This paper evaluates a set of enhancement stages for finger vein enhancement that not only has low computational complexity but also high distinguishing power. This proposed set of enhancement stages is centered around fuzzy histogram equalization. Two sets of evaluation are carried out: one with the proposed approach and one with another unique approach that was formulated by rearranging and cropping down the preprocessing steps of the original proposed approach. To extract features, a combination of Hierarchical Centroid and Histogram of Gradients was used. Both enhancement stages were evaluated with K Nearest Neighbor and Deep Neural Networks using 6 fold stratified cross validation. Results showed improvement as compared to three latest benchmarks in this field that used 6-fold validation.
In this article, we experimentally propose an efficient wide flat gain bandwidth with a parallel hybrid fiber amplifier. The setup includes parallel amplifier branches. In the first branch, serial erbium-doped and Raman fiber amplifiers are used. In the second branch, only a Raman fiber amplifier is used. Three Raman pump power units (i.e., 1410, 1480, and 1495 nm) are used to achieve Raman gain at different optical communication bands. At optimum pump powers and at a small-signal power of À30 dBm, an average gain of 18.5 dB with a maximum gain variation of 3 dB and a gain flatness bandwidth of 83 nm, that is, from 1527 to 1610 nm, is achieved. This gain flatness is expanded to 92 nm (1525-1617 nm) at a large input signal power of À5 dBm with an average gain level of 13 dB. In our proposed amplifier, the Raman amplification peaks (1510 and 1595 nm) are chosen to be far from the erbium amplification peak (1530-1570 nm) in order to avoid the overlapping and the saturation in the first amplifier branch. Therefore, due to such wavelength optimization in addition to the recycling the residual Raman pump power, a wide flatness gain bandwidth is achieved for both of low and large input signal powers.
Currently, Biometrics has been utilized the top five modality of face, voice, IRIs, fingerprint, and palm to identify individuals. Comparatively, these Biometrics systems need complex computation to be slow and an easy target to hack. Alternatively, this work proposes a novel biometrics system of highly secured recognition with low computation time using specifically designed biometrics sensor. Consequently, finger vein recognition has been developed. Although, this recognition requires high point of safety measures comes with its individual experiments. The most prominent one being the vein pattern is very difficult to extract because finger vein images are constantly low in quality, seriously hampering the feature extraction and classification stages. Sophisticated algorithms need to be designed with the conventional hardware for capturing finger-vein images is modified by using red Surface Mounted Diode (SMD) leds. For capturing images, Canon 750D camera is used with micro lens. The integrated micro lens gives better quality images, and with some adjustments it can also capture finger print. Results have been comparatively improvement for SDUMLA-HMT database and extensively evaluated with k-nearest neighbors (KNN) algorithm. The (KNN) algorithm is a simple, easy-to-implement supervised machine learning algorithm that can be used to solve both classification and regression problems. KNN calculations are highly accurate in test data. Using stratified 6-fold analysis on all fingers of all hands in collected database, a maximum accuracy of 100% was achieved with an EER of 0% when select right hand and middle finger, based on the analysis of the 106 persons present in the data set. Many approaches have been used to optimize vein image quality. The proposed system has optimum results as compared to existing related works. The work novelty is due to the hardware design of the sensor within the finger-vein recognition system to obtain, simultaneously, finger vein and finger print at low cost, unlimited users for one device and open source.
Hepatitis is <span>an infection that causes inflammation of liver tissue. Many studies have developed machine learning models for hepatitis disease diagnosis. However, there has been little discussion about the relationship between hepatitis symptoms. The first objective of this study is to provide a brief description of a real-world hepatitis disease symptom dataset. Furthermore, the authors proposed a stand-alone classification platform using random forest, decision tree, and support vector machine into healthy people or hepatitis patients using adaptive wrapper feature selection. It was discovered that there is a strong link between certain characteristics and hepatitis diagnosis. The work presented here may help improve hepatitis diagnosis in the early stages, which may lead to a reduction in the acute effects of hepatitis on human life. It is worth noting that random forest (RF) gave the highest accuracy and stayed slightly consistent through all sets of features in comparison to decision tree (DT) and support vector machines (SVM).</span>
This research paper explores the effectiveness of quick response (QR) code-based attendance systems with the added security measure of generating two QR codes per second. With traditional attendance tracking methods being time-consuming and inefficient, QR codes have become increasingly popular as a quick and efficient alternative. However, one concern with QR code-based attendance systems is the potential for fraud and misuse. To address this issue, this study proposes generating two QR codes per second to ensure that only the current and legitimate QR code is recognized. The purpose of this study is to assess the impact of this technology on student attendance rates, the accuracy and reliability of attendance data, and the overall user experience for both students and instructors. Through data analysis and surveys, we found that the use of QR codes with the added security measure resulted in increased student attendance rates, improved accuracy and reliability of attendance data, and a positive user experience for both students and instructors. This research provides practical insights for educational institutions considering the implementation of QR code-based attendance systems and contributes to the growing body of literature on the use of QR codes in education.
This paper examines a collection of finger vein enhancement stages that have not only low computational complexity but also high distinguishing capacity. This proposed series of enhancement stages is based on the equalization of fuzzy histograms. A mixture of Hierarchical Centroid and Gradient Histograms was used to extract features. Both the enhancement stages were evaluated using 6 fold stratified cross validation with K Nearest Neighbor and Support Vector Machine (SVM). Experimental results show that the (KNN) algorithm is a simple, easy-to-implement supervised machine learning algorithm which can be used to solve problems of classification and regression. Calculations of KNN in the test data are highly accurate. Using stratified 6-fold analyzes on all fingers of all hands in the collected database, when selecting the right and middle fingers based on the analysis of the 106 people in the data set. Compared with SVM and related works, the algorithm proposed has optimum performance.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.