检索结果-内蒙古大学图书馆

4th Asia-Pacific Artificial Intelligence and Big Data Forum, AIBDF 2024

作者： Zhu, Jiale Zhang, Bo Zhong, Ying Feng, Dantong Hu, Hengdi Dan, Yuying Research Institute of Applied Technology for Specialized Robot Chengdu Technological University Sichuan Chengdu China Chengdu Technological University Sichuan Chengdu China Chongqing Jiaotong University Chongqing China

ISBN: (纸本)9798400710865

Paint quality is one of the important standards for measuring the overall quality of the product. Paint defects affect the appearance of the product, which will also expose the product to security risks, such as metal parts exposure corrosion, surface damage, and so on. Traditional paint detection methods mainly rely on manual visual inspection, which has low detection efficiency, low accuracy, and high influence by human factors. This project combines machine vision and deep learning technology and builds a paint defect data set covering eight classes of paint surface defects to train a paint surface deficiency detection model. By constructing the dataset with different backgrounds and optimizing the image processing algorithm before training, the model of multi-target and high-precision automatic identification and classification of paint defects in complex scenes was realized. On the test data set, eight classes of paint defects were detected with 93% accuracy. © 2024 Copyright held by the owner/author(s).

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Scene image recognition with knowledge transfer for drone navigation

引用

Journal of Systems Engineering and Electronics 2023年第5期34卷 1309-1318页

作者： DU Hao WANG Wei WANG Xuerao ZUO Jingqiu WANG Yuanda School of Automation Southeast UniversityNanjing 210096China Autonomous Control Robot Laboratory Jiangsu Zhongke Institute of Applied Research on Intelligent Science and TechnologyChangzhou 213164China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology Nanjing University of Information Science and TechnologyNanjing 210044China

In this paper,we study scene image recognition with knowledge transfer for drone *** divide navigation scenes into three macro-classes,namely outdoor special scenes(OSSs),the space from indoors to outdoors or from outdoors to indoors transitional scenes(TSs),and ***,there are difficulties in how to recognize the TSs,to this end,we employ deep convolutional neural network(CNN)based on knowledge transfer,techniques for image augmentation,and fine tuning to solve the ***,there is still a novelty detection prob-lem in the classifier,and we use global navigation satellite sys-tems(GNSS)to solve it in the prediction *** results show our method,with a pre-trained model and fine tun-ing,can achieve 91.3196%top-1 accuracy on Scenes21 dataset,paving the way for drones to learn to understand the scenes around them autonomously.

关键词： scene recognition convolutional neural network knowledge transfer global navigation satellite systems(GNSS)-aided

来源：评论

学校读者我要写书评

暂无评论

Autonomous landing scene recognition based on transfer learning for drones

引用

Journal of Systems Engineering and Electronics 2023年第1期34卷 28-35页

作者： DU Hao WANG Wei WANG Xuerao WANG Yuanda School of Automation Southeast UniversityNanjing 210096China Autonomous Control Robot Laboratory Jiangsu Zhongke Institute of Applied Research on Intelligent Science and TechnologyChangzhou 213164China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology Nanjing University of Information Science and TechnologyNanjing 210044China

In this paper, we study autonomous landing scene recognition with knowledge transfer for drones. Considering the difficulties in aerial remote sensing, especially that some scenes are extremely similar, or the same scene has different representations in different altitudes, we employ a deep convolutional neural network(CNN) based on knowledge transfer and fine-tuning to solve the problem. Then, LandingScenes-7 dataset is established and divided into seven classes. Moreover, there is still a novelty detection problem in the classifier, and we address this by excluding other landing scenes using the approach of thresholding in the prediction stage. We employ the transfer learning method based on ResNeXt-50 backbone with the adaptive momentum(ADAM) optimization algorithm. We also compare ResNet-50 backbone and the momentum stochastic gradient descent(SGD) optimizer. Experiment results show that ResNeXt-50 based on the ADAM optimization algorithm has better performance. With a pre-trained model and fine-tuning, it can achieve 97.845 0% top-1 accuracy on the LandingScenes-7dataset, paving the way for drones to autonomously learn landing scenes.

关键词： landing scene recognition convolutional neural network(CNN) transfer learning remote sensing image

来源：评论

学校读者我要写书评

暂无评论

Wide-field resolution uniformity for solar ground-layer adaptive optics

引用

Optics and Lasers in Engineering 2025年 193卷

作者： Yang, Ying Zhang, Lanqiang Yan, Nanfei Tong, Dingkang Ran, Xian Zhong, Libo Rao, Changhui National Laboratory on Adaptive Optics Shuangliu Sichuan Chengdu610209 China Research Institute of Applied Technology for Specialized Robot School of Electronic Engineering Chengdu Technological University Pidu Sichuan Chengdu611730 China Institute of Optics and Electronics Chinese Academy of Sciences Shuangliu Sichuan Chengdu610209 China University of Chinese Academy of Sciences Yanqi Lake Beijing100049 China School of Electronic Electrical and Communication Engineering of the University of Chinese Academy of Sciences Yanqi Lake Beijing100049 China

Ground-layer adaptive optics (GLAO) has significant potential for solar observations of ground-based telescopes due to its ability to provide wide field-of-view (FOV) correction. Ground-based telescopes always pursue high spatial resolution to improve observational quality, which is typically evaluated by the full width at half maximum of the point spread function. However, GLAO system also requires uniform spatial compensation across a wide FOV, particularly for accurate solar magnetic field topology and speckle imaging techniques. Multiple guide stars (GS) are used to detect ground-layer turbulence, and their layout greatly influences observational quality. To this end, in this paper, we optimize the GS layout to improve spatial resolution uniformity for wide-field GLAO. Specifically, we propose a novel wide-field resolution uniformity metric to evaluate the observational quality in GLAO system. Based on this innovative metric, simulations identify two effective GS configurations: the center + ring GS layout achieves higher resolution, and the single ring GS layout exhibits more uniform correction across a wide FOV (improving 41.4% resolution uniformity by trading 2.2% average resolution). To validate this result, we conduct the indoor experiment and on-sky observation. An indoor solar GLAO platform is designed and constructed. Experiments show good agreement with our simulation results. Our on-sky observation is conducted on the 1-m New Vacuum Solar Telescope. GSs in a ring layout improve uniformity by 18.70%, although this comes with a 16.25% reduction in the generalized Fried parameter compared with the center + ring GS layout. © 2025

关键词： Adaptive optics

来源：评论

学校读者我要写书评

暂无评论

Wide-Field Resolution Uniformity for Solar Ground-Layer Adaptive Optics

SSRN

引用

SSRN 2025年

作者： Yang, Ying Zhang, Lanqiang Yan, Nanfei Tong, Dingkang Ran, Xian Zhong, Libo Rao, Changhui National Laboratory on Adaptive Optics Shuangliu Sichuan Chengdu610209 China Research institute of applied technology for specialized robot School of Electronic Engineering Chengdu Technological University Pidu Sichuan Chengdu611730 China Institute of Optics and Electronics Chinese Academy of Sciences Shuangliu Sichuan Chengdu610209 China University of Chinese Academy of Sciences Yanqi Lake Beijing100049 China School of Electronic Electrical and Communication Engineering the University of Chinese Academy of Sciences Yanqi Lake Beijing100049 China

Ground-layer adaptive optics (GLAO) has significant potential for solar observations of ground based telescopes due to its ability to provide wide field-of-view (FOV) correction. Ground-based telescopes always pursue high spatial resolution to improve observational quality, which is typi cally evaluated by the full width at half maximum of the point spread function. However, GLAO system also requires uniform spatial compensation across a wide FOV, particularly for accurate solar magnetic field topology and speckle imaging techniques. Multiple guide stars (GS) are used to detect ground-layer turbulence and their layout greatly influences observational quality. To this end, in this paper, we optimize the GS layout to improve spatial resolution uniformity for wide-field GLAO. Specifically, we propose a novel wide-field resolution uniformity metric to evaluate the observational quality in GLAO system. Based on this innovate metric, simulations identify two effective GS configurations: the center + ring GS layout achieves higher resolution, and the single ring GS layout exhibits more uniform correction across a wide FOV (improving 41.4% resolution uniformity by trading 2.2% average resolution). To validate this result, we conduct the indoor experiment and on-sky observation. An indoor solar GLAO platform is designed and constructed. Experiments show good agreement with our simulation results. Our on-sky observation is conducted on the 1-m New Vacuum Solar Telescope. GSs in a ring layout improve uniformity by 18.70%, although this comes with 16.25% reduction in the generalized Fried parameter compared with the center + ring GS layout. © 2025, The Authors. All rights reserved.

关键词： Adaptive optics

来源：评论

学校读者我要写书评

暂无评论

Capturing Contact Surfaces by a Frustrated Total Internal Reflection System Using a Curved Plate for Comparison of the Beginning of Touching Motions by Humanitude Experts and Novices

Capturing Contact Surfaces by a Frustrated Total Internal Re...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Yuguchi, Akishige Toyoda, Mayuki Cho, Sung-Gwi Nakazawa, Atsushi Takamatsu, Jun Yoshino, Koichiro Ogasawara, Tsukasa Tokyo University of Science Faculty of Advanced Engineering Katsushika-ku Tokyo125-8585 Japan Guardian Robot Project Riken Seika-cho Sorakugun Kyoto619-0288 Japan Nara Institute of Science and Technology Nara Ikoma630-0192 Japan School of Science and Engineering Tokyo Denki University Hatoyama-machi Saitama Hiki-gun350-0394 Japan Graduate School of Interdisciplinary Science and Engineering in Health Systems Okayama University Okayama Kita-ku700-8530 Japan Applied Robotics Research Microsoft Corporation RedmondWA98052 United States

ISBN: (纸本)9781665410205

Analyzing time-series changes of the contact surface by touching is important to elucidate the touching skills of Humanitude as one of the pervasive multimodal comprehensive care methodologies. For the analysis, there is a frustrated total internal reflection (FTIR) method to capture contact surfaces on a transparent flat plate by a camera. However, this conventional flat plate is far from the actual surfaces of care receivers because the surfaces of humans consist of curved shapes. In this paper, we propose an FTIR sensing system using a transparent curved plate to capture more ideal contact states with a surface shape more similar to the human body. We collect the contact surface data of the beginning of touching motions by Humanitude experts and novices using the FTIR sensing system with the curved and flat plates. Then, we compare the data by the experts and novices in terms of time-series contact areas and the quantitative indices and subjective evaluation and discuss the analysis results. Through these experiments, we confirm that the proposed system has the potential for the novices to perform more correctly the beginning of Humanitude's touching motions. © 2024 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-Time Velocity and Hovering Control for Rotorcraft Based on Visual State Estimation

Real-Time Velocity and Hovering Control for Rotorcraft Based...

引用

2021 China Automation Congress, CAC 2021

作者： Du, Hao Wang, Wei Liu, Hongxun Wang, Qi Shi, Hongbiao Xue, Lei School of Automation Southeast University Nanjing China Nanjing University of Information Science & Technology Nanjing China Graduate School of Science and Engineering Chiba University Chiba Japan School of Automation Nanjing University of Information Science & Technology Nanjing China Autonomous Control Robot Laboratory Institute of Applied Research Intelligent Science & Technology Jiangsu and Chinese Academy of Sciences Changzhou China

ISBN: (纸本)9781665426473

The purpose of this thesis is to solve the velocity and hover flight control problem of rotorcraft in GNSS-denied environments by using a low-cost Optical Flow Sensor (OFS) and an RGBD camera. An OFS is employed for velocity estimation and an RGBD camera is employed for pose estimation based on ORB-SLAM2 algorithm. Firstly, the mathematical model of velocity is established, then the classical PID control is applied to realize the velocity and hover control, and the designed embedded control system is installed on the drone for flight verification. We verified the effectiveness of this system for estimating velocity, position and controlling the drone in real-time in an indoor environment, and discuss its limitations. © 2021 IEEE

关键词： Velocity

来源：评论

学校读者我要写书评

暂无评论

Identification of functional tumor necrosis factor-alpha promoter variants associated with Helicobacter pylori infection in the Sudanese population: Computational approach

引用

World Journal of Gastroenterology 2022年第2期28卷 242-262页

作者： Abeer Babiker Idris Alaa B Idris Manal A Gumaa Mohammed Babiker Idris Amanda Elgoraish Mohamed Mansour Dalia Allam Bashir MO Arbab Nazar Beirag El-Amin M Ibrahim Mohamed A Hassan Department of Agricultural Science and Technology Institute of Natural and Applied SciencesErciyes UniversityKayseri 38039Turkey Department of Medical Microbiology Faculty of Medical Laboratory SciencesUniversity of KhartoumKhartoum 11111Sudan Department of Neurosurgery Ribat University HospitalKhartoum 11111Sudan BioMérieux Clinical and Application Advisor Al-Jeel Medical Co.Riyadh 11422Saudi Arabia Department of Epidemiology Tropical Medicine Research InstituteKhartoum 11111Sudan Department of Gastroenterology Ibn Sina Specialized HospitalKhartoum 11111Sudan Department of Gastroenterology Modern Medical CentreKhartoum 11111Sudan Biosciences College of HealthMedicine and Life SciencesBrunel UniversityLondon UB83PHUxbridgeUnited Kingdom Department of Translation Bioinformatics Detavax BiotechKayseri 38350Turkey

BACKGROUND Helicobacter pylori(***)is a ubiquitous bacterium that affects nearly half of the world’s population with a high morbidity and mortality *** within the tumor necrosis factor-alpha(TNF-A)promoter region are considered a possible genetic basis for this *** To functionally characterize the genetic variations in the TNF-A 5’-region(-584 to+107)of Sudanese patients infected with *** using in silico *** An observational study was carried out in major public and private hospitals in Khartoum state.A total of 122 gastric biopsies were taken from patients who had been referred for *** DNA was *** of the TNF-A-1030 polymorphism was performed using PCR with confronting two-pair primer to investigate its association with the susceptibility to *** infection in the Sudanese ***,Sanger sequencing was applied to detect single nucleotide polymorphisms in the 5’-region(-584 to+107)of TNF-A in ***-infected *** analyses were used to predict whether these mutations would alter transcription factor binding sites or composite regulatory elements in this region.A comparative profiling analysis was conducted in 11 species using the ECR browser and multiple-sequence local alignment and visualization search engine to investigate the possible ***,a multivariate logistic regression model was constructed to estimate odds ratios and their 95%confidence intervals for the association between TNF-A-1030,sociodemographic characteristics and *** *** were statistically significant if P<*** analyses were performed using Stata version 11 *** A total of seven single nucleotide polymorphisms were observed in the TNF-A 5’-region of Sudanese patients infected with *** one of them(T>A,-76)was located at the in silico-predicted promoter region(-146 to+10),and it was predicted to alter transcription factor b

关键词： 5’-region Promoter TNF-A Helicobacter pylori In silico analysis Sudan

来源：评论

学校读者我要写书评

暂无评论

Quantum machine learning for multiclass classification beyond kernel methods

arXiv

引用

arXiv 2024年

作者： Ding, Chao Wang, Shi Wang, Yaonan Gao, Weibo College of Electrical and Information Engineering Hunan University Changsha410082 China Division of Physics and Applied Physics School of Physical and Mathematical Sciences Nanyang Technological University Singapore637371 Singapore National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China Centre for Quantum Technologies National University of Singapore Singapore117543 Singapore The Photonics Institute Centre for Disruptive Photonic Technologies Nanyang Technological University Singapore637371 Singapore

Quantum machine learning is considered one of the current research fields with great potential. In recent years, Havlíček et al. [Nature 567, 209-212 (2019)] have proposed a quantum machine learning algorithm with quantum-enhanced feature spaces, which effectively addressed a binary classification problem on a superconducting processor and offered a potential pathway to achieving quantum advantage. However, a straightforward binary classification algorithm falls short in solving multiclass classification problems. In this paper, we propose a quantum algorithm that rigorously demonstrates that quantum kernel methods enhance the efficiency of multiclass classification in real-world applications, providing quantum advantage. To demonstrate quantum advantage, we design six distinct quantum kernels within the quantum algorithm to map input data into quantum state spaces and estimate the corresponding quantum kernel matrices. The results from quantum simulations reveal that the quantum algorithm outperforms its classical counterpart in handling six real-world multiclass classification problems. Furthermore, we leverage a variety of performance metrics to comprehensively evaluate the classification and generalization performance of the quantum algorithm. The results demonstrate that the quantum algorithm achieves superior classification and better generalization performance relative to classical counterparts. Copyright © 2024, The Authors. All rights reserved.

关键词： Quantum efficiency

来源：评论

学校读者我要写书评

暂无评论

Single-Step Method for the Immobilization of Hydroxyapatite on 3d-Printed Porous Polyetherketoneketone Implants for the Enhanced Cell Adhesion and Osteogenic Differentiation

SSRN

引用

SSRN 2025年

作者： Goreninskii, Semen Akimchenko, Igor Vorobyev, Alexander Konoplyannikov, Mikhail Efremov, Yuri Sudarev, Evgeniy A. Timashev, Peter S. Zvyagin, Andrei V. Bolbasov, Evgeny Tverdokhlebov, Sergei I. Research Center for Translational Medicine Sirius University of Science and Technology Sirius Federal Territory Olympic av. 1 354340 Russia Additive Technologies Center Tomsk Polytechnic University Lenina av. 30 Tomsk634050 Russia B.P. Weinberg Research Center Tomsk Polytechnic University Lenina av. 30 Tomsk634050 Russia Research School of Chemistry & Applied Biomedical Sciences Tomsk Polytechnic University Lenina av. 30 Tomsk634050 Russia Federal Research Clinical Center of Specialized Medical Care and Medical Technologies Federal Medical-Biological Agency of the Russian Federation Volokolamsk Highway 30 Moscow123182 Russia Institute of Molecular Theranostics Sechenov First Moscow State Medical University Trubetskaya st. 8 Moscow119991 Russia Institute for Regenerative Medicine Sechenov First Moscow State Medical University Trubetskaya st. 8 Moscow119991 Russia N.M. Kizhner Research Center Tomsk Polytechnic University Lenina av. 30 Tomsk634050 Russia Chemistry Department Lomonosov Moscow State University Leninskie Gory 1 Moscow Russia

Owing to its high mechanical performance and biocompatibility, polyetherketoneketone (PEKK) has emerged as a promising material for the development of bone implants. Previously, a method for the immobilization of hydroxyapatite (HAp) particles on the PEKK surface was proposed by our group for the enhancement of stem cell adhesion. In this study, we present a single-step method for immobilizing HAp particles on the surfaces of 3D-printed porous PEKK implants by treating them with a suspension of HAp particles in a mixture of water and 1,1,1,3,3,3-hexafluoropropan-2-ol (HFP). This approach effectively preserved the morphology (pore diameter and printed line width) of the original implants. With that, up to 35.0±14.0% of the sample surface was covered with HAp particles, leading to improved hydrophilicity (0° water contact angle). The calcium and phosphorus content on the surface of modified samples reached 17.4±4.1 wt.% and 8.0±1.7 wt.%, respectively. Importantly, the proposed modification preserved the compressive strength of the 3D-printed porous PEKK implants. HAp immobilization enhanced stem cell adhesion (from 121±40 cells/mm2 to 234±8 cells/mm2) and induced their osteogenic differentiation. Thus, the proposed method may be used for the development of PEKK-based implants for bone tissue restoration. © 2025, The Authors. All rights reserved.

关键词： Stem cells

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：