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

Nanoplastics drive toxicity under co-exposure with perfluorooctanesulfonic acid in human intestinal cells

引用

Environmental Chemistry Letters 2025年 1-9页

作者： Alijagic, Andi Särndahl, Eva Kotlyar, Oleksandr Karlsson, Patrik Duberg, Daniel Scherbak, Nikolai Pinsino, Annalisa Engwall, Magnus Hyötyläinen, Tuulia Man-Technology-Environment Research Center Örebro University Örebro701 82 Sweden Inflammatory Response and Infection Susceptibility Centre Örebro University Örebro701 82 Sweden School of Medical Sciences Faculty of Medicine and Health Örebro University ÖrebroSE-701 82 Sweden Centre for Applied Autonomous Sensor Systems Robot Navigation & Perception Lab Örebro University Örebro701 82 Sweden Department of Mechanical Engineering Örebro University Örebro701 82 Sweden Institute of Translational Pharmacology National Research Council Via Ugo La Malfa 153 Palermo90146 Italy

Per- and polyfluoroalkyl substances and nanoplastics frequently co-occur in environmental matrices, yet the effects of co-exposure on cellular responses upon ingestion are poorly understood. Here, we exposed human intestinal Caco-2 cells to perfluorooctanesulfonic acid, nanoplastics, and their combination. Cell painting-based phenomics was used to map phenotypic alterations across subcellular structures, and untargeted metabolomics using ultra-high-performance liquid chromatography coupled to quadrupole time-of-flight mass spectrometry was employed to assess metabolic changes. Results show that perfluorooctanesulfonic acid predominantly affected the actin cytoskeleton, Golgi apparatus, and plasma membrane, while nanoplastics primarily targeted mitochondria. Combined exposure disrupted the endoplasmic reticulum, RNA, and mitochondria. Perfluorooctanesulfonic acid reduced levels of carnitines, free fatty acids, nucleotides, and sugars, whereas nanoplastics inhibited ceramides, triglycerides, sphingomyelins, and additional free fatty acids. Combined exposure produced a metabolic profile resembling that of nanoplastics, with specific differences attributed to perfluorooctanesulfonic acid. Overall, nanoplastics appear as the main drivers of the co-exposure effects. © The Author(s) 2025.

关键词： Nucleotides

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

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

TransAnno-Net: A Deep Learning Framework for Accurate Cell Type Annotation of Mouse Lung Tissue Using Self-supervised Pretraining

引用

Computer Methods and Programs in Biomedicine 2025年 267卷 108809-108809页

作者： Zhang, Qing Wu, Xiaoxiao Li, Xiang Ma, Wei Wu, Tongquan Li, Liuyue Hu, Fan Xie, Yicheng Wu, Xinglong School of Computer Science and Engineering Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology Hubei Wuhan430205 China School of Mechanical Engineering Hefei University of Technology Hefei China Faculty of Applied Science and Engineering University of Toronto Canada UNISKIN Research Institute on Skin Aging Inertia Shanghai Biotechnology Co. Ltd Shanghai China DermaHealth Shanghai Biotechnology Co. Ltd. Shanghai China Department of Dermatology Children's Hospital Zhejiang University School of Medicine National Clinical Research Center for Child Health Zhejiang Province Hangzhou310052 China

Background: Single-cell RNA sequencing (scRNA-seq) has become a significant tool for addressing complex issuess in the field of biology. In the context of scRNA-seq analysis, it is imperative to accurately determine the type of each cell. However, conventional supervised or semi-supervised methodologies are contingent on expert labels and incur substantial labeling costs, In contrast self-supervised pre-training strategies leverage unlabeled data during the pre-training phase and utilise a limited amount of labeled data in the fine-tuning phase, thereby greatly reducing labor costs. Furthermore, the fine-tuning does not need to learn the feature representations from scratch, enhancing the efficiency and transferability of the model. Methods: The proposed methodology is outlined below. The deep learning framework, TransAnno-Net, is based on transfer learning and a Transformer architecture. It has been designed for efficient and accurate cell type annotations in large-scale scRNA-seq datasets of mouse lung organs. Specifically, TransAnno-Net is pre-trained on the scRNA-seq lung data of approximately 100,000 cells to acquire gene-gene similarities via self-supervised learning. It is then migrated to a relatively small number of datasets to fine-tune specific cell type annotation tasks. To address the issue of imbalance in cell types commonly observed in scRNA-seq data, we applied a random oversampling technique is applied to the fine-tuned dataset. This is done to mitigate the impact of distributional imbalance on the annotation outcomes. Results: The experimental findings demonstrate that TransAnno-Net exhibits superior performance with an AUC of 0.979, 0.901, and 0.982, respectively, on three mouse lung datasets, outperforming eight state-of-the-art (SOTA) methods. In addition, TransAnno-Net demonstrates robust performance on cross-organ, cross-platform datasets, and is competitive with the fully supervised learning-based method. Conclusion: The TransAnno-Net method

关键词： Self-supervised learning

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

引用

Colloids and Surfaces B: Biointerfaces 2025年 254卷 114777页

作者： Goreninskii, Semen Akimchenko, Igor Vorobyev, Alexander Konoplyannikov, Mikhail Efremov, Yuri Sudarev, Evgeniy Timashev, Peter Zvyagin, Andrei Bolbasov, Evgeny Tverdokhlebov, Sergei Research Center for Translational Medicine Sirius University of Science and Technology 354340 Sirius Federal Territory Olympic av . 1 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 ClinicalCenter of Specialized Medical Care and Medical Technologies FederalMedical-Biological Agency of the Russian Federation VolokolamskHighway 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

Being biocompatible and extremely rigid polymer, polyetherketoneketone (PEKK) emerged as a promising material for the development of bone implants, but its inert surface limits bone-implant integration. Herein, we report a single-step approach for the immobilization of hydroxyapatite (HAp) particles on the surface of additively fabricated porous PEKK implants based on the swelling of the implant surface with subsequent entrapment of the HAp particles. By means of the scanning electron microscopy, it was established that 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 ( © 2025 Elsevier B.V.

关键词： Cell adhesion

来源：评论

学校读者我要写书评

暂无评论

Software architecture of human-like robot

Software architecture of human-like robot

引用

ICCAS-SICE 2009 - ICROS-SICE International Joint Conference 2009

作者： Lee, Tae-Geun Yang, Kwang-Woong Choi, Moo-Sung Shin, Un-Chol Intelligent Robot Platform Research Team SoluBot Inc. Ansan Korea Republic of Division for Applied Robot Technology Korea Institute of Industrial Technology Ansan Korea Republic of

ISBN: (纸本)9784907764296

Software architectures have been suggested for a non-industrial robot up to the present, however a few developer who working in the robot field are applying those to manufactured products. Such software architecture of the robot is not using with several reasons in the field of a robot in spite of excellent advantages. This paper proposes using a device management of the software architecture, which has a hierarchical structure, in a human-like robot. Especially, we applied to the rent business of the android platform, EveR1;the compound word of Eve and robot [1]. The device may be real mechanical parts like a sensor, motor, and camera or virtual parts like a motor arbiter, motion generator, and priority maker. The virtual parts are software components which are used in operating the android platform. The device management exists between hardware and software of a robot, and makes the hardware compatibility for applied to applications in the high layer of software. It is compatible due to separating similar functions of each device which is managed in the device management, and providing same abstract interfaces. For instance, an application developed by using a motor driver of one corporation is exchanged for a motor drive of the other corporation with minimal code modification. © 2009 SICE.

关键词： Application programs

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

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：