检索结果-内蒙古大学图书馆

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Sampriti Soor Priyanka Kumari B. S. Daya Sagar Amba Shetty School of Computer Engineering Kalinga Institute of Industrial Technology Bhubaneswar India Department of Water Resources and Ocean Engineering NIT Karnataka India Systems Science and Informatics Unit Indian Statistical Institute Bangalore India

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Matching a target spectrum with known spectra in a spectral library is a common method for material identification in hyperspectral imaging research. Hyperspectral spectra exhibit precise absorption features across different wavelength segments, and the unique shapes and positions of these absorptions create distinct spectral signatures for each material, aiding in their identification. Therefore, only the specific positions can be considered for material identification. This study introduces the Weighted Sum of Segmented Correlation method, which calculates correlation indices between various segments of a library and a test spectrum, and derives a matching index, favoring positive correlations and penalizing negative correlations using assigned weights. The effectiveness of this approach is evaluated for mineral identification in hyperspectral images from both Earth and Martian surfaces.

关键词： Image segmentation Correlation Absorption Shape Geoscience and remote sensing Libraries Iron

来源：评论

学校读者我要写书评

暂无评论

Segmentation and Rigid Registration of Liver Dynamic Computed Tomography Images for Diagnostic Assessment of Fatty Liver Disease

引用

Journal of Computing Science and engineering 2023年第3期17卷 117-126页

作者： Koo, Kyoyeong Lee, Jeongjin Hwang, Jiwon Park, Taeyong Jeong, Heeryeol Khang, Seungwoo Lee, Jongmyoung Kwon, Hyuk Na, Seungwon Lee, Sunyoung Kim, Kyoung Won Kim, Kyung Won School of Computer Science and Engineering Soongsil University Seoul Korea Republic of Hanwha Vision Co. Ltd. Seongnam Korea Republic of Department of Biomedical Informatics Hallym University Medical Center Anyang Korea Republic of SKIA Inc. Seoul Korea Republic of Department of Radiology and Research Institute of Radiological Science Severance Hospital Yonsei University College of Medicine Seoul Korea Republic of Department of Radiology and Research Institute of Radiology Asan Medical Center University of Ulsan College of Medicine Seoul Korea Republic of iAID Inc. Seoul Korea Republic of

This study presents a method for diagnosing fatty liver disease by using time-difference liver computed tomography (CT) images of the same patient to perform segmentation and rigid registration on liver regions, excluding the vascular regions. The proposed method comprises three main steps. First, the liver region is segmented in the precontrast phase, and the liver and liver vessel regions are segmented in the portal phase. Second, rigid registration is performed between the liver regions to align the liver positions affected by the patient's posture or breathing. Finally, fatty liver diagnosis is performed with the average Hounsfield unit (HU) value calculated using only the area removed from the vessel area segmented in the portal phase after registration in the precontrast liver area. The mean distance error between the points corresponding to the liver boundary was 3.136 mm and the mean error between the anatomic landmarks was 4.166 mm. A fatty liver diagnosis was confirmed in a total of 18 cases, and the results were identical to the histology results. This technique may be valuable in clinically diagnosing fatty liver using liver CT imaging, which is widely available and more commonly used than abdominal magnetic resonance. © 2023. The Korean institute of Information Scientists and Engineers

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Access Optimization of Teaching Resource Management Database Based on Semantic Association Mining

Access Optimization of Teaching Resource Management Database...

引用

2021 International Conference on Education, Information Management and Service Science, EIMSS 2021

作者： Wang, Lei Chen, Rongli Feng, Huiya Ma, Yue Engineering Research Institute Guangzhou City University of Technology Guangzhou China Dongguan Polytechnic Department of Computer Engineering Dongguan China Academic Service Office Guangzhou City University of Technology Guangzhou China

ISBN: (纸本)9781665427074

In order to improve the service quality of teaching resource management database, it is necessary to construct an optimized access scheduling model of personalized intelligent teaching resource management database, and propose an access scheduling algorithm of personalized intelligent teaching resource management database based on semantic association mining. Using fuzzy fusion degree feature parameter set matching and adaptive filtering method, the block combination control model of personalized data in teaching resource management database is obtained. Constructing a semantic combination autocorrelation distribution detection model of personalized data of teaching resource management database, adopting rough set feature matching and joint cross-correlation feature detection methods to carry out personalized data fusion, cluster analysis and feature reorganization of teaching resource management database, carrying out personalized access and information clustering of teaching resource management database in the reorganized feature space, combining resource combination allocation and joint mining methods. A fuzzy clustering model for adaptive access and scheduling of teaching resource management database is established. According to the results of fuzzy dynamic detection and fusion clustering, the feature matching in the process of access and scheduling of personalized intelligent teaching resource management database is realized. The adaptive access and scheduling model of teaching resource management database is established by the combination of cluster block clustering and piecewise fusion clustering. Tests show that this method has high accuracy and good matching for adaptive access and scheduling of teaching resource management database. © 2021 IEEE.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

Optimizing Virtual Machine Downtime in Live Migration using the Least Frequently Used Service-based Pre-copy Algorithm

Optimizing Virtual Machine Downtime in Live Migration using ...

引用

International Conference on computer Communication and informatics (ICCCI)

作者： C. P. Shabariram N. Shanthi P. Priya Ponnusamy R. Prema R. S. Sowmiya Priya Department of Computer Science and Engg PSG Institute of Technology and Applied Research Coimbatore India Department of Computer Science and Engg Kongu Engineering College Erode India

Cloud computing has been considered the most reliable and safe technology among many cloud users. Virtual machine migration is a crucial component of cloud computing technology. A Virtual machine is transferred from one host machine to another during the migration process, which is accomplished by repeatedly copying the memory pages available in the virtual disk. The time required for the movement of secondary storage, main memory, process states, and network connectivity, as well as the maintenance of their accuracy, must be considered for the efficient migration of virtual machines from one physical host to another in the cloud service provider. The most robust mechanism for system maintenance, resilience system, balancing the load of the service provider, and power-saving is the live migration of virtual machines between the nodes in the data center. So many services are running in the virtual machines during live migration; thus, it needs to take place with the least amount of downtime possible to prevent service degradation. The memory pages in the virtual storage must be copied to the other host using the least frequently used service-based pre-copy algorithm to optimize the downtime. The effectiveness of the suggested solution was evaluated in comparison to OpenNebula and OpenStack, two cloud computing platforms. The least frequently used service-based pre-copy algorithm reduces the amount of virtual machine downtime during live migration.

关键词： Degradation Cloud computing Data centers Memory management Maintenance engineering Virtual machining Reliability

来源：评论

学校读者我要写书评

暂无评论

Depth and Pitch Control of Autonomous Underwater Glider Using Model Predictive Control with ARX Model

Depth and Pitch Control of Autonomous Underwater Glider Usin...

引用

International Conference on Electrical engineering and informatics, ICEEI

作者： Jason Jeremy Egi Muhammad Idris Hidayat Simon Siregar Bambang Riyanto Trilaksono Natsir Habibullah School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia Department Computer Engineering Faculty of Applied Science Telkom University Bandung Indonesia

Autonomous Underwater Gliders (AUGs) are extensively developed vehicles capable of prolonged exploration and observation in complex marine environments. Control of the AUG is challenging due to its slow response system and its constraints. In this research, a linear model representation of AutoRegressive eXogenous input (ARX) will be constructed using input and output data from the AUG system, built Model Predictive Control (MPC), analyzed the performance, comparing with traditional Proportional-Integral-Derivative (PID). The objective is to enhance setpoint tracking accuracy and minimize energy to extend exploration time while faced with constraints. Simulation results reveal MPC exhibits potential setpoint tracking, low overshoot as low as 0.6% up to 0.3m/s maximum depth rate, has relatively low input changes indicating good efficiency compared to PID. MPC approach effectively addresses slow response systems, managing momentum, and handling actuator constraints commonly encountered in AUG.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Implementation of PSO-Optimized PI Control Algorithm for SMES Based DVR in Power Quality Mitigation

Implementation of PSO-Optimized PI Control Algorithm for SME...

引用

Delhi Section Conference (DELCON), IEEE

作者： Jeba Singh O D. Godwin Immanuel Sheila Mahapatra Rajesh Sharma R Akey Sungheetha G. S. Pradeep Ghantasala Centre for Academic Research Alliance University Bengaluru India School of Electrical and Electronics Sathyabama Institute of Science of Technology Chennai India Department of Electrical and Electronics Engineering Alliance University Bengaluru India Department of Computer Sciences and Engineering Alliance University Bengaluru India

ISBN: (数字)9798331518592

ISBN: (纸本)9798331518608

Nowadays, Power Quality (PQ) problems should be more concentrated in distribution systems of power sector. To maintain the power quality in the distribution system the occurrence of PQ disturbances must be identified and compensated. Disturbances like voltage sag and swell are the major issues that cause failure in electrical devices. In this paper, a Superconducting Magnetic Energy Storage (SMES) integrated Dynamic Voltage Restorer (DVR)is implemented to protect the grid voltage from sag, swell and transients. A better solution to PQ disturbances and mitigation related issues are provided through DVR topology. Voltage sag is one of the dominant problems which cause the PQ issues. In this proposed work, sag, swell and outages are mitigated thus the real power is recovered so that the power wastage is prevented. Moreover, this SMES technology-based DVR method compensates the grid from balanced and unbalanced sag, mitigation of outages, interruption, single phase and two-phase swell conditions. The principle, design and working of the SMES based DVR is implemented using MATLAB / SIMULINK. The testing of the established model and performance results are presented.

关键词： Voltage fluctuations Software packages Prevention and mitigation Power quality Reliability engineering Topology Power system reliability Superconducting magnetic energy storage Transient analysis Testing

来源：评论

学校读者我要写书评

暂无评论

MECG-E: Mamba-based ECG Enhancer for Baseline Wander Removal

arXiv

引用

arXiv 2024年

作者： Hung, Kuo-Hsuan Wang, Kuan-Chen Liu, Kai-Chun Chen, Wei-Lun Lu, Xugang Tsao, Yu Lin, Chii-Wann Department of Biomedical Engineering National Taiwan University Taiwan Research Center for Information Technology Innovation Academic Sinica Taiwan College of Information and Computer Sciences University of Massachusetts Amherst United States National Institute of Information and Communications Technology Japan

Electrocardiogram (ECG) is an important noninvasive method for diagnosing cardiovascular disease. However, ECG signals are susceptible to noise contamination, such as electrical interference or signal wandering, which reduces diagnostic accuracy. Various ECG denoising methods have been proposed, but most existing methods yield suboptimal performance under very noisy conditions or require several steps during inference, leading to latency during online processing. In this paper, we propose a novel ECG denoising model, namely Mamba-based ECG Enhancer (MECG-E), which leverages the Mamba architecture known for its fast inference and outstanding nonlinear mapping capabilities. Experimental results indicate that MECG-E surpasses several well-known existing models across multiple metrics under different noise conditions. Additionally, MECG-E requires less inference time than state-of-the-art diffusion-based ECG denoisers, demonstrating the model’s functionality and efficiency. Copyright © 2024, The Authors. All rights reserved.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

What improves the generalization of graph transformers? a theoretical dive into the self-attention and positional encoding 24

What improves the generalization of graph transformers? a th...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Hongkang Li Meng Wang Tengfei Ma Sijia Liu Zaixi Zhang Pin-Yu Chen Department of Electrical Computer and System Engineering Rensselaer Polytechnic Institute Troy NY Department of Biomedical Informatics Stony Brook University Stony Brook NY Department of Computer Science and Engineering Michigan State University East Lansing MI and MIT-IBM Watson AI Lab IBM Research MA Department of Computer Science and Engineering University of Science and Technology of China Hefei Anhui China IBM Thomas J. Watson Research Center Yorktown Heights NY

Graph Transformers, which incorporate self-attention and positional encoding, have recently emerged as a powerful architecture for various graph learning tasks. Despite their impressive performance, the complex non-convex interactions across layers and the recursive graph structure have made it challenging to establish a theoretical foundation for learning and generalization. This study introduces the first theoretical investigation of a shallow Graph Transformer for semi-supervised node classification, comprising a self-attention layer with relative positional encoding and a two-layer perceptron. Focusing on a graph data model with discriminative nodes that determine node labels and non-discriminative nodes that are class-irrelevant, we characterize the sample complexity required to achieve a desirable generalization error by training with stochastic gradient descent (SGD). This paper provides the quantitative characterization of the sample complexity and number of iterations for convergence dependent on the fraction of discriminative nodes, the dominant patterns, and the initial model errors. Furthermore, we demonstrate that self-attention and positional encoding enhance generalization by making the attention map sparse and promoting the core neighborhood during training, which explains the superior feature representation of Graph Transformers. Our theoretical results are supported by empirical experiments on synthetic and real-world benchmarks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Drug Repurposing Targeting COVID-19 3CL Protease using Molecular Docking and Machine Learning Regression Approach

arXiv

引用

arXiv 2023年

作者： Aqeel, Imra Majid, Abdul Biomedical Informatics Research Lab Department of Computer & Information Sciences Pakistan Institute of Engineering & Applied Sciences Nilore Islamabad45650 Pakistan

The COVID-19 pandemic has initiated a global health emergency, with an exigent need for effective cure. Progressively, drug repurposing is emerging a promise solution as it saves the time, cost and labor. However, the number of drug candidates that have been identified as being repurposed for the treatment of COVID-19 are still insufficient, so more effective and thorough drug exploring strategies are required. In this study, we joint the molecular docking with machine learning regression approaches to find some prospective therapeutic candidates for COVID-19 treatment. We screened the 5903 approved drugs for their inhibition by targeting the main protease 3CL of SARS-CoV-2, which is responsible to replicate the virus. Molecular docking is used to calculate the binding affinities of these drugs to the main protease 3CL. We employed several machine learning regression approaches for QSAR modeling to find out some potential drugs with high binding affinities. Our outcomes demonstrated that the Decision Tree Regression (DTR) model with best scores of R2 and RMSE, is the most suitable model to explore the potential drugs. We shortlisted six favorable drugs with their respective Zinc IDs ZINC (3873365, 85432544, 203757351, 85536956, 8214470, and 261494640) within the range of -15 kcal/mol to -13 kcal/mol. These drugs have novel repurposing potential, except for one antiviral ZINC203757351 compound that has already been identified in other studies. We further examined the physiochemical and pharmacokinetic properties of these most potent drugs and their best binding interaction to specific target protease 3CLpro. Our study provides an efficient framework to explore the potential drugs against COVID-19, and establishes the impending combination of molecular docking with machine learning regression approaches to accelerate the identification of potential therapeutic candidates. Our verdicts contribute to the larger goal of finding effective cures for COVID-19, which is an a

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

A Multi-View Learning-Based Bayesian Ruleset Extraction Algorithm For Accurate Hepatotoxicity Prediction

A Multi-View Learning-Based Bayesian Ruleset Extraction Algo...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Chen, Siyang Wu, Lianlian Xu, Yong Liu, Kunhong He, Song Bo, Xiaochen Xiamen University School of Informatics Xiamen China Tianjin University Academy of Medical Engineering and Translational Medicine Tianjin China Fujian University of Technology School of Computer Science and Mathematics Fuzhou China Xiamen University School of Film Department of Digital Media Technology Xiamen China Institute of Health Service and Transfusion Medicine Department of Bioinformatics Beijing China

ISBN: (纸本)9798350337488

The interpretable machine learning method is important in drug discovery. Unlike traditional ensemble learning methods, this paper proposes an interpretable algorithm based on Bayesian rule extraction to obtain reliable and explainable results for hepatotoxicity prediction. To extract information from different types of omics data, our algorithm employs a multi-view learning strategy to enhance performance. Specifically, a random forest is trained in each view, and then the Bayesian rule extraction algorithm is designed to select an optimal rule subset, controlling the size and accuracy of the ruleset through probabilities. These rule sets are integrated through multi-view voting to get the final decisions. The performance of our algorithm is tested on the hepatotoxicity dataset, demonstrating that compared to traditional machine learning algorithms and rule-based algorithms, our approach maintains excellent performance while achieving high interpretability in most cases. Our python source code and the related Supplementary Materials are available at: ***/MLDMXM2017/MV-BRS. © 2023 IEEE.

关键词： Bayesian Ruleset Hepatotoxicity Prediction Interpretable Machine Learning Multi-view Learning

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：