检索结果-内蒙古大学图书馆

A novel method for the detection and classification of multiple diseases using transfer learning-based deep learning techniques with improved performance

引用

Neural Computing and Applications 2024年第30期36卷 18979-18997页

作者： Natarajan, Krishnamoorthy Muthusamy, Suresh Sha, Mizaj Shabil Sadasivuni, Kishor Kumar Sekaran, Sreejith Charles Gnanakkan, Christober Asir Rajan A.Elngar, Ahmed School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore India Tamil Nadu Perundurai Erode India Centre for Advanced Materials Qatar University Doha Qatar Department of Mechanical and Industrial Engineering Qatar University PO Box 2713 Doha Qatar Department of Electrical Engineering National Institute of Technology Assam Silchar India Department of Electrical and Electronics Engineering Puducherry Technological University Puducherry India Faculty of Computers and Artificial Intelligence Beni-Suef University Beni-Suef City62511 Egypt

A disease is a distinct abnormal state that significantly affects the functioning of all or part of an individual and is not caused by external harm. Diseases are frequently understood as medical conditions connected with distinct indications and symptoms. According to a fairly wide categorization, diseases can also be categorized as mental disorders, deficient diseases, genetic diseases, degenerative diseases, self-inflicted diseases, infectious diseases, non-infectious diseases, social diseases, and physical diseases. Prevention of the diseases is of multiple instances. Primary prevention seeks to prevent illness or harm before it ever happens. Secondary prevention tries to lessen the effect of an illness or damage that has already happened. This is done through diagnosing and treating illness or injury as soon as feasible to stop or delay its course, supporting personal ways to avoid recurrence or reinjury, and implementing programs to restore individuals to their previous health and function to prevent long-term difficulties. Tertiary prevention tries to lessen the impact of a continuing sickness or injury that has enduring repercussions. Diagnosis of the disease at an earlier stage is important for the treatment of the disease. Hence, in this study, deep learning algorithms, such as VGG16, EfficientNetB4, and ResNet, are utilized to diagnose various diseases, such as Alzheimer's, brain tumors, skin diseases, and lung diseases. Chest X-rays, MRI scans, CT scans, and skin lesions are used to diagnose the mentioned diseases. Transfer learning algorithms, such as VGG16, VGG19, ResNet, InceptionV3, and EfficientNetB4, are utilized to categorize various diseases. EfficientNetB4 with the learning rate annealing, having obtained an accuracy of 94.04% on the test dataset, is observed. As a consequence, we observed that every network has unique particular skills on the multi-disease dataset, which includes chest X-rays, MRI scans, etc., © The Author(s) 2024.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

S²RNN: Self-Supervised Reconfigurable Neural Network Hardware Accelerator for Machine Learning Applications

引用

IEEE Internet of Things Journal 2024年第6期12卷 6708-6720页

作者： Kasem Khalil Bappaditya Dey Magdy Bayoumi Electrical and Computer Engineering Department University of Mississippi Oxford MS USA Electrical Engineering Department Assiut University Asyut Egypt Angstrom Patterning Department Interuniversity Microelectronics Centre (Belgium) Leuven Belgium Center for Advanced Computer Studies University of Louisiana Lafayette LA USA Department of Electrical and Computer Engineering University of Louisiana Lafayette LA USA

Hardware implementation of neural networks (NNs) is challenging due to varying application requirements. This often necessitates creating specific field programmable gate arrays (FPGAs) configurations from scratch for each application. This article proposes a flexible, self-supervised reconfigurable method to fit several application requirements by providing only the maximum available computational nodes a priori. The proposed method dynamically reconfigures the required number of hidden layers and nodes based on the application. The goal is to automatically determine the optimal NN configuration through reconfigurability to achieve maximum accuracy. Optimality is demonstrated through minimum average power, average delay, and area overhead, as well as maximum throughput and accuracy. Experimental results show that the proposed approach significantly reduces the optimized architecture search cost (the number of online training iterations) and associated average power consumption for successive datasets/applications. The method’s effectiveness is shown both quantitatively and qualitatively, verified against the MNIST and CIFAR-10 classification problems. Our reconfigurable method demonstrates stable accuracy of 98.97% and 98.95% compared to state-of-the-art NNs with fixed configurations (98.85% and 73.0% for MNIST and 93.47% and 70.21% for CIFAR-10, respectively). Additionally, the proposed method shows a 20.9% reduction in average power dissipation compared to state-of-the-art methods. Implemented and tested using VHDL and Altera FPGA, the results indicate resource utilization comparable with the state-of-the-art method. This reconfigurability is especially advantageous for Internet of Things applications where power efficiency and adaptability to different tasks are critical.

关键词： Hardware computer architecture Neural networks Biological neural networks Artificial neural networks Internet of Things Neurons Field programmable gate arrays Accuracy Resource management

来源：评论

学校读者我要写书评

暂无评论

What Drives I4.0 Adoption? Establishing the Importance of Strategy

引用

IEEE engineering Management Review 2023年第3期51卷 33-41页

作者： Arcidiacono, Francesco Ancarani, Alessandro Di Mauro, Carmela Schupp, Florian University of Catania Department of Electrical Electronic and Computer Engineering Catania95124 Italy Schaeffler Automotive Bühl Bühl77815 Germany University of Catania Department of Civil Engineering and Architecture Catania95124 Italy Corvinus University of Budapest Corvinus Institute for Advanced Studies Budapest1093 Hungary Constructor University School of Business Social and Decision Sciences Bremen28759 Germany

This article investigates the adoption patterns of Industry 4.0 (I4.0) technologies in the automotive component sector and links I4.0 adoption to competitive strategies. Analysis of survey data concerning 288 automotive suppliers reveals that most firms currently focus on implementing real-time collection and analysis of production data (i.e., the Internet of Things, Big Data, and Artificial Intelligence), while other technologies, such as additive manufacturing and blockchain, are infrequently adopted. I4.0 adoption is associated with a simultaneous strategic emphasis on cost, quality, and delivery, thus suggesting automotive suppliers look at I4.0 as a mean to overcome performance tradeoffs. Findings also confirm that small- and medium-sized firms are less likely to adopt I4.0. Based on these results, implications for academics, managers, and policymakers are suggested. © 1973-2011 IEEE.

关键词： Supply chains

来源：评论

学校读者我要写书评

暂无评论

A Study of a (3+1)-Dimensional Hirota Bilinear Model with Variable Coefficients: Generalized Higher-Order Rogue Waves and Wronskian Solutions

引用

Qualitative Theory of Dynamical Systems 2025年第3期24卷 1-35页

作者： Madadi, Majid Inc, Mustafa Department of Mathematics Institute for Advanced Studies in Basic Sciences (IASBS) Zanjan 45137–66731 Iran Department of Mathematics Firat University Elazig 23119 Turkey Department of Mathematics Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Tamil Nadu Chennai 602105 India Department of Computer Engineering Biruni University Istanbul 34010 Turkey

The Hirota bilinear equation with variable coefficients (VCs) serves as a fundamental model for capturing nonlinear wave dynamics in fluids and oceans. Utilizing the Hirota bilinear framework alongside advanced symbolic computation techniques, higher-order rational solutions to this equation have been comprehensively investigated. These solutions unveil a wide range of waveforms, including multi-rogue waves (RWs) and multi-parallel solitons. To further expand the solution space, the rational solutions have been generalized by introducing two adjustable parameters, α and β, referred to as center control parameters. These parameters enable the generation of a versatile class of nonlinear, controllable RWs, enhancing the flexibility and applicability of the model. Soliton solutions have also been constructed using the Wronskian method, with their validity rigorously established through proofs grounded in Plücker relations. By employing various functional forms for the VCs, the dynamic properties of these solutions have been extensively analyzed and visualized through three-dimensional representations, showcasing their rich complexity and diverse behaviors. © The Author(s) 2025.

关键词： Higher-order rogue wave Hirota bilinear equation Soliton solution Symbolic computation method Wronskian solution

来源：评论

学校读者我要写书评

暂无评论

Efficient simulations of Hartree-Fock equations by an accelerated gradient descent method

引用

Physical Review E 2024年第5期110卷 055304页

作者： Y. Ohno A. Del Maestro T. I. Lakoba Department of Mathematics and Statistics Department of Physics and Astronomy Min H. Kao Department of Electrical Engineering and Computer Science Institute for Advanced Materials & Manufacturing

We develop convergence acceleration procedures that enable a gradient descent-type iteration method to efficiently simulate Hartree-Fock equations for many particles interacting both with each other and with an external potential. Our development focuses on three aspects: (i) optimization of a parameter in the preconditioning operator; (ii) adoption of a technique that eliminates the slowest-decaying mode to the case of many equations (describing many particles); and (iii) a novel extension of the above technique that allows one to eliminate multiple modes simultaneously. We illustrate performance of the numerical method for the two-dimensional model of the first layer of helium atoms above a graphene sheet. We demonstrate that incorporation of aspects (i) and (ii) above into the “plain” gradient descent method accelerates it by at least two orders of magnitude, and often by much more. Aspect (iii)—the multiple-mode elimination—may bring further improvement to the convergence rate compared to aspect (ii), the single-mode elimination. Both single- and multiple-mode elimination techniques are shown to significantly outperform the well-known Anderson Acceleration. We believe that our acceleration techniques can also be employed by other iterative methods, especially those handling hard-core-type interaction of many particles.

关键词： First-principles calculations Hartree-Fock methods Numerical techniques

来源：评论

学校读者我要写书评

暂无评论

advanced BERT and CNN-Based Computational Model for Phishing Detection in Enterprise Systems

引用

computer Modeling in engineering & Sciences 2024年第12期141卷 2165-2183页

作者： Brij B.Gupta Akshat Gaurav Varsha Arya Razaz Waheeb Attar Shavi Bansal Ahmed Alhomoud Kwok Tai Chui Department of Computer Science and Information Engineering Asia UniversityTaichung413Taiwan Symbiosis Centre for Information Technology(SCIT) Symbiosis International UniversityPune411057India Center for Interdisciplinary Research University of Petroleum and Energy Studies(UPES)Dehradun248007India University Centre for Research and Development(UCRD) Chandigarh UniversityChandigarh140413India Computer Engineering Ronin InstituteMontclairNJ 07043USA Department of Business Administration Asia UniversityTaichung413Taiwan Department of Electrical and Computer Engineering Lebanese American UniversityBeirut1102Lebanon College of Business Administration Management DepartmentPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Research and Innovation Insights2TechinfoJaipur302001India Department of Computer Sciences Faculty of Computing and Information TechnologyNorthern Border UniversityRafha91911Saudi Arabia Department of Electronic Engineering and Computer Science Hong Kong Metropolitan University(HKMU)Hong Kong518031China

Phishing attacks present a serious threat to enterprise systems,requiring advanced detection techniques to protect sensitive *** study introduces a phishing email detection framework that combines Bidirectional Encoder Representations from Transformers(BERT)for feature extraction and CNN for classification,specifically designed for enterprise information ***’s linguistic capabilities are used to extract key features from email content,which are then processed by a convolutional neural network(CNN)model optimized for phishing *** an accuracy of 97.5%,our proposed model demonstrates strong proficiency in identifying phishing *** approach represents a significant advancement in applying deep learning to cybersecurity,setting a new benchmark for email security by effectively addressing the increasing complexity of phishing attacks.

关键词： Phishing BERT convolutional neural networks email security deep learning

来源：评论

学校读者我要写书评

暂无评论

Soft,full Wheatstone bridge 3D pressure sensors for cardiovascular monitoring

引用

npj Flexible Electronics 2024年第1期8卷 910-917页

作者： Yoonseok Park Haiwen Luan Kyeongha Kwon Ted S.Chung Seyong Oh Jae-Young Yoo Gooyoon Chung Junha Kim Suhyeon Kim Sung Soo Kwak Junhwan Choi Hoang-Phuong Phan Seonggwang Yoo Hyoyoung Jeong Jaeho Shin Sang Min Won Hong-Joon Yoon Yei Hwan Jung John A.Rogers Department of Advanced Materials Engineering for Information and Electronics Integrated Education Institute for Frontier Science&Technology(BK21 Four)Kyung Hee UniversityYongin-siGyeonggi-do 17104Republic of Korea Department of Mechanical and Aerospace Engineering University of California San DiegoLa JollaCA 92093USA School of Electrical Engineering Korea Advanced Institute of Science and TechnologyDaejeonRepublic of Korea Department of Mechanical Engineering Columbia UniversityNew YorkNYUSA Division of Electrical Engineering Hanyang University ERICAAnsan 15588Republic of Korea Department of Semiconductor Convergence Engineering Sungkyunkwan UniversitySuwonRepublic of Korea Biomedical Research Division Korea Institute of Science and TechnologySeoul 02792Republic of Korea Department of Chemical Engineering Dankook UniversityYonginGyeonggi-do 16890Republic of Korea School of Mechanical and Manufacturing Engineering Tyree Institute of Health EngineeringUniversity of New South WalesSydneyNSW 2052Australia Querrey Simpson Institute for Bioelectronics Northwestern University EvanstonEvanstonIL 60208USA Department of Electrical and Computer Engineering University of California DavisDavisCA 95616USA Department of Electrical and Computer Engineering Sungkyunkwan University2066Seobu-roJangan-guSuwon-siGyeonggi-do 16419Republic of Korea Department of Electronic Engineering Gachon UniversitySeongnamsiGyeonggi-do 13120Republic of Korea Department of Electronic Engineering Hanyang UniversitySeoulRepublic of Korea Department of Materials Science and Engineering Biomedical EngineeringNeurological SurgeryChemistryMechanical EngineeringElectrical Engineering and Computer Science Simpson Querrey Institute and Feinberg Medical SchoolCenter for Bio-Integrated ElectronicsNorthwestern University EvanstonEvanstonIL 60208USA

Variations in parameters associated with the ambient environment can introduce noise in soft,body-worn *** example,many piezoresistive pressure sensors exhibit a high degree of sensitivity to fluctuations in temperature,thereby requiring active compensation *** research presented here addresses this challenge with a multilayered 3D microsystem design that integrates four piezoresistive sensors in a full-Wheatstone bridge *** optimized layout of the sensors relative to the neutral mechanical plane leads to both an insensitivity to temperature and an increased sensitivity to pressure,relative to previously reported devices that rely on similar operating *** this 3D pressure sensor into a soft,flexible electronics platform yields a system capable of real-time,wireless measurements from the surface of the *** above the radial and carotid arteries yields high-quality waveforms associated with pulsatile blood flow,with quantitative correlations to blood *** results establish the materials and engineering aspects of a technology with broad potential in remote health monitoring.

关键词： Wheat bridge thereby

来源：评论

学校读者我要写书评

暂无评论

Using NSCTS and DCNN, Rapid Prediction and Forecasting of Breast Cancer 1

Using NSCTS and DCNN, Rapid Prediction and Forecasting of Br...

引用

1st IEEE International Conference on Ambient Intelligence, Knowledge Informatics and Industrial Electronics, AIKIIE 2023

作者： Seethalakshmi, K. Bhagyalakshmi, A. Sangeetha, A. Vijitha, S. Palukuri, P. Suhas Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India R.M.K. College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Vels Institute of Science Technology & Advanced Studies Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350316469

Utilizing the CAD system, which aids radiologists in various diagnostic procedures, a recent study has been conducted on the early identification of breast cancer. Next to lung cancer, breast cancer ranks among the most deadly diseases. Initially, detection is done based on screening tests done through Magnetic resonance imaging (MRI), subsequently Infrared thermography, and digital mammography (DM). Whenever a suspicion is raised, these tests might be recommended by the specialist. Region-based segmentation is used for the test picture in this work, while NSCTS (Non-subsample Contourlet transform segmentation) is used for preprocessing. ResNet-164 DCNN architecture performs feature extraction and classification between normal and aberrant tumor pictures. The diagnosis system adopts the deep learning technology to increase its performance rate. The approach to prediction starts with screening test photos, then preprocessing to enhance the image quality, ROI detection, ROI segmentation, and classification. The resulting images are examined using a variety of evaluation measures, including performance rate, sensitivity, specificity, and accuracy. When compared to other recent work, the outcome is exceptional. The obtained accuracy, sensitivity of the proposed system is 98.58% and 98.78%. The application takes advantage of the MIAS mammography image dataset. © 2023 IEEE.

关键词： Breast cancer contourlet segmentation DCNN Digital mammograms Image preprocessing MRI ResNet

来源：评论

学校读者我要写书评

暂无评论

Cuckoo Search-Optimized Deep CNN for Enhanced Cyber Security in IoT Networks

引用

computers, Materials & Continua 2024年第12期81卷 4109-4124页

作者： Brij B.Gupta Akshat Gaurav Varsha Arya Razaz Waheeb Attar Shavi Bansal Ahmed Alhomoud Kwok Tai Chui Department of Computer Science and Information Engineering Asia UniversityTaichung413TaiwanChina Symbiosis Centre for Information Technology(SCIT) Symbiosis International UniversityPune411057MaharashtraIndia Center for Interdisciplinary Research University of Petroleum and Energy Studies(UPES)Dehradun248007India University Centre for Research and Development(UCRD) Chandigarh UniversityChandigarh140413India Computer Engineering Ronin InstituteMontclairNJ 07043USA Department of Business Administration Asia UniversityTaichung413TaiwanChina Department of Electrical and Computer Engineering Lebanese American UniversityBeirut1102Lebanon Management Department College of Business AdministrationPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Research and Innovation Insights2TechinfoJaipur302001India Department of Computer Science Faculty of ScienceNorthern Border UniversityArar91431Saudi Arabia Department of Electronic Engineering and Computer Science Hong Kong Metropolitan University(HKMU)Hong Kong518031China

Phishing attacks seriously threaten information privacy and security within the Internet of Things(IoT)*** phishing attack detection solutions have been developed for IoT;however,many of these are either not optimally efficient or lack the lightweight characteristics needed for practical *** paper proposes and optimizes a lightweight deep-learning model for phishing attack *** model employs a two-fold optimization approach:first,it utilizes the analysis of the variance(ANOVA)F-test to select the optimal features for phishing detection,and second,it applies the Cuckoo Search algorithm to tune the hyperparameters(learning rate and dropout rate)of the deep learning ***,our model is trained in only five epochs,making it more lightweight than other deep learning(DL)and machine learning(ML)*** proposed model achieved a phishing detection accuracy of 91%,with a precision of 92%for the’normal’class and 91%for the‘attack’***,the model’s recall and F1-score are 91%for both *** also compared our approach with traditional DL/ML models and past literature,demonstrating that our model is more *** study enhances the security of sensitive information and IoT devices by offering a novel and effective approach to phishing detection.

关键词： Deep learning phishing Cuckoo Search cable news network(CNN) IoT ANOVA F-test

来源：评论

学校读者我要写书评

暂无评论

advanced Anomaly Detection Framework Using CNN-Grid Autoencoder Integration and Recursive Fuzzy Feature Selection Approach

Advanced Anomaly Detection Framework Using CNN-Grid Autoenco...

引用

Human-computer Interaction, Optimization and Robotic Applications (HORA), International Congress on

作者： Reem Talal Al-Dulaimi Ayça Kurnaz Türkben Mohammed Kareem Hussein Ali Tariq Kalil Al-Khayyat Osman Nuri Ucan Department of Electrical and Computer Engineering Institute of Graduate Studies Altınbaş University Istanbul Turkey Department of Electrical and Computer Engineering Altınbaş University Istanbul Turkey

ISBN: (数字)9798331510886

ISBN: (纸本)9798331510893

Network intrusion poses a significant threat to data privacy and security in shared networks, often leading to cyber-attacks that compromise both system integrity and user data. Today's digital environment is seeing an increase in unauthorized actions, such as credential theft, illegal access, and data tampering. Despite the availability of various intrusion detection methodologies, accurately identifying and mitigating such threats remains a critical challenge. To address this issue, this paper proposes an automated attack classification model designed to enhance classification accuracy while minimizing errors based on input parameters. The proposed approach presents an innovative system for detecting network intrusions based on deep learning that integrates a fuzzy optimization method. The methodology begins with data pre-processing, including data cleansing and temporal smoothing, followed by feature extraction using Grid Convolutional Neural Networks (Grid-CNN). Optimal features are selected through a recursive multi-level fuzzy optimization algorithm. Finally, attack classification is performed using the SoftMax layer of the Grid-CNN architecture. The model is evaluated on the UNSW_NB15 dataset, with performance metrics including accuracy, precision, recall, and F1 score. Experimental results demonstrate that the proposed model achieves an accuracy of 96.02%, outperforming existing models in terms of both accuracy and robustness. This study highlights the potential of deep learning and fuzzy optimization in enhancing network intrusion

关键词： Deep learning Data privacy Accuracy Network intrusion detection Feature extraction Classification algorithms Security Convolutional neural networks Optimization Cyberattack

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：