检索结果-内蒙古大学图书馆

Dynamic Routing, Spatial Channel and Spectrum Assignment (RSCSA) in Spatial Channel Networks (SCNs)

Dynamic Routing, Spatial Channel and Spectrum Assignment (RS...

2023 Asia Communications and Photonics Conference/2023 International Photonics and Optoelectronics Meetings, ACP/POEM 2023

作者： Zheng, Yu Zheng, Weichang Yang, Mingcong Zhang, Yongbing Graduate School of Systems and Information Engineering University of Tsukuba Tsukuba Japan School of Information and Communication Engineering University of Electronic Science and Technology of China Sichuan China Department of R&D Huawei Technologies Wuhan China

In this paper, we propose a dynamic RSCSA algorithm that employs a granularity switching threshold to efficiently switch between spatially bypassed and spectrally groomed space lanes depending on the request demand in... 详细信息

ISBN: (纸本)9798350312614

关键词： granularity switching threshold routing SCN technologies spatial channel and spectrum assignment

来源：评论

学校读者我要写书评

暂无评论

3D Object Detection with Attention:Shell-Based Modeling

引用

computer systems science & engineering 2023年第7期46卷 537-550页

作者： Xiaorui Zhang Ziquan Zhao Wei Sun Qi Cui School of Computer and Software Nanjing University of Information Science&TechnologyNanjing210044China Wuxi Research Institute Nanjing University of Information Science&TechnologyWuxi214100China Engineering Research Center of Digital Forensics Ministry of EducationJiangsu Engineering Center of Network MonitoringNanjing210044China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET) Nanjing University of Information Science&TechnologyNanjing210044China School of Automation Nanjing University of Information Science&TechnologyNanjing210044China Department of Electrical and Computer Engineering University of WindsorWindsorN9B 3P4Canada

LIDAR point cloud-based 3D object detection aims to sense the surrounding environment by anchoring objects with the Bounding Box(BBox).However,under the three-dimensional space of autonomous driving scenes,the previous object detection methods,due to the pre-processing of the original LIDAR point cloud into voxels or pillars,lose the coordinate information of the original point cloud,slow detection speed,and gain inaccurate bounding box *** address the issues above,this study proposes a new two-stage network structure to extract point cloud features directly by PointNet++,which effectively preserves the original point cloud coordinate *** improve the detection accuracy,a shell-based modeling method is *** roughly determines which spherical shell the coordinates belong ***,the results are refined to ground truth,thereby narrowing the localization range and improving the detection *** improve the recall of 3D object detection with bounding boxes,this paper designs a self-attention module for 3D object detection with a skip connection *** of these features are highlighted by weighting them on the feature *** training,it makes the feature weights that are favorable for object detection get ***,the extracted features are more adapted to the object detection *** comparison experiments and ablation experiments conducted on the KITTI dataset verify the effectiveness of our proposed method in improving recall and precision.

关键词： 3D object detection autonomous driving point cloud shell-based modeling self-attention mechanism

来源：评论

学校读者我要写书评

暂无评论

The Evaluation of Trust Towards The Intention to Use of Blockchain-Based Crowdwork systems (Case Study of Creative Industry) 8

The Evaluation of Trust Towards The Intention to Use of Bloc...

引用

8th International Conference on information Management and Technology, ICIMTech 2023

作者： Hartono, Sugiarto Prabowo, Harjanto Meyliana Hidayanto, Achmad Nizar School of Information Systems Bina Nusantara University Information Systems Department Jakarta11480 Indonesia Binus Business School Undergraduate Program Bina Nusantara University Management Department Jakarta11480 Indonesia Universitas Indonesia Faculty of Computer Science Depok Indonesia

ISBN: (纸本)9798350326093

Current crowdwork research still has issues related to trust. Workers and employers do not know each other, so problems related to trust will arise. This trust issue will influence the desire to use the crowdwork system. This study will evaluate trust in the intention to use blockchain-based crowdwork systems in creative industries. The methodology used is a quantitative approach (questionnaire) which is distributed to 200 respondents consisting of workers and employers. After that, testing the inner and outer models was carried out. The results obtained are technology, risk, and reputation which have the greatest impact on trust. The use of blockchain technology can minimize risks when using a crowdwork system, such as data that cannot be changed, data tracing can be done, and so on. The rating and review features are also important to be able to find out the user's reputation in the system. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers

arXiv

引用

arXiv 2024年

作者： Ai, Guoguo Pang, Guansong Qiao, Hezhe Gao, Yuan Yan, Hui School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Computing and Information Systems Singapore Management University Singapore

Graph Transformers (GTs) have demonstrated remarkable performance in incorporating various graph structure information, e.g., long-range structural dependency, into graph representation learning. However, self-attention – the core module of GTs – preserves only low-frequency signals on graph features, retaining only homophilic patterns that capture similar features among the connected nodes. Consequently, it has insufficient capacity in modeling complex node label patterns, such as the opposite of homophilic patterns – heterophilic patterns. Some improved GTs deal with the problem by learning polynomial filters or performing self-attention over the first-order graph spectrum. However, these GTs either ignore rich information contained in the whole spectrum or neglect higher-order spectrum information, resulting in limited flexibility and frequency response in their spectral filters. To tackle these challenges, we propose a novel GT network, namely Graph Fourier Kolmogorov-Arnold Transformers (GrokFormer), to go beyond the self-attention in GTs. GrokFormer leverages learnable activation functions in order-K graph spectrum through Fourier series modeling to i) learn eigenvalue-targeted filter functions producing learnable base that can capture a broad range of frequency signals flexibly, and ii) extract first- and higher-order graph spectral information adaptively. In doing so, GrokFormer can effectively capture intricate patterns hidden across different orders and levels of frequency signals, learning expressive, order-and-frequency-adaptive graph representations. Comprehensive experiments conducted on 10 node classification datasets across various domains, scales, and levels of graph heterophily, as well as 5 graph classification datasets, demonstrate that GrokFormer outperforms state-of-the-art GTs and other advanced graph neural networks. Our code is available at https://***/GGA23/GrokFormer. Copyright © 2024, The Authors. All rights reserved.

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

DeepSVDNet:A Deep Learning-Based Approach for Detecting and Classifying Vision-Threatening Diabetic Retinopathy in Retinal Fundus Images

引用

computer systems science & engineering 2024年第2期48卷 511-528页

作者： Anas Bilal Azhar Imran Talha Imtiaz Baig Xiaowen Liu Haixia Long Abdulkareem Alzahrani Muhammad Shafiq College of Information Science and Technology Hainan Normal UniversityHaikou571158China Department of Creative Technologies Air UniversityIslamabadPakistan School of Life Science and Technology University of Electronic Science and Technology of China UESTCChengduChina School of Science and Technology University of Management and Technology UMTLahorePunjabPakistan Faculty of Computer Science&Information Technology Al Baha UniversityAl BahaSaudi Arabia School of Information Engineering Qujing Normal UniversityQujingChina

Artificial Intelligence(AI)is being increasingly used for diagnosing Vision-Threatening Diabetic Retinopathy(VTDR),which is a leading cause of visual impairment and blindness ***,previous automated VTDR detection methods have mainly relied on manual feature extraction and classification,leading to *** paper proposes a novel VTDR detection and classification model that combines different models through majority *** proposed methodology involves preprocessing,data augmentation,feature extraction,and classification *** use a hybrid convolutional neural network-singular value decomposition(CNN-SVD)model for feature extraction and selection and an improved SVM-RBF with a Decision Tree(DT)and K-Nearest Neighbor(KNN)for *** tested our model on the IDRiD dataset and achieved an accuracy of 98.06%,a sensitivity of 83.67%,and a specificity of 100%for DR detection and evaluation tests,*** proposed approach outperforms baseline techniques and provides a more robust and accurate method for VTDR detection.

关键词： Diabetic retinopathy(DR) fundus images(FIs) support vector machine(SVM) medical image analysis convolutional neural networks(CNN) singular value decomposition(SVD) classification

来源：评论

学校读者我要写书评

暂无评论

Functional plastic films:nano-engineered composite based flexible microwave antennas with near-unity relative visible transmittance

引用

Light(Advanced Manufacturing) 2024年第2期5卷 95-105页

作者： Cheng Zhang Liang Zhu Chengang Ji Zhilu Ye Nabeel Alsaab Minye Yang Yuhui Hu Pai-Yen Chen L.Jay Guo School of Optical and Electronic Information&Wuhan National Laboratory for Optoelectronics Huazhong University of Science and TechnologyWuhan430074China Department of Electrical and Computer Engineering University of Illinois at ChicagoChicagoIL 60607USA Department of Electrical Engineering and Computer Science University of MichiganAnn ArborMI 48109USA

Microwave antennas are essential elements for various applications,such as telecommunication,radar,sensing,and wireless power *** antennas are conventionally manufactured on rigid substrates using opaque materials,such as metal strips,metallic tapes,or epoxy pastes;thus,prohibiting their use in flexible and wearable devices,and simultaneously limiting their integration into existing optoelectronic ***,we demonstrate that mechanically flexible and optically transparent microwave antennas with high operational efficiencies can be readily fabricated using composite nanolayers deposited on common plastic *** composite nanolayer structure consists of an ultra-thin copper-doped silver film sandwiched between two dielectric films of tantalum pentoxide and aluminum *** material and thickness of each constituent layer are judiciously selected such that the whole structure exhibits an experimentally measured averaged visible transmittance as high as 98.94%compared to a bare plastic substrate,and simultaneously,a sheet resistance as low as 12.5Ω/*** representative types of microwave antennas are implemented:an omnidirectional dipole antenna,unidirectional Yagi-Uda antenna,low-profile patch antenna,and Fabry-Pérot cavity *** devices exhibit great mechanical flexibility with bending angle over 70°,high gain of up to 13.6 dBi,and large radiation efficiency of up to 84.5%.The proposed nano-engineered composites can be easily prepared over large areas on various types of substrates and simultaneously overcome the limitations of poor mechanical flexibility,low electrical conductivity,and reduced optical transparency usually faced by other constituent materials for flexible transparent microwave *** demonstrated flexible microwave antennas have various applications ranging from fifth-generation and vehicular communication systems to bio-signal monitors and wearable electronics.

关键词： Optically transparent antenna Flexible microwave antenna Transparent conductor Ultra-thin silver Doped silver Wearable optoelectronics

来源：评论

学校读者我要写书评

暂无评论

Designing Low-Power Industrial Networks with the Internet of Things 5th

Designing Low-Power Industrial Networks with the Internet of...

引用

5th International Conference on Data science, Machine Learning and Applications, ICDSMLA 2023

作者： Kannagi, A. Ansari, Tabish Nasurudeen Ahamed, N. Alam, Intekhab Karnataka Bangalore India Department of Civil Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Navgaon Manduwala Dehradun India School of Computer Science and Engineering Presidency University Karnataka Bengaluru India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India

ISBN: (纸本)9789819780426

The Internet of Things (IoT) revolution is evolving conventional commercial networks to fulfill the demands of present-day technological advancements. Low-electricity business networks are becoming increasingly vital to allow a green communique between linked systems and remote monitoring and management of gadgets. Designing and deploying low-electricity networks for business programs brings many demanding situations, which include energy control, conversation latency, and cease-to-give-up safety. This summary will offer a top-level view of the layout issues while implementing IoT and occasional-power business networks, in addition to the capability of high-quality practices for ensuring low-strength, comfortable, and reliable communications among connected devices. Furthermore, IoT techniques for localizing network accessibility, improving facts accuracy, and boosting community performance may be discussed. Subsequently, some of the trendy trends and trends in the industrial networking area could be highlighted. Low-power business networks are getting increasingly important to allow the green conversation of connected structures and remote tracking of devices. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Capability Management Strength

来源：评论

学校读者我要写书评

暂无评论

SRTNET: Time Domain Speech Enhancement via Stochastic Refinement 48

SRTNET: Time Domain Speech Enhancement via Stochastic Refine...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Qiu, Zhibin Fu, Mengfan Yu, Yinfeng Yin, Lili Sun, Fuchun Huang, Hao Xinjiang University School of Information Science and Engineering Urumqi China Tsinghua University Department of Computer Science and Technology China Xinjiang Key Laboratory of Multi-lingual Information Technology Urumqi China

ISBN: (纸本)9781728163277

Diffusion model, as a new generative model which is very popular in image generation and audio synthesis, is rarely used in speech enhancement. In this paper, we use the diffusion model as a module for stochastic refinement. We propose SRTNet, a novel method for speech enhancement via Stochastic Refinement in complete Time b domain. Specifically, we design a joint network consisting of a deterministic module and a stochastic module, which makes up the "enhance-and-refine"paradigm. We theoretically demonstrate the feasibility of our method and experimentally prove that our method achieves faster training, faster sampling and higher quality. Our code is available at https://***/zhibinQiu/*** © 2023 IEEE.

关键词： diffusion model enhance-and-refine joint training speech enhancement time domain

来源：评论

学校读者我要写书评

暂无评论

Effective Density-Based Concept Drift Detection for Evolving Data Streams 24th

Effective Density-Based Concept Drift Detection for Evolving...

引用

24th International Conference on Parallel and Distributed Computing, Applications and Technologies, PDCAT 2023

作者： Cui, Zelin Tian, Hui Shen, Hong Institute of Information Security Engineering Chinese Academy of Sciences Beijing China School of Information and Communication Technology Griffith University Brisbane Australia Faculty of Applied Sciences Macao Polytechnic University China School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China

ISBN: (纸本)9789819982103

Concept drift is a common phenomenon appearing in evolving data streams of a wide range of applications including credit card fraud protection, weather forecast, network monitoring, etc. For online data streams it is difficult to determine a proper size of the sliding window for detection of concept drift, making the existing dataset-distance based algorithms not effective in application. In this paper, we propose a novel framework of Density-based Concept Drift Detection (DCDD) for detecting concept drifts in data streams using density-based clustering on a variable-size sliding window through dynamically adjusting the size of the sliding window. Our DCDD uses XGBoost (eXtreme Gradient Boosting) to predict the amount of data in the same concept and adjusts the size of the sliding window dynamically based on the collected information about concept drifting. To detect concept drift between two datasets, DCDD calculates the distance between the datasets using a new detection formula that considers the attribute of time as the weight for old data and calculates the distance between the data in the current sliding window and all data in the current concept rather than between two adjacent windows as used in the exiting work DCDA [2]. This yields an observable improvement on the detection accuracy and a significant improvement on the detection efficiency. Experimental results have shown that our framework detects the concept drift more accurately and efficiently than the existing work. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Intelligent Transportation systems in Smart City: A Systematic Survey

Intelligent Transportation Systems in Smart City: A Systemat...

引用

2023 International Conference on Robotics and Automation in Industry, ICRAI 2023

作者： Hassan, Muhammad Abul Javed, Roofia Farhatullah Granelli, Fabrizio Gen, Xin Rizwan, Muhammad Ali, Syed Haider Junaid, Hazrat Ullah, Sana University of Trento Department of Information Engineering and Computer Science Trento Italy Kinnarid College for Women Department of Computer Science Lahore Pakistan School of Automation China University of Geosciences Wuhan China College of Engineering and Technology University of Derby Derby United Kingdom University of Engineering and Technology Department of Electrical Engineering Peshawar Pakistan University of Malakand Department of Computer Science and Information Technology Pakistan Qurtuba University of Science and Technology Department of Computer Science Peshawar Pakistan

ISBN: (纸本)9781665464727

The idea of Smart Cities (SCs) was developed to digitize conventional urban living areas and redevelop using digital equipment to enhance lifestyle and resident security. Smart cities cover a wide range of applications such as smart government, smart energy, smart transportation, smart health, and smart education. In this paper, we have examined the mobility-related application e.g., smart transportation. We have focused on related to smart transportation like traffic safety, passenger and driver safety, obstacle detection, accident prevention, crime prevention, and detection, and more importantly smart vehicles like UAVs which played a key role in making these gadgets easy to use in urban environments. For a brief overview, 63 academic publications are examined in the field of ITS and SC technologies. Furthermore, we have provided possible solutions in terms of security in the smart transportation system. © 2023 IEEE.

关键词： Big data

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：