检索结果-内蒙古大学图书馆

Federated Conference on computer science and Information Systems (FedCSIS)

作者： Sylvia Melzer Meike Klettke Franziska Weise Kaja Harter-Uibopuu Ralf Möller Universität Hamburg Centre for the Study of Manuscript Cultures Hamburg Germany University of Luebeck Institute of Information Systems Luebeck Germany Faculty for Computer Science and Data Science University of Regensburg Regensburg Germany

The importance of federated information retrieval (FIR) is growing in humanities research. Unlike traditional centralized information retrieval methods, where searches are conducted within a logically centralised collection of documents, FIR treats each information system as an independent source with its own unique characteristics. Searching these systems together as a centralised source results in lower precision in humanities research, even when the research data itself is structured and stored according to standardised guidelines such as EpiDoc, and requires the need to be able to trace the origin of records to avoid incorrect historical conclusions. Matching of queries against all data sets in each source is proving less effective. A global search index that enables traceable matching of key values deemed relevant would provide a more robust solution here. In this article, we propose a solution that introduces a novel EpiDoc data matching procedure, facilitating traceable FIR across distinct epigraphic sources.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Characterizing Continual Learning Scenarios and Strategies for Audio Analysis

arXiv

引用

arXiv 2024年

作者： Bhatt, Ruchi Kumari, Pratibha Mahapatra, Dwarikanath Saddik, Abdulmotaleb El Saini, Mukesh The Department of Computer Science & Engineering Indian Institute of Technology Punjab Ropar India The Faculty of Informatics and Data Science University of Regensburg Regensburg Germany Inception Institute of AI Abu Dhabi United Arab Emirates Abu Dhabi United Arab Emirates School of Electrical Engineering and Computer Science University of Ottawa Canada The Department of Computer Science & Engineering Indian Institute of Technology Punjab Ropar India Abu Dhabi United Arab Emirates

Audio analysis is useful in many application scenarios. The state-of-the-art audio analysis approaches assume that the data distribution at training and deployment time will be the same. However, due to various real-life environmental factors, the data may encounter drift in its distribution or can encounter new classes in the late future. Thus, a one-time trained model might not perform adequately. In this paper, we characterize continual learning (CL) approaches in audio analysis. In this paper, we characterize continual learning (CL) approaches, intended to tackle catastrophic forgetting arising due to drifts. As there is no CL dataset for audio analysis, we use DCASE 2020 to 2023 datasets to create various CL scenarios for audio-based monitoring tasks. We have investigated the following CL and non-CL approaches: EWC, LwF, SI, GEM, A-GEM, GDumb, Replay, Naive, cumulative, and joint training. The study is very beneficial for researchers and practitioners working in the area of audio analysis for developing adaptive models. We observed that Replay achieved better results than other methods in the DCASE challenge data. It achieved an accuracy of 70.12% for the domain incremental scenario and an accuracy of 96.98% for the class incremental scenario. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Advanced Bandwidth Management Techniques Using Wireless Mesh Networks for High-Speed Optical Fiber Communications 3

Advanced Bandwidth Management Techniques Using Wireless Mesh...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Yadav, Rakesh Kumar Sharma, Sunil Seth, Kanika Jeyalaxmi, M. Ingle, Yashwant S. Vivek, V. Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Vivekananda Global University Department of Computer Science & Engineering Jaipur India Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Prince Shri Venkateshwara Padmavathy Engineering College Department of Science and Humanities Chennai127 India Vishwakarma Institute of Information Technology Department of Artificial Intelligence & Data Science Pune India Faculty of Engineering and Technology Karnataka Bangalore India

ISBN: (纸本)9798350319125

This abstract encompasses superior bandwidth management techniques the usage of Wi-Fi mesh networks to improve the performance of high-velocity optical fiber communications. the point of interest lies at the access-, relay-and center-mesh architectures with their diverse, discrete techniques consisting of dynamic frequency allocation, load balancing and node optimization, as well as on highlights from latest research. Within the experiments, the effects exhibit giant enhancement in signal first-rate and effectiveness of bandwidth resources when the use of the proposed version, based totally at the convergence speed of the network fee. Furthermore, it's also evident that the optimized wireless mesh configuration brings about enormous fee financial savings. All the findings obtained at some stage in this research have eminently greater the talents of the proposed structure for growing green communications networks. © 2023 IEEE.

关键词： Communications Convergence Experiments Networks Superior

来源：评论

学校读者我要写书评

暂无评论

Society with Trust: A Scientometrics Review of Zero-Knowledge Proof Advanced Applications in Preserving Digital Privacy for Society 5.0 1

引用

International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications, CITISIA 2022

作者： Dominic, Nicholas Pratama, Naufal Rizqi Cornelius, Kenny Senewe, Shavellin Herliman Pardamean, Bens Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Information System Department School of Information Systems Bina Nusantara University Jakarta11480 Indonesia Department of Computer Science Universitas Multimedia Nusantara Tangerang15111 Indonesia Psychology Department Faculty of Humanities Bina Nusantara University Jakarta11480 Indonesia BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia

ISBN: (数字)9783031290787

ISBN: (纸本)9783031290770

Society 5.0 focuses on human productivity in the midst of advanced technological services. While the concept has human trust at its core, technology development is now leading to zero-trust architecture. In this scientometrics review, 107 selected papers were analyzed to obtain the nature of the Zero-knowledge Proof (ZKP) theory and its advanced applications to favor digital privacy in greater society. With the common literature review strategy, it was found that the most citations in this field appeared in 2018, with IEEE, Springer, and Elsevier as the top three publishers. By affiliations, China and United States are both leading countries where the researcher comes from. And as the positive trend emerged, the ZKP mechanism will keep being leveraged as one of the cryptographic toolsets in the cloud services, Internet of Things (IoT), smart contracts, healthcare, electronic systems, and many other industrial needs. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Rates of (T-)asymptotic regularity of the generalized Krasnoselskii-Mann-type iteration

arXiv

引用

arXiv 2025年

作者： Firmino, Paulo Leuştean, Laurenţiu Departamento de Matemática Faculdade de Ciências Universidade de Lisboa Portugal LOS Faculty of Mathematics and Computer Science University of Bucharest Romania Simion Stoilow Institute of Mathematics The Romanian Academy Romania Institute for Logic and Data Science Bucharest Romania

In this paper we use proof mining methods to compute rates of (T-)asymptotic regularity of the generalized Krasnoselskii-Mann-type iteration associated to a nonexpansive mapping T: X → X in a uniformly convex normed space X. For special choices of the parameter sequences, we obtain quadratic *** Codes 47H05, 47H09, 47J25 © 2025, CC BY.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Pre-trained language models in Spanish for health insurance coverage 5

Pre-trained language models in Spanish for health insurance ...

引用

5th Workshop on Clinical Natural Language Processing, ClinicalNLP 2023. held at ACL 2023

作者： Aracena, Claudio Rodríguez, Nicolás Rocco, Victor Dunstan, Jocelyn Faculty of Physical and Mathematical Sciences University of Chile Chile Millennium Institute Foundational Research on Data Chile Chilean Safety Association Chile Department of Computer Science Catholic University of Chile Chile Institute for Mathematical and Computational Engineering Catholic University of Chile Chile Center for Mathematical Modeling University of Chile Chile

ISBN: (纸本)9781959429883

The field of clinical natural language processing (NLP) can extract useful information from clinical text. Since 2017, the NLP field has shifted towards using pre-trained language models (PLMs), improving performance in several tasks. Most of the research in this field has focused on English text, but there are some available PLMs in Spanish. In this work, we use clinical PLMs to analyze text from admission and medical reports in Spanish for an insurance and health provider to give a probability of no coverage in a labor insurance process. Our results show that fine-tuning a PLM pretrained with the provider's data leads to better results, but this process is time-consuming and computationally expensive. At least for this task, fine-tuning publicly available clinical PLM leads to comparable results to a custom PLM, but in less time and with fewer resources. Analyzing large volumes of insurance requests is burdensome for employers, and models can ease this task by pre-classifying reports that are likely not to have coverage. Our approach of entirely using clinical-related text improves the current models while reinforcing the idea of clinical support systems that simplify human labor but do not replace it. To our knowledge, the clinical corpus collected for this study is the largest one reported for the Spanish language. © 2023 Association for Computational Linguistics.

关键词： Health insurance

来源：评论

学校读者我要写书评

暂无评论

Design of a novel sensory neuromorphic circuit 6

Design of a novel sensory neuromorphic circuit

引用

6th IEEE Information Technology, Networking, Electronic and Automation Control Conference, ITNEC 2023

作者： Chen, Ni Peng, Kangbai Su, Jing Qin, Yurong Guangxi Medical University Department of Biomedical Engineering Nanning China Guangxi University College of Electrical Engineering Nanning China Guangxi University College of Computer and Electronic Information Nanning China Guangxi Medical University College of Information and Management Nanning China City University of Macau Faculty of Data Science China

ISBN: (纸本)9781665460033

To simulate the firing properties of sensory neurons, a sensory neuromorphic circuit was designed using generalized memristors and Mott memristors, and was tested under both DC and AC input conditions, respectively. The test results show that the effective input voltage range of the circuit is 3.5 V ~ 11 V, and the oscillation frequency range is 1.37 KHz ~ 6 KHz. When the input voltage is low ( 8.4 V), the spiking frequency tends to reduce, which faithfully emulates the properties of biological neurons. These research findings provide a new circuit solution scheme for realizing the artificial sensory system. © 2023 IEEE.

关键词： Memristors

来源：评论

学校读者我要写书评

暂无评论

Incremental Learning Algorithms for Broad Learning System with Node and Input Addition

Incremental Learning Algorithms for Broad Learning System wi...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Guang-Ze Chen Junwei Jin Hai-Wei Sun C. L. Philip Chen Department of Mathematics Faculty of Science and Technology University of Macau Macau China School of Artificial Intelligence and Big Data Henan University of Technology Zhengzhou China South China University of Technology and Pazhou Lab School of Computer Science and Engineering Guangzhou China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

The Broad Learning System (BLS) has been established as an effective flat network alternative to Deep Neural Networks (DNNs), delivering high efficiency while achieving competitive accuracy. Despite its advantages, the incremental learning methods of BLS face challenges in stability and computation when expanding with new nodes or input. We introduce two novel incremental learning algorithms based on factorization updates for BLS that optimize node and input additions to overcome these limitations. Our node addition algorithm utilizes QR decomposition and Cholesky factorization, using the update of the Cholesky factor instead of pseudo-inverse computations. For input addition, we propose an iterative Cholesky factor update algorithm. Our algorithms demonstrate not only faster computation compared to the existing BLS but also improved testing accuracy on the MNIST or Fashion-MNIST dataset. This work presents a significant step forward in the practical application and scalability of BLS in various data-dense environments.

关键词： Learning systems Incremental learning Accuracy Scalability Parallel processing Stability analysis Matrix decomposition Thermal stability Numerical stability Testing

来源：评论

学校读者我要写书评

暂无评论

Detail-preserving smoke simulation using an efficient high-order numerical scheme

引用

science China(Information sciences) 2020年第6期63卷 217-219页

作者： Jian ZHU Zhuo YANG Hanqiu SUN Enhua WU Ruichu CAI Zhifeng HAO School of Computer Science Guangdong University of Technology Institute of Space and Earth Info.Science the Chinese University of Hong Kong State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Faculty of Science and Technology University of Macau School of Mathematics and Big Data Foshan University

The advection step in Eulerian fluid simulation is prone to numerical dissipation [1], resulting in the loss of fluid details. Among the various attempts to develop accurate advection solvers, high-order advection schemes such as back and forth error compensation and correction (BFECC)[2] and MacCormack [3] are effective solutions. Complementary to high-order advection schemes are

关键词： CIP simulation Detail-preserving smoke simulation using an efficient high-order numerical scheme

来源：评论

学校读者我要写书评

暂无评论

Correcting for bias due to categorisation based on cluste analysis using multiple continuous error-prone exposures

arXiv

引用

arXiv 2023年

作者： Intemann, Timm Pigeot, Iris Biometry and Data Management Leibniz Institute for Prevention Research Epidemiology - BIPS Bremen Germany Faculty of Mathematics and Computer Science University Bremen Bremen Germany

The association between multidimensional exposure patterns and outcomes is commonly investigated by first applying cluster analysis algorithms to derive patterns and then estimating the associations. However, errors in the underlying continuous, possibly skewed, exposure variables lead to misclassified exposure patterns and therefore to biased effect estimates. This is often the case for lifestyle exposures in epidemiology, e.g. for dietary variables measured on daily basis. We introduce three new algorithms for correcting the biased effect estimates, which are based on regression calibration (RC), simulation extrapolation (SIMEX) and multiple imputation (MI). In addition, the naïve method ignoring the measurement error structure is considered for comparison. These methods are combined with the k-means cluster algorithm and the Gaussian mixture model to derive exposure patterns. The performance of the correction methods is compared in a simulation study regarding absolute, maximum and relative bias. The simulated data mimic a typical situation in nutritional epidemiology when diet is assessed using repeated 24-hour dietary recalls. Continuous and binary outcomes are considered. Simulation results show, that the correction method based on RC and MI perform better than the naïve and the SIMEX-based method. Furthermore, the MI-based approach, which can use outcome information in the error model, is superior to the RC-based approach in most scenarios. Therefore, we recommend using the MI-based approach. Copyright © 2023, The Authors. All rights reserved.

关键词： Measurement errors

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：