检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Khot, Ayush Wang, Xiwei Roy, Avik Kindratenko, Volodymyr Neubauer, Mark S. Department of Physics University of Illinois Urbana-Champaign UrbanaIL61801 United States The Grainger College of Engineering Department of Electrical and Computer Engineering University of Illinois Urbana-Champaign UrbanaIL61801 United States Center for Artificial Intelligence Innovation National Center for Supercomputing Applications University of Illinois Urbana-Champaign UrbanaIL61801 United States The Grainger College of Engineering Siebel School of Computing and Data Science University of Illinois Urbana-Champaign UrbanaIL61801 United States

Current methods commonly used for uncertainty quantification (UQ) in deep learning (DL) models utilize Bayesian methods which are computationally expensive and time-consuming. In this paper, we provide a detailed study of UQ based on evidential deep learning (EDL) for deep neural network models designed to identify jets in high energy proton-proton collisions at the Large Hadron Collider and explore its utility in anomaly detection. EDL is a DL approach that treats learning as an evidence acquisition process designed to provide confidence (or epistemic uncertainty) about test data. Using publicly available datasets for jet classification benchmarking, we explore hyperparameter optimizations for EDL applied to the challenge of UQ for jet identification. We also investigate how the uncertainty is distributed for each jet class, how this method can be implemented for the detection of anomalies, how the uncertainty compares with Bayesian ensemble methods, and how the uncertainty maps onto latent spaces for the models. Our studies uncover some pitfalls of EDL applied to anomaly detection and a more effective way to quantify uncertainty from EDL as compared with the foundational EDL setup. These studies illustrate a methodological approach to interpreting EDL in jet classification models, providing new insights on how EDL quantifies uncertainty and detects out-of-distribution data which may lead to improved EDL methods for DL models applied to classification tasks. © 2025, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Throughput Maximization in Wireless Powered Communication Networks

Throughput Maximization in Wireless Powered Communication Ne...

引用

Automation and Computation (AUTOCOM), International Conference on

作者： Mukul Mishra Koushik V Prasad S Gowri Neeraj Das Shikhar Gupta Prasant Kumar Sahoo Chitkara Centre for Research and Development Chitkara University Baddi Himachal Pradesh India School of Engineering and Technology Mechanical Engineering JAIN (Deemed to be University) Bangalore Karnataka Department of Information Technology Sathyabama Institute of Science and Technology Chennai Tamil Nadu India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Centre of Research Impact and Outcome Chitkara University Rajpura Punjab India Department of Computer Applications Siksha ‘O’ Anusandhan (Deemed to be University) Bhubaneswar Odisha India

ISBN: (数字)9798331542375

ISBN: (纸本)9798331542382

One promising solution for energy-constrained wireless devices is wireless-powered communication networks (WPCNs), where mobile users harvest energy from the dedicated transmitters, which power the information transmission and do not need to rely on limited-life batteries. Nevertheless, the major issue in WPCNs lies in how to achieve high throughput, and yet energy constraint-compliant devices need to be considered. Summary: This paper surveys throughput maximization in WPCNs. One way to enhance the throughput of WPCNs is to perform resource allocation by which available energy and communication resources are jointly allocated among devices. The value of harvesting energy compared to transmitting data will be the same through different techniques like power splitting and time sharing. The third major problem of WPCNs for harvesting maximum throughput is energy transmission, which uses the energy sources through their power levels to ensure optimal scheduling order to supply power. Other advanced techniques like dynamic power control and channel estimation are implemented to optimize the overall system throughput and obtain higher energy efficiency.

关键词： Wireless communication Surveys Transmitters System performance Wireless power transfer Throughput Energy efficiency Communication networks Energy harvesting Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Radio Resource Management for Hybrid Satellite-Terrestrial Network

Radio Resource Management for Hybrid Satellite-Terrestrial N...

引用

Automation and Computation (AUTOCOM), International Conference on

作者： Revathy S Intekhab Alam Maharishi Deepak Minhas Jogeswar Tripathy Ishika Soni Vinay Kumar S B Department of Information Technology Sathyabama Institute of Science and Technology Chennai Tamil Nadu India School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Centre of Research Impact and Outcome Chitkara University Rajpura Punjab India Department of Computer Applications Siksha ‘O’ Anusandhan (Deemed to be University) Bhubaneswar Odisha India Chitkara Centre for Research and Development Chitkara University Baddi Himachal Pradesh India School of Engineering and Technology Electronics and Communication Engineering JAIN (Deemed to be University) Bangalore Kamataka India

ISBN: (数字)9798331542375

ISBN: (纸本)9798331542382

Hybrid satellite-terrestrial networks demand proficient coordination of Radio Resource Management (RRM). Together, these networks offer the best of both satellite and terrestrial communicative technologies for fast and widespread connectivity. However, it is a difficult task to manage the limited radio resources involved in this very heterogeneous environment. The main goal of RRM in hybrid satellite-terrestrial networks is to provide efficient resource utilization and quality of service support for different applications. They touch on areas such as interference management, spectrum sharing, handover between satellite links, and offloading to terrestrial networks. In order to make RRM more efficient, the following techniques are used during resource allocation: adaptive modulation and coding (AMC), dynamic scheduling, and power control. Such techniques exploit network topology, propagation conditions, and user location to increase spectral efficiency and reduce interference.

关键词： Spectral efficiency Wireless networks Satellite broadcasting Power control Quality of service Interference Space-air-ground integrated networks Resource management Security Reliability

来源：评论

学校读者我要写书评

暂无评论

Efficient Abstraction of Healthcare Data for Real-Time Decision Making Using Logistic Regression and Linear Regression

Efficient Abstraction of Healthcare Data for Real-Time Decis...

引用

Automation and Computation (AUTOCOM), International Conference on

作者： Abhinav Rathour Debabrata Singh Hitesh Kalra Anila Bajpai Dhananjay Kumar Yadav A. Sabarivani Centre of Research Impact and Outcome Chitkara University Rajpura Punjab India Department of Computer Applications Siksha ‘O’ Anusandhan (Deemed to be University) Bhubaneswar Odisha India Chitkara Centre for Research and Development Chitkara University Baddi Himachal Pradesh India School of Mangement - UG Management JAIN (Deemed to be University) Bangalore Karnataka India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Department of Biomedical Engineering Sathyabama Institute of Science and Technology Chennai Tamil Nadu India

ISBN: (数字)9798331542375

ISBN: (纸本)9798331542382

Data analytics can help drive decision-making and improve patient outcomes in healthcare. But of course, healthcare data is complex, and the process to access & analyze it can be slow. Here, researchers suggest a way to generalize healthcare data at scale and do so quickly enough for real-time decision support. Logistic regression is used to categorize patient data into various groupings using established standards, which could create a targeted patient population that is at high risk. We then perform linear regression on patients' demographics and medical history to predict their outcomes. This information can help with real-time decisions for patient care. Our method will decrease the time and cost of collecting/analyzing healthcare data for faster decision-making. This is particularly crucial in a rapidly moving healthcare environment where every second counts. Also, logistic and linear regression techniques have been used together to perform a complete data analysis so that the predictions are as accurate as possible. The methodology allows us to effectively abstract healthcare data for healthcare providers' (HCP) real-time decision-making. This process can deliver advances in patient care and efficiencies in effectuating decisions-and it could provide immense benefits across healthcare.

关键词： Logistic regression Accuracy Data analysis Computational modeling Linear regression Decision making Medical services Predictive models Real-time systems Logistics

来源：评论

学校读者我要写书评

暂无评论

On Convergence of Tabu-Enhanced Quantum Annealing Algorithm 24th

On Convergence of Tabu-Enhanced Quantum Annealing Algorithm

引用

24th International Conference on Distributed computer and Communication Networks, DCCN 2021

作者： Rumyantsev, A.S. Pastorello, D. Blanzieri, E. Cavecchia, V. Institute of Applied Mathematical Research Karelian Research Centre of RAS Pushkinskaya Street 11 Republic of Karelia Petrozavodsk185000 Russia Petrozavodsk State University 33 Lenina Pr. Petrozavodsk Russia Department of Information Engineering and Computer Science University of Trento via Sommarive 9 Povo Trento38123 Italy Trento Institute of Fundamental Physics and Applications via Sommarive 14 Povo Trento38123 Italy via alla Cascata 56/c Povo Trento38123 Italy

ISBN: (纸本)9783030971090

The convergence of a recently proposed tabu-enhanced quantum annealing algorithm depends critically on the finiteness of memory of the related stochastic process. We discuss the background of quantum annealing and the convergence issues of the tabu-enhanced algorithm. Given the details of the tabu data structure, the so-called tabu matrix, we consider the sequences of solutions that result in a tabu matrix collisions. As such, convergence of the algorithm is related to the problem of studying the so-called matrix kernel, which we investigate and give an example of such a collision as well. © 2022, Springer Nature Switzerland AG.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Algorithms for Business Management: Ethical Considerations

Deep Learning Algorithms for Business Management: Ethical Co...

引用

Communication, computer sciences and Engineering (IC3SE), International Conference on

作者： Shiney Chib B Santhosh Kumar V Asha Navdeep Singh Melanie Lourens Dyuti Banerjee Management Datta Meghe Institute of Management Studies Nagpur Maharashtra Institute of Aeronautical Engineering Dundigal Hyderabad Department of Computer Applications New Horizon College of Engineering Bangalore Lovely Professional University Phagwara Deputy Dean Faculty of Management Sciences Durban University of Technology South Africa Artificial intelligence & Data Science (AI&DS) Koneru Lakshmaiah Education Foundation Green Fields Vaddeswaram Guntur District Andhra Pradesh

ISBN: (数字)9798350366846

ISBN: (纸本)9798350366853

By applying the right method to extract both structured and unstructured data, data science may add value. Accelerated deep learning advancement has led to substantial changes in data science operations. Deep learning is a sophisticated machine learning algorithmic method. It differs significantly from other machine learning procedures in that it uses a straightforward method to provide data to the system. To tackle difficult issues and make wise business decisions, deep learning leverages cutting-edge analytics. As smart manufacturing initiatives expand, deep leaning is seen as a potential avenue to boost efficiency and sustainability even further. In this study, we look into how DL models can enhance the application of business intelligence by organisational management. The results show that DL models may be trained on diverse data sources to identify linkages and patterns in the data. These models can assist decision-makers in making well-informed decisions based on accurate and reliable data.

关键词： Deep learning Accuracy Computational modeling Soft sensors Decision making Data science Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

A defected ground structure based ultra-compact wider bandwidth terahertz multiple-input multiple-output antenna for emerging communication systems

引用

Heliyon 2024年第17期10卷 e36842页

作者： Kumar, Praveen Sivakumar, V. Rao, Vidya George, Criss Tom Awadhiya, Bhaskar Huchegowda, Yogeshwary Bommenahalli Nanjappa, Yashwanth Department of Electronics and Communication Engineering Manipal Institute of Technology Manipal Academy of Higher Education Manipal 576104 India Department of Information & Communication Technology Manipal Institute of Technology Manipal Academy of Higher Education Manipal 576104 India Department of Data Science and Computer Applications Manipal Institute of Technology Manipal Academy of Higher Education Manipal 576104 India Department of Electronics and Communication Engineering Shri Madhwa Vadiraja Institute of Technology and Management Visvesvaraya Technological University Bantakal 574115 India

This work presents a quad-port Multiple Input Multiple Output (MIMO) wideband antenna that operates in the terahertz (THz) frequency range is designed and analyzed. To improve MIMO performance, a defective ground structure (DGS) is used. A rectangular metallic patch was altered by adding parasitic elements to the radiator with the lowered ground plane on a polyamide substrate in order to achieve the wideband THz operating frequency. The THz antenna was turned into a MIMO antenna by replicating horizontally and vertically with a spacing of 0.05 λ and 0.002 λ, respectively (λ calculated at 1.7 THz). The designed THz MIMO antenna, comprising 40 μm × 46 μm × 2 μm, operates across the 1.7–10.4 THz frequency region. The THz MIMO antenna provides isolation of more than 20 dB in the frequency range of 2.8–10.4 THz and more than 10 dB for the frequency of 1.7–2.7 THz. Isolation augmentation is accomplished by establishing different local current channels using the antenna's DGS. The MIMO diversity properties of the proposed THz MIMO antenna are analyzed and found to be ECC<0.004, DG ~ 10 dB, TARC < −10 dB, MEG < −3 dB, and CCL<0.23 bps/Hz over the antenna's operating frequency. © 2024 The Author(s)

关键词： DGS MIMO THz antenna Wideband

来源：评论

学校读者我要写书评

暂无评论

Survey on Deep Learning Techniques Used for Classification of Underwater Sonar Images

SSRN

引用

SSRN 2020年

作者： Divyabarathi, G. Shailesh, S. Judy, M.V. Department of Computer Applications Cochin University of Science and Technology KochiKerala India

Object detection methods have been evolving as deep learning gives the major support for the classification of the dataset irrespective of the domain. In this paper, underwater sonar image target detection methods are reviewed using deep learning comparatively. Types of sonar-like side-scan sonar, forward-looking sonar, synthetic aperture sonar provide higher resolution images than optical images in low illuminated water. Recently research on underwater exploration using Automated underwater vehicles (AUV) mounted with sonar sensors are evolving to support long searches to find objects of interest. The object detection can help us classify mines, seafloor, ocean habitats, shipwrecks, and finding drowning victims. This paper specifies a survey on state-of-the-art deep learning techniques used for underwater object detection from Sonar images. The study shows that deep learning techniques using transfer learning in real datasets as well as in semisynthetic dataset helps improve the efficiency of object detection. © 2020, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A METHOD TO COMPUTE THE STRENGTH USING BOUNDS

arXiv

引用

arXiv 2023年

作者： Ichishima, Rikio Muntaner-Batle, Francesc A. Takahashi, Yukio Department of Sport and Physical Education Faculty of Physical Education Kokushikan University 7-3-1 Nagayama Tama-shi Tokyo206-8515 Japan Graph Theory and Applications Research Group School of Electrical Engineering and Computer Science Faculty of Engineering and Built Environment The University of Newcastle NSW2308 Australia Department of Science and Engineering Faculty of Electronics and Informatics Kokushikan University 4-28-1 Setagaya Setagaya-ku Tokyo154-8515 Japan

A numbering f of a graph G of order n is a labeling that assigns distinct elements of the set {1, 2, . . ., n} to the vertices of G. The strength str (G) of G is defined by str (G) = min {strf (G) |f is a numbering of G }, where strf (G) = max {f (u) + f (v) |uv ∈ E (G) }. A few lower and upper bounds for the strength are known and, although it is in general hard to compute the exact value for the strength, a reasonable approach to this problem is to study for which graphs a lower bound and an upper bound for the strength coincide. In this paper, we study general conditions for graphs that allow us to determine which graphs have the property that lower and upper bounds for the strength coincide and other graphs for which this approach is *** Codes 05C78 90C27 © 2023, CC BY.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

ASSOCIATION BETWEEN TRANSPORTATION NOISE EXPOSURE AND HYPERTENSION RISK IN THE FRENCH E3N COHORT 10

ASSOCIATION BETWEEN TRANSPORTATION NOISE EXPOSURE AND HYPERT...

引用

10th Convention of the European Acoustics Association, EAA 2023

作者： Faure, É. Houeto, A. Boileau, A. Perrin, C. Gelot, A. Correia, E. Artaud, F. Jamard, P. Munoz, A. Perez Mietlicki, F. Quenez, M. Gissinger, V. Domergue, C. Janillon, V. Vincent, B. Mohamed, F. Godet, K. Giorgis-Allemand, L. Leduc, J. Evrard, A.-S. Severi, G. Paris-Saclay University UVSQ Paris-Sud Univ Inserm Gustave Roussy Exposome and Heredity team Center of Epidemiology and Population Health Villejuif94805 France Bruitparif Center for Technical Assessment of the Sound Environment in Île-de-France Paris France Acoucité Sound Environment Observatory Lyon France Lyon Univ Gustave Eiffel Univ Lyon 1 Univ UMRESTTE UMR_T9405 Lyon France University of Orléans UFR Droit Économie et Gestion Orléans la Source France Department of Statistics Computer Science Applications"G. Parenti" University of Florence Italy

ISBN: (纸本)9788888942674

Background: Exposure to transportation noise seems to be associated with a hypertension (HTA) risk. Few studies have explored this association in Europe and even less in France in a prospective cohort. This is therefore the objective of the present study. Methods: Transportation noise exposure was estimated from two periodic strategic noise maps at the residence of 21, 515 women from the French E3N cohort, residing in the Île-de-France or Auvergne-Rhône-Alpes regions between 2000 and 2014. Lden (day-evening-night level) indicator was used for three noise sources: road, railway and aircraft. Incident HTA cases were identified using follow-up questionnaires and validated using drug reimbursement insurance databases. Results: Over the period 2000 to 2014, 85% of women were exposed to at least one transportation noise source and at least 82% of these women were exposed to noise levels that exceed one of the World Health Organization (WHO) guidelines. Conclusions: A large proportion of the women from the E3N cohort who lived in Île-de-France or Auvergne-Rhône-Alpes during the period 2000-2014 were exposed to noise levels that exceeded WHO guidelines for transportation noise. Results of the study for the association between transportation noise exposure and HTA risk will be presented at the conference. © 2023 E. Faure et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 Unported License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

关键词： Noise pollution

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：