Search

In the present work, Friction stir welding of dissimilar materials AA5083 & AA6061 is carried out and by using Taguchi-based Grey Relational Analysis. The output characteristics like tensile strength, elongation, and hardness values are investigated using response surface methodology and grey relational analysis. The quality of the welded joint is measured based on the experimental values of tensile strength, elongation, and hardness of the joint the experiments were conducted in accordance with the L9 orthogonal array assigning different levels values to the process parameters. Tool pin profile, rotational speed, welding speed, and tool tilt angle are selected as the significant input parameters. Analysis of variance (ANOVA) is used to analyze the effect of each input welding parameter on the output responses. Statistical results show that the results of the confirmatory experiments are within 95% confidence optimal conditions with smaller deviations.

Introduction: COVID-19 is a pandemic disease affecting the global mankind since December 2019 Diagnosing COVID-19 using lung X-ray image is a great challenge faced by the entire world Early detection helps the doctors to suggest suitable treatment and also helps speedy recovery of the patients Advancements in the field of computer vision aid medical practitioners to predict and diagnosis disease accurately Objective: This study aims to analyze the chest X-ray for determining the presence of COVID-19 using machine learning algo-rithm Methods: Researchers propose various techniques using machine learning algorithms and deep learning approaches to de-tect COVID-19 However, obtaining an accurate solution using these AI techniques is the main challenge still remains open to researchers Results: This paper proposes a Local Binary Pattern technique to extract discriminant features for distinguishing COVID-19 disease using the X-ray images The extracted features are given as input to various classifiers namely Random Forest (RF), Linear Discriminant Analysis (LDA), k-Nearest Neighbour (kNN), Classification and Regression Trees (CART), Support Vector Machine (SVM), Linear Regression (LR), and Multi-layer perceptron neural network (MLP) The proposed model has achieved an accuracy of 77 7% from Local Binary Pattern (LBP) features coupled with Random Forest classifier Conclusion: The proposed algorithm analyzed COVID X-ray images to classify the data in to COVID-19 or not The features are extracted and are classified using machine learning algorithms The model achieved high accuracy for linear binary pattern with random forest classifier © IJCRR

Computational based classification of gene expression data for analyzing the genetic pattern provides better clinical prediction for breast cancer. Breast cancer is one of the leading cancers among women all over India. This type of cancer leads to malignant tumor developed in the breast. Recent methodologies have undergone many classification methods to analyze the characteristics of gene expression. This paper focuses on computational method such as fuzzy based logistic regression to predict the expression of the gene data. In order to bring accuracy and to solve the inefficiency in feature selection of gene expression data, LASSO Logistic Regression (LLR), a novel methodology is implemented. For computational tractable, Maximum Likelihood Estimation (MLE) is implied with regression model. Diagnosis and prognosis of breast cancer becomes a great challenge in the medical era. This research work explores the mining technology based algorithm to classify the cancer data using fuzzy methodology by evaluating few samples of gene expression data of breast cancer as a training set and the resultant test data are validated to predict the cancer at the earlier stage. For feasible analysis, Expectation Maximization (EM) algorithm is deployed for unknown or missing parameters of gene data expression.

Base drag, arising from flow separation at the blunt base of a body can be a sizeable fraction of total drag in the context of projectiles, missiles and after bodies of fighter aircrafts. The base drag is the major contribution of total drag for low speed regimes, flight tests have shown that the base drag may account for up to 50% of the total drag. Computational and experimental investigation for a hemispherical flight vehicle body of length 500mm and diameter 50mm was conducted for the purpose of investigating the base drag. Three case studies were conducted to investigate the properties of the flow field around the flight vehicle at different flow velocities of 20m/s, 30m/s and 50m/s at zero angle of attack (AoA). The three cases were (i) a flight vehicle with flat base configuration, (ii) a flight vehicle with a nozzle at the base and (iii) a flight vehicle configuration with a boat tail, Fig 1. Also, the three configurations were investigated at different AoA of -2, 0 and +2. The base drags for three configurations are calculated and the experimental results are compared with the CFD results.

Visual Cryptography is an encryption technique where a secret image is cryptographically encoded into n shares. In visual secret sharing scheme (k, n) the secret images can be visually revealed by stacking together any k or more transparencies of the shares and by inspecting less than k shares one cannot retrieve the secret image. Visual Secret Sharing based on halftone visual cryptography, the continuous-tone image is first transformed into a halftone image, and then encrypted using visual secret sharing schemes. In visual cryptography, meaningless shares are encoded into halftone shares taking meaningful visual information which reduces the suspicion of intruders. These halftone shares are concurrently error diffused to give visually pleasing effect. Error diffusion is computationally efficient with less complexity. Techniques such as classical fixed, edge enhancement, green noise and block error diffusion are performed and a comparative study is made. The quality of the halftone shares enhanced by using Floyd - Steinberg and Jarvis error filters. Secret image is reconstructed by stacking the qualified halftone shares. The simulation results shows that the visual quality of the obtained halftone share are observably better.