Search

Finger veins are one of the emerging biometric traits attracting many researchers in biometric recognition. Despite the growing literature on finger vein recognition, little interest has been shown in the impact of acquisition devices on recognition performance due to the lack of a multi-sensor finger vein database. This work aims to fill this gap by creating such a database using five different acquisition devices. We then analyze their impact on finger vein recognition performance. The analysis shows two main challenges that decrease recognition performance, namely scaling between device sensors and horizontal shifts between image pairs. The findings of this research give insight into developing more robust finger vein recognition algorithms.

Diabetes mellitus and its complication such as heart disease, stroke, kidney failure, etc. is a serious concern all over the world. Hence, monitoring some important blood parameters non-invasively is of utmost importance, that too with high accuracy. This paper presents an in-house developed system, which will be helpful for diabetes patients with Chronic Kidney Disease (CKD) to monitor blood urea and glucose. This manuscript discusses a comparative study for the prediction of blood urea and glucose using Backpropagation Artificial Neural Network (BP- ANN) and Partial Least Square Regression (PLSR) model. The NVIDIA Jetson Nano board controls the five fixed LED wavelengths in the Near Infrared (NIR) region from \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}$2.0~\mu \text{m}$\end{document} to \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}$2.5~\mu \text{m}$ \end{document} with a constant emission power of 1.2 mW. The spectra for 57 laboratory prepared samples conforming with major blood constituents of the blood sample were recorded. From these samples, 53 spectra were used for training/calibration of the BP-ANN/PLSR model and the remaining 4 samples were used for validating the model. The PLSR model predicts blood urea and glucose with a Root Mean Square Error (RMSE) of 0.88 & 12.01 mg/dL, Coefficient of Determination R2 = 0.93 & R2 = 0.97, Accuracy of 94.2 % and 90.14 %, respectively. To improve the prediction accuracy, BP-ANN model is applied. Later the Principal Component Analysis (PCA) technique was applied to these 57 spectra values. These PCA values were used to train and validate the BP-ANN model. After applying the BP-ANN model, the prediction of blood urea & glucose improved remarkably, which achieved RMSE of 0.69 mg/dL, R2 = 0.96, Accuracy of 95.96 % for urea and RMSE of 2.06 mg/dL, R2 = 0.99, and Accuracy of 98.65 % for glucose. The system performance is then evaluated with Bland Altman analysis and Clarke Error Grid Analysis (CEGA).

As technology and artificial intelligence conquer a place under the spotlight in the automotive world, driver drowsiness monitoring systems have sparked much interest as a way to increase safety and avoid sleepiness-related accidents. Such technologies, however, stumble upon the observation that each driver presents a distinct set of behavioral and physiological manifestations of drowsiness, thus rendering its objective assessment a non-trivial process. The AUTOMOTIVE project studied the application of signal processing and machine learning techniques for driver-specific drowsiness detection in smart vehicles, enabled by immersive driving simulators. More broadly, comprehensive research on biometrics using the electrocardiogram (ECG) and face enables the continuous learning of subject-specific models of drowsiness for more efficient monitoring. This paper aims to offer a holistic but comprehensive view of the research and development work conducted for the AUTOMOTIVE project across the various addressed topics and how it ultimately brings us closer to the target of improved driver drowsiness monitoring.

With the advancement in the surrounding sensing technologies for autonomous driving systems, the immense potential is yet to be explored in vehicle safety. A robust binary decision (Yes/No) about the requirement of any irreversible safety action such as the deployment of airbags in the pre-crash phase is a big step. In this work, we investigate different machine learning approaches for determining the severity of occupant injury in two classes: Safe Zone and Injury Zone. One of the essential outcomes of this paper is the selection of the input features through feature engineering. Five machine learning models are investigated and compared based on different evaluation criteria to find the best classification model for the application. XGBoost, Catboost, Random Forest, Kernel SVM, K-nearest neighbors, and Artificial Neural Network (ANN) were trained on data collected through FEM simulations. XGBoost was found to be the best performing model. If the predicted severity lies in the Injury Zone during pre-crash, airbag activation is required. Hence, this prediction can be used in pre-crash for steering an inevitable crash in a crash with low severity.

Perception of the vehicle surrounding is one of the most vital tasks in achieving a vision of fully autonomous driving. To achieve this task, forward-looking sensors like RADAR, LiDAR, and camera are widely used for object detection and classification. Accurate range information at several closely distributed points from the object’s outer surface gives the LiDAR sensor an advantage for estimating the shape and size of the opponent object. Though the LiDAR sensor can provide accurate range information in point cloud data, there are some variations in intensity values and no. of points reflected from objects with different colors. In this paper, we analyze the differences in the LiDAR intensities and no. of point clouds received from different colored objects by recording LiDAR data of three different colored cars at varied orientation angles and distances from the LiDAR sensor in similar environmental conditions and the impact it might have in perception of vehicle surrounding. The results show that the color of the object has a considerable influence on the LiDAR data and can affect the output of the pre-crash estimation algorithms. This highlights the need to further investigate this effect to improve the pre-crash estimation algorithms by considering the behavior of the variation in the LiDAR data based on the object color.

A lightweight optical constellations modeling method based on concatenating ANNs is proposed. Statistical validation of the reproduced constellations is shown. The method accelerates data generation and facilitates detecting (un)intentioned misconfigurations, among others. This work has been partially supported by the EC through the MSC REAL-NET project (G.A. 813144), by the AEI/FEDER through the TWINS project (TEC2017-90097-R), and by the ICREA institution.

The recent Covid-19 pandemic and the fact that wearing masks in public is now mandatory in several countries, created challenges in the use of face recognition systems (FRS). In this work, we address the challenge of masked face recognition (MFR) and focus on evaluating the verification performance in FRS when verifying masked vs unmasked faces compared to verifying only unmasked faces. We propose a methodology that combines the traditional triplet loss and the mean squared error (MSE) intending to improve the robustness of an MFR system in the masked-unmasked comparison mode. The results obtained by our proposed method show improvements in a detailed step-wise ablation study. The conducted study showed significant performance gains induced by our proposed training paradigm and modified triplet loss on two evaluation databases., Comment: Accepted at 20th International Conference of the Biometrics Special Interest Group (BIOSIG 2021)

This paper presents a summary of the Masked Face Recognition Competitions (MFR) held within the 2021 International Joint Conference on Biometrics (IJCB 2021). The competition attracted a total of 10 participating teams with valid submissions. The affiliations of these teams are diverse and associated with academia and industry in nine different countries. These teams successfully submitted 18 valid solutions. The competition is designed to motivate solutions aiming at enhancing the face recognition accuracy of masked faces. Moreover, the competition considered the deployability of the proposed solutions by taking the compactness of the face recognition models into account. A private dataset representing a collaborative, multisession, real masked, capture scenario is used to evaluate the submitted solutions. In comparison to one of the topperforming academic face recognition solutions, 10 out of the 18 submitted solutions did score higher masked face verification accuracy.