Driver Drowsiness Detection: A Machine Learning Approach on Skin Conductance.

The majority of car accidents worldwide are caused by drowsy drivers. Therefore, it is important to be able to detect when a driver is starting to feel drowsy in order to warn them before a serious accident occurs. Sometimes, drivers are not aware of their own drowsiness, but changes in their body signals can indicate that they are getting tired. Previous studies have used large and intrusive sensor systems that can be worn by the driver or placed in the vehicle to collect information about the driver's physical status from a variety of signals that are either physiological or vehicle-related. This study focuses on the use of a single wrist device that is comfortable for the driver to wear and appropriate signal processing to detect drowsiness by analyzing only the physiological skin conductance (SC) signal. To determine whether the driver is drowsy, the study tests three ensemble algorithms and finds that the Boosting algorithm is the most effective in detecting drowsiness with an accuracy of 89.4%. The results of this study show that it is possible to identify when a driver is drowsy using only signals from the skin on the wrist, and this encourages further research to develop a real-time warning system for early detection of drowsiness.

Over the Limits of Traditional Sampling: Advantages and Issues of AICs for Measurement Instrumentation.

Data acquisition systems have shown the need of wideband spectrum monitoring for many years. This paper describes and discusses a recently proposed architecture aimed at acquiring efficiently wideband signals, named the Analog-to-Information Converter (AIC). AIC framework and working principle implementing the sub-Nyquist sampling are analyzed in general terms. Attention is specifically focused on the idea of exploiting the condition of the signals that, despite their large bandwidth, have a small information content in the frequency domain. However, as clarified in the paper, employing AICs in measurement instrumentation necessarily entails their characterization, through the analysis of their building blocks and the corresponding non-idealities, in order to improve the signal reconstruction.

ECG Monitoring Based on Dynamic Compressed Sensing of Multi-Lead Signals.

This paper presents an innovative method for multiple lead electrocardiogram (ECG) monitoring based on Compressed Sensing (CS). The proposed method extends to multiple leads signals, a dynamic Compressed Sensing method, that were previously developed on a single lead. The dynamic sensing method makes use of a sensing matrix in which its elements are dynamically obtained from the signal to be compressed. In this method, for the application to multiple leads, it is proposed to use a single sensing matrix for which its elements are obtained from a combination of multiple leads. The proposed method is evaluated on a wide set of signals and acquired on healthy subjects and on subjects affected by different pathologies, such as myocardial infarction, cardiomyopathy, and bundle branch block. The experimental results demonstrated that the proposed method can be adopted for a Compression Ratio (CR) up to 10, without compromising signal quality. In particular, for CR= 10, it exhibits a percentage of root-mean-squared difference average among a wide set of ECG signals lower than 3%.