Search

An authentication method that combines various systems is called an iris recognition strategy. used to increase the iris recognition method's accuracy. Iris recognition has built-in flaws that put system security at risk. Among them are parody attacks. Compared to standard iris recognition techniques, enhanced iris recognition is more susceptible to parody assaults. The biometric sensor receives duplicate input during parodying. To determine whether a given input is unique or a copy, parody detection is utilised. Overcoming parody attacks on the iris recognition process is the goal. Using mean, median, variance, and local trinary pattern (LTP) approaches, the suggested methodology extracts a set of features from the iris. The retrieved biometric characteristics are then merged and used in deep learning. In order to identify mocked features, it is fed into a convolutional neural network. original purpose. The suggested method for iris recognition performs better than current liveness detection methods. [ABSTRACT FROM AUTHOR]

An improved motorcycle accident detection and ready system is introduced. The system comprises of series of modules to be specific an accelerometer, GPS and GPRS module. Firstly, the framework controls on along while the bike start, at that point it keeps monitoring if the angle of the automobile is more prominent or greater than 60°. Likewise, accelerometer keeps on checks whether there may be any sudden deceleration due to any collision; alongside those modules, the impact sensor monitors if there may be any pressure applied on the automobile, assuming it is thus, this device affirms that crash has happened. During this occurrence, the GPRS module which is present in this device sends data of the rider location from the GPS module info and sends it to the SOS contacts which was first stored within the GPRS module. At that point utilizing Google Programming interface, close-by emergency hospitals may be directed and alarmed for short medical assistance. [ABSTRACT FROM AUTHOR]

This paper presents machine learning algorithms for predicting different stages of breast cancer tumour such as benign and malignant. Machine learning (ML) models such as Logistic regression (LR), Decision tree (DT), Naive Bayes (NB), Support vector machine (SVM), K-nearest neighbour (KNN), Random Forest (RF) and XG Boost (XGB) used for predicting different stages of breast cancer. The Breast cancer data is collected from UCI machine learning Repository, this data is used training and testing the machine algorithms. Performance and evaluation of machine learning algorithms using confusion matrix and metrics are used Accuracy, Precision, Recall and f1-score. Support vector machine (SVM) performed better result of metrics score to compared with other machine learning algorithms. [ABSTRACT FROM AUTHOR]