检索结果-南通市图书馆

Enhanced Object Detection and Classification via Multi-Method Fusion

Computers, Materials & Continua 2024年第5期79卷 3315-3331页

作者： Muhammad Waqas Ahmed Nouf Abdullah Almujally Abdulwahab Alazeb Asaad Algarni Jeongmin park Department of Computer Science Air UniversityIslamabad44000Pakistan Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Science College of Computer Science and Information SystemNajran UniversityNajran55461Saudi Arabia Department of Computer Sciences Faculty of Computing and Information TechnologyNorthern Border UniversityRafha91911Saudi Arabia Department of Computer Engineering Tech University of Korea237 Sangidaehak-roSiheung-siGyeonggi-do15073South Korea

Advances in machine vision systems have revolutionized applications such as autonomous driving,robotic navigation,and augmented *** substantial progress,challenges persist,including dynamic backgrounds,occlusion,and limited labeled *** address these challenges,we introduce a comprehensive methodology toenhance image classification and object detection *** proposed approach involves the integration ofmultiple methods in a complementary *** process commences with the application of Gaussian filters tomitigate the impact of noise *** images are then processed for segmentation using Fuzzy C-Meanssegmentation in parallel with saliency mapping techniques to find the most prominent *** Binary RobustIndependent Elementary Features(BRIEF)characteristics are then extracted fromdata derived fromsaliency mapsand segmented *** precise object separation,Oriented FAST and Rotated BRIEF(ORB)algorithms *** Algorithms(GAs)are used to optimize Random Forest classifier parameters which lead toimproved *** method stands out due to its comprehensive approach,adeptly addressing challengessuch as changing backdrops,occlusion,and limited labeled data concurrently.A significant enhancement hasbeen achieved by integrating Genetic Algorithms(GAs)to precisely optimize *** minor adjustmentnot only boosts the uniqueness of our system but also amplifies its overall *** proposed methodologyhas demonstrated notable classification accuracies of 90.9%and 89.0%on the challenging Corel-1k and MSRCdatasets,***,detection accuracies of 87.2%and 86.6%have been *** ourmethod performed well in both datasets it may face difficulties in real-world data especially where datasets havehighly complex *** these limitations,GAintegration for parameter optimization shows a notablestrength in enhancing the overall adaptability and performance of our system.

关键词： BRIEF features saliency map fuzzy c-means object detection object recognition

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Enhanced prediction of anisotropic deformation behavior using machine learning with data augmentation

引用

Journal of Magnesium and Alloys 2024年第1期12卷 186-196页

作者： Sujeong Byun Jinyeong Yu Seho Cheon Seong Ho Lee Sung Hyuk park Taekyung Lee School of Mechanical Engineering Pusan National UniversityBusan 46241South Korea School of Materials Science and Engineering Kyungpook National UniversityDaegu 41566South Korea

Mg alloys possess an inherent plastic anisotropy owing to the selective activation of deformation mechanisms depending on the loading *** characteristic results in a diverse range of flow curves that vary with a deformation *** study proposes a novel approach for accurately predicting an anisotropic deformation behavior of wrought Mg alloys using machine learning(ML)with data *** developed model combines four key strategies from data science:learning the entire flow curves,generative adversarial networks(GAN),algorithm-driven hyperparameter tuning,and gated recurrent unit(GRU)*** proposed model,namely GAN-aided GRU,was extensively evaluated for various predictive scenarios,such as interpolation,extrapolation,and a limited dataset *** model exhibited significant predictability and improved generalizability for estimating the anisotropic compressive behavior of ZK60 Mg alloys under 11 annealing conditions and for three loading *** GAN-aided GRU results were superior to those of previous ML models and constitutive *** superior performance was attributed to hyperparameter optimization,GAN-based data augmentation,and the inherent predictivity of the GRU for *** a first attempt to employ ML techniques other than artificial neural networks,this study proposes a novel perspective on predicting the anisotropic deformation behaviors of wrought Mg alloys.

关键词： Plastic anisotropy Compression Annealing Machine learning Data augmentation

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

TEAM:Transformer Encoder Attention Module for Video Classification

引用

Computer Systems Science & Engineering 2024年第2期48卷 451-477页

作者： Hae Sung park Yong Suk Choi Department of Artificial Intelligence Hanyang UniversitySeoulKorea Department of Computer Science Hanyang UniversitySeoulKorea

Much like humans focus solely on object movement to understand actions,directing a deep learning model’s attention to the core contexts within videos is crucial for improving video *** the recent study,Video Masked Auto-Encoder(VideoMAE)employs a pre-training approach with a high ratio of tube masking and reconstruction,effectively mitigating spatial bias due to temporal redundancy in full video *** steers the model’s focus toward detailed temporal ***,as the VideoMAE still relies on full video frames during the action recognition stage,it may exhibit a progressive shift in attention towards spatial contexts,deteriorating its ability to capture the main spatio-temporal *** address this issue,we propose an attention-directing module named Transformer Encoder Attention Module(TEAM).This proposed module effectively directs the model’s attention to the core characteristics within each video,inherently mitigating spatial *** TEAM first figures out the core features among the overall extracted features from each *** that,it discerns the specific parts of the video where those features are located,encouraging the model to focus more on these informative ***,during the action recognition stage,the proposed TEAM effectively shifts the VideoMAE’s attention from spatial contexts towards the core spatio-temporal *** attention-shift manner alleviates the spatial bias in the model and simultaneously enhances its ability to capture precise video *** conduct extensive experiments to explore the optimal configuration that enables the TEAM to fulfill its intended design purpose and facilitates its seamless integration with the VideoMAE *** integrated model,i.e.,VideoMAE+TEAM,outperforms the existing VideoMAE by a significant margin on Something-Something-V2(71.3%vs.70.3%).Moreover,the qualitative comparisons demonstrate that the TEAM encourages the model to disregard insignificant featur

关键词： Video classification action recognition vision transformer masked auto-encoder

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Effect of characteristics and distribution of Mg_(17)Al_(12)precipitates on tensile and bending properties of high-Al-containing Mg alloys

引用

Journal of Magnesium and Alloys 2024年第2期12卷 779-793页

作者： Sumi Jo Gyo Myeong Lee Jong Un Lee Young Min Kim Sung Hyuk park School of Materials Science and Engineering Kyungpook National UniversityDaegu 41566Republic of Korea Department of Magnesium Korea Institute of Materials ScienceChangwon 51508Republic of Korea

This study investigates the effect of characteristics and distribution of Mg_(17)Al_(12)precipitates on the uniaxial tensile and three-point bending properties of extruded Mg alloys containing high Al *** extruded Mg–9Al–1Zn–0.3Mn(AZ91)alloy contains lamellar-structured Mg_(17)Al_(12)discontinuous precipitates along the grain boundaries,which are formed via static precipitation during natural air *** extruded Mg–11Al–1Zn–0.3Mn(AZ111)alloy contains spherical Mg_(17)Al_(12)precipitates at the grain boundaries and inside the grains,which are formed via dynamic precipitation during *** to inhomogeneous distribution of precipitates,the AZ111 alloy consists of two different precipitate regions:precipitate-rich region with numerous precipitates and finer grains and precipitate-scarce region with a few precipitates and coarser *** AZ111 alloy exhibits a higher tensile strength than the AZ91 alloy because its smaller grain size and more abundant precipitates result in stronger grain-boundary hardening and precipitation hardening effects,***,the tensile elongation of the AZ111 alloy is lower than that of the AZ91 alloy because the weak cohesion between the dynamic precipitates and the matrix facilitates the crack initiation and *** bending,a macrocrack initiates on the outer surface of bending specimen in both *** AZ111 alloy exhibits higher bending yield strength and lower failure bending strain than the AZ91 *** bending specimens of the AZ91 alloy have similar bending formability,whereas those of the AZ111 alloy exhibit considerable differences in bending formability and crack propagation behavior,depending on the distribution and number density of precipitates in the *** bending specimens of the AZ111 alloy,it is found that the failure bending strain(ε_(f,bending))is inversely proportional to the area fraction of precipitates in the outer zone of bending specimen(A_(ppt)),with a relation

关键词： Mg–Al alloy Extrusion Bending Precipitation Microstructure

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Evolution of nonmetallic inclusions in 80-t 9CrMoCoB large-scale ingots during electroslag remelting process

引用

International Journal of Minerals,Metallurgy and Materials 2024年第7期31卷 1525-1539页

作者： Shengchao Duan Min Joo Lee Yao Su Wangzhong Mu Dong Soo Kim Joo Hyun park School of Mechanical and Materials Engineering North China University of TechnologyBeijing 100144China Department of Materials Science and Chemical Engineering Hanyang UniversityAnsan 15588Rep.of Korea Department of Materials Science and Engineering KTH Royal Institute of TechnologyBrinellvägen 23Stockholm 10044Sweden Department of Engineering Science and Mathematics Division of Materials ScienceLuleåUniversity of Technology97187 LuleåSweden Casting&Forging Business Unit Nuclear Business GroupDoosan EnerbilityChangwon 51711Rep.of Korea

In combination with theoretical calculations,experiments were conducted to investigate the evolution behavior of nonmetallic inclusions(NMIs)during the manufacture of large-scale heat-resistant steel ingots using 9CrMoCoB heat-resistant steel and CaF_(2)–CaO–Al_(2)O_(3)–SiO_(2)–B_(2)O_(3)electroslag remelting(ESR)-type slag in an 80-t industrial ESR *** main types of NMI in the consumable electrode comprised pure alumina,a multiphase oxide consisting of an Al_(2)O_(3)core and liquid CaO–Al_(2)O_(3)–SiO_(2)–MnO shell,and M_(23)C_(6)carbides with an MnS *** Al_(2)O_(3)and MnS inclusions had higher precipitation temperatures than the M_(23)C_(6)-type carbide under equilibrium and nonequilibrium solidification ***,inclusions can act as nucleation sites for carbide layer *** ESR process completely removed the liquid CaO–Al_(2)O_(3)–SiO_(2)–MnO oxide and MnS inclusion with a carbide shell,and only the Al_(2)O_(3)inclusions and Al_(2)O_(3)core with a carbide shell occupied the remelted *** M_(23)C_(6)-type carbides in steel were determined as Cr_(23)C_(6)based on the analysis of transmission electron microscopy *** substitution of Cr with W,Fe,or/and Mo in the Cr_(23)C_(6)lattice caused slight changes in the lattice parameter of the Cr_(23)C_(6)***,Cr_(21.34)Fe_(1.66)C_(6),(Cr_(19)W_(4)C_(6),Cr_(18.4)Mo_(4.6)C_(6),and Cr_(16)Fe_(5)Mo_(2)C_(6)can match the fraction pattern of Cr_(23)C_(6)*** Al_(2)O_(3)inclusions in the remelted ingot formed due to the reduction of CaO,SiO_(2),and MnO components in the liquid *** increased Al content in liquid steel or the higher supersaturation degree of Al_(2)O_(3)precipitation in the remelted ingot than that in the electrode can be attributed to the evaporation of CaF_(2)and the increase in CaO content in the ESR-type slag.

关键词： nonmetallic inclusion heat-resistant steel electroslag remelting M_(23)C_(6) carbide MnS inclusion supersaturation degree

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Erratum to: Pyrometallurgical recycling of end -of-life lithium-ion batteries

引用

International Journal of Minerals,Metallurgy and Materials 2024年第11期31卷 2535-2535页

作者： Juheon Lee Kwang won park Il Sohn Sanghoon Lee Department of Materials Science and Engineering Yonsei UniversitySeoul 03722Korea Yonsei Industry Cooperation Center Yonsei UniversitySeoul 03722Korea RD Solution Wanju gunJeollabuk do 55365Korea

Erratum to:International Journal of Minerals,Metallurgy and Materials Volume 31,Number 7,July 2024,Page 1554 https://***/10.1007/s12613-024-2907-7 In this article,affiliation 1 has been erroneously given as Department... 详细信息

关键词： lithium recycling Number

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Anion storing,oxygen vacancy incorporated perovskite oxide composites for high-performance aqueous dual ion hybrid supercapacitors

引用

Journal of Energy Chemistry 2024年第7期94卷 646-655页

作者： Taehun Kang Puritut Nakhanivej kyung Jae Wang Yu Chen Yongchul G Chung Ho Seok park School of Chemical Engineering Sungkyunkwan University(SKKU)2066Seobu-roJangan-guSuwonGyeonggi-do 16419Republic of Korea Warwick Manufacturing Group(WMG) University of WarwickCoventry CV47ALUnited Kingdom School of Chemical Engineering Pusan National UniversityGeumjeong-guBusanGyeongsangnam-do 46241Republic of Korea SKKU Institute of Energy Science and Technology(SIEST) Sungkyunkwan University2066SeoburoJangan-guSuwon 440-746Republic of Korea SKKU Advanced Institute of Nano Technology(SAINT) Sungkyunkwan University2066SeoburoJangan-guSuwon 440-746Republic of Korea Department of Health Sciences and Technology Samsung Advanced Institute for Health Sciences and Technology(SAIHST)Sungkyunkwan UniversitySuwon 16419Republic of Korea

Dual ion storage hybrid supercapacitors(HsCs)are considered as a promising device to overcome the limited energy density of existing supercapacitors while preserving high power and long ***,the development of high-capacity anion-storing materials,which can be paired with fast charg-ing capacitive electrodes,lags behind cation-storing ***,we demonstrate the surface faradaic OH-storage mechanism of anion storing perovskite oxide composites and their application in high-performance dual ion *** oxygen vacancy and nanoparticle size of the reduced LaMnO_(3)(r-LaMnO_(3))were controlled,while r-LaMnO_(3) was chemically coupled with ozonated carbon nanotubes(oCNTs)for the improved anion storing capacity and cycle *** taken by in-situ and ex-situ spectroscopic and computational analyses,OH-ions are inserted into the oxygen vacancies coordi-nating with octahedral Mn with the increase in the oxidation state of Mn during the charging process or vice *** OH-storing r-LaMnO_(3)/oCNT composite with Na*storing MXene,the as-fabricated aqueous dual ion HSCs achieved the cycle performance of 73.3%over 10,000 cycles,delivering the max-imum energy and power densities of 47.5 w h kg^(-1) and 8 kw kg^(-1),respectively,far exceeding those of previously reported aqueous anion and dual ion storage *** research establishes a foundation for the unique anion storage mechanism of the defect engineered perovskite oxides and the advancement of dual ion hybrid energy storage devices with high energy and power densities.

关键词： Anion storage Dual ion storage Defect engineered perovskites Hybrid supercapacitors Nanocomposites

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Efficient Object Segmentation and Recognition Using Multi-Layer Perceptron Networks

引用

Computers, Materials & Continua 2024年第1期78卷 1381-1398页

作者： Aysha Naseer Nouf Abdullah Almujally Saud S.Alotaibi Abdulwahab Alazeb Jeongmin park Department of Computer Science Air UniversityIslamabad44000Pakistan Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Information System Department Umm Al-Qura UniversityMakkahSaudi Arabia Department of Computer Science College of Computer Science and Information SystemNajran UniversityNajran55461Saudi Arabia Department of Computer Engineering Tech University of KoreaGyeonggi-do15073South Korea

Object segmentation and recognition is an imperative area of computer vision andmachine learning that identifies and separates individual objects within an image or video and determines classes or categories based on their *** proposed system presents a distinctive approach to object segmentation and recognition using Artificial Neural Networks(ANNs).The system takes RGB images as input and uses a k-means clustering-based segmentation technique to fragment the intended parts of the images into different regions and label thembased on their ***,two distinct kinds of features are obtained from the segmented images to help identify the objects of *** Artificial Neural Network(ANN)is then used to recognize the objects based on their *** were carried out with three standard datasets,MSRC,MS COCO,and Caltech 101 which are extensively used in object recognition research,to measure the productivity of the suggested *** findings from the experiment support the suggested system’s validity,as it achieved class recognition accuracies of 89%,83%,and 90.30% on the MSRC,MS COCO,and Caltech 101 datasets,respectively.

关键词： K-region fusion segmentation recognition feature extraction artificial neural network computer vision

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Biochar-based materials as remediation strategy in petroleum hydrocarbon-contaminated soil and water:Performances,mechanisms,and environmental impact

引用

Journal of Environmental Sciences 2024年第4期138卷 350-372页

作者： Zhuo Wei YiWei Yang Liu Shuai Niu Yaxi Xu Jong-Hwan park Jim J.Wang Faculty of Environmental Science&Engineering Kunming University of Science&TechnologyKunming 650500China School of Plant Environment&Soil SciencesLouisiana State University AgCenter.Baton RougeLA 70803USA Department of Life Resources Industry Dong-A University37Nakdong-daero 550 beon-gilSaha-guBusan 49315South Korea

Petroleum contamination is considered as a major risk to the health of humans and *** as low-cost and eco-friendly carbon materials,have been widely used for the removal of petroleum hydrocarbon in the *** purpose of this paper is to review the performance,mechanisms,and potential environmental toxicity of biochar,modified biochar and its integration use with other materials in petroleum contaminated soil and ***,the use of biochar in oil-contaminated water and soil as well as the factors that could influence the removal ability of biochar were systematically *** addition,the modification and integrated use of biochar for improving the removal efficiency were summarized from the aspects of sorption,biodegradation,chemical degradation,and ***,the functional impacts and associated ecotoxicity of pristine and modified biochars in various environments were ***,some shortcoming of current approaches,and future research needs were provided for the future direction and challenges of modified biochar ***,this paper gain insight into biochar application in petroleum remediation from the perspectives of performance enhancement and environmental sustainability.

关键词： Petroleum contamination Adsorbent Bioremediation Biochar modification Ecotoxicity

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Road Traffic Monitoring from Aerial Images Using Template Matching and Invariant Features

引用

Computers, Materials & Continua 2024年第3期78卷 3683-3701页

作者： Asifa Mehmood Qureshi Naif Al Mudawi Mohammed Alonazi Samia Allaoua Chelloug Jeongmin park Department of Creative Technologies Air UniversityIslamabad46000Pakistan Department of Computer Science College of Computer Science and Information SystemNajran UniversityNajran55461Saudi Arabia Department of Information Systems College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAl-Kharj16273Saudi Arabia Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Engineering Tech University of KoreaGyeonggi-do15073South Korea

Road traffic monitoring is an imperative topic widely discussed among *** used to monitor traffic frequently rely on cameras mounted on bridges or ***,aerial images provide the flexibility to use mobile platforms to detect the location and motion of the vehicle over a larger *** this end,different models have shown the ability to recognize and track ***,these methods are not mature enough to produce accurate results in complex road ***,this paper presents an algorithm that combines state-of-the-art techniques for identifying and tracking vehicles in conjunction with image *** extracted frames were converted to grayscale,followed by the application of a georeferencing algorithm to embed coordinate information into the *** masking technique eliminated irrelevant data and reduced the computational cost of the overall monitoring ***,Sobel edge detection combined with Canny edge detection and Hough line transform has been applied for noise *** preprocessing,the blob detection algorithm helped detect the *** of varying sizes have been detected by implementing a dynamic thresholding *** was done on the first image of every ***,to track vehicles,the model of each vehicle was made to find its matches in the succeeding images using the template matching *** further improve the tracking accuracy by incorporating motion information,Scale Invariant Feature Transform(SIFT)features have been used to find the best possible match among multiple *** accuracy rate of 87%for detection and 80%accuracy for tracking in the A1 Motorway Netherland dataset has been *** the Vehicle Aerial Imaging from Drone(VAID)dataset,an accuracy rate of 86%for detection and 78%accuracy for tracking has been achieved.

关键词： Unmanned Aerial Vehicles(UAV) aerial images dataset object detection object tracking data elimination template matching blob detection SIFT VAID

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：