检索结果-内蒙古大学图书馆

Clinical deep model to analyse medical multivariate time-series data for health diagnosis

Cyber-Physical Systems 2025年第2期11卷 139-164页

作者： Almahadeen, Layth Vijay, Richa Shabaz, Mohammad Soni, Mukesh Singh, Pavitar Parkash Patel, Pavan Byeon, Haewon Department of Financial and Administrative Sciences Al- Balqa’Applied University Al-Salt Jordan Department of computer science Amity University UP Noida India Department of Computer Science Engineering Model Institute of Engineering and Technology Jammu Jammu and Kashmir India Department of Computer Science Engineering University Centre for Research & Development Chandigarh University Mohali India Department of Management Lovely Professional University Phagwara India Department of Computer Science Engineering Ahmedabad Institute of Technology Ahmedabad India Department of Digital Anti-Aging Healthcare Inje University Gimhae Korea Republic of

Clinical auxiliary decision-making is related to life and health of patients, so the deep model needs to extract the personalised representation of patients to ensure high analysis and prediction accuracy;and provide a basis for prediction conclusions. In this context, a clinical deep model proposed an interpretable assessment method of patient health status based on contextual learning of medical features, encoding the time-series features of each variable separately, and using a multi-head de-coordination self-attention mechanism for learning Relationships between different features;feature skip-connection encoding based on a compressed excitation mechanism is proposed to improve the sensitivity of the model. © 2024 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Integration of FAERS, DrugBank and SIDER Data for Machine Learning-based Detection of Adverse Drug Reactions

引用

Datenbank-Spektrum 2024年第3期24卷 233-242页

作者： Schreier, Tobias Tropmann-Frick, Marina Böhm, Ruwen Computer Science Hamburg University of Applied Sciences Hamburg Germany Institute of Experimental and Clinical Pharmacology University Hospital Schleswig-Holstein Kiel Germany ScoraTec R & amp D Erfurt Germany

Traditionally, disproportionality analysis (DPA) methods are employed for signal detection in pharmacovigilance, but these methods utilize only a limited portion of the data available from spontaneous event reports (SERs). This research aims to enhance signal detection by applying machine learning (ML) methods that can leverage additional data. We create a dataset by integrating SER data from the FDA Adverse Event Reporting System (FAERS) with biological and chemical data from DrugBank, and information on known adverse drug reactions (ADRs) from Side Effect Resource (SIDER). The known ADRs from SIDER are used to label the dataset for ML training. Using the AutoML library TPOT, ML models are trained on this dataset. Our findings indicate that ML models, even when trained with the same features as DPA methods, achieve higher recall and precision. Moreover, incorporating additional features related to drugs and events significantly boosts the performance of ML models. Analysis using the explainable AI (XAI) technique SHAP reveals that the drug name, event name, and fifth-level ATC code are the most influential features for model predictions. These ML models offer a promising alternative or supplement to conventional DPA methods for signal detection in pharmacovigilance. © The Author(s) 2024.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Bug Prioritization Using Average One Dependence Estimator

引用

Intelligent Automation & Soft Computing 2023年第6期36卷 3517-3533页

作者： Kashif Saleem Rashid Naseem Khalil Khan Siraj Muhammad Ikram Syed Jaehyuk Choi Department of IT and Computer Science Institute of Applied Sciences and TechnologyPakAustriaFochhshuleHaripurPakistan Faculty of Computer Sciences and Information Technology Superior UniversityLahore54660Pakistan Department of Computer Science Shaheed Benazir Bhutto UniversitySheringalUpper DirKhyber PakhtunkhwaPakitan School of Computing Gachon University1342Seongnam-daeroSujeong-guSeongnam-si13120Korea

Automation software need to be continuously updated by addressing software bugs contained in their ***,bugs have different levels of importance;hence,it is essential to prioritize bug reports based on their sever-ity and *** managing the deluge of incoming bug reports faces time and resource constraints from the development team and delays the resolu-tion of critical ***,bug report prioritization is *** study pro-poses a new model for bug prioritization based on average one dependence estimator;it prioritizes bug reports based on severity,which is determined by the number of *** more the number of attributes,the more the *** proposed model is evaluated using precision,recall,F1-Score,accuracy,G-Measure,and Matthew’s correlation *** of the proposed model are compared with those of the support vector machine(SVM)and Naive Bayes(NB)*** and Mozilla datasetswere used as the sources of bug *** proposed model improved the bug repository management and out-performed the SVM and NB ***,the proposed model used a weaker attribute independence supposition than the former models,thereby improving prediction accuracy with minimal computational cost.

关键词： Bug report triaging prioritization support vector machine Naive Bayes

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of image super-resolution: A concurrent study of RGB and depth images

Comparative analysis of image super-resolution: A concurrent...

引用

2024 International Workshop on the Theory of Computational Sensing and its Applications to Radar, Multimodal Sensing and Imaging, CoSeRa 2024

作者： Qiu, Zhouyan Zeng, Shang Sanchez, Joaquin Martinez Arias, Pedro Cintecx Universidade de Vigo Applied Geotechnology Group Vigo Spain Chengdu Institute of Computer Applications Chinese Academy of Sciences Chengdu China

ISBN: (纸本)9798350365504

The introduction of deep learning has significantly advanced super-resolution techniques, allowing for the extraction of detailed textures and nuances vital for accurately analyzing visual information. The main contribution of our study is the development of the iDFD-SR dataset, an enhancement of the existing Indoor Depth from Defocus (iDFD) dataset [1], designed to evaluate super-resolution algorithms in the complex and varied indoor settings. Utilizing cutting-edge deep learning models such as EDSR (Enhanced Deep Super-Resolution Network), ESRGAN (Enhanced Super-Resolution Generative Adversarial Networks), RDN (Residual Dense Network), LIIF (Local Implicit Image Function) and HAT (Hybrid Attention Transformer), we perform a thorough comparison across several datasets - All in Focus (AIF), Out of Focus (OOF), Raw Depth (DR), and Depth after In-Painting (DI) - to identify the strengths and challenges of each approach. Our findings demonstrate notable enhancements in image quality for both RGB and depth images. However, the research acknowledges limitations, notably its indoor setting focus and the extensive computational resources required. Future work aims to broaden the application of super-resolution techniques, increase computational efficiency, and enhance the accuracy of depth estimations. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

ZeitGeist: A Generic Tool Supporting the Dissemination of Time Series Data Following FAIR Principles 15

ZeitGeist: A Generic Tool Supporting the Dissemination of Ti...

引用

15th International Conference on Knowledge Management and Information Systems, KMIS 2023 as part of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, IC3K 2023

作者： Schmidt, Andreas Koubaa, Mohamad Anis Schweikert, Jan Stucky, Karl-Uwe Süß, Wolfgang Hagenmeyer, Veit Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Karlsruhe Germany Department of Computer Science and Business Information Systems University of Applied Sciences Karlsruhe Germany

ISBN: (纸本)9789897586712

An important point for the widespread dissemination of FAIR-data is the lowest possible entry barrier for preparing and providing data to other scientists according to the FAIR criteria. If scientists have to manually extract, transform and annotate the data according to the FAIR criteria and then export it to make it available to the public, this requires a significant investment of time that does not primarily reward the scientist who prepares and provides the data. The Energy Lab at KIT is running a large cluster of an Influx database management system with energy related time series data being stored in a variety of individual databases over periods of up to 15 years. In order to increase the willingness to make data available to the scientific public, we develop a tool that greatly supports and automates the publication and annotation process of time series data stored in Influx databases. Copyright © 2023 by SCITEPRESS - Science and Technology Publications, Lda.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Safe and Secure' on the Timing Analysability of Cryptographic Implementations 30

Safe and Secure' on the Timing Analysability of Cryptographi...

引用

30th IEEE Real-Time and Embedded Technology and Applications Symposium, RTAS 2024

作者： Stegmeier, Alexander Knauer, Peter Schubaur, Philipp Piatka, Christian Merli, Dominik Altmeyer, Sebastian University of Augsburg Department of Computer Science Augsburg Germany Augsburg Technical University of Applied Sciences Institute for Innovative Safety and Security Augsburg Germany

ISBN: (纸本)9798350358414

Hard real-Time systems are increasingly vulnerable to cyberattacks. Since real-Time systems represent a significant proportion of safety-critical systems not only established safety standards but also security standards have to be considered. In particular, standard cryptographic libraries are required to reach an adequate level of protection. In this study, we investigate whether it is possible to en-sure security and hard real-Time without compromising either side. Thus, we examine relevant state-of-The-Art cryptographic primitives provided by one of the de-facto standard libraries Mbed TLS, which is widely-used in embedded systems. We investigate the possibility to derive a Worst-Case Execution Time (WCET) for these primitives and review the code base with regard to compliance on safety-related coding guidelines. In addition, we assess the relevant aspects when security concerns must be considered in the safety-related context. Our research reveals several obstacles to fully apply Mbed TLS in hard real-time systems. © 2024 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Handwritten Alphabet Recognition Using Convolutional Neural Networks

Handwritten Alphabet Recognition Using Convolutional Neural ...

引用

2024 International Conference Automatics and Informatics, ICAI 2024

作者： Jamal, Yasir Neemuchwala, Sakina Juzar Kouatly, Rand Hassan, Ahmed Puthiyapurayil, Nafeesath Parappurath Karunanithi, Meerah Institute of Engg. Sciences & Tech Faculty of Computer Science & Engg. Gik Topi Pakistan University of Europe for Applied Sciences Department of Business Potsdam Germany Berlin School of Business and Innovation Department of Computer Science Berlin Germany

ISBN: (纸本)9798350353907

Instruction of hand-written alphabet recognition using an intelligent adaptive Optical Character Recognition (OCR) system is one of the vital pattern recognition problems, which has a very broad spectrum of frequent applications in various fields, such as language comprehension and archival document investigation. Instruction Recognition has seen a lot of progress in the data recognition field, but the handwritten alphabet recognition follows a separate track and computer with this can be a challenge due to the different styles and shapes of handwriting which are not marked. The project provides room for further work in which the Convolutional Neural Network (CNN) model can be trained to interpret handwritten alphabet characters. In connection with the exact naming of the handwritten images in the A-Z collection, deep neural networks are applied. AI-generated images of the outcome corroborate the effectiveness and accuracy of the constructed CNN algorithm, which precisely identifies handwritten characters of the alphabet with an accuracy above 96-97 percent. Insights from this analysis are pivotal in making this research area a success and CNNs are a powerful tool that can be exploited for this purpose. The presentation seems to enjoy the fact that their results are useful in many areas which includes digitization of historical documents, automatic online form processing, as well as well as customized learning system. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Cost Optimization Based on a Linear Programming Approach for a Hybrid Renewable Energy System 1

引用

2nd International Conference on Green Energy Conversion System, ICGECS 2023

作者： Ouederni, Ramia Bouaziz, Bechir Bacha, Faouzi Computer Lab for Industrial Systems National Institute of Applied Sciences and Technology Centre Urbain Nord BP 676 Tunis Cedex1080 Tunisia

ISBN: (数字)9789819761487

ISBN: (纸本)9789819761470

The objectives of the studies presented here are to develop an efficient method adapted to the energy production of an isolated hybrid power system located on the island of Djerba, Tunisia. To this end, we have proposed two optimization methods, based respectively on linear programming (LP) and software (HOMER), with the aim of minimizing the energy cost of the hybrid system while respecting constraints linked to all the elements of the system. We therefore compared the two optimization strategies. The proposed linear program yields an electricity cost of 0.206$/kWh, lower than the HOMER cost of 0.308$/kWh. This system would therefore have advantages in terms of energy independence in particular. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Hybrid power

来源：评论

学校读者我要写书评

暂无评论

Acoustic Signal Analysis of the Targets of Distributed Airspace Monitoring System 11

Acoustic Signal Analysis of the Targets of Distributed Airsp...

引用

11th IEEE International Workshop on Metrology for AeroSpace, MetroAeroSpace 2024

作者： Siechko, Oleksii Kitsera, Anton Kochan, Roman Jozwik, Jerzy Tofil, Arkadiusz Mika, Dariusz Lviv Polytechnic National University Department of Specialized Computer Systems Lviv Ukraine Institute of Technical Sciences and Aviation The University College of Applied Sciences in Chelm Chelm Poland

ISBN: (纸本)9798350385045

Acoustic methods of aircraft detection are an alternative method of airspace monitoring that was widely used in the pre-radar era and is now being developed again using new achievements in microelectronics, computer science, and communications. Turning the acoustic channel of an acoustic airspace monitoring system requires an investigation of the parameters of acoustic signals generated by aircraft. The significant number of existed aircrafts, as well as their acoustic signal variation depended of operating mode requires a huge amount of experiments. This paper utilizes the recordings posted on public video and audio data services to analyze acoustic signals. The essence of the analysis is a investigations the spectral composition of acoustic signals for seven classes of aircraft. The obtained results represent the frequency ranges of the three main harmonics of acoustic signals for each class of aircraft. The obtained results provide the possibility of frequency optimization of data acquisition channels of acoustic airspace monitoring systems. © 2024 IEEE.

关键词： Signal analysis

来源：评论

学校读者我要写书评

暂无评论

Findings of the Second Shared Task on Multilingual Coreference Resolution 6

Findings of the Second Shared Task on Multilingual Coreferen...

引用

CRAC Shared Task on Multilingual Coreference Resolution at 6th Workshop on Computational Models of Reference, Anaphora and Coreference, CRAC 2023

作者： Žabokrtský, Zdeněk Konopík, Miloslav Nedoluzhko, Anna Novák, Michal Ogrodniczuk, Maciej Popel, Martin Pražák, Ondřej Sido, Jakub Zeman, Daniel Charles University Faculty of Mathematics and Physics Institute of Formal and Applied Linguistics Prague Czech Republic University of West Bohemia Faculty of Applied Sciences Department of Computer Science and Engineering Pilsen Czech Republic Institute of Computer Science Polish Academy of Sciences Warsaw Poland

ISBN: (纸本)9781955917025

This paper summarizes the second edition of the shared task on multilingual coreference resolution, held with the CRAC 2023 workshop. Just like last year, participants of the shared task were to create trainable systems that detect mentions and group them based on identity coreference;however, this year’s edition uses a slightly different primary evaluation score, and is also broader in terms of covered languages: version 1.1 of the multilingual collection of harmonized coreference resources CorefUD was used as the source of training and evaluation data this time, with 17 datasets for 12 languages. 7 systems competed in this shared task. © CRAC 2023. All Rights Reserved.

关键词：

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：