CAD System Research Articles

Intelligent Pattern Identification and Design of Garment CAD System Based on Computer Vision and Neural Networks

Intelligent Pattern Identification and Design of Garment CAD System Based on Computer Vision and Neural Networks

Genetic algorithm based detection of breast cancer using least square-support vector machine classifier

Breast tumors are a dangerous disease among women worldwide. They are the second leading cause of death among all forms of cancers in women. Their early detection is critical to increasing the survival rate of women. Mammography is a reliable screening technique in the early detection of abnormal breast tissue severity. Radiologist abnormalities in the breast tissue, radiologists employ mammography. However, detecting breast abnormalities through digital diagnostic techniques by a radiologist could be time consuming. Consequently, computerized studying of digital mammography has emerged via the development of CAD systems. Several CAD systems have been developed for breast cancer detection. However, obtaining a satisfactory performance of CAD systems is a challenging task. We propose a CAD architecture for the classification of breast tissues as either benign or malignant using an LS-SVM classifier with various kernels namely linear, quadratic, polynomial, MLP, and RBF kernels. From the experimental outputs, it is clear that GA based LS-SVM classifier with RBF kernel outputs classification accuracy of 94.59% for normal/abnormal case classification is better, when it is compared with all other kernels. It is also stated that GA based LS-SVM classifier with RBF kernel produces a better classification accuracy of 98.26% for benign/malignant case classification when it is compared with other reported works.

DEEP NETWORK-BASED METHOD AND SOFTWARE FOR SMALL SAMPLE BIOMEDICAL IMAGE GENERATION AND CLASSIFICATION

Context. The authors of the article investigated the problem of generating and classifying breast cancer histological images. The widespread incidence of breast cancer explains the problem’s relevance. The automated diagnosing procedure saves time and eliminates the subjective aspect. The study’s findings can be applied to cancer CAD systems.
 Objective. The purpose of the study is to develop a deep neural network-based method and software tool for generating and classifying histological images in order to increase classification accuracy.
 Method. The method of histological image generation and classification was developed in the research study. This method employs CNN and GAN. To improve the classification accuracy, the initial image sample was expanded using GAN.
 Results. The computer research of the developed method of image generation and classification was conducted on the basis of the dataset located on the Zenodo platform. Light microscopy served as the basis for obtaining the image. The dataset contained three classes of G1, G2, and G3 breast cancer histological images. Based on the developed method, the accuracy of image classification was 96%. This is a higher classification accuracy compared to existing models such as AlexNet, LeNet5, and VGG16. The software module can be integrated into CAD.
 Conclusions. The developed method of generating and classifying images is the basis of the software module. The software module can be integrated into CAD.

Качественная модификация геометрически ориентированных методов построения пространственных кривых в C3D FairCurveModeler

The article provides a detailed algorithm for improving the C3D FairCurveModeler commands for constructing a class F spatial curve with approximation by a rational cubic spline Bezier curve (NURBzS-curve) and with approximation by a highdegree B-spline curve. The improvement is achieved by optimizing the structure of the Hermite spatial Geometric Determinant when defining it on a spatial virtual curve (V-curve) created on a set of double-tap conical curves. The structure of the Hermite Geometric Determinant is improved by changing the direction of the tangents, taking into account the spatial directions of the tangents at the end points of the conic segments at the step of constructing the set of double-tap conical curves. To demonstrate the modified method, the work shows 1) Improving the quality of a conical spiral modeled by the regular _Helix command of CAD systems ZWCAD, BricsCAD, AutoCAD by using the C3D FairCurveModeler command for creating a NURBzS-curve. 2) Construction of a B-spline curve of the 8th degree on the points of a conical spiral by the C3D FairCurveModeler command and comparison with similar constructions in the CAD systems 'Rhino Ceros D', 'Alias Design Studio', NX which declare the construction of high quality curves (class A).

Research on Space Cam Automation Design and Manufacturing Scheme Based on CAD and CAM Systems

Research on Space Cam Automation Design and Manufacturing Scheme Based on CAD and CAM Systems

Enhanced Design Automation for Hydraulic Manifolds Produced Using Additive Manufacturing

Complex, highly functional components such as hydraulic manifolds can be produced using metal additive manufacturing (AM). The design process is a major challenge in the development of AM components that exploit this potential. Since traditional CAD systems are not made to efficiently create highly complex designs, new approaches to the design process are required. Design Automation (DA) and Knowledge-Based Engineering (KBE) are approaches that can be used to create designs and implement design changes faster and improve functionality. For the application of fluid components, KBE design workflows were developed which enable the automated generation of AM manifolds.However, these workflows have some limitations that need to be improved to provide a flexible design tool that enables users to automatically create geometries that meet all requirements. This paper shows how the workflows have been improved by introducing two new features. First, the object-oriented input format presents a new approach to how the information of a hydraulic circuit diagram can be processed to start the workflows. This is done through a component library that contains a selection of flow components providing all information and geometries of one component, a 3D layout assembly to orient the relevant components in space, and a connectivity matrix that defines the connection through flow channels for the manifold. Second, the bending radius constraint allows users to define a radius that the centerline of a flow channel should not undergo along the whole path. The new features are presented in detail in this paper. Further, the advantages are shown and compared to the previously published workflows in a case study. This work lays the foundation for future work that has the aim to fully automate the design process by only taking a hydraulic circuit diagram as an input and providing all required manufacturing files as an output.

Machine learning-based CAD system for thyroid tumour characterisation using ultrasound images

Machine learning-based CAD system for thyroid tumour characterisation using ultrasound images

Neural Network Emulators Towards a CAD System for Neural Architectures

Neural Network Emulators Towards a CAD System for Neural Architectures

Theoretical and Methodological Bases for Implementing BIM Technologies in Construction Companies: Essence. Characteristics. Economic Efficiency

The theoretical concepts and methodological characteristics of implementing BIM technologies in construction companies have been defined. BIM is an information modelling of a construction object, which involves the collection and processing of all information about a building with all its interconnections and dependencies, when the building is considered as a single object. It should be noted that when analysing the definitions of BIM, it is possible to come to the conclusion that it is necessary to make a clearer distinction as to what type of object is meant. Thus, there are some definitions that refer directly to the building model (Building Information Model), the building lifecycle process (Building Information Modelling) and the entire investment and construction process system (Building Information Management). It is pointed out that the traditional approach to design is based on two-dimensional models – plans, drawings and paper documentation. In contrast, Building Information Modelling (BIM) technologies add new aspects – construction plans, time and costs. These can be presented in any convenient form using an information model of the object in virtual reality. The short and long term benefits of using BIM technology in the construction industry are analysed in this article. It was noted that BIM goes beyond standard CAD systems as it allows to create three-dimensional models, known as 3D models, as well as models defined as 4D, 5D, 6D and even 7D. An automated project management system is described on the basis of three elements: the structure of project activities, the structure of resources and the matrix of resource allocation to project activities. In an automated system that ensures effective project planning, control and execution, these elements form a project management model. However, effective cost management throughout the project lifecycle is crucial to the successful implementation of the information system and maximising its benefits to the organisation. According to the authors, the overall cost-effectiveness factor of using BIM technology is determined by several factors: reduction of the overall level of project risks due to proven, accurate and optimised design solutions for engineering systems; reduction of construction time and construction costs as a result of reducing the number of errors in installation and use of materials; improvement of the quality and efficiency of building use will help reduce the negative impact on the environment. The conclusions emphasise that the successful implementation of BIM technologies in a construction company can lead to economic efficiency through an increase in labour productivity, a reduction in the cost of resources and materials, as well as an improvement in the quality and safety of construction processes. In addition, using BIM can help improve the quality of buildings and optimise the use of resources, helping to reduce environmental impact. In fact, BIM is a significant cost driver through this comprehensive approach to project management in construction.

Development of a voxel-based CAD system for upstream life cycle design and its application to LCA

The comprehensive design of product life cycles is a promising approach to realizing circular manufacturing systems. However, design support systems that can be used for the life cycle design during upstream stages have not been established. The purpose of this study is to develop an easy-to-use CAD system for the early stages of product life cycle design. The system supports creating a product model in voxel format and a life cycle process model as a process network in an integrated manner. The voxel models make it easy to create the rough shape of products and quantify the mass of each component for LCA. An LCD monitor's life cycle was designed using the proposed CAD tool. Fourteen design candidates were created and LCA was performed to compare the designs from the perspective of life cycle environmental impact. Through the case study, we confirmed that the tool is a practical system that can quantitatively examine what design improvements contributed to the reduction of environmental impact at an early design stage before creating detailed 3D-CAD models.

IMPLEMENTATION OF BUILDING INFORMATION MODELING (BIM) PRINCIPLES AND INFORMATION TECHNOLOGIES FOR STRUCTURAL ANALYSIS IN THE DESIGN OF REINFORCED CONCRETE AND СOMPOSITE STEEL-REINFORCED CONCRETE FRAMED BUILDINGS

The development of Building Information Modeling (BIM) in historical context hasbeen analyzed, including CAD systems for 2D and 3D modeling, considered predecessors of modern BIM systems, parametric 3D modeling systems, the use of information technologies for structural analysis, issues of combined use of BIM systems and information technologies for structural analysis.Using the example of a 20-story frame-monolithic residential building, the sequence of creating a building information model in PC SAPPHIRE, forming a calculation model of the reinforced concrete frame in PC Lira-SAPR through direct integration of the specified software complexes is demonstrated. The issues of preparing a building information model in PC SAPPHIRE for transfer to PCLira-SAPR are discussed, as well as the issues of refining the calculation model in PC Lira-SAPR, including assigning stiffness and load characteristics, and selecting reinforcement for structural elements. Тhe sequence of creating a calculation model of a steel-reinforced concrete frame for three options of steel-reinforced concrete columns is considered: tubular concrete columns; tubular concrete columns with rigid reinforcement by cross steel strips; tubular concrete columns with rigid reinforcement by cross double T-sections.For the selected most loaded columns, mainly on the first floor, operating under the conditions of central or off-center compression, the sequence of forming refined calculation models is demonstratedby modeling these columns and areas of their connection to the floor slabs with 3D finite elements.Equivalent stress iso-surfaces are provided, as well as separate iso-surfaces of equivalent stresses of the steel shell and separately the concrete core of the columns

MODELLING AND MANUFACTURING OF TECHNOLOGICAL EQUIPMENT AND COMPLEX ELEMENTS OF A LOOM USING ADDITIVE TECHNOLOGIES

Equipment for three-dimensional orthogonal weaving has significant differences from looms used to obtain single-layer fabrics. At the same time, many structural elements are in the debugging stage, which requires frequent changes in their shape, which is associated with the refinement of the process parameters. The use of traditional technologies such as sheet stamping to obtain such parts is impractical due to the low serialisation of parts and complex shape. The way out, in this case, is the widespread use of additive technologies in this case. In this case, the parts are made of plastic. The most common materials are ABS; petg; PVA. Compared to steels, they have very low mechanical characteristics such as yield strength, elastic modulus, etc. Therefore, their use for the manufacture of tooling should be accompanied by appropriate design calculations that can be performed in one of the common CAD systems.

Интеграция программного продукта Calibre в среду Cadence Virtuoso и повышение интеллектуальных свойств САПР проектировании микросхем

The article discusses the technology for integrating Caliber into the Cadence Virtuoso environment and describes the impact of this integration on the productivity of engineers. The possibility of ensuring optimal interaction between developers and increasing the overall efficiency of the design team is considered, leading to end-to-end design optimization. The integration of Caliber and Cadence Virtuoso represents an important step in Electronic Design Development (EDA) and can solve a number of problems while improving the efficiency of the verification and analysis process. Here are a few aspects that demonstrate the need and benefits of such integration, data interoperability, ensuring that information received from Virtuoso can be used correctly and efficiently in Caliber and vice versa, automating the data transfer process and performing verification, speeding up all development cycles, verification can carry out, even in the early stages of design, smoother interaction between different teams using Virtuoso and Caliber. In the second part of the article, physical verification and extraction of the project is carried out using the graphical interface of the Mentor Graphics Caliber CAD system, where the topology is checked for compliance with the CTO (DRC check). For the DRC check of a project, check is performed using the Caliber application. Using Caliber in Cadence Virtuoso allows for more accurate verification of designed electronic circuits and microchips. Caliber provides deeper analysis of physical parameters such as layer compatibility, electrical and geometric rules, leading to the identification of potential problems earlier in development.

Minimally processed recycled yttria-stabilized tetragonal zirconia for dental applications: Effect of sintering temperature on glass infiltration

This study aimed to develop a recycling process for the remnants of milled 3Y-TZP and enhance their properties using glass infiltration. 3Y-TZP powder was gathered from the vacuum system of CAD–CAM milling equipment, calcined and sieved (x < 75 μm). One hundred twenty discs were fabricated and pre-sintered at 1000 °C/h. These specimens were then divided into four groups, categorized by glass infiltration (non-infiltrated [Zr] or glass-infiltrated [Zr-G]) and sintering temperature (1450 °C [Zr-1450] or 1550 °C [Zr-1550]/2h). After sintering, the specimens were characterized by X-Ray Diffraction (XRD), relative density measurement, and scanning electron microscopy and energy dispersive spectroscopy (SEM-EDS). The biaxial flexural strength test was performed according to the ISO 6872 and followed by fractographic analysis. Subsequent results were analyzed using Weibull statistics. Relative density values of the sintered specimens from Zr-1450 and Zr-1550 groups were 86.7 ± 1.5% and 92.2 ± 1.7%, respectively. Particle size distribution revealed particles within the range of 0.1–100 μm. XRD analysis highlighted the presence of the ZrO2-tetragonal in both the Zr-1450 and Zr-1550 groups. Glass infiltration, however, led to the formation of the ZrO2-monoclinic of 9.84% (Zr-1450-G) and 18.34% (Zr-1550-G). SEM micrographs demonstrated similar microstructural characteristics for Zr-1450 and Zr-1550, whereas the glass-infiltrated groups exhibited comparable infiltration patterns. The highest characteristic strength was observed in the glass-infiltrated groups. Fractographic analyses suggested that fracture origins were related to defects on the tensile side, which propagated to the compression side of the samples. Both the sintering temperature and glass infiltration significantly influenced the mechanical properties of the 3Y-TZP recycled.

CAD system for intelligent grading of COVID-19 severity with green computing and low carbon footprint analysis

CAD system for intelligent grading of COVID-19 severity with green computing and low carbon footprint analysis

An Efficient FrWT and IPCA Tools for an Automated Healthcare CAD System

An Efficient FrWT and IPCA Tools for an Automated Healthcare CAD System

CAD System Design for Pituitary Tumor Classification based on Transfer Learning Technique.

A brain tumor is an asymmetrical expansion by cells inevitably emulating amid them. Image processing is a vibrant research area where the handing out of the image in the medical field is an exceedingly tricky field. In this paper, an expert algorithm is suggested for the detection of pituitary brain tumors from MR images. The preprocessing techniques (smoothing, edge detection, filtering) and segmentation techniques (watershed) are applied to the online data set. The transfer learning technique is used as a classifier whose performance is measured in terms of classification accuracy. Resnet 50, Inception V3VGG16, and VGG19 models are used as classification algorithms. The proposed model is validated using different machine learning techniques considering hybrid features. 96% accuracy was obtained employing the Inception V3 model & 95% accuracy was attained using hybrid GLDS and GLCM features employing Support Vector Machine algorithm while 93% was attained using Probabilistic Neural Network and k Nearest Neighbor techniques. Computer-aided systems gave much faster and more accurate results than image processing techniques.1.0% accuracy improvement was observed while using Inception V3 over GLDS + GLCM + SVM and 2.1% accuracy improvement using GLDS + GLCM + SVM over GLDS + GLCM + kNN.

Hepatocellular Carcinoma Diagnosis Based on Ultrasound Images Using Feature Selection Techniques and K-nearest Neighbor Classifier

Background: Liver cancer is one of the most common types of cancer, in which early detection plays a significant role in preventing progression and reducing mortality. Ultrasound is one of the methods of liver examination recommended by guidelines due to its performance in detecting focal liver lesions. These small lesions may be missed in the early stages or diagnosed only when the prognosis is poor. Objectives: This study aimed to implement the best classification model for two liver stages by extracting optimal feature subsets to be used in computer-aided diagnosis systems (CAD). Methods: The model classifies the liver into two stages using B-mode ultrasound images of the liver. It involves extracting statistical texture features utilizing discrete wavelet transform (DWT) and gray level co-occurrence matrix (GLCM). This study applied two feature selection methods: t-test and sequential forward floating selection (SFFS). The subset of selected features was presented to the k-nearest neighbor classifier for incorporation into a CAD system. Results: The accuracy, sensitivity, and specificity of the k-NN classifier were 98.75%, 98.82%, and 99.1%, respectively. Conclusions: Image analysis approaches were successfully performed to extract and select useful features. Therefore, this model is recommended for classifying two liver stages, normal and HCC.

GMRLNet: A graph-based manifold regularization learning framework for placental insufficiency diagnosis on incomplete multimodal ultrasound data.

Multimodal analysis of placental ultrasound (US) and microflow imaging (MFI) could greatly aid in the early diagnosis and interventional treatment of placental insufficiency (PI), ensuring a normal pregnancy. Existing multimodal analysis methods have weaknesses in multimodal feature representation and modal knowledge definitions and fail on incomplete datasets with unpaired multimodal samples. To address these challenges and efficiently leverage the incomplete multimodal dataset for accurate PI diagnosis, we propose a novel graph-based manifold regularization learning (MRL) framework named GMRLNet. It takes US and MFI images as input and exploits their modality-shared and modality-specific information for optimal multimodal feature representation. Specifically, a graph convolutional-based shared and specific transfer network (GSSTN) is designed to explore intra-modal feature associations, thus decoupling each modal input into interpretable shared and specific spaces. For unimodal knowledge definitions, graph-based manifold knowledge is introduced to describe the sample-level feature representation, local inter-sample relations, and global data distribution of each modality. Then, an MRL paradigm is designed for inter-modal manifold knowledge transfer to obtain effective cross-modal feature representations. Furthermore, MRL transfers the knowledge between both paired and unpaired data for robust learning on incomplete datasets. Experiments were conducted on two clinical datasets to validate the PI classification performance and generalization of GMRLNet. State-of-the-art comparisons show the higher accuracy of GMRLNet on incomplete datasets. Our method achieves 0.913 AUC and 0.904 balanced accuracy (bACC) for paired US and MFI images, as well as 0.906 AUC and 0.888 bACC for unimodal US images, illustrating its application potential in PI CAD systems.

Post-processing feature-mapping topology optimisation designs towards feature-based CAD processing

Feature-mapping (FM) optimisation frameworks have received much attention for structural topology optimisation with explicit geometric parameters. This paper presents a methodology for constructing parametric feature-based CAD models from designs generated using Moving Morphable Components (MMC). Emphasis is placed on constructing feature-based CAD models that conform to conventional modelling practices, where individual parameterised features are modelled using feature templates and united through Boolean union operations. This involves the use of algorithms to facilitate feature clean-up and identify connexions between features. The progression through several examples demonstrates how the developed algorithms can realise a feature-based CAD model from the results of an FM optimisation. Integration with a commercial CAD system provides a wide range of modelling capabilities to the designer for downstream design tasks.