检索结果-内蒙古大学图书馆

68. Jahrestagung der Deutsche Gesellschaft fur Medizinische Informatik, Biometrie und Epidemiologie e.V., GMDS 2023 - 68th Annual Conference of the German Association for Medical Informatics, Biometry and Epidemiology, GMDS 2023

作者： Savoska, Snezana Ristevski, Blagoj Blazheska-Tabakovska, Natasha Jolevski, Ilija Bocevska, Andrijana Trajkovik, Vladimir Faculty of Information and Communication Technologies University "St. Kliment Ohridski" Bitola Macedonia Faculty of Computer Science and Engineering "Ss. Cyril and Methodius" University of Skopje Macedonia

The shortage of data for patients with chronic and other diseases and previous medical treatments shows significant weakness in the diagnosis and treatment of patients. Due to the healthcare system insufficiency, patients with comorbidities might not survive the diseases, especially when the disease is novel. The lack of information on patients’ genetic disorders, especially when they are unaware of them, also contributes to increased patient deaths. This conveys the necessity to integrate medical and health data with various biological omics and other data, especially in pandemic circumstances. Patients’ health data matters are apparent, but they are stored in multiple hospitals and health systems such as electronic health records (EHRs), healthcare institutions, and laboratories. Furthermore, biological data are often not integrated and cannot be used by patients, physicians, and specialists to treat particular diseases. Although the urgent need for healthcare and medical data integration is apparent, personal data protection regulations are severe. They do not allow much progress in the area without implementing security and privacy standards for patient healthcare data. One solution for this issue is setting a personal health record (PHR) as an integrative system for the patient. Many ontological frameworks have been proposed to unify the record formats, but none of them is accepted as a healthcare standard. The efforts toward approving the Health Level Seven (HL7) standards and the common medical coding systems ensure further data integration. Some efforts are made to associate particular diseases with data obtained from external environmental sensors that measure disease-associated data. Using these data, which are called exposome, the increasing symptoms of particular diseases influenced by external factors can be clarified. This paper suggests a cloud-based model for integrating healthcare and medical data from different sources such as EHRs, health informat

关键词： Data integration

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Ensemble Learning Methods for Turkish Text Categorization

A Comparative Study of Ensemble Learning Methods for Turkish...

引用

International Artificial Intelligence and Data Processing Symposium (IDAP)

作者： Ezgi Zorarpaci Department of Computer Engineering Faculty of Computer and Information Technologies Istanbul University Istanbul Turkey

ISBN: (数字)9798331531492

ISBN: (纸本)9798331531508

Text categorization (TC) is a natural language processing (NLP) task commonly used in text mining. It is defined as the automatic assignment of text to a set of given categories. Ensemble-based methods that unify multiple models effectively improve the prediction performance and result in higher accuracies than a standalone classifier in general. Motivated by this idea, it is proposed to evaluate the performances of the different ensemble classifiers on Turkish TC dataset (i.e., TTC-3600) in this paper. Firstly, OneR attribute evaluator algorithm diminishes the high dimensionality of Turkish text training data. Different combinations of the base classification algorithms are then compared using this reduced data to assess the impact of ensemble learning on Turkish text data. Bayesian network (BN), extra tree (ET), random forest (RF), and multinomial naive bayes (MNB) classification algorithms are used for the base classifiers. bagging, adaBoost, and voting mechanisms are employed to unify these base classifiers in ensemble learning. According to the experimental results, the proposed model achieves a competitive classification accuracy ($93.83 \%$) to the state-of-the-art (SOTA) methods. Moreover, the proposed method has a pretty low runtime that is only 125.8 seconds for TC task.

关键词： Accuracy Runtime Text categorization Training data Natural language processing Classification algorithms Bayes methods Ensemble learning Random forests Classification tree analysis

来源：评论

学校读者我要写书评

暂无评论

Monitoring of Heart and Respiration Rate Using a 3D Knitted T-shirt with Textile-based Electrodes

引用

IFAC-PapersOnLine 2024年第30期58卷 49-54页

作者： Nada Al-azzawi Irem Yunculer Asli Tuncay Atalay Ozgur Atalay Gökhan Ince Faculty of Computer and Informatics Engineering Computer Engineering Department Istanbul Technical University Istanbul 34469 Turkey Faculty of Textile Technologies and Design Textile Engineering Department Istanbul Technical University Istanbul 34437 Turkey

The emergence of e-textiles has facilitated impressive growth in the field of wearable technologies in recent years. Textile-based electrodes enabled long-period electrocardiogram monitoring within the health care field as they are less irritant to the skin and can be naturally embedded into the clothes. Beyond the specific health-oriented applications, physiological signals monitoring is also beneficial during other activities such as daily activities and sports. In this work, a system of a knitted t-shirt embedded with textile electrodes that targets measuring heart rate and respiration rate during various positions and activities is created. The performance of the implemented system is benchmarked against the performance of an off-the-shelf product using root mean square error. It has been shown that the proposed system can achieve good performance with heart rate respiration rate values close to that of the benchmark device.

关键词： E-textile technology smart t-shirt wearable technology heart rate monitoring ECG ECG derived respiration

来源：评论

学校读者我要写书评

暂无评论

MQDD: Pre-training of Multimodal Question Duplicity Detection for Software engineering Domain

MQDD: Pre-training of Multimodal Question Duplicity Detectio...

引用

2023 International Conference Recent Advances in Natural Language Processing: Large Language Models for Natural Language Processing, RANLP 2023

作者： Pašek, Jan Sido, Jakub Konopík, Miloslav Pražák, Ondřej NTIS - New Technologies for the Information Society Department of Computer Science and Engineering Faculty of Applied Sciences University of West Bohemia Plzeň Czech Republic

ISBN: (纸本)9789544520922

This work proposes a new pipeline for leveraging data collected on the Stack Overflow website for pre-training a multimodal model for searching duplicates on question answering websites. Our multimodal model is trained on question descriptions and source codes in multiple programming languages. We design two new learning objectives to improve duplicate detection capabilities. The result of this work is a mature, fine-tuned Multimodal Question Duplicity Detection (MQDD) model, ready to be integrated into a Stack Overflow search system, where it can help users find answers for already answered questions. Alongside the MQDD model, we release two datasets related to the software engineering domain. The first Stack Overflow Dataset (SOD) represents a massive corpus of paired questions and answers. The second Stack Overflow Duplicity Dataset (SODD) contains data for training duplicate detection models. © 2023 Incoma Ltd. All rights reserved.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Improving long-tail classification via decoupling and regularisation

引用

CAAI Transactions on Intelligence Technology 2025年第1期10卷 62-71页

作者： Shuzheng Gao Chaozheng Wang Cuiyun Gao Wenjian Luo Peiyi Han Qing Liao Guandong Xu School of Computer Science and Technology Harbin Institute of TechnologyShenzhenChina Peng Cheng Laboratory ShenzhenChina Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies Harbin Institute of TechnologyShenzhenChina Faculty of Engineering and Information Technology University of Technology SydneySydneyNew South WalesAustralia

Real-world data always exhibit an imbalanced and long-tailed distribution,which leads to poor performance for neural network-based *** methods mainly tackle this problem by reweighting the loss function or rebalancing the ***,one crucial aspect overlooked by previous research studies is the imbalanced feature space problem caused by the imbalanced angle *** this paper,the authors shed light on the significance of the angle distribution in achieving a balanced feature space,which is essential for improving model performance under long-tailed ***,it is challenging to effectively balance both the classifier norms and angle distribution due to problems such as the low feature *** tackle these challenges,the authors first thoroughly analyse the classifier and feature space by decoupling the classification logits into three key components:classifier norm(*** magnitude of the classifier vector),feature norm(*** magnitude of the feature vector),and cosine similarity between the classifier vector and feature *** this way,the authors analyse the change of each component in the training process and reveal three critical problems that should be solved,that is,the imbalanced angle distribution,the lack of feature discrimination,and the low feature *** from this analysis,the authors propose a novel loss function that incorporates hyperspherical uniformity,additive angular margin,and feature norm *** component of the loss function addresses a specific problem and synergistically contributes to achieving a balanced classifier and feature *** authors conduct extensive experiments on three popular benchmark datasets including CIFAR-10/100-LT,ImageNet-LT,and iNaturalist *** experimental results demonstrate that the authors’loss function outperforms several previous state-of-the-art methods in addressing the challenges posed by imbalanced and longtailed datasets,t

关键词： computer vision image classification long-tailed data machine learning

来源：评论

学校读者我要写书评

暂无评论

Application of Parallel Signal Processing Using Reverse Blockchain Technology in Conditions of Network Instability 4

Application of Parallel Signal Processing Using Reverse Bloc...

引用

4th International Conference on Electrical, computer, Communications and Mechatronics engineering, ICECCME 2024

作者： Khilenko, Volodymyr Zinchenko, Andrii Stepanov, Oleksii Kotuliak, Ivan Ries, Michal Institute of Computer Engineering and Applied Informatics Slovak University of Technology in Bratislava Faculty of Informatics and Information Technologies Bratislava Slovakia Institute of Transport Systems and Technologies National Academy of Sciences of Ukraine Dnipro Ukraine National University of Life and Environmental Sciences of Ukraine Kyiv Department of Information Technologies Ukraine Slovak University of Technology in Bratislava Faculty of Informatics and Information Technologies Bratislava Slovakia

ISBN: (纸本)9798350391183

The theses is in line with works aimed at studying the possibility of using mathematical algorithms for parallel processing of information in reverse blockchain technology. The paper examines the use of parallel signal processing algorithms to improve the speed and quality of control systems for autonomous dynamic objects using reverse blockchain technology. The use of reverse blockchain technology is due to the possibility of loss of control signals and, at the same time, the inadmissibility of loss of control in the event of changes in the conditions and parameters of the operation of the obj ect. The purpose of the work is to analyze the implementation of solutions for parallel information processing for various models of industrially produced equipment and to develop solutions to increase the efficiency of reverse blockchain technology when using parallel data processing. © 2024 IEEE.

关键词： blockchain dynamic objects and technological processes improving the quality of control systems instability of communication channels loss of information and control signals reverse blockchain technology

来源：评论

学校读者我要写书评

暂无评论

Implementation of the Time Series and the Convolutional Vision Transformers for Biological Signal Processing - Blood Pressure Estimation from Photoplethysmogram 15th

Implementation of the Time Series and the Convolutional ...

引用

15th International Conference on ICT Innovations, ICT Innovations 2023

作者： Kuzmanov, Ivan Ackovska, Nevena Lehocki, Fedor Bogdanova, Ana Madevska University Ss. Cyril and Methodius Faculty of Computer Science and Engineering Rugjer Boskovikj 16 Skopje1000 Macedonia Institute of Measurement Science Slovak Academy of Sciences and Faculty of Informatics and Information Technologies STU Bratislava Slovakia

ISBN: (纸本)9783031543203

Blood pressure estimation is crucial for early detection and prevention of many cardiovascular diseases. This paper explores the potential of the relatively new transformer architecture for accomplishing this task in the domain of biological signal processing. Several preceding studies of blood pressure estimation solely for PPG signals have had success with CNN and LSTM neural networks. In this study two types of transformer variants are considered: the time series and the convolutional vision transformers. The results obtained from our research indicate that this type of approach may be unsuitable for the task. However, further research is needed to make a definitive claim, since only simple transformer type are considered. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Blood pressure

来源：评论

学校读者我要写书评

暂无评论

Verification of the Usefulness of the Virtual Reality Application for URM Assembly 15

Verification of the Usefulness of the Virtual Reality Applic...

引用

15th International Conference on computer and Automation engineering, ICCAE 2023

作者： Svetlik, Jozef Kovac, Juraj Pollak, Martin Kocisko, Marek Stejskal, Tomas Sasala, Michal Technical University of Košice Faculty of Mechanical Engineering Department of Production Systems and Robotics Košice Slovakia Technical University of Košice Faculty of Mechanical Engineering Department of Industrial and Digital Engineering Košice Slovakia Technical University of Košice Faculty of Manufacturing Technologies Department of Computer Aided Manufacturing Technologies Prešov Slovakia

ISBN: (纸本)9798350396225

The article deals with the use of virtual reality in assembly processes. It defines the basic concepts regarding montage and virtual reality. In the individual chapters of the article, the hardware and software resources necessary to implement the assembly simulation in virtual reality are listed and described. The specific Virtual Reality software Pixyz Review is also described in more detail, where its functions and a specific example of assembling the URM assembly are listed. © 2023 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Design,simulation,and testing of a tunable MEMS multi-threshold inertial switch

引用

Microsystems & Nanoengineering 2024年第2期10卷 37-46页

作者： Qiu Xu Rodrigo T.Rocha Yousef Algoos Eric Feron Mohammad I.Younis Faculty of Electronic Information Engineering Huaiyin Institute of TechnologyHuai’an223003PR China Computer Electrical and Mathematical Science and Engineering DivisionKing Abdullah University of Science and TechnologyThuwal23955-6900Saudi Arabia Piezoelectric Microsystem Technologies Silicon Austria LabsVillach9524Austria Physical Sciences and Engineering Division King Abdullah University of Science and TechnologyThuwal23955Saudi Arabia Mechanical Engineering Department State University of New YorkBinghamtonNY13902USA

This paper presents a tunable multi-threshold micro-electromechanical inertial switch with adjustable threshold *** demonstrated device combines the advantages of accelerometers in providing quantitative acceleration measurements and g-threshold switches in saving power when in the inactive state upon experiencing acceleration below the *** designed proof-of-concept device with two thresholds consists of a cantilever microbeam and two stationary electrodes placed at different positions in the sensing *** adjustable threshold capability and the effect of the shock duration on the threshold acceleration are analytically investigated using a nonlinear beam *** are shown for the relationships among the applied bias voltage,the duration of shock impact,and the tunable *** fabricated prototypes are tested using a shock-table *** analytical results agree with the experimental *** designed device concept is very promising for the classification of the shock and impact loads in transportation and healthcare applications.

关键词： tunable acceleration testing

来源：评论

学校读者我要写书评

暂无评论

Propagation of EM Waves Through Biomaterial Based on Harvest Waste - Influence of Biomaterial Density, Moisture and Temperature 33rd

Propagation of EM Waves Through Biomaterial Based on Harvest...

引用

33rd International Conference on Organization and Technology of Maintenance, OTO 2024

作者： Mandrić, Vanja Rupčić, Slavko Pavković, Bogdan Bogdanović, Nataša Faculty of Electrical Engineering Computer Science and Information Technology Osijek Osijek Croatia Faculty of Technical Sciences University of Novi Sad Novi Sad Serbia Department of Information and Communication Technologies Academy of Applied Technical and Preschool Studies Niš Serbia

ISBN: (纸本)9783031805967

This paper deals with the simulation calculation of the transmission (S21) parameter in a biomaterial calculated parametrically on the basis harvest waste (residues) as a function of the density, moisture and temperature of the material. Since this material is essentially wood, empirical and semi-empirical models are used to determine the electromagnetic parameters of the wood material as a function of the density, moisture and temperature of the material according to the available literature. The structural - geometric and environmental parameters of the material that are the subject of the research are: density, moisture and temperature of the material, and the electromagnetic parameters that "describe" them are: relative permittivity Εr, loss tangent tan δ and electrical conductivity σ. The simulation model is based on a system for measuring coupling parameters in free space, which consists of two antennas, between which a 600 × 600 mm sample of the biomaterial is placed, and a network analyzer. With increasing density and moisture significantly increases the relative dielectric constant, the loss tangent and the electrical conductivity of the measured biosamples. The temperature change in a wide temperature range (20 ℃–100 ℃) has no significant influence on the electromagnetic parameters. The measured results were used to verify the simulation model. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Electric conductivity

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：