检索结果-内蒙古大学图书馆

8th International Conference on Intelligent Computing and Signal Processing, ICSP 2023

作者： Fan, XiaoJie Huang, ZhangQin Huo, SiJia Zhang, XiaoBo Beijing University of Technology Beijing Engineering Research Center for IoT Software and System Beijing China

ISBN: (纸本)9798350302455

The number of Internet of Things (IoT) devices in the world has grown to 43 billion in 2023. With the expansion of the IoT industry, the types and communication protocols of IoT devices are also increasing. In the actual deployment of the Internet of Things, it is more complicated and difficult to develop a truly interconnected IoT platform in the face of a variety of IoT devices. At the same time, the increasing number of devices has brought great challenges to the high availability of the platform. We designed and implemented a multi-protocol access method for the IoT platform, which can configure public and private protocols according to requirements, and make up for the shortcomings of the current IoT platform in device access. In order to ensure the availability of the platform, the container dynamic scheduling method is generally adopted when the sudden high load demand is needed. However, due to the time-consuming operation in the container scaling process, the existing container scheduling method cannot immediately meet the load demand. We proposed a combined prediction model based on LSTM and RELM, and proposed a container dynamic scheduling strategy based on load prediction. This scheduling strategy is applied to the multi-protocol access method to ensure the stability and availability of the access process. Finally, the multi-protocol access method is tested. The results show that this method can ensure the access of multi-protocol IoT devices. The reliability test shows that it has good performance and meets the current demand for IoT platforms. In addition, the strategy of this paper is compared with other strategies to further verify the rationality and availability of the method. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Transformer-based Siamese Neural Network Face Verification Method 8

Transformer-based Siamese Neural Network Face Verification M...

引用

8th International Conference on Intelligent Computing and Signal Processing, ICSP 2023

作者： Qiu, Shen Yang, HuaPeng Huang, ZhangQin Shen, DiYuan Beijing University of Technology Beijing Engineering Research Center for IoT Software and System Beijing China

ISBN: (纸本)9798350302455

Face verification, as a key part of person intelligence tracing, aims to determine whether the same person is in two face photos, which can be approximately transformed into a binary classification problem. In this paper, the siamese neural network architecture is adopted as the overall structure of the method, and the traditional bacbone network generally uses a convolutional neural network, this paper will use Vision Transformer as the backbone network as the method. Compared with convolutional neural network, its multi-headed attention mechanism can better focus on the larger sensory field and extract face features, which can then better perform face verification, while Binary cross-entropy is used as the loss function. After the validation of the private dataset, the model can recognize faces well and has excellent validation effect, which is of great value for the field of human intelligence tracing. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Bug localization based on syntactical and semantic information of source code

引用

Journal of systems engineering and Electronics 2023年第1期34卷 236-246页

作者： YAN Xuefeng CHENG Shasha GUO Liqin College of Computer Science Technology Nanjing University of Aeronautics and AstronauticsNanjing 211106China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing 211106China State Key Laboratory of Intelligent Manufacturing System Technology Beijing Institute of Electronic System EngineeringBeijing 100854China

The existing software bug localization models treat the source file as natural language, which leads to the loss of syntactical and structure information of the source file. A bug localization model based on syntactical and semantic information of source code is proposed. Firstly, abstract syntax tree(AST) is divided based on node category to obtain statement sequence. The statement tree is encoded into vectors to capture lexical and syntactical knowledge at the statement ***, the source code is transformed into vector representation by the sequence naturalness of the statement. Therefore,the problem of gradient vanishing and explosion caused by a large AST size is obviated when using AST to the represent source code. Finally, the correlation between bug reports and source files are comprehensively analyzed from three aspects of syntax, semantics and text to locate the buggy code. Experiments show that compared with other standard models, the proposed model improves the performance of bug localization, and it has good advantages in mean reciprocal rank(MRR), mean average precision(MAP) and Top N Rank.

关键词： bug report abstract syntax tree code representation software bug localization

来源：评论

学校读者我要写书评

暂无评论

Design and Performance Analysis of LoRa for Smart Forestry Video Services 8

Design and Performance Analysis of LoRa for Smart Forestry V...

引用

8th International Conference on Intelligent Computing and Signal Processing, ICSP 2023

作者： Huang, Zhangqin Gao, Han Yang, Huapeng Huang, Ling Beijing University of Technology Beijing Engineering Research Center for IoT Software and System Beijing China

ISBN: (纸本)9798350302455

Camera monitoring is more intuitive than other environmental sensors, and it is of great significance for predicting, preventing, and tracing fire events in smart forestry. This paper analyzes the data transmission tasks and capabilities of LoRa in video services at the network edge, based on a practical smart forestry project. We propose the design method of intelligent hardware at the network edge and the optimization method of LoRa communication. We demonstrate the communication performance between LoRa terminals and LoRa gateways through practical deployment experiments, proving that the use of LoRa with a higher rate for wireless communication networking and reporting of video analysis results can meet the requirements of smart forestry and achieve beneficial effects. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Advancements in Dental Diagnostics: YOLOv3-Powered Machine Learning for Automated Teeth Problem Detection 24

Advancements in Dental Diagnostics: YOLOv3-Powered Machine L...

引用

24th International Arab Conference on Information Technology, ACIT 2023

作者： Odeh, Suhail Samara, Anas Zreineh, Nicola Obeid, Seif Ibrieghieth, Maen Obaid, Mahmoud Bethlehem University Software Engineering Dept. Palestine Arab American University Computer System Engineering Jenin Palestine

ISBN: (纸本)9798350384307

This paper presents a rigorous investigation into the application of state-of-the-art machine learning techniques for the automated detection of dental issues, utilizing the YOLOv3 Algorithm, a cutting-edge one-stage object detection method. The study encompasses the meticulous annotation and utilization of a carefully curated dataset featuring 126 panoramic X-ray images, illustrating a diverse range of dental conditions. Among these conditions, the primary emphasis is placed on the precise detection of six specific dental problems. Employing advanced computer vision methodologies, the model demonstrates exceptional accuracy in the identification and precise localization of these targeted dental issues. The implications of these findings are profound for the field of dental healthcare, as the automated detection of dental problems holds the potential to significantly enhance the diagnostic and treatment planning capabilities of dental professionals. The results presented in this research represent a notable stride in the ongoing evolution of machine learning and underscore its capacity to revolutionize the landscape of dental diagnostics, ultimately contributing to the advancement of oral health management and patient care. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DiaSet: An Annotated Dataset of Arabic Conversations 30

DiaSet: An Annotated Dataset of Arabic Conversations

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Israeli, Abraham Naaman, Aviv Makhoul, Rawaa Maduel, Guy Ejmail, Amir Jubran, Julian Karain, Dana Lisnyansky, Dina Fine, Shai Bar, Kfir The Data Science Institute Reichman University Israel Department of Software and Information System Engineering Ben-Gurion University of the Negev Israel

ISBN: (纸本)9782493814104

We introduce DiaSet, a novel dataset of dialectical Arabic speech, manually transcribed and annotated for two specific downstream tasks: sentiment analysis and named entity recognition. The dataset encapsulates the Palestine dialect, predominantly spoken in Palestine, Israel, and Jordan. Our dataset incorporates authentic conversations between YouTube influencers and their respective guests. Furthermore, we have enriched the dataset with simulated conversations initiated by inviting participants from various locales within the said regions. The participants were encouraged to engage in dialogues with our interviewer. Overall, DiaSet consists of 644.8K tokens and 23.2K annotated instances. Uniform writing standards were upheld during the transcription process. Additionally, we established baseline models by leveraging some of the pre-existing Arabic BERT language models, showcasing the potential applications and efficiencies of our dataset. We make DiaSet publicly available for further research. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

UAV-Mounted Intelligent Reflecting Surface in Maritime Wireless Powered Communication Network

引用

China Communications 2025年第3期22卷 254-269页

作者： Liu Yuan Han Fengxia Zhao Shengjie School of Information Science and Electrical Engineering Shandong Jiaotong UniversityJinan 250357China College of Electronic and Information Engineering Tongji UniversityShanghai 201804China School of Software Engineering Tongji UniversityShanghai 201804China Engineering Research Center of Key Software Technologies for Smart City Perception and Planning Ministry of EducationShanghai 200003China Key Laboratory of Embedded System and Service Computing Tongji University Shanghai 201804China

Intelligent reflecting surface(IRS)assisted with the wireless powered communication network(WPCN)can enhance the desired signal energy and carry out the power-sustaining problem in ocean monitoring *** this paper,we investigate a reliable communication structure where multiple buoys transmit data to a base station(BS)with the help of the unmanned aerial vehicle(UAV)-mounted IRS and harvest energy from the base station *** organically combine WPCN with maritime data collection scenario,a scheduling protocol that employs the time division multiple access(TDMA)is proposed to serve multiple buoys for uplink data ***,we compare the full-duplex(FD)and half-duplex(HD)mechanisms in the maritime data collection system to illustrate different performances under these two *** maximize the fair energy efficiency under the energy harvesting constraints,a joint optimization problem on user association,BS transmit power,UAV’s trajectory and IRS’s phase shift is *** solve the non-convex problem,the original problem is decoupled into several subproblems,and successive convex optimization and block coordinate descent(BCD)methods are employed obtain the near-optimal solutions *** results demonstrate that the UAV-mounted IRS can significantly improve energy efficiency in our considered system.

关键词： full-duplex IRS joint optimization TDMA UAV WPCN

来源：评论

学校读者我要写书评

暂无评论

Intelligent Computing in Communication Networks: Challenges, Solutions, and Research Prospects

Intelligent Computing in Communication Networks: Challenges,...

引用

2023 IEEE International Conference on Computing, ICOCO 2023

作者： Fakhrul Safitra, Muhammad Prastika Putri, Deyana Lubis, Muharman Fakhrurroja, Hanif Saidi Lubis, Fahdi Satria, Villy School of Industrial and System Engineering Telkom University Information System Department Bandung Indonesia School of Industrial and System Engineering Telkom University Industrial Engineering Department Bandung Indonesia School of Applied Science Telkom University Application Software Engineering Department Bandung Indonesia

ISBN: (纸本)9798350302684

Communication networks can be transformed through the implementation of computing, which can improve their overall performance, security, and energy efficiency. Nevertheless, several obstacles must be overcome before computing can be fully integrated into communication networks. This paper examines the challenges and research opportunities in the field of computing in communication networks. To take full advantage of computing, new algorithms and techniques must be developed, and machine learning must be explored. Big data analytics and the integration of edge and fog computing with computing techniques are also promising areas for research. The challenges that must be addressed include ethical and privacy concerns, energy consumption, integration with 5G networks, IoT, and cloud computing, and the development of resilient computing systems that can identify and respond to cyber threats. Overcoming these challenges will ensure that computing remains an essential tool for designing and optimizing communication networks. © 2023 IEEE.

关键词： Data Analytics

来源：评论

学校读者我要写书评

暂无评论

Massively parallel algorithms for fully dynamic all-pairs shortest paths

引用

Frontiers of Computer Science 2024年第4期18卷 201-203页

作者： Chilei WANG Qiang-Sheng HUA Hai JIN Chaodong ZHENG National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabCluster and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China State Key Laboratory for Novel Software Technology Nanjing UniversityNanjing 210023China

1 Introduction In recent years,the Massively Parallel Computation(MPC)model has gained significant ***,most of distributed and parallel graph algorithms in the MPC model are designed for static graphs[1].In fact,the graphs in the real world are constantly *** size of the real-time changes in these graphs is smaller and more *** graph algorithms[2,3]can deal with graph changes more efficiently[4]than the corresponding static graph ***,most studies on dynamic graph algorithms are limited to the single machine ***,a few parallel dynamic graph algorithms(such as the graph connectivity)in the MPC model[5]have been proposed and shown superiority over their parallel static counterparts.

关键词： dynamic shortest gained

来源：评论

学校读者我要写书评

暂无评论

Evaluating machine learning models and feature selection for reference evapotranspiration estimation in semi-arid regions: a case study in Doukkala, Morocco

引用

Theoretical and Applied Climatology 2025年第6期156卷 1-24页

作者： Belarbi, Zaid EL Younoussi, Yacine Information System and Software Engineering Laboratory Abdelmalek Essaadi University Tetouan Morocco

Accurate estimation of reference evapotranspiration (ETo) is crucial for effective water resource management and irrigation planning, particularly in regions with significant agricultural activity, such as Doukkala, Morocco. This study explores the potential of machine learning (ML) models to estimate daily ETo using 18 years of climatic data collected from two meteorological stations in the region. The dataset includes key meteorological variables—temperature, humidity, solar radiation, wind speed, and rainfall—with ETo calculated using the FAO-56 Penman-Monteith (PM) equation as the reference. A range of ML models, including Artificial Neural Networks (ANN), Support Vector Regression (SVR), XGBoost, Random Forest (RF), k-Nearest Neighbors (KNN), Decision Trees (DT), and Multiple Linear Regression (MLR), were trained and compared. Additionally, deep learning architectures such as Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN) were evaluated for their ability to capture temporal dependencies within the data. Among the tested models, ANN demonstrated the highest performance, achieving an R² of 0.9868 and an MSE of 0.0440, followed closely by SVR and XGBoost, both of which also exhibited high predictive accuracy. In contrast, simpler models like MLR and DT showed comparatively lower performance, underscoring the advantages of more advanced ML techniques for ETo estimation. While LSTM displayed moderate success, CNN underperformed relative to other models. The inclusion of data from two stations enabled the evaluation of model generalizability across distinct locations within the region. However, this study has some limitations. While cross-site validation improves generalizability, the findings are based on two stations within the same semi-arid region, which may not fully represent ETo dynamics in more diverse climatic conditions. Additionally, while ML models demonstrated strong predictive capabilities, further improvements could be achieved b

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：