检索结果-内蒙古大学图书馆

Exploring the Relation between Blood Tests and Covid-19 Using Machine Learning

Exploring the Relation between Blood Tests and Covid-19 Usin...

2020 International Conference on data analytics for Business and Industry: Way Towards a Sustainable Economy, ICDABI 2020

作者： Almansoor, Mohamed Hewahi, Nabil M. University of Bahrain Big Data Science Analytics Program Bahrain University of Bahrain Department of Computer Science Bahrain

ISBN: (纸本)9781728196756

COVID-19 is a global pandemic that hit the world in 2019-2020 and caused massive losses. Every day, hundreds of thousands of tests are being done on possible infected cases. It usually takes several hours to get the results of virus test in advanced countries, whereas in other countries might take days. The aim of this study is to investigate whether normal blood medical tests help in detecting covid-19 using various machine learning approaches. If true, this would give an indication to people who should undergo the virus test. In this paper we independently use machine learning algorithms including support vector machines, adaptive boosting, random forest and k-nearest neighbors. These algorithms are then merged to form ensemble learning which leads to the classification. The results show that the ensemble learning is having the highest true positive rate of 30%. The obtained results show that normal blood tests do not help much in giving right indications about detecting COVID-19. © 2020 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Discrete null field equation methods for solving Laplace's equation: Boundary layer computations

引用

Numerical Methods for Partial Differential Equations 2024年第4期40卷 e23092-e23092页

作者： Zhang, Li-Ping Li, Zi-Cai Lee, Ming-Gong Huang, Hung-Tsai School of Mathematical Sciences Qufu Normal University Shandong Qufu China Department of Applied Mathematics National Sun Yat-sen University Kaohsiung Taiwan Department of Tourism and Leisure/Ph.D. Program in Engineering Science Chung Hua University Hsinchu Taiwan Department of Data Science and Analytics I-Shou University Kaohsiung Taiwan

Consider Dirichlet problems of Laplace's equation in a bounded simply-connected domain (Formula presented.), and use the null field equation (NFE) of Green's representation formulation, where the source nodes (Formula presented.) are located on a pseudo-boundary (Formula presented.) outside (Formula presented.) but not close to its boundary (Formula presented.). Simple algorithms are proposed in this article by using the central rule for the NFE, and the normal derivatives (Formula presented.) of the solutions on the boundary (Formula presented.) can be easily obtained. These algorithms are called the discrete null field equation method (DNFEM) because the collocation equations are, indeed, the direct discrete form of the NFE. The bounds of the condition number are like those by the method of fundamental solutions (MFS) yielding the exponential growth as the number of unknowns increases. One trouble of the DNFEM is the near singularity of integrations for the solutions in boundary layers in Green's representation formulation. The traditional BEM also suffers from the same trouble. To deal with the near singularity, quadrature by expansions and the sinh transformation are often used. To handle this trouble, however, we develop two kinds of new techniques: (I) the interpolation techniques by Taylor's formulas with piecewise (Formula presented.) -degree polynomials and the Fourier series, and (II) the mini-rules of integrals, such as the mini-Simpson's and the mini-Gaussian rules. Error analysis is made for technique I to achieve optimal convergence rates. Numerical experiments are carried out for disk domains to support the theoretical analysis made. The numerical performance of the DNFEM is excellent for disk domains to compete with the MFS. The errors with (Formula presented.) can be obtained by combination algorithms, which are satisfactory for most engineering problems. In summary, the new simple DNFEM is based on the NFE, which is different from the boundary elem

关键词： Fourier series

来源：评论

学校读者我要写书评

暂无评论

Secure decentralized decisions to enhance coordination in consolidated hospital systems

引用

IISE Transactions on Healthcare Systems Engineering 2020年第2期10卷 99-112页

作者： Badré, Adrien Mohebbi, Shima Soltanisehat, Leili Data Science and Analytics Program University of Oklahoma Norman OK United States School of Industrial and Systems Engineering and Data Science and Analytics Program University of Oklahoma Norman OK United States School of Industrial and Systems Engineering University of Oklahoma Norman OK United States

Shared decision making has become a crucial solution to build a consolidated healthcare system. While there is some research in the healthcare literature discussing the advantages and disadvantages of shared decision making, its efficiency has not been addressed quantitatively. In this paper, we propose a Decentralized Patients Assignment System (DPAS) as a universal decentralized decision making architecture. It utilizes the blockchain technology, machine learning, and integer programing to enhance coordination among healthcare providers and patients in consolidated hospital systems. To test the efficiency of the proposed DPAS, a prototype system is developed using an Agent-based model and Ethereum and is compared to the current practice of central referral systems in consolidated hospital systems. The agent-based model consists of four agents including patients, physicians, hospitals, and miners interacting within a decentralized system. The proposed system highlights the importance of interoperability and consensus among healthcare agents in the decision making process. The results demonstrate the DPAS efficiency in decreasing computational time and rejection rates for patients transfer. © 2019, © 2019 “IISE”.

关键词： Blockchain architecture intelligent agents optimization patients referral predictive analytics smart contracts

来源：评论

学校读者我要写书评

暂无评论

Enhancing Localized Surface Plasmon Resonance Response for Albumin Detection by Optimizing the Lateral Size of Hexagonal Gold Nanoparticles

Enhancing Localized Surface Plasmon Resonance Response for A...

引用

IEEE International Conference on Semiconductor Electronics (ICSE)

作者： Silva Nurfasha Chandra Wulandari Lilik Hasanah Ahmad Aminuddin Yanurita Dwi Hapsari Mohammad Arifin Roer Eka Pawinanto Budi Mulyanti Study Program of Physics Universitas Pendidikan Indonesia Bandung Indonesia Study Program of Physics Institut Teknologi Bandung Bandung Indonesia Department of Physics Faculty of Science and Data Analytics Institut Teknologi Sepuluh Nopember Surabaya Indonesia Study Program of Industrial Automation and Robotics Engineering Education Universitas Pendidikan Indonesia Bandung Indonesia Study Program of Electrical Engineering Universitas Pendidikan Indonesia Bandung Indonesia

ISBN: (数字)9798350378313

ISBN: (纸本)9798350378320

The kidney is a human organ with numerous vital functions, mainly for blood filtration. Damage to the kidneys can be detected from albumin levels in urine, higher levels of albumin in urine indicate the kidney's filtration function is impaired. The latest breakthrough in the medical field is the use of localized sensor plasma resonance (LSPR) in the field of biosensors to detect albumin protein in urine. Using Finite-Difference Time-Domain (FDTD) simulation, the lateral size of hexagonal gold nanoparticles (AuNPs) is varied to increase the optimal LSPR. AuNPs are well-known as the most promising material for plasmonic applications. In several studies, the hexagonal geometry was reported to increase the surface area of nanoparticles as well as enhance the LSPR signal. Varying the geometry of the hexagonal AuNPs will affect their sensitivity and optical properties. In this study, the lateral size of the hexagonal AuNPs varied from 10 nm to 60 nm, with a controlled thickness of 30 nm. The absorption graph blue shifts with the peak decreasing until the graph has almost no peak as the lateral size decreases. The lateral size of 40 nm at a thickness of 30 nm was found to have the highest shifting response towards the change of refractive index, indicating good sensitivity for sensors. Simulation of hexagonal AuNPs-based LSPR detection of albumin concentrations of 0.35 –5.71 mM produces a sensitivity of 2.59 nm/mM, equivalent to 245.96 nm/RIU. The competitive performance and ease of detection procedures in real applications show the potential of the hexagonal AuNPs-based LSPR sensor to be further explored in developing alternative albumin detection techniques.

关键词： Nanoparticles Geometry Gold Sensitivity Filtration Absorption Refractive index

来源：评论

学校读者我要写书评

暂无评论

Gradient Boosting Model for Water Quality Forecasting

Gradient Boosting Model for Water Quality Forecasting

引用

International Conference on data analytics and Management, ICDAM 2023

作者： Panda, Parnani Banerjee, Sushovan Mishra, Sushruta Shashidhar, Chitra de Albuquerque, Victor Hugo C. Reis, Marcello Singh, Pooja Kalinga Institute of Industrial Technology Deemed to Be University Bhubaneswar India Department of Commerce and Management Seshadripuram College Bengaluru560020 India Graduate Program in Telecommunication Engineering Federal Institute of Education Science and Technology of Ceará Fortaleza Brazil Federal University of Ceará Ceará Brazil Fort Lauderdale United States Lead of the Biomedical Data Analytics Research Group Bengaluru India Federal Institute of Ceará Ceará Brazil Meteora Consultoria Fortaleza Brazil Galgotias University Uttar Pradesh Greater Noida India

ISBN: (纸本)9789819965465

The aim of our study is to evaluate the quality of water using machine learning methods. Potability is a subjective word that quantifies water quality. In this research, a variety of metrics were used to measure general potability of the water. The prescribed elements are applied like variable matrix to denote water quality. The article used three different classification methods, with success rates ranging from 84.27 to 93.16%, to predict the water quality class including ensemble approach like Random Forest (RFC), SVM for classification (SVC), as well as XGBoost. The Gradient Boosting approach, out of all the ones used, received the greatest accuracy (93.16%), precision (96.3%), recall (92.76%) and F-score (94.54%). Also, it achieved the least computational delay with a mean latency of 1.34 s. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Water quality

来源：评论

学校读者我要写书评

暂无评论

A General Framework for Clustering and Distribution Matching with Bandit Feedback

arXiv

引用

arXiv 2024年

作者： Yavas, Recep Can Huang, Yuqi Tan, Vincent Y.F. Scarlett, Jonathan Descartes Program CNRS@CREATE 138602 Singapore Department of Information Systems and Analytics School of Computing National University of Singapore 119077 Singapore Department of Mathematics Department of Electrical and Computer Engineering National University of Singapore 119077 Singapore Department of Computer Science Department of Mathematics Institute of Data Science National University of Singapore 119077 Singapore

We develop a general framework for clustering and distribution matching problems with bandit feedback. We consider a K-armed bandit model where some subset of K arms is partitioned into M groups. Within each group, the random variable associated to each arm follows the same distribution on a finite alphabet. At each time step, the decision maker pulls an arm and observes its outcome from the random variable associated to that arm. Subsequent arm pulls depend on the history of arm pulls and their outcomes. The decision maker has no knowledge of the distributions of the arms or the underlying partitions. The task is to devise an online algorithm to learn the underlying partition of arms with the least number of arm pulls on average and with an error probability not exceeding a pre-determined value δ. Several existing problems fall under our general framework, including finding M pairs of arms, odd arm identification, and N-ary clustering of K arms belong to our general framework. We derive a non-asymptotic lower bound on the average number of arm pulls for any online algorithm with an error probability not exceeding δ. Furthermore, we develop a computationally-efficient online algorithm based on the Track-and-Stop method and Frank–Wolfe algorithm, and show that the average number of arm pulls of our algorithm asymptotically matches that of the lower bound. Our refined analysis also uncovers a novel bound on the speed at which the average number of arm pulls of our algorithm converges to the fundamental limit as δ *** Codes 68T05 Copyright © 2024, The Authors. All rights reserved.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Dermatological Diagnostics: A Unified Deep Learning Framework for Skin Lesion and Cancer Classification

Dermatological Diagnostics: A Unified Deep Learning Framewor...

引用

Advances in Computing, Communication and Networking (ICAC2N), International Conference on

作者： Vinod Kumar Isha Jain Durga Sritha Dongla Shivangi Rai Vani Rastogi Eva Kaushik Rohit Kaushik School of Engineering & Applied Science The George Washington University Washington D.C USA Computer Science & Engineering Department Dr. Akhilesh Das Gupta Institute of Technology and Management New Delhi India Computer Science & Engineering Department Gandhi Institute of Technology and Management Visakhapatnam Andhra Pradesh Data Scientist DXC Technology Noida India CS and Mathematics Department Data Analytics Program University of Illinois Springfield USA

ISBN: (数字)9798350356816

ISBN: (纸本)9798350356823

Skin pathologies encompass a spectrum of conditions, with malignancies such as melanoma representing a critical diagnostic urgency. This investigation delineates the deployment of Convolutional Neural Networks (CNNs) for the classification of dermatological anomalies, benchmarking CNN diagnostic fidelity against dermatological expert evaluations. The study underscores the efficacy of CNN classifiers in expediting the diagnostic workflow for various cutaneous disorders. Advocating for an automated diagnostic framework, the research introduces a CNN-based system aimed at reducing human diagnostic load, accelerating diagnostic timelines, and enhancing survival outcomes. Utilizing advanced image processing algorithms and deep learning architectures, the research presents an automated classification system for skin pathologies, addressing both benign and malignant presentations. The classification matrix includes nine dermatological conditions: actinic keratosis, basal cell carcinoma, benign keratosis, dermatofibroma, melanoma, nevus, seborrheic keratosis, squamous cell carcinoma, and vascular lesions. The objective is to engineer a CNN model with robust diagnostic performance across a diverse lesion dataset, ensuring accurate identification and categorization of dermatological conditions.

关键词： Deep learning Pathology Accuracy Melanoma Computer architecture Benchmark testing Skin Convolutional neural networks Lesions Medical diagnosis

来源：评论

学校读者我要写书评

暂无评论

Research on Traffic Sign Detection and Recognition System Using Deep Ensemble Learning

Research on Traffic Sign Detection and Recognition System Us...

引用

IEEE International Conference on Computer Communication and the Internet (ICCCI)

作者： Lung-Jen Wang Taweelap Suwattanapunkul Jarinya Thalauy Parinya Jansengrat Department of Computer Science and Information Engineering National Pingtung University Pingtung Taiwan International Master Program in Information Technology and Applications International College National Pingtung University Pingtung Taiwan Department of Big Data Management and Analytics Rajamangala University of Technology Thanyaburi Pathum Thani Thailand

ISBN: (数字)9798350351767

ISBN: (纸本)9798350351774

There is a rise in car accidents due to human errors on the road. A critical task of self-driving cars that can reduce accidents on the road is traffic sign detection and recognition (TSDR), which is vital in alerting drivers to the presence of traffic signs in advance. This research will separate the proposed deep ensemble learning algorithm into two methods. First, after the traffic scene process, the algorithm will detect the traffic sign as two categories with the YOLOv5s network. Then, process the traffic sign to recognize the traffic sign into seven classes with the MobileNet network. The detection model was trained with the Taiwan Traffic Sign Detection (TTSD) dataset collected from Taiwan roads. The recognition model was trained with the Taiwan Traffic Sign Recognition (TTSR) dataset. The result of the proposed algorithm showed high performance when experimenting with 95.83% accuracy, 87.34% true prediction, and 191.3 milliseconds (ms) of inference time.

关键词： YOLO Roads Prediction algorithms Inference algorithms Internet Autonomous automobiles Ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Fractal geometry predicts dynamic differences in structural and functional connectomes

arXiv

引用

arXiv 2025年

作者： Rădulescu, Anca Kaslik, Eva Fikl, Alexandru Nakuci, Johan Muldoon, Sarah Anderson, Michael Department of Mathematics SUNY New Paltz United States Department of Computer Science West University of Timișoara Romania Institute for Advanced Environmental Research West University of Timișoara Romania U.S. ARMY DEVCOM Army Research Laboratory United States Department of Mathematics Institute for Artificial Intelligence and Data Science Neuroscience Program University of Buffalo SUNY United States Department of Data Analytics Georgia Tech United States

Understanding the intricate architecture of brain networks and its connection to brain function is essential for deciphering the underlying principles of cognition and disease. While, traditional graph-theoretical measures have been widely used to characterize these networks, they often fail to fully capture the emergent properties of large-scale neural dynamics. Here, we introduce an alternative approach to quantify brain networks that is rooted in complex dynamics, fractal geometry, and asymptotic analysis. We apply these concepts to brain connectomes and demonstrate how quadratic iterations and geometric properties of Mandelbrot-like sets can provide novel insights into structural and functional network dynamics. Our findings reveal fundamental distinctions between structural (positive) and functional (signed) connectomes, such as the shift of cusp orientation and the variability in equi-M set geometry. Notably, structural connectomes exhibit more robust, predictable features, while functional connectomes show increased variability for non-trivial tasks. We further demonstrate that traditional graph-theoretical measures, when applied separately to the positive and negative sub-networks of functional connectomes, fail to fully capture their dynamic complexity. Instead, size and shape-based invariants of the equi-M set effectively differentiate between rest and emotional task states, which highlights their potential as superior markers of emergent network dynamics. These results suggest that incorporating fractal-based methods into network neuroscience provides a powerful tool for understanding how information flows in natural systems beyond static connectivity measures, while maintaining their simplicity. © 2025, CC BY.

关键词： Fractal dimension

来源：评论

学校读者我要写书评

暂无评论

The largest genome-wide association study for breast cancer in Taiwanese Han population

引用

Breast Cancer Research and Treatment 2024年第2期203卷 291-306页

作者： Hsu, Yu-Ching Chen, Hung-Lin Cheng, Chi-Fung Chattopadhyay, Amrita Chen, Pei-Shan Lin, Che-Chen Chiang, Hsiu-Yin Liu, Ting-Yuan Huang, Chi-Hao Kuo, Chin-Chi Chuang, Eric Y. Lu, Tzu-Pin Tsai, Fuu-Jen Bioinformatics Program Taiwan International Graduate Program National Taiwan University Taipei Taiwan Bioinformatics Program Institute of Statistical Science Taiwan International Graduate Program Academia Sinica Taipei Taiwan Institute of Health Data Analytics and Statistics Department of Public Health College of Public Health National Taiwan University Taipei Taiwan Big Data Center China Medical University Hospital Taichung Taiwan Center for Translational Genomic Research Department of Medical Research China Medical University Hospital Taichung Taiwan Million-Person Precision Medicine Initiative Department of Medical Research China Medical University Hospital Taichung Taiwan Division of Breast Surgery Department of Surgery China Medical University Hospital Taichung Taiwan Division of Nephrology Department of Internal Medicine China Medical University Hospital Taichung Taiwan Department of Medical Research China Medical University Hospital Taichung Taiwan Bioinformatics and Biostatistics Core Center of Genomic and Precision Medicine National Taiwan University Taipei Taiwan Graduate Institute of Biomedical Electronics and Bioinformatics National Taiwan University Taipei Taiwan Biomedical Technology and Device Research Laboratories Industrial Technology Research Institute Hsinchu Taiwan Genetic Center Department of Medical Research China Medical University Hospital Taichung Taiwan

Purpose: Breast cancer is a molecularly heterogeneous disease, and multiple genetic variants contribute to its development and prognosis. Most of previous genome-wide association studies (GWASs) and polygenic risk scores (PRSs) analyses focused on studying breast cancers of Caucasian populations, which may not be applicable to other population. Therefore, we conducted the largest breast cancer cohort of Taiwanese population to fill in the knowledge gap. Methods: A total of 152,534 Participants recruited by China Medical University Hospital between 2003 and 2019 were filtered by several patient selection criteria and GWAS quality control steps, resulting in the inclusion of 2496 cases and 9984 controls for this study. We then conducted GWAS for all breast cancers and PRS analyses for all breast cancers and the four breast cancer subtypes, including luminal A, luminal B, basal-like, and HER2-enriched. Results: The GWAS analyses identified 113 SNPs, 50 of which were novel. The PRS models for all breast cancers and the luminal A subtype showed positively correlated trends between the PRS and the risk of developing breast cancer. The odds ratios (95% confidence intervals) for the groups with the highest PRS in all breast cancers and the luminal A subtype were 5.33 (3.79–7.66) and 3.55 (2.13–6.14), respectively. Conclusion: In summary, we explored the association of genetic variants with breast cancer in the largest Taiwanese cohort and developed two PRS models that can predict the risk of developing any breast cancer and the luminal A subtype in Taiwanese women. © 2023, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Breast cancer Genome-wide association study Polygenic risk score Taiwanese population

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：