检索结果-内蒙古大学图书馆

Application of Kronecker convolutions in deep learning technique for automated detection of kidney stones with coronal CT images

引用

Information Sciences 2023年 640卷

作者： Patro, Kiran Kumar Allam, Jaya Prakash Neelapu, Bala Chakravarthy Tadeusiewicz, Ryszard Acharya, U Rajendra Hammad, Mohamed Yildirim, Ozal Plawiak, Pawel Department of Electronics and Communication Engineering Aditya Institute of Technology and Management AP Tekkali532201 India Department of Electronics and Communication Engineering National Institute of Technology Rourkela Odisha Rourkela769008 India Department of Biotechnology and Medical Engineering National Institute of Technology Rourkela Odisha Rourkela769008 India AGH University of Science and Technology Department of Biocybernetics and Biomedical Engineering Krakow Poland School of Mathematics Physics and Computing University of Southern Queensland Springfield Australia EIAS Data Science Lab College of Computer and Information Sciences Prince Sultan University Riyadh11586 Saudi Arabia Department of Information Technology Faculty of Computers and Information Menoufia University Shibin El Kom32511 Egypt Department of Software Engineering Firat University Elazig Turkey Department of Computer Science Faculty of Computer Science and Telecommunications Cracow University of Technology Warszawska 24 Krakow31-155 Poland Institute of Theoretical and Applied Informatics Polish Academy of Sciences Baltycka 5 Gliwice44-100 Poland

Kidney stone disease is a serious public health concern that is getting worse with changes in diet, obesity, medical conditions, certain supplements etc. A kidney stone also called a renal calculus, is a hard buildup of urine minerals that form in the kidneys. Computed tomography (CT) is one of the imaging models used to identify kidney stones by clinical experts. Due to the low resolution of these images, sometimes detecting kidney stones is tedious with the naked eye, which may lead to false alarms. In this work, a computer-based diagnosis system with a deep learning technique has been developed as a practical solution to aid clinicians in their diagnosis. The traditional convolutional neural network (CNN)-based deep learning technology can detect stones in the kidney. Still, it suffers from the performance and standard implementation of the convolution operations in convolution layers. A Kronecker product-based convolution technique is incorporated in the proposed deep learning architecture to reduce the redundancy in feature maps without convolution overlapping. Our proposed method helps to make the network more effective by extracting abstract and in-depth features from the input images. The publicly available GitHub kidney stone CT scans are utilized to develop the proposed architecture. Our automated model detected kidney stones with an accuracy of 98.56% utilizing CT images. Our system is more effective than the most recent and cutting-edge techniques developed for identifying kidney stones of any size, including the smallest ones. © 2023 The Author(s)

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Dynamic SDN-based Privacy-Preserving Approach for Smart City Using Trust Technique 9

A Dynamic SDN-based Privacy-Preserving Approach for Smart Ci...

引用

9th Iranian Joint Congress on Fuzzy and Intelligent Systems, CFIS 2022

作者： Alzubi, Jafar A. Movassagh, AliAkbar Gheisari, Mehdi Najafabadi, Hamid Esmaeili Abbasi, Aaqif Afzaal Liu, Yang Pingmei, Zhou Izadpanahkakhk, Mahdieh Najafabadi, AmirHossein Pourishaban Al-Balqa Applied University Faculty of Engineering Salt Jordan Tehran University of Medical Sciences School of Medicine Department of Medical Physics and Biomedical Engineering Tehran Iran Islamic Azad University Young Researchers and Elite Club Parand Branch Parand Iran University of Calgary Canada Foundation University Department of Software Engineering Islamabad44000 Pakistan Harbin Institute of Technology Department of Computer Science and Technology Shenzhen China Shenzhen BKD Company Shenzhen China La Sapienza University DIET Department Rome Italy University of Yazd Department of Electrical and Computer Engineering Yazd Iran

ISBN: (纸本)9781665478724

A smart city is an Internet-based application of things that automates city management with no need for human interference. Exchanging data via devices obviate some challenges in intelligent cities. In a smart city, Internet-of-Things (IoT) devices may detect sensitive data, posing a risk of privacy violation and system harm. We discover that existing solutions are either too expensive or ineffective at limiting unintended disclosure of sensitive data to build a dependable, smart city. The fact that they create static surroundings is the fundamental reason behind this. software-Defined Networking (SDN) technology has recently evolved to configure the network for performance and monitoring improvement. This study offers a work-in-progress that uses the SDN to protect the privacy of IoT devices by creating a dynamic SDN-based privacy-preserving ecology. The mechanism of the SDN controller performs under the nodes' mutual trust;it chooses various routes from the IoT device to the Cloud space destination dependent on the level of confidence. The packet is re-routed if the SDN controller identifies a device that does not trust its neighbor. Then it instructs the owner to deliver data over a different path. To demonstrate its improved performance, we are currently evaluating it from the perspective of overhead criteria in the future. © 2022 IEEE.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

Shunt Capacitor Bank Fault Detection and Localization Using Sub-Cycle Algorithm

Shunt Capacitor Bank Fault Detection and Localization Using ...

引用

IEEE Canada Electric Power Conference, EPEC

作者： Mohsen Tajdinian Behzad Behdani Ali Goodarzi Harold R. Chamorro Vijay K. Sood Department of Power and Control Engineering School of Electrical and Computer Engineering Shiraz University Shiraz Iran Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft the Netherlands Fars Electricity Distribution Company Fars Iran School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Department of Electrical Computer and Software Engineering Faculty of Engineering and Applied Science Ontario Tech University Ontario Canada

ISBN: (纸本)9781665463195

Fast internal detection and location in Shunt Ca-pacitor Banks (SCBs) can lead to the prevention of damages to other SCBs' elements and consequently avoid undesirable performance and effects in power system operation. This paper targets the performance of phasor-based algorithms of failure detection and fault location of SCBs. Being dependent on the fundamental phasor components which usually are calculated based on the Discrete Fourier Transform (DFT), the failure detection and fault location algorithms suffer from almost one-cycle delay. This paper provides sub-cycle phasor estimation based on the least-square technique. The proposed algorithm is evaluated for different configurations of SCBs considering different fuse protection designs. The proposed method provides a criterion for relay decision-making in the case of multiple faulty phases condition. The proposed method is designed to monitor and detect consecutive failures based on the existing data of commercial relays. Performance evaluations are conducted under different circumstances namely voltage unbalance conditions and multiple internal fault locations.

关键词： Performance evaluation Fault detection Capacitors Discrete Fourier transforms Estimation Voltage Fault location

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based New Energy Grid Electric Energy Measurement Transaction System

Blockchain-based New Energy Grid Electric Energy Measurement...

引用

Symposium of Image, Signal Processing, and Artificial Vision (STSIVA)

作者： Wei Chen Chengfu Sun School of Computer and Software Engineering Huaiyin Institute of Technology Huaian China

ISBN: (数字)9781728170862

ISBN: (纸本)9781728170879

With the maturity of hlockchain technology, it has heen employed in many fields. This article aims to apply hlockchain technology to the real-time electric power transaction of alternative energy sources. A new energy grid electricity measurement transaction system based on hlockchain is designed. First, the architecture design of the system is introduced. Second, the smart contracts are deployed in the private hlockchain to realize the basic power measurement and trading. The real-time active and reactive powers are measured by smart meters which connect to the smart contracts with the MQTT protocol. Data is uploaded to the hlockchain and the trading can be completed automatically. Finally, the comparison with the traditional power trading system shows the advantages of the hlockchain based electricity transaction system.

关键词： Visualization Smart contracts Energy measurement Blockchain Real-time systems Smart meters Servers

来源：评论

学校读者我要写书评

暂无评论

Model Checking Quantum Continuous-Time Markov Chains 32

Model Checking Quantum Continuous-Time Markov Chains

引用

32nd International Conference on Concurrency Theory, CONCUR 2021

作者： Xu, Ming Mei, Jingyi Guan, Ji Yu, Nengkun MoE Engineering Research Center of Software/Hardware Co-design Technology and Application Shanghai Key Lab of Trustworthy Computing East China Normal University Shanghai China Shanghai Key Lab of Trustworthy Computing East China Normal University Shanghai China State Key Lab of Computer Science Institute of Software Chinese Academy of Sciences Beijing China Centre for Quantum Software and Information Faculty of Engineering and Information Technology University of Technology Sydney Australia

ISBN: (纸本)9783959772037

Verifying quantum systems has attracted a lot of interests in the last decades. In this paper, we initialise the model checking of quantum continuous-time Markov chain (QCTMC). As a real-time system, we specify the temporal properties on QCTMC by signal temporal logic (STL). To effectively check the atomic propositions in STL, we develop a state-of-the-art real root isolation algorithm under Schanuel's conjecture;further, we check the general STL formula by interval operations with a bottom-up fashion, whose query complexity turns out to be linear in the size of the input formula by calling the real root isolation algorithm. A running example of an open quantum walk is provided to demonstrate our method. © Ming Xu, Jingyi Mei, Ji Guan, and Nengkun Yu;.

关键词： Model checking

来源：评论

学校读者我要写书评

暂无评论

Enhancing Multi-Label ECG Classification via Task-Guided Lead Correlations in Internet of Medical Things

引用

IEEE Internet of Things Journal 2025年第12期12卷 20544-20555页

作者： Yuan, Xiaoyan Wang, Wei Chen, Junxin Fang, Kai Bashir, Ali Kashif Mondal, Tapas Hu, Xiping Deen, M. Jamal Beijing Institute of Technology School of Medical Technology Beijing100081 China Shenzhen MSU-BIT University Guangdong-Hong Kong-Macao Joint Laboratory for Emotion Intelligence and Pervasive Computing Artificial Intelligence Research Institute Guangdong Shenzhen518172 China Dalian University of Technology School of Software Dalian116621 China Zhejiang A and F University College of Mathematics and Computer Science Hangzhou311300 China Manchester Metropolitan University Department of Computing and Mathematics United Kingdom Chitkara University Institute of Engineering and Technology Centre for Research Impact and Outcome Chitkara University Punjab Rajpura140401 India McMaster University Faculty of Health Science and the Department of Pediatrics Hamilton Canada McMaster University McMaster School of Biomedical Engineering Hamilton Canada McMaster University Electrical and Computer Engineering Department Hamilton Canada

With the rise of the Internet of Things (IoT), wearable devices have enabled real-time health monitoring, particularly through physiological signals like electrocardiograms (ECG). The standard 12-lead ECG records the electrical activity of the heart from multiple perspectives, providing valuable insights into cardiac health. However, existing 12-lead ECG analysis methods often treat leads as channel-level arrangements or rely on spatial adjacency to predefine lead connections, limiting their ability to capture the complex spatial and functional relationships between leads fully. To address this limitation, we propose TGLLNet, a task-driven model that automatically learns inter-lead relationships to improve multi-label ECG classification. TGLLNet adaptively learns lead connectivity patterns and relational strengths, enhancing ECG representation and improving model generalizability across tasks. Specifically, TGLLNet employs a Temporal Graph Construction (ETGC) module to convert ECG signals into temporal graphs and uses a Residual Pyramid Graph Convolution (RPG) module for multi-level graph embeddings, utilizing a Graph Convolutional Network (GCN) with independently learnable adjacency matrices. Combined with a Temporal Context Convolution (TCC) module, TGLLNet captures spatio-temporal dependencies, significantly improving ECG representation. Experimental results on 7 tasks from PTB-XL and CPSC2018 datasets demonstrate that TGLLNet outperforms existing methods, showing superior generalizability across different tasks. Our code is available at https://***/rosemary333/TGLLnet. © 2014 IEEE.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

COVID TCL:A Joint Metric Loss Function for Diagnosing COVID-19 Patient in the Early and Incubation Period

引用

computer Systems Science & engineering 2023年第10期47卷 187-204页

作者： Rui Wen Jie Zhou Zhongliang Shen Xiaorui Zhang Sunil Kumar Jha Department of Electromechanical Engineering Zhejiang Business Technology InstituteNingbo315012China Engineering Research Center of Digital Forensics Ministry of EducationJiangsu Engineering Center of Network MonitoringSchool of Computer and SoftwareNanjing University of Information Science&TechnologyNanjing210044China Wuxi Research Institute Nanjing University of Information Science&TechnologyWuxi214100China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET) Nanjing University of Information Science&TechnologyNanjing210044China Department of Physics Faculty of ScienceAdani UniversityAhmedabadIndia

Convolution Neural Networks(CNN)can quickly diagnose COVID-19 patients by analyzing computed tomography(CT)images of the lung,thereby effectively preventing the spread of ***,the existing CNN-based COVID-19 diagnosis models do consider the problem that the lung images of COVID-19 patients in the early stage and incubation period are extremely similar to those of the non-COVID-19 *** reduces the model’s classification sensitivity,resulting in a higher probability of the model misdiagnosing COVID-19 patients as non-COVID-19 *** solve the problem,this paper first attempts to apply triplet loss and center loss to the field of COVID-19 image classification,combining softmax loss to design a jointly supervised metric loss function COVID Triplet-Center Loss(COVID-TCL).Triplet loss can increase inter-class discreteness,and center loss can improve intra-class ***,COVID-TCL can help the CNN-based model to extract more discriminative features and strengthen the diagnostic capacity of COVID-19 patients in the early stage and incubation ***,we use the extreme gradient boosting(XGBoost)as a classifier to design a COVID-19 images classification model of CNN-XGBoost architecture,to further improve the CNN-based model’s classification effect and operation *** experiment shows that the classification accuracy of the model proposed in this paper is 97.41%,and the sensitivity is 97.61%,which is higher than the other 7 reference *** COVID-TCL can effectively improve the classification sensitivity of the CNN-based model,the CNN-XGBoost architecture can further improve the CNN-based model’s classification effect.

关键词： Covid-19 diagnose convolutional neural networks XGBoost COVID triplet-center loss early and incubation COVID-19 patients

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Learning on 3D Point Clouds by Clustering and Contrasting

arXiv

引用

arXiv 2022年

作者： Mei, Guofeng Yu, Litao Wu, Qiang Zhang, Jian Huang, Xiaoshui Bennamoun, Mohammed The Faculty of Engineering and Information Technology University of Technology Sydney SydneyNSW2007 Australia The Image X Institute of Faculty of Medicine and Health University of Sydney SydneyNSW2015 Australia The Department of Computer Science and Software Engineering The University of Western Australia WA6009 Australia

Learning from unlabeled or partially labeled data to alleviate human labeling remains a challenging research topic in 3D modeling. Along this line, unsupervised representation learning is a promising direction to auto-extract features without human intervention. This paper proposes a general unsupervised approach, named ConClu, to perform the learning of point-wise and global features by jointly leveraging point-level clustering and instance-level contrasting. Specifically, for one thing, we design an Expectation-Maximization (EM) like soft clustering algorithm that provides local supervision to extract discriminating local features based on optimal transport. We show that this criterion extends standard cross-entropy minimization to an optimal transport problem, which we solve efficiently using a fast variant of the Sinkhorn-Knopp algorithm. For another, we provide an instance-level contrasting method to learn the global geometry, which is formulated by maximizing the similarity between two augmentations of one point cloud. Experimental evaluations on downstream applications such as 3D object classification and semantic segmentation demonstrate the effectiveness of our framework and show that it can outperform state-of-the-art techniques. © 2022, CC BY-NC-ND.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

Dual-View Pyramid Pooling in Deep Neural Networks for Improved Medical Image Classification and Confidence Calibration

arXiv

引用

arXiv 2024年

作者： Zhang, Xiaoqing Nie, Qiushi Xiao, Zunjie Zhao, Jilu Wu, Xiao Guo, Pengxin Li, Runzhi Liu, Jin Wei, Yanjie Pan, Yi Center for High Performance Computing Shenzhen Key Laboratory of Intelligent Bioinformatics Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen518055 China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Department of Statistics and Actuarial Science The University of Hong Kong 999077 Hong Kong Cooperative Innovation Center of Internet Healthcare Zhengzhou University Zhengzhou450001 China Hunan Provincial Key Lab on Bioinformatics School of Computer Science and Engineering Central South University Changsha410083 China Xinjiang Engineering Research Center of Big Data and Intelligent Software School of software Xinjiang University Wulumuqi830046 China Faculty of Computer Science and Control Engineering Shenzhen University of Advanced Technology Shenzhen China

Spatial pooling (SP) and cross-channel pooling (CCP) operators have been applied to aggregate spatial features and pixel-wise features from feature maps in deep neural networks (DNNs), respectively. Their main goal is to reduce computation and memory overhead without visibly weakening the performance of DNNs. However, SP often faces the problem of losing the subtle feature representations, while CCP has a high possibility of ignoring salient feature representations, which may lead to both miscalibration of confidence issues and suboptimal medical classification results. To address these problems, we propose a novel dual-view framework, the first to systematically investigate the relative roles of SP and CCP by analyzing the difference between spatial features and pixel-wise features. Based on this framework, we propose a new pooling method, termed dual-view pyramid pooling (DVPP), to aggregate multi-scale dual-view features. DVPP aims to boost both medical image classification and confidence calibration performance by fully leveraging the merits of SP and CCP operators from a dual-axis perspective. Additionally, we discuss how to fulfill DVPP with five parameter-free implementations. Extensive experiments on six 2D/3D medical image classification tasks show that our DVPP surpasses state-of-the-art pooling methods in terms of medical image classification results and confidence calibration across different DNNs. © 2024, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

MSKI-Net: Towards modality-specific knowledge interaction for glioma survival prediction

MSKI-Net: Towards modality-specific knowledge interaction fo...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Ran Su Jin Xiao Hui Cui Ping Xuan Xikang Feng Leyi Wei Qiangguo Jin School of Computer Software College of Intelligence and Computing Tianjin University Tianjin China Department of Computer Science and Information Technology La Trobe University Melbourne Australia Department of Computer Science School of Engineering Shantou University China School of Software Northwestern Polytechnical University China AIDD Faculty of Applied Science Macao Polytechnic University Macao SAR China School of Information Xiamen University Xiamen China Yangtze River Delta Research Institute of Northwestern Polytechnical University Taicang China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Gliomas hold a prominent position in neurooncology due to their high malignancy and poor survival rates. Accurately predicting the prognosis and survival risk of glioma patients is crucial for clinical treatment. Recent advances in survival prediction methods emphasize the importance of integrating complementary information from diverse modalities while neglecting the significant modality gap between pathological images and genomic data. To address this issue, we propose a modality-specific knowledge interaction network (MSKI-Net), which integrates whole slide images (WSI), RNA-Seq gene expression data, and copy number variation (CNV) data for glioma survival analysis. The MSKI-Net consists of a modality-specific feature enhancement (MSFE) module, a modality-interactive cross-attention (MICA) module, and a modality-specific knowledge-guided representation learning (MSKR) module. The three modules collaborate by complementing modality-specific features with modality-agnostic knowledge to improve the learning capability of MSKI-Net. Furthermore, we construct a dataset named TCGA mm , which combines WSI, RNA-Seq, and CNV data from The Cancer Genome Atlas (TCGA) to address the issue of data scarcity. Extensive experiments demonstrate that MSKI-Net achieves superior performance in predicting the survival risk of glioma cancer.

关键词： Knowledge engineering Representation learning Pathology Genomics Prediction methods Data models Gene expression Bioinformatics Prognostics and health management Cancer

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：