检索结果-内蒙古大学图书馆

Severity of Liver Cirrhosis Evaluated by Digital Subtraction Angiography Using Quantitative Color-Coding Analysis Before Transarterial Embolization

引用

Journal of Medical and Biological engineering 2023年第5期43卷 566-573页

作者： Giiang, Lung-Hui Liu, Chang-Hsien Yu, Chih-Yung Lin, Te-Pao Chen, Hsiang-Cheng Juan, Chun-Jung Chou, Yu-Ching Department of Radiology Tri-Service General Hospital and National Defense Medical Center Taipei Taiwan Department of Medical Imaging China Medical University Hsinchu Hospital and China Medical University No. 199 Sec. 1 Xinglong Rd Hsinchu Zhubei Taiwan Institute of Nuclear Engineering and Science National Tsing Hua University Hsinchu Taiwan Department of Radiology Tzu Chi Hospital Buddhist Tzu Chi Medical Foundation Taipei Taiwan Department of Radiology Kaohsiung Armed Forces General Hospital Kaohsiung Taiwan Division of Rheumatology Immunology and Allergy Department of Internal Medicine Tri-Service General Hospital and National Defense Medical Center Taipei Taiwan Department of Medical Imaging China Medical University Hospital Taichung Taiwan Department of Radiology School of Medicine China Medical University Taichung Taiwan Department of Biomedical Engineering National Defense Medical Center Taipei Taiwan Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan School of Public Health National Defense Medical Center Taipei Taiwan

Purpose: This study examined whether the quantitative color-coding analysis (QCA) of two-dimensional digital subtraction angiography (DSA) can accurately measure the maximal density time (Tmax) on the time–density curves of a contrast agent in selected vessels and evaluated the severity of liver cirrhosis during transarterial chemoembolization. Methods: 48 patients were divided into the Child-Pugh A and Child-Pugh B groups based on the severity of liver cirrhosis. The Tmax values of the contrast agent in the proximal superior mesenteric artery, right colic artery and extra-hepatic portal vein were calculated based on the superior mesenteric angiography results. Different grades of liver cirrhosis were evaluated by the clinical biochemistry values, liver-to-spleen ratio (LSR), and Tmax duration. Results: The Child-Pugh B group had a longer T3max duration (13.37 ± 3.76 s) than the Child-Pugh A group (13.04 ± 4.71 s), but the difference was not statistically significant (p = 0.825). The T3max duration correlated negatively and significantly (both p © 2023, Taiwanese Society of Biomedical engineering.

关键词： Biochemistry

来源：评论

学校读者我要写书评

暂无评论

Differential Evolution for Optimizing Parameter Estimation in Practical D2D Channels

Differential Evolution for Optimizing Parameter Estimation i...

引用

IEEE Conference on Wireless Communications and Networking

作者： Samuel B. Ferreira Gomes Nidhi Simmons Michel Daoud Yacoub Paschalis C. Sofotasios Simon L. Cotton Wireless Technology Laboratory School of Electrical and Computer Engineering University of Campinas Campinas Brazil Centre for Wireless Innovation School of Electronics Electrical Engineering and Computer Science Queen's University Belfast Belfast UK Department of Computer and Communication Engineering C2PS and 6G Center Khalifa University Abu Dhabi UAE Department of Electrical Engineering Tampere University Tampere Finland

ISBN: (数字)9798350303582

ISBN: (纸本)9798350303599

Inspired by the theory of natural evolution, Differential Evolution (DE) functions constitute an optimization tool in the field of evolutionary algorithms. Here, we propose employing DE to estimate physically acceptable fading parameters in device-to-device (D2D) communication channels. We examine four real-world D2D propagation channel measurements obtained under various conditions: indoor, outdoor, line-of-sight (LOS), and non-LOS. Four popular fading models, $\kappa-\mu, \eta-\mu, \kappa-\mu$ /inverse gamma, and $\eta-\mu$ /inverse gamma are used to characterize these links. Two fitness functions, Kullback-Leibler divergence (KLD) and mean squared error (MSE), are utilized for evaluation. We also compare the DE with another evolutionary algorithm, namely the genetic algorithm (GA). Notably, our results demonstrate that while both algorithms deliver excellent estimation performances, DE emerges as significantly faster and more robust compared to GA. Regarding fitness performances, the algorithm, when paired with KLD, outperforms the pairing with MSE, as assessed through the minimization of the Akaike information criterion.

关键词： Fading channels Parameter estimation Metaheuristics Estimation Channel estimation Line-of-sight propagation Evolutionary computation

来源：评论

学校读者我要写书评

暂无评论

Assisted Physical Interaction: Autonomous Aerial Robots with Neural Network Detection, Navigation, and Safety Layers

Assisted Physical Interaction: Autonomous Aerial Robots with...

引用

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Andrea Berra Viswa Narayanan Sankaranarayanan Achilleas Santi Seisa Julien Mellet Udayanga G.W.K.N. Gamage Sumeet Gajanan Satpute Fabio Ruggiero Vincenzo Lippiello Silvia Tolu Matteo Fumagalli George Nikolakopoulos Miguel Ángel Trujillo Soto Guillermo Heredia CATEC Advanced Center for Aerospace Technologies Seville Spain Department of Computer Electrical and Space Engineering Robotics and AI Team Luleå University of Technology Luleå Sweden Department of Electrical Engineering and Information Technology PRISMA Lab University of Naples Federico II Naples Italy Department of Electrical Engineering and Photonics Automation and Control Group Technical University of Denmark Denmark Robotics Vision and Control Group School of Engineering University of Seville Seville Spain

ISBN: (数字)9798350357882

ISBN: (纸本)9798350357899

The paper introduces a novel framework for safe and autonomous aerial physical interaction in industrial settings. It comprises two main components: a neural network-based target detection system enhanced with edge computing for reduced onboard computational load, and a control barrier function (CBF)-based controller for safe and precise maneuvering. The target detection system is trained on a dataset under challenging visual conditions and evaluated for accuracy across various unseen data with changing lighting conditions. Depth features are utilized for target pose estimation, with the entire detection framework offloaded into low-latency edge computing. The CBF-based controller enables the UAV to converge safely to the target for precise contact. Simulated evaluations of both the controller and target detection are presented, alongside an analysis of real-world detection performance.

关键词： Visualization Pose estimation Neural networks Lighting Object detection Autonomous aerial vehicles Aircraft navigation

来源：评论

学校读者我要写书评

暂无评论

Bidirectional Looking with A Novel Double Exponential Moving Average to Adaptive and Non-adaptive Momentum Optimizers

arXiv

引用

arXiv 2023年

作者： Chen, Yineng Li, Zuchao Zhang, Lefei Du, Bo Zhao, Hai National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan430072 China Hubei Luojia Laboratory Wuhan430072 China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China

Optimizer is an essential component for the success of deep learning, which guides the neural network to update the parameters according to the loss on the training set. SGD and Adam are two classical and effective optimizers on which researchers have proposed many variants, such as SGDM and RAdam. In this paper, we innovatively combine the backward-looking and forward-looking aspects of the optimizer algorithm and propose a novel ADMETA (A Double exponential Moving averagE To Adaptive and non-adaptive momentum) optimizer framework. For backward-looking part, we propose a DEMA variant scheme, which is motivated by a metric in the stock market, to replace the common exponential moving average scheme. While in the forward-looking part, we present a dynamic lookahead strategy which asymptotically approaches a set value, maintaining its speed at early stage and high convergence performance at final stage. Based on this idea, we provide two optimizer implementations, ADMETAR and ADMETAS, the former based on RAdam and the latter based on SGDM. Through extensive experiments on diverse tasks, we find that the proposed ADMETA optimizer outperforms our base optimizers and shows advantages over recently proposed com- Copyright © 2023, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Pano-NeRF: Synthesizing High Dynamic Range Novel Views with Geometry from Sparse Low Dynamic Range Panoramic Images

arXiv

引用

arXiv 2023年

作者： Lu, Zhan Zheng, Qian Shi, Boxin Jiang, Xudong School of Electrical and Electronic Engineering Nanyang Technological University Singapore College of Computer Science and Technology Zhejiang University China The State Key Lab of Brain-Machine Intelligence Zhejiang University China National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China National Engineering Research Center of Visual Technology School of Computer Science Peking University China

Panoramic imaging research on geometry recovery and High Dynamic Range (HDR) reconstruction becomes a trend with the development of Extended Reality (XR). Neural Radiance Fields (NeRF) provide a promising scene representation for both tasks without requiring extensive prior data. However, in the case of inputting sparse Low Dynamic Range (LDR) panoramic images, NeRF often degrades with under-constrained geometry and is unable to reconstruct HDR radiance from LDR inputs. We observe that the radiance from each pixel in panoramic images can be modeled as both a signal to convey scene lighting information and a light source to illuminate other pixels. Hence, we propose the irradiance fields from sparse LDR panoramic images, which increases the observation counts for faithful geometry recovery and leverages the irradiance-radiance attenuation for HDR reconstruction. Extensive experiments demonstrate that the irradiance fields outperform state-of-the-art methods on both geometry recovery and HDR reconstruction and validate their effectiveness. Furthermore, we show a promising byproduct of spatially-varying lighting estimation. The code is available at https://***/Lu-Zhan/Pano-NeRF. Copyright © 2023, The Authors. All rights reserved.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

BeHAutH: A KNN-Based Classification Scheme for Behavior-Based Authentication in Web 3.0

BeHAutH: A KNN-Based Classification Scheme for Behavior-Base...

引用

2022 IEEE International Conference on Communications, Computing, Cybersecurity and Informatics, CCCI 2022

作者： Bhattacharya, Pronaya Trivedi, Chandan Obaidat, Mohammad S. Patel, Kartik Tanwar, Sudeep Hsiao, Kuei-Fang Department of Computer Science and Engineering Institute of Technology Nirma University Gujarat Ahmedabad India Department of Computer Science Cybersecurity Center University of Texas Permian Basin OdessaTX70762 United States King Abdullah II School of IT University of Jordan Jordan University of Science and Technology Beijing China Computer Science Department University of Texas-Permian Basin 4901 E. University Blvd. OdessaTX79762 United States

ISBN: (数字)9781665486170

ISBN: (纸本)9781665486170

Web 3.0 would allow users and processes to communicate and interpret data semantically. It is expected to employ web user (WU) behaviour data, which is sampled and collected at different time instants for verification. Recent approaches have suggested behaviour-based authentication (BBA), but most schemes suffer from a high rate of false positives. Motivated from the gap, the paper presents a scheme named BeHAutH, that constructs a two-factor authentication (2FA) scheme for WU, based on real-time keystroke dynamics. We employ the K-nearest neighbour classification (KNN) algorithm and compute the similarity across two vectors in K dimensions. The similarity is computed in terms of both Euclidean and Manhattan distance metrics. The scheme achieves an accuracy of 87% over 146 testing samples, and a recall value of 0.95, which address the false negative issues. © 2022 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Merging UAV-Derived Metrics with Crop Physiology to Estimate Sunflower Yield

Merging UAV-Derived Metrics with Crop Physiology to Estimate...

引用

Frontiers of Information Technology (FIT)

作者： Usama Athar Muhammad Ali Zuhair Zafar Haris Khurshid Karsten Berns Muhammad Moazam Fraz School of Electrical Engineering and Computer Science National University of Sciences and Technology (NUST) Islamabad Pakistan Oilseeds Research Program National Agricultural Research Center (NARC) Islamabad Pakistan Department of Computer Science Rheinland-Pfälzische Technische Universität Kaiserslautern Germany

ISBN: (数字)9798331510503

ISBN: (纸本)9798331510510

Accurate and timely estimation of sunflower yield is crucial for agricultural researchers, farmers, and breeders. Use of Unmanned Aerial Vehicles (UAVs) with multi-spectral sensors has been adopted to meet the need for precise sunflower seed yield predictions. This study proposes a combined approach that integrates 12 remotely sensed vegetation indices (VIs) with 3 key physiological traits - fresh weight, dry weight, and moisture factor - to capture the complex dynamics affecting sunflower crop. Predictive performance of VIs alone and in combination with physiological traits is evaluated using Root Mean Squared Error (RMSE). Our results show that incorporating these two sets of features, along with their temporal, spectral, and statistical characteristics, leads to consistent improvements in sunflower seed yield estimation that can reduce the root mean squared error to as low as 0.4075 ( $\text{kg} / \text{plot}$ ).

关键词： Vegetation mapping Moisture Autonomous aerial vehicles Physiology Seeds (agriculture) Sensors Yield estimation Reliability Vehicle dynamics Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Internet-of-Explainable-Digital-Twins: A Case Study of Versatile Corn Production Ecosystem

Internet-of-Explainable-Digital-Twins: A Case Study of Versa...

引用

2022 IEEE International Conference on Communications, Computing, Cybersecurity and Informatics, CCCI 2022

作者： Bhattacharya, Pronaya Obaidat, Mohammad S. Sanghavi, Sakshi Sakariya, Vatsal Tanwar, Sudeep Hsiao, Kuei-Fang Department of Computer Science and Engineering Institute of Technology Nirma University Gujarat Ahmedabad India Department of Computer Science Cybersecurity Center University of Texas-Permian Basin OdessaTX70762 United States King Abdullah II School of IT University of Jordan Jordan University of Science and Technology Beijing China Computer Science Department University of Texas-Permian Basin 4901 E. University Blvd. OdessaTX79762 United States

ISBN: (数字)9781665486170

ISBN: (纸本)9781665486170

In this paper, the authors present a new architectural concept named as Internet-of-Explainable-Digital-Twins (IoxDT), that holistically integrates explainable AI (xAI) and digital twin (DT) in Industry 5.0 production processes. The authors present the architecture over a versatile production system (VPS) corn production plant, where processes are sensor-driven and monitored to minimize bias. The collaboration of DT and xAI leverages the robustness, predictability, and maintainability of VPS processes. In the proposed architecture, the VPS sensor-controlled inputs are sent to the DT controller. The controller is supplied with virtual inputs, which are replicas of real inputs, and the controller behaviour is monitored. The outputs are connected to an xAI module designed with Shapley additive explanations (SHAP) model, which generates the output predictability and dependence on inputs. The unsafe outputs are rejected. A case-study evaluation is carried out in terms of the mean and standard deviation of DT module creation, and SHAP predictability outputs, which shows an accuracy of 96% of unsafe inputs. The proposed results indicate the viability of the framework in real Industry 5.0 VPS setups. © 2022 IEEE.

关键词： Ecosystems

来源：评论

学校读者我要写书评

暂无评论

An Improvement of K-means Algorithm for Big Data Clustering

An Improvement of K-means Algorithm for Big Data Clustering

引用

International Conference on computer Applications Technology (ICCAT)

作者： Bingshan Liu Yaxuan Zhang Dandan Chen Engineering Research Center of Digital Forensics Ministry of Education Nanjing University of Information Science and Technology Nanjing China School of Computer Science Nanjing University of Information Science and Technology Nanjing China

Clustering data, the process of categorizing comparable data into distinct groups, is a fundamental task in data analysis. K-means is a widely used and fundamental clustering technique that employs iterative calculations to divide a given dataset into k clusters. It is particularly effective and adaptable for large datasets. However, determining the number of clusters and their centers in advance is a complex problem that often plagues researchers. In this article, we propose an innovative strategy to address these two obstacles by utilizing preprocessing to obtain the necessary information for k-means. We employ density-based clustering methods, represented by DENCLUE (DENsity-based CLUstEring), which can separate clusters regardless of the total number of clusters. DENCLUE is highly effective in producing excellent clusters and has received extensive attention. Our proposed method, Dek-means (Density-based kmeans algorithm), uses DENCLUE as a preliminary processing step to determine the quantity of clusters and calculate cluster centers. The resulting information is then passed on to k-means for final calculation and clustering. To evaluate the performance of our novel algorithm, we conducted tests on large datasets and analyze the results. The proposed method is guaranteed to converge to global minima, which improves the quality of the final result.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semantic-Aware Dual Contrastive Learning for Multi-label Image Classification

arXiv

引用

arXiv 2023年

作者： Ma, Leilei Sun, Dengdi Wang, Lei Zhao, Haifeng Luo, Bin School of Computer Science and Technology Anhui University China School of Artificial Intelligence Anhui University China School of Computer Science and Engineering Nanjing University of Science and Technology China Anhui Provincial key Laboratory of Multimodal Cognitive Computing Anhui University China Institute of Artificial Intelligence Hefei Comprehensive National Science Center China

Extracting image semantics effectively and assigning corresponding labels to multiple objects or attributes for natural images is challenging due to the complex scene contents and confusing label dependencies. Recent works have focused on modeling label relationships with graph and understanding object regions using class activation maps (CAM). However, these methods ignore the complex intra- and inter-category relationships among specific semantic features, and CAM is prone to generate noisy information. To this end, we propose a novel semantic-aware dual contrastive learning framework that incorporates sample-to-sample contrastive learning (SSCL) as well as prototype-to-sample contrastive learning (PSCL). Specifically, we leverage semantic-aware representation learning to extract category-related local discriminative features and construct category prototypes. Then based on SSCL, label-level visual representations of the same category are aggregated together, and features belonging to distinct categories are separated. Meanwhile, we construct a novel PSCL module to narrow the distance between positive samples and category prototypes and push negative samples away from the corresponding category prototypes. Finally, the discriminative label-level features related to the image content are accurately captured by the joint training of the above three parts. Experiments on five challenging large-scale public datasets demonstrate that our proposed method is effective and outperforms the state-of-the-art methods. Code and supplementary materials are released on https://***/yu-gi-oh-leilei/SADCL. Copyright © 2023, The Authors. All rights reserved.

关键词： Image classification

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：