9798350335934

During the last few years, there has been a growing interest in the topic of using natural or synthetic esters as an alternative to mineral oils in oil transformers due to the easier way to obtain them and their ability to exhibit better electrical properties. In addition, more and more researchers are describing in their work that doping esters with nanoparticles is capable of further improving these properties. Therefore, in the current work, it was decided to see what effect the addition of a hydrophobic carbon shell iron nanoparticle to ORLEN mineral oil and Midel 7131 synthetic ester would have on selected electrical parameters of the insulating fluid, i.e. breakdown voltage and electrical strength. © 2023 IEEE.

关键词： Nanoparticles

来源：评论

学校读者我要写书评

暂无评论

The Using of Mixed Reality Technology for Digital Transformation in Tourism 10

The Using of Mixed Reality Technology for Digital Transforma...

引用

10th International Conference on ICT for Smart Society, ICISS 2023

作者： Tresnawati, Dewi Latifah, Ayu Mahpudin, Indra Pratama, Vitradisa Sukoco, Agus Prihatmanto, Ary Setijadi Informatics Institut Teknologi Garut Department of Computer Science Garut Indonesia School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia Department of Computer Science Informatics Universitas Bandar Lampung Garut Indonesia

ISBN: (纸本)9798350339543

The tourism industry in Indonesia experienced a decrease in the number of tourist visits that occurred at the end of 2020. This was due to the outbreak of the COVID-19 outbreak that occurred at the end of January 2020. Apart from having an impact on decreasing the number of foreign tourist visits, it also had an impact on domestic tourists or local tourists. especially Bandung residents who are reluctant to travel because they are worried about the spread. Bandung has several popular tourist destinations such as history, culinary, fashion, handicrafts, arts, and interesting amusement parks to visit. One of them is Gedung Sate. For this reason, media promotion is needed to attract tourists to Bandung. The purpose of this research is to implement mixed reality technology that can be used to support tourism. This study uses the multimedia development life cycle which consists of six stages, namely concept, design, material collection, assembly, testing, and distribution. The results of this study are mixed reality application prototypes as promotional media for tourist attractions in Bandung that can be used by domestic and foreign tourists. Additionally, by using mixed reality technology as a promotional tool for Bandung's tourism sites, users may interact with 3D objects in real-time, making the information offered more engaging and dynamic. © 2023 IEEE.

关键词： Life cycle

来源：评论

学校读者我要写书评

暂无评论

A Link-Quality Anomaly Detection Framework for Software-Defined Wireless Mesh Networks

IEEE Transactions on Machine Learning in Communications and ...

引用

IEEE Transactions on Machine Learning in Communications and Networking 2024年 2卷 495-510页

作者： Skaperas, Sotiris Mamatas, Lefteris Tsaoussidis, Vassilis University of Macedonia Department of Applied Informatics Thessaloniki546 36 Greece Athena Research and Innovation Center Marousi15125 Greece Democritus University of Thrace Department of Electrical and Computer Engineering Xanthi67100 Greece

Software-defined wireless mesh networks are being increasingly deployed in diverse settings, such as smart cities and public Wi-Fi access infrastructures. The signal propagation and interference issues that typically characterize these environments can be handled by employing SDN controller mechanisms, effectively monitoring link quality and triggering appropriate mitigation strategies, such as adjusting link and/or routing protocols. In this paper, we propose an unsupervised machine learning (ML) online framework for link quality detection consisting of: 1) improved preprocessing clustering algorithm, based on elastic similarity measures, to efficiently characterize wireless links in terms of reliability, and 2) a novel change point (CP) detector for the real-time identification of anomalies in the quality of selected links, which minimizes the overestimation error through the incorporation of a rank-based test and a recursive max-type procedure. In this sense, considering the communication constraints of such environments, our approach minimizes the detection overhead and the inaccurate decisions caused by overestimation. The proposed detector is validated, both on its individual components and as an overall mechanism, against synthetic but also real data traces;the latter being extracted from real wireless mesh network deployments. © 2023 CCBY.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Adaptive Strategies for Enhancing Quality of Experience in 360° Video Streaming 58

Adaptive Strategies for Enhancing Quality of Experience in 3...

引用

58th Asilomar Conference on Signals, Systems and computers, ACSSC 2024

作者： Valiandi, Ioanna Pattichis, Marios S. Kyriacou, Efthyvoulos Panayides, Andreas S. Videomics Group Cyens Centre of Excellence Nicosia Cyprus University of New Mexico Department of Electrical and Computer Engineering AlbuquerqueNM87131-0001 United States Cyprus University of Technology Department of Electrical Eng. Computer Engineering and Informatics Limassol Cyprus

ISBN: (纸本)9798350354058

The unprecedented growth of immersive virtual and mixed reality technologies is driving the increasing demand of 360° video streaming applications. Facilitating unique opportunities, but also challenges, 360° videos require substantially higher video resolutions, and hence bandwidth demands, for a better viewing experience. This study examined four tile-based Region of Interest (ROI) encoding techniques to optimize 360° video encoding and streaming. These techniques encode the user's viewport regions with higher quality compared to the background, non-ROI areas. A dataset of ten 4K omnidirectional videos at 30 frames per second was used to evaluate the performance of four distinct tile-based ROI methods using four video encoding standards, namely hevc - nvenc, x265, h264 - nvenc, and x264. Overall, the proposed tile-based ROI encoding methods achieve substantial bitrate reductions compared to the uniform full-frame encoding while maintaining adequate subjective video quality levels, demonstrating their potential for efficient and scalable 360° video streaming. The ROI-3 method, which uses a sliding window approach to encode the user's field of view based on eye gaze movement (EM) data coordinates translated to tile regions, was found to achieve the best trade-off between bitrate demands savings and perceptual quality for all investigated video compression standards. © 2024 IEEE.

关键词： Video streaming

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：