scholarly journals Application of U-Net with Global Convolution Network Module in Computer-Aided Tongue Diagnosis

2021 ◽  
Vol 2021 ◽  
pp. 1-15
Author(s):  
Meng-Yi Li ◽  
Ding-Ju Zhu ◽  
Wen Xu ◽  
Yu-Jie Lin ◽  
Kai-Leung Yung ◽  
...  
Keyword(s):  
Improve Patient Safety ◽  
Rapid Development ◽  
Strong Support ◽  
Semantic Segmentation ◽  
Identification Accuracy ◽  
Network Module ◽  
Tongue Diagnosis ◽  
Medical Quality ◽  
Computer Aided ◽  
Fissured Tongue

The rapid development of intelligent manufacturing provides strong support for the intelligent medical service ecosystem. Researchers are committed to building Wise Information Technology of 120 (WIT 120) for residents and medical personnel with the concept of simple smart medical care and through core technologies such as Internet of Things, Big Data Analytics, Artificial Intelligence, and microservice framework, to improve patient safety, medical quality, clinical efficiency, and operational benefits. Among them, how to use computers and deep learning technology to assist in the diagnosis of tongue images and realize intelligent tongue diagnosis has become a major trend. Tongue crack is an important feature of tongue states. Not only does change of tongue crack states reflect objectively and accurately changed circumstances of some typical diseases and TCM syndrome but also semantic segmentation of fissured tongue can combine the other features of tongue states to further improve tongue diagnosis systems’ identification accuracy. Although computer tongue diagnosis technology has made great progress, there are few studies on the fissured tongue, and most of them focus on the analysis of tongue coating and body. In this paper, we do systematic and in-depth researches and propose an improved U-Net network for image semantic segmentation of fissured tongue. By introducing the Global Convolution Network module into the encoder part of U-Net, it solves the problem that the encoder part is relatively simple and cannot extract relatively abstract high-level semantic features. Finally, the method is verified by experiments. The improved U-Net network has a better segmentation effect and higher segmentation accuracy for fissured tongue image dataset. It can be used to design a computer-aided tongue diagnosis system.

scholarly journals Learning the ““Special Note””: Evidence for a Critical Period for Absolute Pitch Acquisition

2003 ◽  
Vol 21 (1) ◽  
pp. 119-127 ◽  
Author(s):  
FRANK A. RUSSO ◽  
DEBORAH L. WINDELL ◽  
LOLA L. CUDDY
Keyword(s):  
Critical Period ◽  
Strong Support ◽  
Absolute Pitch ◽  
Identification Accuracy ◽  
Single Tone ◽  
The Third

Children (3––6 years old) and adults were trained for 6 weeks to identify a single tone, C5. Test sessions, held at the end of each week, had participants identify C5 within a set of seven alternative tones. By the third week of training, identification accuracy of children 5––6 years old surpassed the accuracies of children 3––4 years old and adults. Combined with an analysis of perceptual strategies, the data provide strong support for a critical period for absolute pitch acquisition. Received July 12, 2003, accepted August 1,2003

scholarly journals Use of Reverse Engineering and Additive Printing in the Reconstruction of Gears

2020 ◽  
Vol 3 (1) ◽  
pp. 274-284
Author(s):  
Dorota Palka
Keyword(s):  
3D Printing ◽  
Reverse Engineering ◽  
Fused Deposition Modeling ◽  
Rapid Development ◽  
Spare Parts ◽  
Common Element ◽  
Practical Application ◽  
Computer Aided Manufacturing ◽  
Fused Deposition ◽  
Computer Aided

AbstractDespite the very rapid technological development, the general concept of mechanical devices has not changed. Still, the most common element of these devices are gears, whose range of use is very wide. There are both technological and historical considerations for the reconstruction of gears and other elements. In particular, this applies to spare parts for technical facilities that are not available on the market or service costs are too high. Contemporary reconstruction is called Reverse Engineering, which offers tools that allow transformation of an existing object through a virtual model into the final real product. Modern production engineering is based on innovative CAD – Computer Aided Designed design methods and computer-aided manufacturing technologies, CAM – Computer Aided Manufacturing. The rapid development of 3D CAD systems has led to the development of solutions to obtain the designed object, already at the development stage. Such a solution is the Rapid Prototyping method, designed for fast, precise and repeatable production of machine components. Widespread use and growing interest in the use of additive printing influenced the development of this technology. The purpose of the article is to present the practical application of the Reverse Engineering method and 3D printing in the reconstruction of gears. The object of research is the real gear, which has been reconstructed using Reverse Engineering and 3D printing. The article presents the basic assumptions of the methods used and the methodology for conducting reconstruction work. FDM (Fused Deposition Modeling) technology was used for the research. The results obtained are a real example of the practical application of the presented methods. At the same time, they create great opportunities for their wider use.

scholarly journals Computer Numerically Controlled Drawing Robot Based on Computer-Aided Design

2021 ◽  
Author(s):  
Antor Mahamudul Hashan ◽  
Abdullah Haidari ◽  
Srishti Saha ◽  
Titas Paul
Keyword(s):  
Open Source ◽  
Computer Aided Design ◽  
Low Cost ◽  
Rapid Development ◽  
Main Idea ◽  
Numerical Control ◽  
Computer Aided ◽  
Complex Circuits ◽  
Open Source Hardware ◽  
Aided Design

Due to the rapid development of technology, the use of numerically controlled machines in the industry is increasing. The main idea behind this paper is computer-aided design (CAD) based low-cost computer numerical control 2D drawing robot that can accurately draw complex circuits, diagrams, logos, etc. The system is created using open-source hardware and software, which makes it available at a low cost. The open-source LibreCAD application has been used for computer-aided design. Geometric data of a CAD model is converted to coordinate points using the python-based F-Engrave application. This system uses the Arduino UNO board as a signal generator of the universal g-code sender without compromising the performance. The proposed drawing robot is designed as a low-cost robot for educational purposes and aims to increase the student's interest in robotics and computer-aided design (CAD) skills to the next level. The drawing robot structure has been developed, and it meets the requirements of low cost with satisfactory experimental results.

scholarly journals A Modeling Method for Automatic Extraction of Offshore Aquaculture Zones Based on Semantic Segmentation

2020 ◽  
Vol 9 (3) ◽  
pp. 145 ◽  
Author(s):  
Baikai Sui ◽  
Tao Jiang ◽  
Zhen Zhang ◽  
Xinliang Pan ◽  
Chenxi Liu
Keyword(s):  
Recognition Rate ◽  
Semantic Segmentation ◽  
Recognition Algorithm ◽  
Identification Accuracy ◽  
Generative Adversarial Networks ◽  
Automatic Extraction ◽  
Large Area ◽  
Marine Aquaculture ◽  
Floating Raft ◽  
Offshore Aquaculture

Monitoring of offshore aquaculture zones is important to marine ecological environment protection and maritime safety and security. Remote sensing technology has the advantages of large-area simultaneous observation and strong timeliness, which provide normalized monitoring of marine aquaculture zones. Aiming at the problems of weak generalization ability and low recognition rate in weak signal environments of traditional target recognition algorithm, this paper proposes a method for automatic extraction of offshore fish cage and floating raft aquaculture zones based on semantic segmentation. This method uses Generative Adversarial Networks to expand the data to compensate for the lack of training samples, and uses ratio of green band to red band (G/R) instead of red band to enhance the characteristics of aquaculture spectral information, combined with atrous convolution and atrous space pyramid pooling to enhance the context semantic information, to extract and identify two types of offshore fish cage zones and floating raft aquaculture zones. The experiment is carried out in the eastern coastal waters of Shandong Province, China, and the overall identification accuracy of the two types of aquaculture zones can reach 94.8%. The results show that the method proposed in this paper can realize high-precision extraction both of offshore fish cage and floating raft aquaculture zones.

scholarly journals Voxel-based 3D Point Cloud Semantic Segmentation: Unsupervised Geometric and Relationship Featuring vs Deep Learning Methods

2019 ◽  
Vol 8 (5) ◽  
pp. 213 ◽  
Author(s):  
Florent Poux ◽  
Roland Billen
Keyword(s):  
Deep Learning ◽  
Point Cloud ◽  
Semantic Representation ◽  
Structural Connectivity ◽  
Three Dimensional ◽  
Strong Support ◽  
Semantic Segmentation ◽  
Point Clouds ◽  
Learning Methods ◽  
Cloud Data

Automation in point cloud data processing is central in knowledge discovery within decision-making systems. The definition of relevant features is often key for segmentation and classification, with automated workflows presenting the main challenges. In this paper, we propose a voxel-based feature engineering that better characterize point clusters and provide strong support to supervised or unsupervised classification. We provide different feature generalization levels to permit interoperable frameworks. First, we recommend a shape-based feature set (SF1) that only leverages the raw X, Y, Z attributes of any point cloud. Afterwards, we derive relationship and topology between voxel entities to obtain a three-dimensional (3D) structural connectivity feature set (SF2). Finally, we provide a knowledge-based decision tree to permit infrastructure-related classification. We study SF1/SF2 synergy on a new semantic segmentation framework for the constitution of a higher semantic representation of point clouds in relevant clusters. Finally, we benchmark the approach against novel and best-performing deep-learning methods while using the full S3DIS dataset. We highlight good performances, easy-integration, and high F1-score (> 85%) for planar-dominant classes that are comparable to state-of-the-art deep learning.

RESEARCH ON COLLABORATIVE DESIGN SOFTWARE INTEGRATION BASED ON SOA

2008 ◽  
Vol 07 (01) ◽  
pp. 91-94 ◽  
Author(s):  
YAOGUANG HU ◽  
RAO WANG
Keyword(s):  
Enterprise Resource Planning ◽  
Collaborative Design ◽  
Computer Aided Design ◽  
Rapid Development ◽  
Resource Planning ◽  
Heterogeneous Environment ◽  
Software Integration ◽  
Cooperative Research ◽  
Computer Aided ◽  
Design Software

With the rapid development of economic globalization, more and more complex products have to be designed by the cooperation of the designers in different geographic locations. The effective sharing and deployment of collaborative design software are of great significance to enhance the capability of cooperative research and development of products. To solve the problem of software integration for collaborative design in the distributed and heterogeneous environment, a distributed software integration framework for collaborative product design based on Service Oriented Architecture (SOA) was proposed. Based on Web Service technology, a collaborative design platform was built, which encapsulates the functions of Computer Aided Design (CAD), Computer Aided Engineering (CAE), Product Data Management (PDM) and Enterprise Resource Planning (ERP) software to integrate distributed collaborative design software in heterogeneous environment.

Study on Integration of Computer Aided Process Planning System and PDM System

2013 ◽  
Vol 416-417 ◽  
pp. 919-924
Author(s):  
Hong Xia Yang ◽  
Wei Dong Chen ◽  
Hua Sheng Feng
Keyword(s):  
Product Design ◽  
Process Planning ◽  
Rapid Development ◽  
Computer Integrated Manufacturing ◽  
Planning System ◽  
Strong Basis ◽  
Computer Technique ◽  
Computer Aided Process Planning ◽  
Process Planning System ◽  
Computer Aided

With the rapid development of modern science and technology and computer technique, modern enterprise faces new challenges for product design, production, management, market planning and sales. The products of enterprises develop towards diversification, serialization and individualization. Technological design is important in product manufacturing process and is a bond of product design and actual production. Therefore, modern enterprises need to develop computer aided process planning system to improve the quality and efficiency of process design of the enterprise. Starting from the requirements of enterprises on computer aided process planning systems and combining the existing Web technology, the paper proposes the study on integration of computer aided process planning system and PDM system. The development and application of the system not only provides strong support for enterprises realizing rapid design and manufacture and strong basis for enterprises realizing computer integrated manufacturing system, but also makes informationization degree, economic benefit and social benefit of enterprises improve greatly.

On Optimization of Non-Intelligence Factors in College English Teaching in Computer-Aided Language Learning Environments

2014 ◽  
Vol 644-650 ◽  
pp. 6124-6127
Author(s):  
Jing Wang
Keyword(s):  
Language Learning ◽  
Learning Environments ◽  
Rapid Development ◽  
Traditional Teaching ◽  
Training Methods ◽  
College English ◽  
English Teaching ◽  
Teaching College ◽  
Computer Aided ◽  
New Perspective

With the rapid development of computer technology, combined with the features of computer-aided English teaching, college English teaching has tremendously challenged the traditional teaching mode. This change, however, provides a new perspective for the research of non-intelligence factors in students’ learning process. Based on the definition and importance of non-intelligence factors, this paper briefly discusses the cultivation of college students’ non-intelligence factors in the computer-aided language learning environments and put forward some suggestions to optimize the non-intelligence factors from the perspectives of interest in learning, communication awareness and teamwork ability in order to update our teaching idea and improve the quality of college English teaching and training methods.

scholarly journals Bias Evaluation of the Accuracy of Two Extraoral Scanners and an Intraoral Scanner Based on ADA Standards

Scanning ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Naiyu Cui ◽  
Jiayin Wang ◽  
Xingyu Hou ◽  
Shixun Sun ◽  
Qixuan Huang ◽  
...  
Keyword(s):  
Computer Aided Design ◽  
Rapid Development ◽  
Subsequent Treatment ◽  
National Standard ◽  
Mean Deviation ◽  
Intraoral Scanner ◽  
Point Matching ◽  
Three Samples ◽  
Computer Aided ◽  
Measuring Machine

The spread and application of computer-aided design/computer-aided manufacturing (CAD/CAM) technology have contributed to the rapid development of digitalization in dentistry. The accuracy of scan results is closely related to the devising subsequent treatment plans and outcomes. Professional standards for evaluating scanners are specified in the American National Standard/American Dental Association Standard 132 (ANSI/ADA No. 132). The aims of this study were to use the three samples mentioned in ANSI/ADA No. 132 and evaluate the accuracy and reproducibility of two extraoral scanners and an intraoral scanner based on the inspection standards recommended by ANSI/ADA No. 132. In this study, two trained operators used two extraoral scanners (E4, 3Shape, Denmark & SHINING DS100+, Shining, China) and an intraoral scanner (TRIOS SERIES3, 3Shape, Denmark) to perform 30 scans of each of the three samples at a temperature of 25 ± 2 ° C and export standard tessellation language files and used reverse engineering software to perform measurements and iterative nearest point matching experiments. The measured values obtained were compared with the reference values measured by a coordinate measuring machine (NC8107, Leader Metrology, USA). We performed a normal distribution test (Shapiro-Wilk test), the nonparametric Kruskal-Wallis test, and an independent-samples t -test to analyze the reproducibility of each scan for different models. The experimental results indicate that the trueness and precision of the two extraoral scanners and the intraoral scanner had a slight mean deviation. The trueness and precision of the three scanners on the curved surface and groove areas are poor. The accuracy and reproducibility of E4 outperformed SHINING and TRIOS. The iterative closest point matching experiment also showed good matching results. The two extraoral scanners and the intraoral scanner in this study can meet the basic clinical requirements in terms of accuracy, and we hope that digital technology will be more widely used in dentistry in the future.

scholarly journals GLACIER IDENTIFICATION FROM LANDSAT8 OLI IMAGERY USING DEEP U-NET

2020 ◽  
Vol V-3-2020 ◽  
pp. 381-386
Author(s):  
Q. He ◽  
Z. Zhang ◽  
G. Ma ◽  
J. Wu
Keyword(s):  
Regional Climate ◽  
Spectral Characteristics ◽  
Semantic Segmentation ◽  
Identification Accuracy ◽  
Landsat 8 ◽  
Landsat 8 Oli ◽  
Visual Interpretation ◽  
Identification Methods ◽  
Identification Method ◽  
Data Source

Abstract. Glacier is one of the clearest signal of climate change, and its changes have important effects on regional climate and water resources. Glacier identification is the basic of glacial changes research. Traditional remote sensing glacier identification methods usually perform simple bands calculation based on the spectral characteristics of glacier. The identification results are greatly affected by threshold segmentation. In addition, there is a misclassification of water body and glacier. As a simple and efficient semantic segmentation network, U-Net has been widely used in many fields of image processing. This paper performs an improved semantic segmentation network Deep U-Net for glacier identification using Landsat 8 OLI image as the data source, and compares it with the traditional NDSI glacier identification method. The identification results are validated by the glacier label data produced by visual interpretation. The results indicate that the proposed method achieves an identification accuracy of 97.27%, which is higher than the NDSI glacier identification method. It can effectively exclude the interference of water bodies on glacier identification, and has a higher degree of automation.

Sign in / Sign up

Export Citation Format

Share Document