ALBERT

Description: This article describes the design of a smart steering wheel intended for use in unobtrusive health and drowsiness monitoring. The aging population, cardiovascular disease, personalized medicine, and driver fatigue were significant motivations for developing a monitoring platform in cars because people spent much time in cars. The purpose was to create a unique, comprehensive monitoring system for the driver. The crucial parameters in health or drowsiness monitoring, such as heart rate, heart rate variability, and blood oxygenation, are measured by an electrocardiograph and oximeter integrated into the steering wheel. In addition, an inertial unit was integrated into the steering wheel to record and analyze the movement patterns performed by the driver while driving. The developed steering wheel was tested under laboratory and real-life conditions. The measured signals were verified by commercial devices to confirm data correctness and accuracy. The resulting signals show the applicability of the developed platform in further detecting specific cardiovascular diseases (especially atrial fibrillation) and drowsiness.

Description: Driver fatigue can be manifested by various highly dangerous direct and indirect symptoms, for example, inattention or lack of concentration. The aim of the study was to compare the behavior of young drivers, older drivers and professional drivers, particularly in situations where they feel fatigued. In the online questionnaire, drivers answered various questions which analysed their responsibility of driving a car during fatigue, the optimum temperature in the car, or experience with microsleep. The sample of drivers consisted of 507 women and 951 men in Slovakia. Young drivers are more responsible when driving during fatigue, while professional drivers take risks, break the law, and drive tired more often. A total of 25% of all drivers experience fatigue more than once a week. Adverse results were found in connection with driving and fatigue, where more than 42% of respondents stated that their duties require them to drive even when they are tired. A total of 27% of drivers have had microsleep while driving. The survey showed that drivers are aware that thermoneutral temperature in a car interior can improve driving performance and a lower temperature can positively affect a person’s attention. The regulation of the temperature in the car was helpful for 75% of all drivers when they felt tired, and more than 97% of the drivers lowered the temperature in the interior of the vehicle in order to achieve a better concentration. In addition to standard statistical methods, a neural network was used for the evaluation of the questionnaire, which sought for individual connections and subsequent explanations for the hypotheses. The applied neural network was able to determine parameters such as the age of the driver and the annual raid as the riskiest and closely associated with the occurrence of microsleep between drivers.

Description: At present, inspection systems process visual data captured by cameras, with deep learning approaches applied to detect defects. Defect detection results usually have an accuracy higher than 94%. Real-life applications, however, are not very common. In this paper, we describe the development of a tire inspection system for the tire industry. We provide methods for processing tire sidewall data obtained from a camera and a laser sensor. The captured data comprise visual and geometric data characterizing the tire surface, providing a real representation of the captured tire sidewall. We use an unfolding process, that is, a polar transform, to further process the camera-obtained data. The principles and automation of the designed polar transform, based on polynomial regression (i.e., supervised learning), are presented. Based on the data from the laser sensor, the detection of abnormalities is performed using an unsupervised clustering method, followed by the classification of defects using the VGG-16 neural network. The inspection system aims to detect trained and untrained abnormalities, namely defects, as opposed to using only supervised learning methods.