检索结果-内蒙古大学图书馆

Support vector machine combined with magnetic resonance imaging for accurate diagnosis of paediatric pancreatic cancer

引用

IET image processing 2020年第7期14卷 1233-1239页

作者： Zhang, Yuling Wang, Shuchang Qu, Shuqiang Zhang, Hongli Habin Med Univ Affiliated Hosp 2 Dept Pediat Habin 150086 Peoples R China Habin Second Hosp Dept Thyroid & Breast Surg Habin 150001 Peoples R China Harbin Med Univ Canc Hosp Dept Hemolymph Habin 150081 Peoples R China

When performing paediatric pancreatic cancer (PC) diagnosis, magnetic resonance imaging (MRI) will be interfered by many factors, resulting in poor diagnosis. In order to improve the diagnostic effect of MRI on PC, this study is based on machine learning and combines SVM (support vector machine) and MRI detection with the support of image processing technology and improves the diagnostic accuracy of MRI for PC by the computer-assisted method. At the same time, in the research, this study combines the characteristics of MRI detection to construct an MRI detection model based on SVM. In addition, this study obtains test samples through data collection, analyses the performance of the algorithm model through actual cases, and combines image processing to improve the detection effect. Studies have shown that the algorithm model proposed in this study can effectively improve the accuracy of MRI diagnosis of PC and provide a theoretical reference for subsequent related research.

关键词： medical image processing learning (artificial intelligence) cancer patient diagnosis paediatrics support vector machines biomedical MRI image processing technology PC computer-assisted method MRI detection model algorithm model combines image processing detection effect MRI diagnosis support vector machine magnetic resonance imaging performing paediatric pancreatic cancer diagnosis poor diagnosis diagnostic effect machine learning SVM

来源：评论

学校读者我要写书评

暂无评论

Analysis of soil impulse discharge characteristics based on optical-electrical synchronous observation

引用

IET GENERATION TRANSMISSION & DISTRIBUTION 2022年第11期16卷 2287-2297页

作者： Li, Yuanjie Li, Chun Lu, Hailiang Liu, Gang Cai, Hansheng Chen, Huaifei Lan, Lei Wen, Xishan Wuhan Univ Sch Elect Engn Wuhan 430072 Peoples R China CSG Elect Power Res Inst Guangzhou Peoples R China

The impulse performance of grounding electrodes highly depends on soil impulse discharge characteristics. The analysis of soil discharge dynamic process images is helpful to understand the impulse discharge mechanism of grounding electrodes. This paper designed an optical-electrical synchronous observation platform for simulate soil (SiO2 crystal) discharge, and discharge dynamic process images is obtained by high-speed camera. Through analysing breakdown delay time and thermal power before breakdown, it is found that soil impulse discharge is mainly an electrical breakdown process, and soil ionization intensity is positively correlated with the light intensity emitted by whole soil sample in breakdown channel development stage. The time from voltage application to the occurrence of ionization is defined as initial ionization delay time (IIDT). Using image processing technology, the change curve of optical image average grayscale value with time in the process of soil discharge is obtained, and a calculation method of IIDT is proposed by comparing the difference between average grayscale value curve and background image average grayscale value. Experiment results show that IIDT is negatively correlated with impulse voltage, particle size and water content, but not with salt content.

关键词： image processing IIDT impulse voltage initial ionization delay time impulse performance soil ionization intensity electric breakdown breakdown delay time analysis ionisation background image average grayscale value soil discharge dynamic process image analysis optical image average grayscale value discharges (electric) soil optical information processing soil impulse discharge characteristic analysis optical-electrical synchronous observation breakdown channel development stage impulse discharge mechanism electrical breakdown process image processing technology

来源：评论

学校读者我要写书评

暂无评论

Orientation holes positioning of printed board based on LS-Power spectrum density algorithm

引用

TRAITEMENT DU SIGNAL 2018年第3-4期35卷 277-288页

作者： Zeng, Xiaxia Shao, Zhenhua Lin, Wenzhong Luo, Haibo Minjiang Univ China Digital Fujian IoT Lab Intelligent Prod Fuzhou 350108 Fujian Peoples R China Minjiang Univ Fujian Prov Key Lab Informat Proc & Intelligent C Fuzhou 350108 Fujian Peoples R China MinJiang Univ Coll Comp & Control Engn Fuzhou 350108 Fujian Peoples R China

With ROI can not obtained easily under uneven illumination ,the purpose of this study was to solve the the problem of low precision and slow speed when orientation holes positioning is performed manually. A novel hybrid extraction method in . frequency domain( LS- Power Density Algorithm)was adopted in this paper. The results indicated that the region of interest (ROI) can be obtained easily with help of Canny operator and Otsu algorithm in image prepossessing technology. Furthermore, in the context of PCB images with background noise and uneven illumination, LS- power density algorithm play an important role on punching recognition and the orientation holes positioning of printed hoard. Moreover. compared with the existing orientation positioning techniques( k-means . LMS and SvM), the improved algorithm can reach a good result. At last the performance of LS-PSD is carefully evaluated by simulation in *** the findings of this study may serve as electronic information process of mobile industry.

关键词： orientation holes positioning LS-Power spectrum density(LS-PSD) image processing technology region of interest (ROI)

来源：评论

学校读者我要写书评

暂无评论

Research on wheat leaf water content based on machine vision

引用

CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS 2019年第4-Sup期22卷 S9199-S9208页

作者： Ding, Xiao-Ling Zhao, Li-Xin Zhou, Tian-Tian Li, Yi-Bin Huang, Xi-Mei Zhao, Ya-Li Shandong Univ Sch Control Sci & Engn Jinan 250061 Shandong Peoples R China Shandong Agr Univ Mech & Elect Engn Coll Shandong Prov Key Lab Hort Machineries & Equipmen Tai An 271018 Shandong Peoples R China

This paper is based on Matlab software to predict the water content of wheat leaves. The object of study are 100 wheat leaves which collected in the field, the moisture content of the blade was measured by drying, preprocess the image with Matlab so as to denoise the image, segmentation of blade images by image two valued operation of Otsu method then, image features are extracted. By correlation analysis, the H feature and the area of the shape feature of the color feature which are related to the water content are extracted, Through correlation analysis, we extracted the five components of the color feature, which are related to the water content, the area of the shape feature, the average value of the texture features, consistency and entropy, and so on, and the H features are extracted, it can reduce the influence of single parameter on decision and improve the precision of comprehensive decision. Finally, the BP neural network was used to train 80 samples and meet the requirements, and then to predict the 20 new samples. The results show that the prediction accuracy can reach above 96%.

关键词： Matlab Water content detection Machine vision The BP neural network image processing technology

来源：评论

学校读者我要写书评

暂无评论

Research on variational optical flow method for rockfall monitoring

引用

SIGNAL image AND VIDEO processing 2024年第SUPPL 1期18卷 713-730页

作者： Chen, Hui Zhang, Lu Zhang, Ying Liu, Juan Chengdu Univ Technol State Key Lab Geohazard Prevent & Geoenvironm Prot Chengdu 610059 Sichuan Peoples R China Chengdu Univ Technol Geomath Key Lab Sichuan Prov Chengdu 610059 Sichuan Peoples R China Chengdu Univ Technol Coll Math & Phys Chengdu 610059 Sichuan Peoples R China

Rockfall is a global mountain disaster problem, which has the characteristics of wide distribution, strong randomness, and inconspicuousness. The contacted monitoring method is difficult to deploy. Simultaneously, the non-contact detection is easily affected by complex environments and generally has less robustness. This paper presents a rockfall monitoring technology based on machine vision. First, a high-resolution industrial camera continuously acquires images of the monitoring area. Then, we perform a series of operations on the landslide rockfall images, including image preprocessing, image optical flow algorithm preprocessing to identify the features of the rockfall. Finally, a dynamic target detection experiment is carried out to verify the feasibility of the image optical flow algorithm. Experiments of rockfall monitoring verify the effectiveness and generalization abilities of the algorithm. From the results: (1) The features of the image data in this paper are clear, and the recognition range covers the whole visual field. (2) The technology can capture the motion characteristics of landslide rockfall in different scenes. (3) The processing efficiency of the algorithm can reach 10 frames per second. Thus, this technology can be used in a monitoring system for rockfall.

关键词： Machine vision Variational optical flow technology Non-contact automatic identification technology image processing technology

来源：评论

学校读者我要写书评

暂无评论

Crack Evolution and Strength Attenuation of Red Clay under Dry-Wet Cycles

引用

JOURNAL OF MATERIALS IN CIVIL ENGINEERING 2024年第4期36卷

作者： Ma, Hongyan Pei, Chenglin Huang, Renjie Xu, Song Fuzhou Univ Coll Civil Engn Fuzhou 350108 Peoples R China Huizhou Creat Life TCL Yunchuang Technol Co Ltd 5th FloorTCL Technol Bldg17 Huifeng Third Rd Huizhou 516000 Guangdong Peoples R China

Red clay is a special soil that loses water and shrinks easily, which causes expansion and contraction and leads to the generation and development of cracks, weakening the strength and engineering properties of the soil. This investigation analyzed the mechanism of crack evolution and patterns of strength decay in red clay under dry-wet cycles and established a relationship between strength and crack ratio by employing image processing techniques and conducting direct shear tests on red clay with various initial moisture contents and humidification times. The results show that the crack ratio increases with the number of dry-wet cycles and eventually tends to be stable after the fourth dry-wet cycle, and the stress-displacement curve of red clay changes from weak hardening to hardening. With the progress of the dry and wet cycles, the shear strength indexes of red clay decrease extensively, displaying a negative association with the sample's initial moisture content and the duration of humidification. Based on the experimental result, a quadratic function was established to model the relationship between soil cracking ratio and shear strength, which can predict the shear strength of red clay from the cracking ratio.

关键词： Red clay Crack Dry-wet cycle Shear strength image processing technology

来源：评论

学校读者我要写书评

暂无评论

A System Model for Analyzing and Accumulating Construction Work Crew's Productivity Data Using image processing Technologies

引用

JOURNAL OF ASIAN ARCHITECTURE AND BUILDING ENGINEERING 2014年第3期13卷 547-554页

作者： Lee, Chankyu Son, Jaeho Lee, Seunghyun Hongik Univ Grad Sch Architectural Engn Jochiwon Eup 339701 Sejong South Korea Hongik Univ Sch Architectural Engn Jochiwon Eup 339701 Sejong South Korea

Recently, several studies pertaining to the measurement and analysis of construction productivity data have been attempted using image-processing technology. However, these studies have mainly focused on the recognition of individual labor and the materials at construction job sites. This research develops a new system model, which automatically analyzes and accumulates a construction work crew's productivity data using image processing technologies. It includes the three modules as follows: 1) the acquisition of a construction job site's video images and calibration for their recognition, 2) measurement and analysis of the construction work crew's productivity data, and 3) creation and utilization of a productivity database. New algorithms are proposed for each module. YCbCr settings are used to develop a calibration algorithm for improving the rate of recognition. Work sampling and video editing are used to develop an algorithm for measuring and analyzing the crew's productivity data. Then, an algorithm for productivity data accumulation and its utilization is proposed by utilizing the integration of the BIM Model. This developed system model is applied to a real construction site and validates its feasibility through two case studies.

关键词： automatic data acquisition construction work crew's productivity image processing technology system model BIM integration

来源：评论

学校读者我要写书评

暂无评论

Highlights of the novel dewaterability estimation test (DET) device

引用

ENVIRONMENTAL technology 2020年第20期41卷 2594-2602页

作者： Scholz, Miklas Almuktar, Suhad Clausner, Christian Antonacopoulos, Apostolos Lund Univ Div Water Resources Engn Lund Sweden Univ Salford Sch Comp Sci & Engn Salford Lancs England Univ Johannesburg Dept Civil Engn Sci Johannesburg South Africa Univ Basrah Dept Architectural Engn Al Basrah Iraq

Many industries, which are producing sludge in large quantities, depend on sludge dewatering technology to reduce the corresponding water content. A key design parameter for dewatering equipment is the capillary suction time (CST) test, which has, however, several scientific flaws, despite that the test is practical and easy-to-perform. The standard CST test has a few considerable drawbacks: its lack of reliability and difficulties in obtaining results for heavy sludge types. Furthermore, it is not designed for long experiments (e.g. >30 min), and has only two measurement points (its two electrodes). In comparison, the novel dewaterability estimation test (DET) test is almost as simple as the CST, but considerably more reliable, faster, flexible and informative in terms of the wealth of visual measurement data collected with modern image analysis software. The standard deviations associated with repeated measurements for the same sludge is lower for the DET than for the CST test. In contrast to the CST device, capillary suction in the DET test is linear and not radial, allowing for a straightforward interpretation of findings. The new DET device may replace the CST test in the sludge-producing industries in the future.

关键词： Capillary suction time filter paper property image processing technology resistance to filtration sludge treatment water technology

来源：评论

学校读者我要写书评

暂无评论

Theoretical and experimental study of a new defrost control strategy based on gray scale graph theory

引用

INTERNATIONAL JOURNAL OF REFRIGERATION 2022年 139卷 214-224页

作者： Sun, Huan Zhu, Junda Liu, Xinghua Sun, Zhili Lei, Zhuoya Tianjin Univ Commerce Tianjin Key Lab Refrigerat Technol Tianjin 300134 Peoples R China

Frosting of the evaporators is inevitable during system operation. As such, defrosting must be conducted peri-odically to ensure stable and efficient operation of the system. However, the current control methods often cause ?mal-defrosting " due to the complexity and randomness of frosting. To improve the defrosting accuracy of the system a new detection method for the amount of frost was proposed based on the image processing gray scale image theory. Further, the theory of combining the frosting characteristic parameter St with gray contrast C of the frosting image to forecast the critical defrosting time t of the system was established. Through experiments, the best defrosting times (t(best1) and t(best2)) of the system were determined, compared with t. Additionally, a frosting error factor (FEF) was identified, compared with the St value of times(t(best1),t(best2) and t). The results show that there was a defrost lag in the defrost time determined by the existing defrost control method,the average time error TEF was by 177.25 s and 321 s. Finally, in view of the illumination effect, the influence of illumination intensity on the accuracy of the proposed method was explored. After changing the illumination intensity,new defrost control method still offers high control accuracy, TEF was by 64 s and 324 s. Overall, from the perspective of engineering applications, the proposed method can reduce the influence of illumination intensity on frosting image recognition, allowing the system to accurately judge the defrosting start point, thereby realising accurate defrosting.

关键词： Coldstorage Control method Frost characteristic parameter image processing technology

来源：评论

学校读者我要写书评

暂无评论

GADF/GASF-HOG:feature extraction methods for hand movement classification from surface electromyography

引用

JOURNAL OF NEURAL ENGINEERING 2020年第4期17卷 046016-046016页

作者： Xiao, Feiyun Chen, Yanyan Zhu, Yanhe Hefei Univ Technol Sch Mech Engn Hefei 230009 Peoples R China State Key Lab Robot & Syst HIT Harbin 150001 Peoples R China Jiangsu Automat Res Inst Lianyungang 222000 Jiangsu Peoples R China CSIC Informat Technol Co LTD Lianyungang 222000 Jiangsu Peoples R China

Objective Human intention gesture recognition is widely used in hand rehabilitation, artificial limb control, teleoperation, human-computer interaction and other fields. It has great application value, however, how to extract human intention gesture accurately has been a research hotspot. Approach Inspired by the image processing technology of machine vision, the surface electromyographic (sEMG) signal was selected as the source signal of motion intention in this work, and the original sEMG signal was converted into Gramian Angular Summation/Difference Field (GASF/GADF) image. Then, Histogram of Oriented Gradient (HOG) features of the corresponding GADF and GASF image were extracted. The extracted features are named as GASF-HOG and GADF-HOG. The Bagging method was used to map the features to six common gestures to realize the classification of intention gestures. Ten volunteers participated in the experiment, and the experimental data were used to verify the proposed method. Main results The experimental results showed that the average accuracies of the proposed methods (GADF-HOG with Bagging, GASF-HOG with Bagging) were as follow: GADF-HOG with Bagging was with 95.73 +/- 1.90%, and GASF-HOG with Bagging was with 93.63 +/- 1.54%. Significance The method proposed in this paper is inspired by image processing technology of machine vision, which provides a new idea about the human intention gesture recognition by combining the interdisciplinary knowledge.

关键词： sEMG human intention gesture recognition HOG GADF GASF image processing technology

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：