检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zhang, Wenyu Bai, Kaiyuan Zeadally, Sherali Zhang, Haijun Shao, Hua Ma, Hui Leung, Victor C.M. The School of Intelligence Science and Technology The Institute of Artificial Intelligence University of Science and Technology Beijing Beijing100083 China The China Telecom Research Institute Beijing100096 China The College of Communication and Information University of Kentucky LexingtonKY40506 United States Institute of Artificial Intelligence Beijing Advanced Innovation Center for Materials Genome Engineering Beijing Engineering and Technology Research Center for Convergence Networks and Ubiquitous Services University of Science and Technology Beijing Beijing100083 China The College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China The Department of Electrical and Computer Engineering The University of British Columbia VancouverBCV6T 1Z4 Canada

Semantic communication is a new paradigm that exploits deep learning models to enable end-to-end communications processes, and recent studies have shown that it can achieve better noise resiliency compared with traditional communication schemes in a low signal-to-noise (SNR) regime. To achieve multiple access in semantic communication, we propose a deep learning-based multiple access (DeepMA) method by training semantic communication models with the abilities of joint source-channel coding (JSCC) and orthogonal signal modulation. DeepMA is achieved by a DeepMA network (DMANet), which is comprised of several independent encoder-decoder pairs (EDPs), and the DeepMA encoders can encode the input data as mutually orthogonal semantic symbol vectors (SSVs) such that the DeepMA decoders can recover their own target data from a received mixed SSV (MSSV) superposed by multiple SSV components transmitted from different encoders. We describe frameworks of DeepMA in wireless device-to-device (D2D), downlink, and uplink channel multiplexing scenarios, along with the training algorithm. We evaluate the performance of the proposed DeepMA in wireless image transmission tasks and compare its performance with the attention module-based deep JSCC (ADJSCC) method and conventional communication schemes using better portable graphics (BPG) and Low-density parity-check code (LDPC). The results obtained show that the proposed DeepMA can achieve effective, flexible, and privacy-preserving channel multiplexing process, and demonstrate that our proposed DeepMA approach can yield comparable bandwidth efficiency compared with conventional multiple access schemes. © 2023, CC BY.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Teacher-student networks with multiple decoders for solving math word problem 29

Teacher-student networks with multiple decoders for solving ...

引用

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Zhang, Jipeng Lee, Roy Ka-Wei Lim, Ee-Peng Qin, Wei Wang, Lei Shao, Jie Sun, Qianru Center for Future Media University of Electronic Science and Technology of China China School of Information Systems Singapore Management University Singapore Department of Computer Science University of Saskatchewan Canada School of Computer Science and Information Engineering Hefei University of Technology China Sichuan Artificial Intelligence Research Institute China

ISBN: (纸本)9780999241165

Math word problem (MWP) is challenging due to the limitation of training data where only one "standard" solution is provided. MWP models often fit the solution rather than truly understand or solve the problem. The generalization of models (to diverse word scenarios) is thus limited. To address this problem, we propose a novel approach we call TSN-MD that leverages a teacher network to integrate the knowledge of equivalent solution expressions such as to better regularize the learning behavior of the student network. In addition, we introduce the multiple-decoder student network to generate multiple candidate solution expressions by which the final answer is voted. In experiments, we conduct extensive comparisons and ablative studies on two large-scale MWP benchmarks, and show that using TSN-MD can surpass the state-of-the-art works by large margins. Intriguingly, the visualization results demonstrate that TSN-MD not only produces correct answers but also generates diverse equivalent expressions for the solution. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Case study on the tactical level of an autonomous vehicle control

Case study on the tactical level of an autonomous vehicle co...

引用

2021 IEEE International Conference on Electrical, computer, Communications and Mechatronics engineering, ICECCME 2021

作者： Pozna, Claudiu Radu Antonya, Csaba Horvath, Erno Transilvania University of Brasov Department of Automation and Information Technology Brasov Romania Department of Computer Science Széchenyi István University Györ Hungary Transilvania University of Brasov Department of Automotive and Transport Engineering Brasov Romania Széchenyi István University Department of Research Center of Vehicle Industry Györ Hungary

ISBN: (纸本)9781665412629

In this paper, a case study is presented on the tactical level of autonomous vehicle control. Inspired by the human driver behavior, vehicle control is structured in a hierarchy on three levels: the strategic, the tactical, and the operational level. These are connected by specific links, and based on prior information and models, are transforming the input data from the environment into actuator commands on the various degree of freedom of the vehicle. The case study is presenting a simulation of a scenario, detailing the vehicle models with sensors, the collection of behavior, and the behavior selector. © 2021 IEEE.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

Combined Federated and Split Learning in Edge Computing for Ubiquitous Intelligence in Internet of Things: State of the Art and Future Directions

arXiv

引用

arXiv 2022年

作者： Duan, Qiang Hu, Shijing Deng, Ruijun Lu, Zhihui The Information Sciences & Technology Department Pennsylvania State University AbingtonPA19002 United States The School of Computer Science Fudan University Shanghai200082 China The Shanghai Blockchain Engineering Research Center Shanghai200000 China

Federated learning (FL) and split learning (SL) are two emerging collaborative learning methods that may greatly facilitate ubiquitous intelligence in Internet of Things (IoT). Federated learning enables machine learning (ML) models locally trained using private data to be aggregated into a global model. Split learning allows different portions of an ML model to be collaboratively trained on different workers in a learning framework. Federated learning and split learning, each has unique advantages and respective limitations, may complement each other toward ubiquitous intelligence in IoT. Therefore, combination of federated learning and split learning recently became an active research area attracting extensive interest. In this article, we review the latest developments in federated learning and split learning and present a survey on the state-of-the-art technologies for combining these two learning methods in an edge computing-based IoT environment. We also identify some open problems and discuss possible directions for future research in this area with a hope to further arouse the research community's interest in this emerging field. © 2022, CC BY-NC-ND.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Differential Privacy Based on Data Provenance Publishing Method

引用

Jisuanji Xuebao/Chinese Journal of computers 2020年第3期43卷 573-586页

作者： Ni, Wei-Wei Shen, Tao Yan, Dong Department of Computer Science and Engineering Southeast University Nanjing211189 China Key Laboratory of Computer Network and Information Integration in Southeast University Ministry of Education Nanjing211189 China

Data provenance describes the mechanism and process of data generation and evolution, which records information about the node module executions used to produce concrete data items, as well as those intermediate data items acting as parameters passed between nodes' executions. Data provenance plays an important role in research and applications of data quality assessment, data recovery and data analysis. With increasingly deepening of data sharing, the need for publishing and sharing workflow of provenance, which is the main representation structure of data provenance, becomes increasingly urgent. However, the provenance workflow often contains private or confidential data. For instance, the node modules included in the provenance workflow, as well as the temporal relations among those nodes, may involve the privacy of the data owner. Direct release of provenance workflow will inevitably bring privacy protection issues. Privacy-preserving data provenance publication becomes an urgent problem to be solved. That is to say, the utility of published provenance workflow needs well maintaining under the premise that data privacy should not be disclosed. The existing research mainly focuses on the maintenance of the local mapping relationship of provenance workflow. For example, privacy protection process is implemented to the provenance workflow, which ensures that the degree of a single node would not be leaked, or sensitive mapping relationship would not be leaked in parallel with effective maintaining of provenance workflow's overall input and output mapping relations. For another important manifestation of provenance workflow's utility, i.e. temporal dependence among those front and corresponding back task nodes of the provenance workflow, the maintenance effect is relatively poor. As for the privacy of adjacent nodes distribution in the provenance workflow, the protection ability of existing methods is also far insufficient. To solve the above problems, the definitio

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Machine learning model for predicting pancreatic fistula after pancreatoduodenectomy

Machine learning model for predicting pancreatic fistula aft...

引用

Intelligent Methods, Systems, and Applications (IMSA)

作者： Hager Saleh Nora El-Rashidy Eman Mohamed Ahmad M Sultan Ayman El Nakeeb Shaker El-Sappagh Faculty of Computers and Artificial Intelligence South Valley University Hurghada Egypt Machine Learning and Information Retrieval Department Faculty of Artificial Intelligence Kafrelsheiksh University Kafrelsheiksh Egypt Faculty of Computers and Information Damnhour University Damnhour Egypt Gastroenterology Surgical Center Faculty of Medicine Mansoura University Mansoura Egypt Faculty of Computer Science and Engineering Galala University Suez Egypt

Pancreaticoduodenectomy (PD) is a complex surgery used mainly to treat tumors and other pancreas disorders. PD is considered one of the most challenging surgeries because it may have several complications, including bleeding and infections in the surgical area, temporary or permanent diabetes, and pancreatic leakage (PL), which may lead to morbidity and mortality. In this study, we build an accurate and medically oriented machine learning model that predicts PL after PD based on patient markers collected only before the PD operation. The study is made using a real-world dataset for 397 Egyptian patients. The proposed machine learning pipeline starts with a data preprocessing step that handles the missing data values by the median values. In the next step, diverse interpretable classifiers, including logistic regression, random forest, decision tree, support vector machine, XGBoost, and AdaBoost, are utilized to predict the PL. Hyperparameter optimization is done using grid search with k-fold cross-validation. The results indicate that XGBoost achieves the highest marks, outperforming the state-of-the-art techniques in several evaluation metrics (i.e., accuracy= 91%, precision= 90.96%, recall= 91.0%, F1-score= 90.97%, and AUC=89.78%. The resulting model is accurate enough to be medically relevant for PL prediction in real healthcare settings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Nanoparticle aggregation effect on nonlinear convective nanofluid flow over a stretched surface with linear and exponential heat source/sink

引用

International Journal of Thermofluids 2023年 19卷

作者： Rawat, Sawan Kumar Yaseen, Moh Shafiq, Anum Kumar, Manoj Al-Mdallal, Qasem M. Department of Mathematics Graphic Era Deemed to be University Uttarakhand Dehradun248 002 India Department of Applied Science Meerut Institute of Engineering and Technology Uttar Pradesh Meerut250 005 India School of Mathematics and Statistics Nanjing University of Information Science and Technology Nanjing China Center for Applied Mathematics of Jiangsu Province Nanjing University of Information Science and Technology Nanjing210044 China Department of Mathematics Statistics and Computer Science G. B. Pant University of Agriculture and Technology Uttarakhand Pantnagar263 145 India Department of Mathematical Sciences College of Science UAE University Al-AinP.O. Box 17551 United Arab Emirates

A nanofluid flow (TiO2/Ethylene Glycol) over a stretched surface caused by the considerable nonlinear convection is investigated with the nanoparticle aggregation effect in the presence of quadratic thermal radiation. The modified Maxwell model and Bruggeman model are utilized, which depict the nanoparticle aggregation effect. In addition, the system employs two separate variable heat sources i.e., linear heat source and exponential heat source. The similarity transformations are utilized to convert the basic governing PDEs to ODEs. The "bvp4c function" in MATLAB is used to numerically handle the resultant nonlinear system. The impact of the involved parameters is explored on the non-dimensional fields of velocity boundary layer patterns, velocity, streamlines, temperature, and heat transfer rate. Graphs compare and display the control of pertinent parameters on the distinct flow properties. A comparison of the behavior of the solution profiles with and without the influence of nanoparticle aggregation is illustrated. The nanoparticle aggregates significantly enhance the velocity and heat transmission mechanism. Furthermore, the influence of varied heat sources (linear and exponential) aids in growing the thermal boundary layer. Nanofluid flow with nanoparticle aggregation has a 5.36% higher Nusselt number value in comparison to flow without aggregation effect when the volume fraction of nanoparticles is varied from 0 to 0.1. The results of the study will be helpful in the fields where applications of a continuously stretching/shrinking surface are used like in many engineering processes and industries, glass-fiber production, aerodynamic extrusion of plastic sheets, and manufacturing of paper and rubber sheets. © 2023 The Author(s)

关键词： Titanium dioxide

来源：评论

学校读者我要写书评

暂无评论

Single-Photon Emitters in Aluminum Nitride by Zr ion Implantation

Single-Photon Emitters in Aluminum Nitride by Zr ion Implant...

引用

Conference on Lasers and Electro-Optics (CLEO)

作者： Alexander Senichev Zachariah O. Martin Yongqiang Wang Han Htoon Alexei S. Lagutchev Alexandra Boltasseva Vladimir M. Shalaev School of Electrical and Computer Engineering Birck Nanotechnology Center and Purdue Quantum Science and Engineering Institute Purdue University West Lafayette IN USA U.S. Department of Energy (DOE) National Quantum Information Science Research Center Quantum Science Center (QSC) Oak Ridge TN USA Materials Science and Technology Division Los Alamos National Laboratory Ion Beam Materials Laboratory Los Alamos NM USA Center for Integrated Nanotechnologies Materials Physics and Applications Division Los Alamos National Laboratory Los Alamos NM USA

We report on the generation of single-photon emitters in aluminum nitride films through Zr-ion implantation, which was predicted to form optically addressable spin defects. We studied implantation conditions, post-imp... 详细信息

ISBN: (纸本)9781957171258

关键词： Chemical vapor deposition Emission Fluorescence Ion beams Ions Photoluminescence

来源：评论

学校读者我要写书评

暂无评论

A facial feature discovery framework for race classification using deep learning

arXiv

引用

arXiv 2021年

作者： Khan, Khalil Ali, Jehad Uddin, Irfan Khan, Sahib Roh, Byeong-Hee Department of Information Technology and Computer Science Pak-Austria Institute of Applied Science and Technology Haripur Pakistan Dept. of Computer Engineering Dept. of AI Convergence Network Suwon Korea Republic of Departmet of Computer Science Superior College Lahore Pakistan Department of Electronics and Telecommunications Politecnico di Torino Torino Italy

Race classification is a long-standing challenge in the field of face image analysis. The investigation of salient facial features is an important task to avoid processing all face parts. Face segmentation strongly benefits several face analysis tasks, including ethnicity and race classification. We propose a race-classification algorithm using a prior face segmentation framework. A deep convolutional neural network (DCNN) was used to construct a face segmentation model. For training the DCNN, we label face images according to seven different classes, that is, nose, skin, hair, eyes, brows, back, and mouth. The DCNN model developed in the first phase was used to create segmentation results. The probabilistic classification method is used, and probability maps (PMs) are created for each semantic class. We investigated five salient facial features from among seven that help in race classification. Features are extracted from the PMs of five classes, and a new model is trained based on the DCNN. We assessed the performance of the proposed race classification method on four standard face datasets, reporting superior results compared with previous studies. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Continuity of entropies via integral representations

arXiv

引用

arXiv 2024年

作者： Berta, Mario Lami, Ludovico Tomamichel, Marco Institute for Quantum Information RWTH Aachen University Germany QuSoft Science Park 123 Amsterdam1098 XG Netherlands Korteweg–de Vries Institute for Mathematics University of Amsterdam Science Park 105-107 Amsterdam1098 XG Netherlands Institute for Theoretical Physics University of Amsterdam Science Park 904 Amsterdam1098 XH Netherlands Center for Quantum Technologies National University of Singapore Singapore Department of Electrical and Computer Engineering College of Design and Engineering National University of Singapore Singapore

We show that Frenkel’s integral representation of the quantum relative entropy provides a natural framework to derive continuity bounds for quantum information measures. Our main general result is a dimension-independent semi-continuity relation for the quantum relative entropy with respect to the first argument. Using it, we obtain a number of results: (1) a tight continuity relation for the conditional entropy in the case where the two states have equal marginals on the conditioning system, resolving a conjecture by Wilde in this special case;(2) a stronger version of the Fannes–Audenaert inequality on quantum entropy;(3) better estimates on the quantum capacity of approximately degradable channels;(4) an improved continuity relation for the entanglement cost;(5) general upper bounds on asymptotic transformation rates in infinite-dimensional entanglement theory;and (6) a proof of a conjecture due to Christandl, Ferrara, and Lancien on the continuity of ‘filtered’ relative entropy distances. Copyright © 2024, The Authors. All rights reserved.

关键词： Quantum entanglement

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：