检索结果-内蒙古大学图书馆

Surface Defects Detection of Cylindrical High-Precision Industrial Parts Based on Deep Learning Algorithms: A Review

引用

Operations Research Forum 2024年第3期5卷 58页

作者： Wei, Li Solihin, Mahmud Iwan Saruchi, Sarah ‘Atifah Astuti, Winda Hong, Lim Wei Kit, Ang Chun School of Computer Science and Technology (School of Software) Guangxi University of Science and Technology Guangxi 545006 China Faculty of Engineering Technology and Built Environment UCSI University Kuala Lumpur 56000 Malaysia Faculty of Manufacturing and Mechatronics Engineering Technology Universiti Malaysia Pahang Al-Sultan Abdullah Pahang Pekan 26600 Malaysia Computer Engineering Department Automotive and Robotics Engineering Program BINUS ASO School of Engineering Bina Nusantara University Jakarta Indonesia

High-precision cylindrical parts are critical components across various industries including aerospace, automotive, and manufacturing. Since these parts play a pivotal role in the performance and safety of the systems they are integrated into, they are often subject to stringent quality control measures. Defects on the interior and exterior wall surfaces of these cylindrical parts can severely undermine their function, leading to degraded performance, increased wear, and even catastrophic failures in extreme cases. This article aims to comprehensively summarize the task definition, challenges, mainstream methods, public datasets, evaluation metrics, and other aspects of surface defect detection for high-precision cylindrical parts, in order to help researchers quickly grasp this field. Specifically, the background and characteristics of industrial defect detection are first introduced. Owing to the unique geometric features of cylindrical part surfaces, algorithms and equipment for image data acquisition used in surface defect detection are elaborated in detail. This article presents an extensive overview of state-of-the-art surface defect detection techniques designed for high-precision cylindrical components, all rooted in deep learning. The methods are systematically classified into three main categories: fully supervised, unsupervised, and alternative approaches, based on their data labeling strategies. Additionally, the paper conducts a comprehensive analysis within each category, shedding light on their unique strengths, limitations, and practical use cases. Concluding the discussion, the paper provides insights into future development trends and potential research directions in this field that will lead to manufacturing innovation. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Anomaly detection computer vision Deep learning Defect detection High-precision cylindrical parts Image processing Optical illumination

来源：评论

学校读者我要写书评

暂无评论

Vibrating Particles System Algorithm for Solving Classification Problems

引用

computer Systems science & engineering 2022年第12期43卷 1189-1206页

作者： Mohammad Wedyan Omar Elshaweesh Enas Ramadan Ryan Alturki Department of Autonomous Systems Faculty of Artificial IntelligenceAl-Balqa Applied UniversityAl-Salt19117Jordan Department of Software Engineering Information Technology CollegeAL-Hussein bin Talal UniversityMa’an71111Jordan Department of Computer Science Prince Abdullah Bin Ghazi Faculty of Communication and Information TechnologyAl-Balqa Applied UniversityAl-Salt19117Jordan Department of Information Science College of Computer and Information SystemsUmm Al-Qura UniversityMakkah21961Saudi Arabia

Big data is a term that refers to a set of data that,due to its largeness or complexity,cannot be stored or processed with one of the usual tools or applications for data management,and it has become a prominent word in recent years for the massive development of *** immediately thereafter,the term“big data mining”emerged,i.e.,mining from big data even as an emerging and interconnected field of *** is an important stage in data mining since it helps people make better decisions in a variety of situations,including scientific endeavors,biomedical research,and industrial *** probabilistic neural network(PNN)is a commonly used and successful method for handling classification and pattern recognition *** this study,the authors proposed to combine the probabilistic neural network(PPN),which is one of the data mining techniques,with the vibrating particles system(VPS),which is one of the metaheuristic algorithms named“VPS-PNN”,to solve classi-fication problems more *** data set is eleven common benchmark medical datasets from the machine-learning library,the suggested method was *** suggested VPS-PNN mechanism outperforms the PNN,biogeography-based optimization,enhanced-water cycle algorithm(E-WCA)and the firefly algorithm(FA)in terms of convergence speed and classification accuracy.

关键词： Vibrating particles system(VPS) probabilistic neural network(PNN) classification problem data mining

来源：评论

学校读者我要写书评

暂无评论

A-REA: Relation-Aware Graph Convolutional Network Entity Alignment Via a Differential Adjacency Matrix

A-REA: Relation-Aware Graph Convolutional Network Entity Ali...

引用

2023 Asia-Pacific Conference on Image Processing, Electronics and computers, IPEC 2023

作者： Dang, Yuemei Qiu, Chen Gao, Feng Gu, Jinguang Zhang, Lihua Arman, Ghazaleh School of Computer Science and Technology Wuhan University of Science and Technology Hubei Wuhan China Software College East China Jiaotong University Jiangxi Nanchang China Urmia University of Technology Faculty of Information Technology and Computer Engineering Urmia Iran

ISBN: (纸本)9781665457033

Entity Alignment is the task of seeking entities with the same semantics from distinct knowledge graphs (KGs). Researchers have recently proposed Graph Convolutional Network (GCN) based approaches to achieve this task. Most existing GCN-based methods embed all the relations into an identical value, making the underlying loss on the diversity of the relationship. Relation semantics of entities and relation structure have benefitted the entity alignment task in the monolingual scenarios. This paper proposes a Relation-Aware Graph Convolutional Network with a Differential Adjacency Matrix (A-REA), which exploits the relation-specific semantics and structural information of entities in the KGs to promote the entity representations. The experiments on DBP-15K and DWY-100K datasets, including three cross-lingual subsets and two cross-knowledge graph sub-datasets, reveal that our approach leads to advance in entity alignment task in both the cross-lingual and cross-knowledge KGs. Discriminating the relation shows the effective signal for entity alignment, especially for the schema heterogeneity of different KGs. © 2023 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Facial Recognition Utilizing the CLM Model and Supervised Machine Learning: A Comparative Analysis 25

Facial Recognition Utilizing the CLM Model and Supervised Ma...

引用

25th International Arab Conference on information technology, ACIT 2024

作者： Iqtait, Musab Ababneh, Jafar Abu-Jassar, Amer Al-Refai, Mohammad Dmour, Mohammad Arabiat, Mohammad Binsaddig, Ruaa Zarqa University Faculty of Information Technology Department of Artificial Intelligence Zarqa Jordan Zarqa University Faculty of Information Technology Cyber Security Department Zarqa Jordan Amman Arab University University College of of Computer Sciences and Information Amman Jordan Zarqa University Faculty of Information Technology Software Engineering Department Zarqa Jordan University of Business and Technology College of Business Administration Department of Finance Jeddah21432 Saudi Arabia

ISBN: (纸本)9798331540012

Facial recognition is a common challenge in artificial intelligence. We extensively utilized this program in our daily life. Face recognition software was implemented on many phones to protect user identities and promptly recognize Facebook users in photographs. Despite the numerous methodologies proposed to date, the actual implementation of facial recognition continues to pose significant challenges. Distinguishing individuals by a fundamental method relies on various factors, including lighting, postural differences, and partial facial obstruction. This study aims to develop a facial recognition technique utilizing a constrained local model (CLM) and a machine learning algorithm. It is evaluated with KNN, SVR, and CCA. Furthermore, it has employed CLM and CCA to achieve a maximum recognition accuracy of 3.98 MAE. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approach for Analysis and Characterization of COVID-19

引用

computers, Materials & Continua 2022年第1期70卷 451-468页

作者： Indrajeet Kumar Sultan S.Alshamrani Abhishek Kumar Jyoti Rawat Kamred Udham Singh Mamoon Rashid Ahmed Saeed AlGhamdi School of Computing Graphic Era Hill UniversityDehradun(UK)India Department of Information Technology College of Computer and Information TechnologyTaif UniversityTaif21944Saudi Arabia School of Computer Science&IT JAIN(to be Deemed University)BangaloreIndia School of Computing Dehradun Institute of TechnologyUttarakhandIndia Department of Computer Engineering Faculty of Science and TechnologyVishwakarma UniversityPuneIndia Department of Computer Engineering College of Computer and Information TechnologyTaif UniversityTaif21944Saudi Arabia

Early diagnosis of a pandemic disease like COVID-19 can help deal with a dire situation and help radiologists and other experts manage human resources more *** a recent pandemic,laboratories perform diagnostics manually,which requires a lot of time and expertise of the laboratorial technicians to yield accurate ***,the cost of kits is high,and well-equipped labs are needed to perform this ***,other means of diagnosis is highly *** is one of the existing methods that finds its use in the diagnosis of *** radiography observes change in Computed Tomography(CT)chest images of patients,developing a deep learning-based method to extract graphical features which are used for automated diagnosis of the disease ahead of laboratory-based *** proposed work suggests an Artificial Intelligence(AI)based technique for rapid diagnosis of COVID-19 from given volumetric chest CT images of patients by extracting its visual features and then using these features in the deep learning *** proposed convolutional neural network aims to classify the infectious and non-infectious SARS-COV2 *** proposed network utilizes 746 chests scanned CT images of 349 images belonging to COVID-19 positive cases,while 397 belong to negative cases of *** experiment resulted in an accuracy of 98.4%,sensitivity of 98.5%,specificity of 98.3%,precision of 97.1%,and F1-score of 97.8%.The additional parameters of classification error,mean absolute error(MAE),root-mean-square error(RMSE),and Matthew’s correlation coefficient(MCC)are used to evaluate our proposed *** obtained result shows the outstanding performance for the classification of infectious and non-infectious for COVID-19 cases.

关键词： Coronavirus covid-19 respiratory infection computed tomography deep neural network

来源：评论

学校读者我要写书评

暂无评论

AKQ: A Hybrid Quantum-Classical Image Encryption System

AKQ: A Hybrid Quantum-Classical Image Encryption System

引用

2023 RIVF International Conference on Computing and Communication Technologies, RIVF 2023

作者： Nguyen, Tran Khanh Thi Thanh Truc, Nguyen Hai, Vu Tuan University of Information Technology VNU-HCM Ho Faculty of Computer Science Chi Minh city Viet Nam University of Information Technology VNU-HCM Ho Faculty of Software Engineering Chi Minh city Viet Nam

ISBN: (纸本)9798350315844

Image encryption is an essential field between computer vision and security which aims to protect the image before future attacks. Nowadays, it is threatened by quantum computers, which can break some classical cryptography. The encryption system has been upgraded from quantum key exchange protocol to post-quantum key-establishment mechanisms, but they are not explicitly designed for the image encryption task. In this paper, we propose a hybrid quantum-classical theoretical framework and its instance AKQ system which is more secure and suitable in the post-quantum era. © 2023 IEEE.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

An Efficient Distributed Framework for Secured Multimedia Content using Cloud Storage 2

An Efficient Distributed Framework for Secured Multimedia Co...

引用

2nd International Conference on computer Technologies, ICCTech 2023

作者： Faniband, Yunus Parvej Ishak, Iskandar Sidi, Fatimah Jabar, Marzanah A. Yap, Deloria Shaniska Razin C.H. Center for Communication & IT Research Research Institute King Fahd University of Petroleum & Minerals Dhahran31261 Saudi Arabia Department of Computer Science Faculty of Computer Science and Information Technology Universiti Putra Malaysia UPM Serdang Selangor 43400 Malaysia Department of Software Engineering Faculty of Computer Science and Information Technology Universiti Putra Malaysia UPM Serdang Selangor 43400 Malaysia

ISBN: (纸本)9781665455824

Applications that support multimedia data such as medical pictures and videos, video broadcasting, and secure video conferencing consume vast quantities of information that require large numbers of servers to provide services for the many client users who access them. Cloud-based sensitive data becomes increasingly important for the respective users to be kept confidential without infringing confidentiality, integrity, and availability. We propose a framework based on the OpenStack cloud-computing platform for multimedia data security. A prototype framework with a helper tool EncSwift is implemented, which allows stringent data access control and applying the data-at-rest Over-Encryption approach. The implementation is evaluated for computation of cryptography operations, cost of communications, and update policy consequences for the framework. With OpenStack Swift’s open source and modular design, our multimedia data management and management framework is well suited to protecting and managing clouds’ multimedia with low computational costs as shown in the experimental results. © 2023 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Improving Multiple Sclerosis Disease Prediction Using Hybrid Deep Learning Model

引用

computers, Materials & Continua 2024年第10期81卷 643-661页

作者： Stephen Ojo Moez Krichen Meznah A.Alamro Alaeddine Mihoub Gabriel Avelino Sampedro Jaroslava Kniezova Department of Electrical and Computer Engineering College of EngineeringAnderson UniversityAndersonSC 29621USA Faculty of Computing and Information Al-Baha UniversityAl-Baha65528Saudi Arabia ReDCAD Laboratory University of SfaxSfax3038Tunisia Department of Information Technology College of Computer&Information SciencePrincess Nourah Bint Abdul Rahman UniversityRiyadh11564Saudi Arabia Department of Management Information Systems College of Business and EconomicsQassim UniversityP.O.Box 6640Buraidah51452Saudi Arabia School of Management and Information Technology De La Salle-College of Saint BenildeManila1004Philippines Department of Information Management and Business Systems Faculty of ManagementComenius University BratislavaBratislava 2582005Slovakia

Myelin damage and a wide range of symptoms are caused by the immune system targeting the central nervous system in Multiple Sclerosis(MS),a chronic autoimmune neurological *** disrupts signals between the brain and body,causing symptoms including tiredness,muscle weakness,and difficulty with memory and *** methods for detecting MS are less precise and time-consuming,which is a major gap in addressing this *** gap has motivated the investigation of new methods to improve MS detection consistency and *** paper proposed a novel approach named FAD consisting of Deep Neural Network(DNN)fused with an Artificial Neural Network(ANN)to detect MS with more efficiency and accuracy,utilizing regularization and combat *** use gene expression data for MS research in the GEO GSE17048 *** dataset is preprocessed by performing encoding,standardization using min-max-scaler,and feature selection using Recursive Feature Elimination with Cross-Validation(RFECV)to optimize and refine the ***,for experimenting with the dataset,another deep-learning hybrid model is integrated with different ML models,including Random Forest(RF),Gradient Boosting(GB),XGBoost(XGB),K-Nearest Neighbors(KNN)and Decision Tree(DT).Results reveal that FAD performed exceptionally well on the dataset,which was evident with an accuracy of 96.55%and an F1-score of 96.71%.The use of the proposed FAD approach helps in achieving remarkable results with better accuracy than previous studies.

关键词： Multi Sclerosis(MS) machine learning deep learning artificial neural network healthcare

来源：评论

学校读者我要写书评

暂无评论

PolyLite: A Lightweight Transformer With Multi-Scale Attention for Colorectal Polyp Segmentation 15

PolyLite: A Lightweight Transformer With Multi-Scale Attenti...

引用

15th International Conference on software, Knowledge, information Management and Applications, SKIMA 2023

作者： Elkarazle, Khaled Raman, Valliappan Chua, Caslon Then, Patrick Faculty of Engineering Sarawak Malaysia Coimbatore Institute of Technology Department of Artificial Intelligence and Data Science Tamil Nadu India University of Technology Department of Computer Science and Software Engineering Swinburne Melbourne Australia

ISBN: (纸本)9798350316551

The urgent need for early detection and intervention in colorectal cancer highlights the importance of automating colorectal polyp detection. Despite the use of deep learning techniques for polyp detection from medical images, these methods often struggle with issues such as skewed data distribution and class imbalances. In this study, we introduce PolyLite, a lightweight transformer-based model designed to balance performance and efficiency. PolyLite features a custom SegFormer encoder that takes advantage of its lightweight design, and a decoder that uses a multi-scale attention network (MA-NET) to achieve an optimal balance between accuracy and efficiency. To improve accuracy and reduce false negatives, we incorporate a reverse attention layer that effectively counteracts input mask attention during training. This refocuses the model's efforts to better learn non-polyp regions. PolyLite undergoes a two-stage training process, beginning with pre-training on the ImageNet dataset and then fine-tuning on the Kvasir-SEG dataset. We conduct rigorous evaluations on three complex datasets: CVC-ClinicDB, CVC-ColonDB, and ETIS-LaribPolypDB. Empirical results demonstrate PolyLite's superiority over existing techniques, as evidenced by its performance in terms of Intersection over Union and Dice scores. This validates its effectiveness and scalability in polyp segmentation, making complex and computationally intensive architectures unnecessary. © 2023 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Efficient Power Control for UAV Based on Trajectory and Game Theory

引用

computers, Materials & Continua 2023年第3期74卷 5589-5606页

作者： Fadhil Mukhlif Ashraf Osman Ibrahim Norafida Ithnin Roobaea Alroobaea Majed Alsafyani Information Assurance and Security Research Group(IASRG) School of ComputingFaculty of EngineeringUniversiti Teknologi MalaysiaJohorMalaysia Faculty of Computing and Informatics University Malaysia SabahKota KinabaluMalaysia Department of Computer Science College of Computers and Information TechnologyTaif UniversityTaifSaudi Arabia

Due to the fact that network space is becoming more limited,the implementation of ultra-dense networks(UDNs)has the potential to enhance not only network coverage but also network *** Aerial Vehicle(UAV)communications have recently garnered a lot of attention due to the fact that they are extremely versatile and may be applied to a wide variety of contexts and purposes.A cognitive UAV is proposed as a solution for the Internet of Things ground terminal’s wireless nodes in this *** the IoT system,the UAV is utilised not only to determine how the resources should be distributed but also to provide power to the wireless *** quality of service(QoS)offered by the cognitive node was interpreted as a price-based utility function,which was demonstrated in the form of a non-cooperative game theory in order to maximise customers’net utility *** energyefficient non-cooperative game theory power allocation with pricing strategy abbreviated as(EE-NGPAP)is implemented in this study with two trajectories Spiral and Sigmoidal in order to facilitate effective power management in Internet of Things(IoT)wireless *** has also been demonstrated,theoretically and by the use of simulations,that the Nash equilibrium does exist and that it is one of a *** proposed energy harvesting approach was shown,through simulations,to significantly reduce the typical amount of power thatwas *** is taken into consideration to agree with the objective of 5G *** order to converge to Nash Equilibrium(NE),the method that is advised only needs roughly 4 iterations,which makes it easier to utilise in the real world,where things aren’t always the same.

关键词： UAV spiral&sigmoid trajectory drones IoT game theory energy efficiency 6G

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：