scholarly journals An Efficient ensemble of Brain Tumour Segmentation and Classification using Machine Learning and Deep Learning based Inception Networks

2021 ◽  
Vol 12 (2) ◽  
pp. 987-998
Author(s):  
R. Aruna Kirithika, Et. al.
Keyword(s):  
Deep Learning ◽  
Computer Aided Design ◽  
Tumour Segmentation ◽  
Area Of Interest ◽  
Proposed Model ◽  
Diagnosis And Classification ◽  
Almost All ◽  
Aided Design ◽  
Brain Tumour Segmentation

In recent times, Brain Tumor (BT) has become a common phenomenon affecting almost all age group of people. Identification of this deadly disease using computer tomography, magnetic resonance imaging are very popular now-a-days. Developing a Computer Aided Design (CAD) tool for diagnosis and classification of BT has become vital. This paper focuses on designing a tool for diagnosis and classification of BT using Deep Learning (DL) models, which involves a series of steps via acquiring (CT) image, pre-processing, segmenting and classifying to identify the type of tumor using SIFT with DL based Inception network model. The proposed model uses fuzzy C means algorithm for segmenting area of interest from the BT image acquired. Techniques like Gaussian Naïve Bayes (GNB) and logistic regression (LR) are used for classification processes. To ascertain all the techniques for its efficiency a benchmark dataset was used. The simulation outcome ensured that the performance of the proposed method with maximum sensitivity of 100%, specificity of 97.41% and accuracy of 97.96%.

scholarly journals Bidirectional ConvLSTMXNet for Brain Tumor Segmentation of MR Images

2021 ◽  
Vol 15 (1) ◽  
pp. 37-42
Author(s):  
M. Ravikumar ◽  
B.J. Shivaprasad
Keyword(s):  
Deep Learning ◽  
Brain Tumor ◽  
Tumor Segmentation ◽  
Mr Images ◽  
Mr Image ◽  
Brain Tumor Segmentation ◽  
Data Set ◽  
Tumour Segmentation ◽  
Brain Tumour Segmentation

In recent years, deep learning based networks have achieved good performance in brain tumour segmentation of MR Image. Among the existing networks, U-Net has been successfully applied. In this paper, it is propose deep-learning based Bidirectional Convolutional LSTM XNet (BConvLSTMXNet) for segmentation of brain tumor and using GoogLeNet classify tumor & non-tumor. Evaluated on BRATS-2019 data-set and the results are obtained for classification of tumor and non-tumor with Accuracy: 0.91, Precision: 0.95, Recall: 1.00 & F1-Score: 0.92. Similarly for segmentation of brain tumor obtained Accuracy: 0.99, Specificity: 0.98, Sensitivity: 0.91, Precision: 0.91 & F1-Score: 0.88.

Product Model Preparation and Processing for Micromanufacturing

2008 ◽  
Vol 8 (2) ◽  
Author(s):  
Chao-Yaug Liao ◽  
Jean-Claude Léon ◽  
Cédric Masclet ◽  
Michel Bouriau ◽  
Patrice L. Baldeck ◽  
...  
Keyword(s):  
Laser Beam ◽  
Computer Aided Design ◽  
Welding Process ◽  
Product Model ◽  
Processing Scheme ◽  
Proposed Model ◽  
Layer Manufacturing ◽  
Manifold Models ◽  
Model Preparation ◽  
Aided Design

Based on the two-photon polymerization technique, an analysis of product shapes is performed so that their digital manufacturing models can be efficiently processed for micromanufacture. To describe microstructures, this analysis shows that nonmanifold models are of interest. These models can be intuitively understood as combinations of wires, surfaces, and volumes. Minimum acceptable wall thickness, wire dimension, and laser density of energy are among the elements justifying this category of models. Taking into account this requirement, a model preparation and processing scheme is proposed that widens the laser beam trajectories with a concept of extended layer manufacturing technique. A tessellation process suited for non-manifold models has been developed for computer-aided design models imported from standard for the exchange of product files. After tessellation, several polyhedral subdomains form a nonmanifold polyhedron. To plan the trajectories of the laser beam, adaptive slicing and global 3D hatching processes as well as a “welding” process (for joining subdomains of different dimensionality) have been combined. Finally, two nonmanifold microstructures are fabricated according to the proposed model preparation and processing scheme.

scholarly journals Deep Learning Based Depthwise Separable Model For Effective Diagnosis And Classification of Lung Ct Images

2019 ◽  
Vol 9 (1) ◽  
pp. 1808-1819 ◽  
Keyword(s):  
Lung Cancer ◽  
Feature Extraction ◽  
Deep Learning ◽  
Noise Removal ◽  
Ct Images ◽  
Classification Model ◽  
Diagnosis And Classification ◽  
Effective Diagnosis ◽  
Lung Ct

Lung cancer is a serious illness which leads to increased mortality rate globally. The identification of lung cancer at the beginning stage is the probable method of improving the survival rate of the patients. Generally, Computed Tomography (CT) scan is applied for finding the location of the tumor and determines the stage of cancer. Existing works has presented an effective diagnosis classification model for CT lung images. This paper designs an effective diagnosis and classification model for CT lung images. The presented model involves different stages namely pre-processing, segmentation, feature extraction and classification. The initial stage includes an adaptive histogram based equalization (AHE) model for image enhancement and bilateral filtering (BF) model for noise removal. The pre-processed images are fed into the second stage of watershed segmentation model for effectively segment the images. Then, a deep learning based Xception model is applied for prominent feature extraction and the classification takes place by the use of logistic regression (LR) classifier. A comprehensive simulation is carried out to ensure the effective classification of the lung CT images using a benchmark dataset. The outcome implied the outstanding performance of the presented model on the applied test images.

scholarly journals Stock Pattern Classification from Charts using Deep Learning Algorithms

2020 ◽  
Vol 3 (1) ◽  
pp. 445-454
Author(s):  
Celal Buğra Kaya ◽  
Alperen Yılmaz ◽  
Gizem Nur Uzun ◽  
Zeynep Hilal Kilimci
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Pattern Classification ◽  
Short Term Memory ◽  
Stock Exchange ◽  
Learning Techniques ◽  
Proposed Model ◽  
Istanbul Stock Exchange

Pattern classification is related with the automatic finding of regularities in dataset through the utilization of various learning techniques. Thus, the classification of the objects into a set of categories or classes is provided. This study is undertaken to evaluate deep learning methodologies to the classification of stock patterns. In order to classify patterns that are obtained from stock charts, convolutional neural networks (CNNs), recurrent neural networks (RNNs), and long-short term memory networks (LSTMs) are employed. To demonstrate the efficiency of proposed model in categorizing patterns, hand-crafted image dataset is constructed from stock charts in Istanbul Stock Exchange and NASDAQ Stock Exchange. Experimental results show that the usage of convolutional neural networks exhibits superior classification success in recognizing patterns compared to the other deep learning methodologies.

scholarly journals IT in the Processes of Creation and Operation of Construction Objects

2020 ◽  
pp. 218-225
Author(s):  
Oleh Kyslun ◽  
◽  
Yuriy Parhomenko ◽  
Ivan Skrynnik ◽  
Viktor Dariienko ◽  
...  
Keyword(s):  
Computer Aided Design ◽  
Construction Projects ◽  
Life Cycles ◽  
Management Systems ◽  
Accounting Systems ◽  
Area Of Interest ◽  
Building Management ◽  
Computer Aided ◽  
Aided Design ◽  
Building Management Systems

The article presents the results of IT research in the processes of creation and operation of construction projects. An overview of the means of complex accounting automation in Ukraine is given. An overview of the market of computer-aided design tools for architecture and construction is given also their characteristics are given. An overview of integrated market management systems in Ukraine is presented. The field of application of information technologies is constantly expanding, and growing constantly require monitoring of new implementations and search for effective innovations. Awareness provides a competitive advantage for both the developer and the consumer. Thus, the task of IT monitoring arises, and in the presence of a common area of interest, a team of like-minded people faces the problem of IT research in the processes of creation and operation of construction projects. IT in the process of creating and operating construction projects is used in all life cycles of the latter. The software that serves these processes is diverse and mostly disparate and is a set of software products aimed at sectoral use [1]. The issue of introduction of modern IT in this area is relevant and there is a need for development by specialists, which requires their study. The software used can generally be divided into: general purpose software; specialized accounting programs and other accounting systems; computer-aided design systems; integrated management systems of the organization; building management systems; scheduling systems. The so-called specialized accounting programs and accounting systems presented on the Ukrainian market in the construction sector are the same as for other sectors of the economy, there are only certain adaptations to take into account the specifics of the scope. At this stage of economic development of Ukraine in the construction industry ERP systems have not yet become widespread. Building management systems are also waiting to be expanded in Ukraine.

Deep learning for diagnosis and classification of faults in industrial rotating machinery

2021 ◽  
Vol 153 ◽  
pp. 107060
Author(s):  
Roberto M. Souza ◽  
Erick G.S. Nascimento ◽  
Ubatan A. Miranda ◽  
Wenisten J.D. Silva ◽  
Herman A. Lepikson
Keyword(s):  
Deep Learning ◽  
Rotating Machinery ◽  
Diagnosis And Classification

scholarly journals A computer-aided design mammography screening system for detection and classification of microcalcifications

2000 ◽  
Vol 60 (1) ◽  
pp. 29-57 ◽  
Author(s):  
San-Kan Lee ◽  
Chien-Shun Lo ◽  
Chuin-Mu Wang ◽  
Pau-Choo Chung ◽  
Chein-I Chang ◽  
...  
Keyword(s):  
Mammography Screening ◽  
Computer Aided Design ◽  
Screening System ◽  
Computer Aided ◽  
Aided Design

scholarly journals Brushless Electric Machines with Axial Magnetic Flux: Analysis and Synthesis

2021 ◽  
Author(s):  
Sergey Gandzha ◽  
Dmitry Gandzha
Keyword(s):  
Magnetic Flux ◽  
Computer Aided Design ◽  
Electric Machines ◽  
Engineering Practice ◽  
Flux Analysis ◽  
Electromagnetic Moment ◽  
Electromagnetic Power ◽  
Analysis And Synthesis ◽  
Aided Design

An analysis of electric machines with axial magnetic flux is given. First, the effect of commutation on the electromagnetic moment and electromagnetic power is analyzed. Two types of discrete switching are considered. The analysis is performed for an arbitrary number of phases. The first type of switching involves disabling one phase for the duration of switching. The second type of switching involves the operation of all phases in the switching interval. The influence of the pole arc and the number of phases on the electromagnetic moment and electromagnetic power is investigated. The conclusion is made about the advantage of the second type of switching. It is recommended to increase the number of phases. Next, the classification of the main structures of the axial machine is carried out. Four main versions are defined. For each variant, the equation of the electromagnetic moment and electromagnetic power is derived. This takes into account the type of commutation. The efficiency of the selected structures is analyzed. The comparative analysis is tabulated for choosing the best option. The table is convenient for engineering practice. This chapter forms the basis for computer-aided design of this class of machines.

Sign in / Sign up

Export Citation Format

Share Document