检索结果-内蒙古大学图书馆

International Conference on Modern Mechanics and Applications, ICOMMA 2020

作者： Tai, V.V. Ngoc, L.T.K. College of Natural Science Can Tho University Can Tho City Viet Nam Faculty of Engineering Van Lang University Ho Chi Minh City Viet Nam University of Science Ho Chi Minh City Viet Nam Vietnam National University Ho Chi Minh City Viet Nam

ISBN: (纸本)9789811632389

This article proposes a novel techniques for unsupervised learning in image recognition using automatic fuzzy clustering algorithm (AFCA) for discrete data. There are two main stages in order to recognize images in this study. First of all, new technique is shown to extract sixty four textural features from n images represented by a matrix n × 64. Afterwards, we use the proposed method based on Hausdorff distance to simultaneously determine the appropriate number of clusters. At the end of the unsupervised clustering process, discrete data belonging to the same cluster converge to the same position, which represents the cluster’s center. After determining number of cluster, we have probability of assigning objects to the established clusters. The simulation result built by Matlab program shows the effectiveness of the proposed method using the corrected rand, the partition entropy, and the partition coefficients index. The experimental outcomes illustrate that the proposed method is better than the existing ones as Fuzzy C-mean. As a result, we believe that the proposed method is filled with a potential possibility which can be applied in practical realization. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： automatic algorithm Fuzzy Hausdorff distance Image recognition Unsupervised clustering

来源：评论

学校读者我要写书评

暂无评论

Real-Time Defect Monitoring of Laser Micro-drilling Using Reflective Light and Machine Learning Models

引用

INTERNATIONAL JOURNAL OF PRECISION ENGINEERING AND MANUFACTURING 2024年第1期25卷 155-164页

作者： Lee, Yong Kwan Lee, Sumin Kim, Sung Hwan Tech Univ Korea Shihung South Korea RESHENIE Co Ltd Suwon South Korea 21 Century Co Ltd Hwasung South Korea

Laser micro-drilling is a significant manufacturing method used to drill precise microscopic holes into metals. Quality inspection of micro-holes is costly and redrilling defective holes can lead to imperfection owing to the misalignment in re-aligning the removed specimens. Thus this paper proposes an in-situ, automatic inspection method using photodiode data and machine learning models to detect defects in real-time during the fabrication of SK5 steel plates with 1064 nm Nd:YAG Laser machines to reduce the workload and increase the quality of products. Further, it explores the possibility of generalizing the models to 51 different scenarios of fabrication by classifying unseen data into 51 classes. A dataset of around 1,500,000 time series data points was generated using an optical probe while drilling over 56,000 holes into test specimens. 15 different combinations of thickness and diameter were drilled using suggested parameters. An additional 12 potential defect-prone conditions were designed to obtain data during conditional drilling. Hole quality was measured for each hole using OGP 3D profile microscope measuring machine. Results showed high accuracy in specialized defect detection within each scenario and showed a possibility of classifying photodiode data patterns, offering opportunities to improve the practicality of the proposed solution.

关键词： Machine learning Laser drilling Optical probe Failure detection automatic algorithm

来源：评论

学校读者我要写书评

暂无评论

Fuzzy cluster analysis algorithm for image data based on the extracted feature intervals

引用

GRANULAR COMPUTING 2023年第6期8卷 2067-2081页

作者： Le, Kim-Ngoc T. Nguyenthihong, Dan Vovan, Tai Sungkyunkwan Univ Dept AI Syst Engn Suwon South Korea Ho Chi Minh City Univ Technol HCMUT Fac Sci Appl Ho Chi Minh City Vietnam Vietnam Natl Univ Ho Chi Minh City Ho Chi Minh City Vietnam Can Tho Univ Coll Nat Sci Can Tho City Vietnam

Cluster analysis is a crucial issue in multivariate statistics and data science due to its application in various fields. This study proposes a cutting-edge clustering algorithm for image data with important improvements. First, we extract the texture features from each image and represent them as two-dimensional intervals, which serve as effective input data for recognizing similarities between images. Subsequently, we introduce a measure called overlap distance for evaluating the similarity between intervals in multi-dimensional cases. Furthermore, the study develops an automatic fuzzy clustering algorithm specifically designed for images. This algorithm addresses multiple challenges simultaneously, including determining the appropriate number of clusters, identifying specific elements within clusters, and estimating the probability of each element belonging to clusters. In addition, the study implements a Matlab program to test the effectiveness and practical applications of the proposed algorithm. The results obtained from the proposed algorithm outperform those of current methods when applied to datasets with variations in the number of elements, fields, and characteristics of images.

关键词： automatic algorithm Image data Interval data Fuzzy clustering

来源：评论

学校读者我要写书评

暂无评论

algorithm based automatic templating is less accurate than manual digital templating in total knee arthroplasty

引用

JOURNAL OF ORTHOPAEDIC RESEARCH 2020年第7期38卷 1472-1476页

作者： Seaver, Thomas McAlpine, Kenneth Garcia, Enrique Niu, Ruijia Smith, Eric L. Boston Med Ctr Dept Orthopaed Surg Boston MA USA Keystone Orthopaed Specialists Bone & Joint Care Ctr W Reading PA USA Boston Univ Sch Med Boston MA 02118 USA New England Baptist Hosp 125 Parker Hill Ave Boston MA 02120 USA

The purpose of the study was to evaluate the accuracy of a commercial automatic digital templating algorithm compared to manual digital templating in total knee arthroplasty (TKA). The study also evaluated if race and the presence of a standardized calibration marker on preoperative radiographs effect the accuracy of digital templating. One hundred twenty-five consecutive patients undergoing primary TKA were included in the study. Patient demographics, etiology of arthritis, and the presence of a standardized calibration marker on preoperative anteroposterior (AP) and lateral radiographs was recorded. Manual digital templating and the use of the "auto-knee" templating algorithm with "Traumacad" software was performed and recorded. Intraoperative sizes of the actual implants used were recorded. Pearson chi 2 test was used to evaluate the accuracy of auto versus manual templating. Manual templating was within 1 size of the implant used intraoperatively for femoral and tibial implants 97.6% and 94.2% of the time, respectively. The "auto-knee" algorithm was within one size of the implant used for femoral and tibial implants 51.2% and 71.2% of the time, respectively. The presence of a standardized calibration marker on the AP view did not change accuracy of templating for both components. There was no difference in accuracy of templating between races. We caution surgeons from exclusively using an automatic algorithm as it is less accurate than manual templating for TKA.

关键词： accuracy automatic algorithm digital templating TKA

来源：评论

学校读者我要写书评

暂无评论

Accurate Recognition of Vascular Lumen Region from 2D Ultrasound Cine Loops for Bubble Detection

引用

CURRENT MEDICAL IMAGING 2024年 20卷 e15734056298529页

作者： Wang, Ziyi Yang, Zhuochang Chen, Ziye Huang, Xiaoyu Xu, Lifan Zhou, Chang Zhou, Yingjie Zhu, Baoliang Zhang, Kun Gong, Deren Xu, Weigang Chen, Jiangang East China Normal Univ Shanghai Key Lab Multidimens Informat Proc Shanghai Peoples R China Xian Jiaotong Liverpool Univ Dept Biol Sci Suzhou 215123 Jiangsu Peoples R China Univ Liverpool Univ Liverpool Xian Jiaotong Dept Elect Engn & Elect Suzhou 215123 Jiangsu Peoples R China Xian Jiaotong Liverpool Univ Sch Adv Technol Dept Comp Suzhou 215123 Jiangsu Peoples R China Second Mil Med Univ Naval Special Med Ctr Dept Diving & Hyperbar Med Shanghai 200433 Peoples R China Shanghai Jiao Tong Univ Sch Aeronaut & Astronaut Shanghai 200240 Peoples R China

Background Accurate identification of vascular lumen region founded the base of bubble detection and bubble grading, which played a significant role in the detection of vascular gas emboli for the diagnosis of decompression *** To assist in the detection of vascular bubbles, it is crucial to develop an automatic algorithm that could identify vascular lumen areas in ultrasound videos with the interference of bubble *** This article proposed an automated vascular lumen region recognition (VLRR) algorithm that could sketch the accurate boundary between vessel lumen and tissues from dynamic 2D ultrasound videos. It adopts 2D ultrasound videos of the lumen area as input and outputs the frames with circled vascular lumen boundary of the videos. Normalized cross-correlation method, distance transform technique, and region growing technique were adopted in this *** A double-blind test was carried out to test the recognition accuracy of the algorithm on 180 samples in the images of 6 different grades of bubble videos, during which, intersection over union and pixel accuracy were adopted as evaluation metrics. The average IOU on the images of different bubble grades reached 0.76. The mean PA on 6 of the images of bubble grades reached *** It is concluded that the proposed method could identify the vascular lumen with high accuracy, potentially applicable to assist clinicians in the measurement of the severity of vascular gas emboli in clinics.

关键词： Ultrasound videos KCF Tissue segmentation Bubble detection automatic algorithm DCS

来源：评论

学校读者我要写书评

暂无评论

An MLS-based high-accuracy measurement and automatic analysis method for roadway deformation

引用

TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY 2023年第1期140卷

作者： Wu, Chao Li, Yuanhui An, Long Dong, Erhu Han, Lin Northeastern Univ Key Lab Minist Educ Safe Min Deep Met Mines Shenyang 110819 Peoples R China Northeastern Univ Inst Deep Engn & Intelligent Technol Shenyang 110819 Peoples R China

The 3D laser scanning has increasingly been applied in the field of monitoring roadway deformation. Different from a terrestrial laser scanner (TLS), a mobile laser scanner (MLS) is more flexible in on-site operations, but its scanning range accuracy is only precise to the centimeter level. still remains in centimeters. In addition, extracting deformation information from point cloud data of roadway is a complex process. In order to improve the accuracy of deformation monitoring and the efficiency of point cloud processing, with the aid of the identification plate for measurement (IPM) and the statistical analysis methods, an MLS-based high-accuracy measurement and automatic analysis method of roadway deformation is proposed. In this approach, the center point of the identification plate for measurement (IPM-CP) is taken as the control point for deformation monitoring (CPDM). The IPMs in the point cloud are positioned based on the locations of the seed points. The K-radius search algorithm and the density-based spatial clustering of applications with noise (DBSCAN) algorithm are introduced to extract and segment the point cloud of the target area (PCTA). The calculation methods for the key parameters of the algorithms are developed. The judgement index for identifying the IPM point cloud and the methods for target point extraction are presented. The convergence features of the surrounding rocks is analyzed by comparing the lengths of measuring lines of monitoring sections at different stages. The method was applied and validated in the Sanshandao Gold Mine for roadway deformation monitoring. The results show that this method is able to automatically obtain a highly precise data on roadway deformation.

关键词： Roadway deformation monitoring MLS Point cloud IPM automatic algorithm

来源：评论

学校读者我要写书评

暂无评论

A novel methodology for the modeling of catheter aspiration in high-fidelity thrombectomy simulations

引用

Procedia Structural Integrity 2023年 49卷 67-73页

作者： Sara Bridio Giulia Luraghi Anushree Dwivedi Ray McCarthy Jose Felix Rodriguez Matas Francesco Migliavacca Department of Chemistry Materials and Chemical Engineering “Giulio Natta” Politecnico di Milano Piazza Leonardo Da Vinci 32 20133 Milan Italy Cerenovus Neuro Technology Center Ballybrit Business Park H91 K5YD Galway Ireland

The development of high-fidelity in silico simulations of the endovascular thrombectomy (EVT) procedure, the treatment for acute ischemic stroke, is gaining importance for the possibility of investigating the causes of failure of the clinical procedure and optimizing the treatment. This work proposed a novel methodology for a realistic modeling of the thrombus aspiration in a combined EVT procedure, with stent-retriever and proximal aspiration catheter. In the combined EVT procedure, the thrombus is entrapped in the stent struts and is retrieved towards the aspiration catheter. During the retrieval, the thrombus may rotate, and therefore different portions of its surface are subjected to aspiration forces. An automatic algorithm is implemented allowing to redefine the portion of the thrombus surface subjected to the aspiration pressure in different time points of a high-fidelity finite-element EVT simulation. The algorithm updates at each iteration the loaded portion of thrombus surface, by selecting elements aligned with the vascular centerline. The algorithm is applied in a high-fidelity EVT simulation in a patient-like vascular model, demonstrating the ability of obtaining a realistic simulation of thrombus aspiration.

关键词： thrombectomy aspiration catheter finite-element automatic algorithm

来源：评论

学校读者我要写书评

暂无评论

Nearshore sandbars crest position dynamics analysed based on Earth Observation data

引用

REMOTE SENSING OF ENVIRONMENT 2020年 237卷 111555-000页

作者： Tatui, Florin Constantin, Sorin Univ Bucharest Res Inst Bucharest Romania Univ Bucharest Fac Geog Bucharest Romania Terrasigna Bucharest Romania

Understanding long-term underwater sandbars dynamics is a key element for optimal coastal zone management, but this endeavour is often held back by data availability. In order to increase the spatial and temporal resolution, availability and quality of sandbars observations, this study proposes and evaluates a new approach for automatic extraction of sandbars positions from freely available satellite imagery, using a case study of complex waters located on the Danube Delta coast, Black Sea. Validation of the satellite extracted sandbars locations against 4 in-situ measurements between 2016 and 2018 shows a very good correlation between the two datasets, demonstrating the high accuracy of satellite-derived data in revealing the underwater morphology of the upper shoreface along large areas and with high temporal resolution. The obtained sandbars positions were then integrated into an automatic workflow able to accurately represent the seasonal and multi-annual sandbars dynamics and also to give an insight about the sandbars alongshore behavioural changes. The results are similar to the ones previously suggested by other studies, which empowered different methods. These prove the high potential of the newly proposed algorithm to be used for the automatic extraction of the positions of underwater features in the surf zone on other sites worldwide, after proper tuning of parameters in accordance with local conditions. The main constraints of the proposed approach are represented by the omission of sandbars position that imprint a low signal on the satellite image due to increased water depth (especially for the outer bar), high turbidity (mostly for the inner bar) or any other noise generation situation (sun glint, small wind waves). The main advantages of the described algorithm are related to the simplicity of implementation and adaptability to other areas of interest and other types of satellite data.

关键词： Sentinel-2 Sandbars crest automatic algorithm Offshore migration Bar migration cycle

来源：评论

学校读者我要写书评

暂无评论

automatic generation of landslide profile for complementing landslide inventory

引用

GEOMATICS NATURAL HAZARDS & RISK 2020年第1期11卷 1000-1030页

作者： Li, Langping Lan, Hengxing Strom, Alexander Chinese Acad Sci Inst Geog Sci & Nat Resources Res State Key Lab Resources & Environm Informat Syst Beijing Peoples R China Changan Univ Sch Geol Engn & Geomat Xian Peoples R China Geodynam Res Ctr LLC Moscow Russia

Landslide profile has been widely used in the dynamics analysis, characteristics illustration and parameter measurement along the longitudinal direction of landslide. However, landslide profile and landslide characteristic parameters that can be derived from landslide profile have not been formally included in landslide inventories. This paper firstly presented a newly developed algorithm for automatic generation of landslide profile, and then suggested 14 parameters that can be directly derived from landslide profile to characterize landslides. The proposed approach has been coded in a freely available R script called ALPA. A case study showed that the profiles of landslides with various scales and morphologies can be successfully generated by ALPA. A correlation analysis suggested that the 14 parameters can provide independent and informative complements to landslide characterization, which are different from the landslide area and volume. The results also implied that landslide area, which quantifies the total area affected by a landslide, is highly correlated with the product of volume and maximum drop height and the product of volume and maximum residual height, which are related to destructive power. Although limited by some complications, ALPA provides a practical tool for producing landslide profiles and landslide characteristic parameters, which are valuable complements to landslide inventory.

关键词： Landslide profile automatic algorithm landslide inventory landslide characteristic parameters

来源：评论

学校读者我要写书评

暂无评论

automatic algorithm of Effectiveness of Accounting Management Systems based on Finite Element Simulation

Automatic Algorithm of Effectiveness of Accounting Managemen...

引用

International Conference on Mechatronics and Industrial Informatics (ICMII 2013)

作者： Cheng YaNing Beihua Univ Sch Econ Management Jilin Peoples R China

ISBN: (纸本)9783037856949

The right panel drawing direction is an important prerequisite for generating qualified parts, an important step before the panel forming simulation is to determine the reasonable direction of the drawing. Manually adjust parts in order to overcome rely on experience, the drawbacks to the drawing direction, the direction of the drawing punch and forming the contact area of the sheet as the goal of automatic determination algorithm. Objective function of the direction of the drawing for the variable contact area in the drawing direction of the feasible region, the use of heritage algorithms to optimize the objective function of the contact area and, ultimately feasible within the contact area corresponding to the drawing direction, that is the best drawing direction. The measured results show that the direction of the drawing based on genetic algorithm, the automatic algorithm can fast and accurate to obtain the optimal direction of drawing.

关键词： automatic algorithm Automotive Covering Stamping Direction Binary algorithm

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

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

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：