检索结果-内蒙古大学图书馆

3rd IEEE International Conference on Computational Intelligence and Knowledge Economy, ICCIKE 2023

作者： Naghibolhosseini, Maryam Yousef, Ahmed M Zayernouri, Mohsen Zacharias, Stephanie Rc Deliyski, Dimitar D Michigan State University Department of Communicative Sciences and Disorders East LansingMI United States Michigan State University Department of Mechanical Engineering Statistics and Probability East LansingMI United States Head and Neck Regenerative Medicine Program Mayo Clinic Scottsdale Department of Otolaryngology-Head and Neck Surgery PhoenixAZ United States

ISBN: (纸本)9798350338263

High-speed imaging of the larynx provides a valuable means for studying vocal folds function and vibratory behaviors. Using laryngeal high-speed videoendoscopy (HSV) with a flexible nasolaryngoscope, one can record the detailed vibratory movements of vocal folds during connected speech. This high-speed imaging tool enables us to study the normal function of the vocal folds and how this function can be disrupted due to the presence of voice disorders. In this work, HSV data were utilized during connected speech from subjects with normophonic voices (no voice disorders) and a neurological voice disorder. The data were obtained using a high-speed camera, coupled with a flexible endoscope, at 4,000 frames per second. Deep learning was used for the analysis of the big HSV dataset to extract the vibratory behaviors of the vocal folds. This deep-learning-based tool achieved high levels of accuracy for analysis of challenging HSV data in connected speech. This tool provides a computationally cost-effective and an accurate measurement approach that could help design more advanced voice assessment protocols in future. © 2023 IEEE.

关键词： High speed cameras

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection using Deep Neural Network Algorithm on the Internet of Things 11

Intrusion Detection using Deep Neural Network Algorithm on t...

引用

11th IEEE International Conference on Communication, Networks and Satellite, COMNETSAT 2022

作者： Ikhwan, Syariful Wibowo, Adi Warsito, Budi School of Postgraduate Studies Diponegoro University Doctoral Program of Information System Semarang Indonesia Institut Teknologi Telkom Purwokerto D3 Telecommunication Engineering Banyumas Indonesia Diponegoro University Computer Science Informatics Department of Science and Mathematics Faculty Semarang Indonesia Diponegoro University Statistics Department of Science and Mathematics Faculty Semarang Indonesia

ISBN: (纸本)9781665460309

The increasing use of IoT devices on future networks is very helpful for humans in their lives. However, the increase in devices connected to IoT networks also increases the potential for attacks against those networks. Vulnerabilities in Internet of Things (IoT) networks can be exposed at any time. Artificial intelligence can be used to protect the IoT network by being able to detect attacks on the network so that they can be prevented. In this study, network detection was carried out using the Deep Neural Network (DNN) algorithm. The test was carried out using the UNSW Bot-IoT dataset with a comparison of training data of 75% of the overall data. The results obtained show the ability of the algorithm to detect attacks on average with 99.999% accuracy. The validation loss and training loss look very small. In this study, there is a validation loss that still occurs in overfitting, but the difference is very small. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Assessing Organizational Learning in IT Organizations: An Experience Report from Industry

Assessing Organizational Learning in IT Organizations: An Ex...

引用

Joint Conference of the Int'l Workshop on and International Conference on Software Process and Product Measurement Software Measurement

作者： Güven Özen N. Alpay Karagöz Oumout Chouseinoglou Semih Bilgen Software Management Program METU Ankara Turkey Statistics and Computer Science Department Başkent University Ankara Turkey Electrical and Electronics Engineering Department METU Ankara Turkey

With the increase in demand for higher-quality and more capable IT services, IT organizations in order to obtain competitive advantage require extensive knowledge that needs to be shared and reused among different entities within the organization. The existing IT Service Management (ITSM) mechanisms mention the importance of organizational learning (OL) and knowledge management (KM) for IT organizations. However, they do not explicitly address how OL capabilities of an IT organization can be assessed. This paper, by using an OL assessment model developed for software organizations, namely AiOLoS, shows that with the proper adjustment, the application of the model to IT organizations is feasible. We report the results of applying the model in four functional teams in an IT organization from private sector.

关键词： Organizations Software Software measurement Phase measurement Training Length measurement

来源：评论

学校读者我要写书评

暂无评论

GPU-Accelerated Vecchia Approximations of Gaussian Processes for Geospatial Data using Batched Matrix Computations

GPU-Accelerated Vecchia Approximations of Gaussian Processes...

引用

ISC High Performance 2024 Research Paper Proceedings (39th International Conference)

作者： Qilong Pan Sameh Abdulah Marc G. Genton David E. Keyes Hatem Ltaief Ying Sun Division of Computer Electrical and Mathematical Sciences and Engineering (CEMSE) Statistics Program Extreme Computing Research Center King Abdullah University of Science and Technology Thuwal Jeddah Saudi Arabia

Gaussian processes (GPs) are commonly used for geospatial analysis, but they suffer from high computational complexity when dealing with massive data. For instance, the log-likelihood function required in estimating the statistical model parameters for geospatial data is a computationally intensive procedure that involves computing the inverse of a covariance matrix with size $n$ × n, where $n$ represents the number of geographical locations in the simplest case. As a result, in the literature, studies have shifted towards approximation methods to handle larger values of $n$ effectively while maintaining high accuracy. These methods encompass a range of techniques, including low-rank and sparse approximations. Among these techniques, Vecchia approximation is one of the most promising methods to speed up evaluating the log-likelihood function. This study presents a parallel implementation of the Vecchia approximation technique, utilizing batched matrix computations on contemporary GPUs. The proposed implementation relies on batched linear algebra routines to efficiently execute individual conditional distributions in the Vecchia algorithm. We rely on the KBLAS linear algebra library to perform batched linear algebra operations, reducing the time to solution compared to the state-of-the-art parallel implementation of the likelihood estimation operation in the ExaGeoStat software by up to 700X, 833X, 1380X on 32GB GV100, 80GB A100, and 80GB H100 GPUs, respectively, with the largest matrix dimension that can fully fit into the GPU memory in the dense Maximum Likelihood Estimation (MLE) case. We also successfully manage larger problem sizes on a single NVIDIA GPU, accommodating up to 1 million locations with 80GB A100 and H100 GPUs while maintaining the necessary application accuracy. We further assess the accuracy performance of the implemented algorithm, identifying the optimal settings for the Vecchia approximation algorithm to preserve accuracy on two real geos

关键词：

来源：评论

学校读者我要写书评

暂无评论

Continuous air cleaning by filtration and UV-C treatment of airborne pathogens and particulate matter in indoor spaces

Continuous air cleaning by filtration and UV-C treatment of ...

引用

2022 ASABE Annual International Meeting

作者： Li, Peiyang Koziel, Jacek A. Macedo, Nubia Zimmerman, Jeffrey J. Wrzesinski, Danielle Sobotka, Erin Balderas, Mateo Walz, William B. Paris, Reid Vincent Liu, Dongjie Department of Agricultural and Biosystems Engineering Iowa State University AmesIA United States Department of Veterinary Diagnostic and Production Animal Medicine Iowa State University AmesIA United States Department of Mechanical Engineering Iowa State University AmesIA United States Department of Statistics Iowa State University AmesIA United States Interdepartmental Toxicology Program Iowa State University AmesIA United States

Since COVID-19 became a global pandemic, improving air quality has been increasingly important to mitigate the transmission of pathogenic aerosols. Air filters such as MERV filters have been widely used in heating, ventilation, and air conditioning (HVAC) systems to clean inlet air. In recent years, ultraviolet (UV) light has been used for decontamination and disinfection in various applications, including indoor air cleaning, e.g., upper-room ultraviolet germicidal irradiation (UVGI). There are a variety of air purification devices available in the market, with some incorporating UV technology. However, many of them are not formally tested and certified for their effectiveness in mitigating airborne pathogens and particulate matter. The research's objectives are to (1) evaluate, design, and upgrade an existing air filtration device (~2,200 CFM) with the addition of UV-C lamps;(2) test the effectiveness of the upgraded device in mitigating airborne pathogens (bacteria) and particulate matter (PM) in real scenario (poultry farm). The testing results of air quality are expressed in particular matter (PM) levels and colony-forming units (CFUs). The preliminary data showed that both MERV-8 & MERV 13 and UV-C lamps can inactivate up to 100% of airborne bacteria, and the device can remove over 95% of total PM after treatment in a ~150-layer room. © 2022 ASABE. All Rights Reserved.

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

Generalized Dissipativity and Nonlinear Negative Imaginary Systems

Generalized Dissipativity and Nonlinear Negative Imaginary S...

引用

UKACC International Conference on Control (CONTROL)

作者： Nader Meskin Mohamed A. Mabrok Alexander Lanzon Electrical Engineering Department College of Engineering Qatar University Department of Mathematics Statistics and Physics Mathematics Program College of Arts and Sciences Qatar University Doha Qatar Department of Electrical and Electronic Engineering Control Systems Centre University of Manchester Manchester UK

ISBN: (数字)9798350374261

ISBN: (纸本)9798350374278

Nonlinear negative imaginary systems find application in a range of engineering fields, including the control of flexible structures and air vehicles. Nevertheless, unlike their linear counterparts, the theory for nonlinear negative imaginary systems is not as well-established. In this paper, we propose a generalized k-th order dissipativity framework with respect to a supply rate which is a function of the k-th time-derivative of the system output. It is shown that positive realness and negative imaginaryness can be defined in this general framework in a unified manner. Then, necessary and sufficient conditions for first order dissipativity of nonlinear systems are obtained. These capture and are more general than the negative imaginary property. Moreover, the concept of exponentially negative imaginary systems for both linear and nonlinear systems is developed and the required conditions are obtained.

关键词： Linear systems Sufficient conditions Robust stability Control systems Nonlinear systems Flexible structures

来源：评论

学校读者我要写书评

暂无评论

A Lagrangian Method for Reactive Transport with Solid/Aqueous Chemical Phase Interaction i

arXiv

引用

arXiv 2018年

作者： Schmidt, Michael J. Pankavich, Stephen D. Navarre-Sitchler, Alexis Benson, David A. Hydrologic Science and Engineering Program Department of Geology and Geological Engineering Colorado School of Mines GoldenCO80401 United States Department of Applied Mathematics and Statistics Colorado School of Mines GoldenCO80401 United States

A significant drawback of Lagrangian (particle-tracking) reactive transport models has been their inability to properly simulate interactions between solid and liquid chemical phases, such as dissolution and precipitation reactions. This work addresses that problem by implementing a mass-transfer algorithm between mobile and immobile sets of particles that allows aqueous species of reactant that are undergoing transport to interact with stationary solid species. This mass-transfer algorithm is demonstrated to solve the diffusion equation for an arbitrarily small level of diffusion and thus does not introduce any spurious mixing. The algorithm can be combined with random walks to simulate the desired total level of diffusion in a reactive transport system. Copyright © 2018, The Authors. All rights reserved.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

COULD DROPPING A FEW CELLS CHANGE THE TAKEAWAYS FROM DIFFERENTIAL EXPRESSION?

arXiv

引用

arXiv 2023年

作者： Shiffman, Miriam Giordano, Ryan Broderick, Tamara MIT Computational & Systems Biology Program United States MIT Dept. of Electrical Engineering & Computer Science United States UC Berkeley Dept. of Statistics United States

Analysis of differential gene expression plays a fundamental role in biology toward illuminating the molecular mechanisms driving a difference between groups (e.g., due to treatment or disease). While any analysis is run on particular cells or samples, the intent is to generalize to future occurrences of the treatment or disease. Implicitly, generalization is justified under the assumption that present and future samples are independent and identically distributed from the same population. Though this assumption is always false, we might hope that any deviation from the assumption is small enough that A) fundamental conclusions of the analysis still hold, and B) standard tools like standard error, significance, and power still reflect generalizability. Conversely, we might worry about these deviations, and reliance on standard statistical tools, if conclusions could be substantively changed by dropping a very small fraction of observations. While checking every small fraction is computationally intractable, recent work develops an approximation to identify when such an influential subset exists. Building on this work, we develop a metric for dropping-data robustness of differential expression;namely, we cast the analysis in a differentiable form suitable to the approximation, extend the approximation to models whose hyperparameters depend on the full dataset, and extend the notion of a data point from a single cell to a pseudobulk observation. We then overcome the inherent non-differentiability of gene set enrichment analysis to develop an additional approximation for the robustness of top gene sets. We use our tool to assess the robustness of differential expression for published single-cell RNA-seq data, and discover that thousands of genes can have their results flipped by dropping Copyright © 2023, The Authors. All rights reserved.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Ordinal Classification Method for the Evaluation Of Thai Non-life Insurance Companies

引用

International Journal of Computer Science Issues 2012年第1 1-2期9卷 362-366页

作者： Jhonpita, Phaiboon Sinthupinyo, Sukree Chaiyawat, Thitivadee Technopreneurship and Innovation Management Program Graduate School Chulalongkorn University Bangkok Thailand Department of Computer Engineering Faculty of Engineering Chulalongkorn University Bangkok Thailand Department of Statistics Faculty of Commerce and Accountancy Chulalongkorn University Bangkok Thailand

This paper proposes a use of an ordinal classifier to evaluate the financial solidity of non-life insurance companies as strong, moderate, weak, and insolvency. This study constructed an efficient classification model that can be used by regulators to evaluate the financial solidity and to determine the priority of further examination as an early warning system. The proposed model is beneficial to policy-makers to create guidelines for the solvency regulations and roles of the government in protecting the public against insolvency. © 2012 International Journal of Computer Science Issues.

关键词： Insurance

来源：评论

学校读者我要写书评

暂无评论

Classification of EEG-based brain connectivity networks in schizophrenia using a multi-domain connectome convolutional neural network

arXiv

引用

arXiv 2019年

作者： Phang, Chun-Ren Ting, Chee-Ming Noman, Fuad Ombao, Hernando School of Biomedical Engineering & Health Sciences Universiti Teknologi Malaysia Skudai Johor81310 Malaysia Statistics Program King Abdullah University of Science and Technology Thuwal23955 Saudi Arabia

Objective: We exploit altered patterns in brain functional connectivity as features for automatic discriminative analysis of neuropsychiatric patients. Deep learning methods have been introduced to functional network classification only very recently for fMRI, and the proposed architectures essentially focused on a single type of connectivity measure. Methods: We propose a deep convolutional neural network (CNN) framework for classification of electroencephalogram (EEG)-derived brain connectome in schizophrenia (SZ). To capture complementary aspects of disrupted connectivity in SZ, we explore combination of various connectivity features consisting of time and frequency-domain metrics of effective connectivity based on vector autoregressive model and partial directed coherence, and complex network measures of network topology. We design a novel multi-domain connectome CNN (MDC-CNN) based on a parallel ensemble of 1D and 2D CNNs to integrate the features from various domains and dimensions using different fusion strategies. Results: Hierarchical latent representations learned by the multiple convolutional layers from EEG connectivity reveal apparent group differences between SZ and healthy controls (HC). Results on a large resting-state EEG dataset show that the proposed CNNs significantly outperform traditional support vector machine classifiers. The MDC-CNN with combined connectivity features further improves performance over single-domain CNNs using individual features, achieving remarkable accuracy of 93.06% with a decision-level fusion. Conclusion: The proposed MDC-CNN by integrating information from diverse brain connectivity descriptors is able to accurately discriminate SZ from HC. Significance: The new framework is potentially useful for developing diagnostic tools for SZ and other disorders. Copyright © 2019, The Authors. All rights reserved.

关键词： Electroencephalography

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：