Security of information is one of the most important factors of information technology and communication. So systems need strong procedures to protect data and resources access from unauthorized users.Biometric-based authentication systems represent a valid alternative to conventional approaches. Multimodal biometric system is used in order to improve the accuracy. A multimodal biometric identification systems aims to fuse two or more physical or behavioral traits. Multimodal biometric identification system based on iris & fingerprint trait is proposed. Typically in a multimodal biometric system each biometric trait processes its information independently. The processed information is combined using an appropriate fusion scheme. A template level fusion algorithm results in a homogeneous biometric vector by integrating iris & fingerprint data. Successively, the comparison of data base template and the input data is done with the help of hammingdistance matching algorithm. If the templates are matched we can allow the person to access the system. The proposed multimodal biometric system will improve system accuracy & dependability.
In recent days, study on retinal image remains a significant area for analysis. Several retinal diseases are identified by examining the differences occurring in the retina. Anyhow, the major shortcoming between these analyses was that the identification accuracy is not satisfactory. The adopted framework includes two phases namely; (i) feature extraction and (ii) classification. Initially, the input fundus image is subjected to the feature extraction process, where the features like Local Binary Pattern (LBP), Local Vector Pattern (LVP) and Local Tetra Patterns (LTrP) are extracted. These extracted features are subjected to the classification process, where the Deep Belief Network (DBN) is used as the classifier. In addition, to improve the accuracy, the activation function and hidden neurons of DBN are optimally tuned by means of the Self Improved Grey Wolf Optimization (SI-GWO). Finally, the performance of implemented work is compared and proved over the conventional models.
This paper presents deep learning models for the classification of Diabetic Retinopathy (DR) grades. The goal of this research is to find and create a deep learning model that will help us identify the image with high accuracy into one of the five phases of the DR as no DR, mild, moderate, severe, and proliferative DR.The whole work is developed using four steps. The first, using Ben Graham's pre-possessing form, the fundus images were pre-processed. Secondly, in order to train the models, the preprocessed images are contributed to the deep learning algorithm. The third,deep learning models such as Deep CNN, Dense Net, and Group 19 Visual Geometry (VGG19) are developed to predict the severity of the DR. The APTOS Blindness Detection dataset is used to train the proposed deep learning models. Since the data set is imbalanced in nature, the issue of training bias contributes to it. Therefore, at the time of training the models, class weight technique is used to eliminate the training bias problem. In the case of DR grading structures, the proposed deep learning models work well. The Dense Net has been found to work better than the other two models.
Filtering techniques have been elaborated in the HA field to improve signal clarity and enhance the hearing capacity of deaf people. However, public sounds are highly noisy, so filtering those signals is not an easy task. Hence, the present article has aimed to develop a novel Ant Lion based power Noise-Variable Bandwidth Filter (ALPN-VBF) for the HA applications. Here, the proposed optimized power efficient filter has incorporated several functions like de-noising and frequency tuning based on the word features. Here, the signal's noise has been removed with the maximum possible range with the help of High-pass-Filter (HPF) and low-pass filter (LPF). Finally, the developed model is tested with a few audiograms, and the filter parameters have been analyzed and compared with other models. The testing results have proved that the designed filter is better in frequency tuning and signal transmission than the previous approaches by attaining less delay and reduced power consumption rate.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.