Detecting drowsiness in drivers, especially multi-level drowsiness, is a difficult problem that is often approached using neurophysiological signals as the basis for building a reliable system. In this context, electroencephalogram (EEG) signals are the most important source of data to achieve successful detection. In this paper, we first review EEG signal features used in the literature for a variety of tasks, then we focus on reviewing the applications of EEG features and deep learning approaches in driver drowsiness detection, and finally we discuss the open challenges and opportunities in improving driver drowsiness detection based on EEG. We show that the number of studies on driver drowsiness detection systems has increased in recent years and that future systems need to consider the wide variety of EEG signal features and deep learning approaches to increase the accuracy of detection.

This paper presents a system for classification of asthma and chronic obstructive pulmonary disease (COPD) based on fuzzy rules and the trained neural network.

Muscle fatigue, as a common physiological phenomenon, has attracted much attention in the fields of rehabilitation and athletic training. A wearable technology for monitoring the muscle fatigue anytime and anywhere is urgently needed. In this paper we apply Electrical impedance myography (EIM) technique, usually used for non-invasive detection of neuromuscular diseases with the four-electrode array, for evaluation of the local muscle fatigue status via the variation of electrical impedance. An equivalent multilayer inhomogeneous 3D finite element model of human arm was built in order to optimize the four-electrode configuration to improve EIM detection sensitivity. Current density in muscle layer and differential potential of induction electrodes were selected as the evaluation indexes for optimization. Then the in vivo experiments of dynamic contraction with different maximal voluntary contractions (MVC) were performed on the biceps brachii muscle of eight healthy volunteers. The results showed that muscle resistance (R) decreased almost 8 Ω from the completely relaxed muscle to exhaustion, which is the same trend as for the median frequency (MF) of measured surface electromyography (sEMG) signals. The model and experiments in this paper indicate the feasibility and efficiency of EIM for detection of muscle fatigue using wearable devices.

Drowsiness is a risk to human lives in many occupations and activities where full awareness is essential for the safe operation of systems and vehicles, such as driving a car or flying an airplane. Although it is one of the main causes of many road accidents, there is still no reliable definition of drowsiness or a system to reliably detect it. Many researchers have observed correlations between frequency-domain features of the EEG signal and drowsiness, such as an increase in the spectral power of the theta band or a decrease in the spectral power of the beta band. In addition, features calculated as ratio indices between these frequency-domain features show further improvements in detecting drowsiness compared to frequency-domain features alone. This work aims to develop novel multichannel ratio indices that take advantage of the diversity of frequency-domain features from different brain regions. In contrast to the state-of-the-art, we use an evolutionary metaheuristic algorithm to find the nearly optimal set of features and channels from which the indices are calculated. Our results show that drowsiness is best described by the powers in delta and alpha bands. Compared to seven existing single-channel ratio indices, our two novel six-channel indices show improvements in (1) statistically significant differences observed between wakefulness and drowsiness segments, (2) precision of drowsiness detection and classification accuracy of the XGBoost algorithm and (3) model performance by saving time and memory during classification. Our work suggests that a more precise definition of drowsiness is needed, and that accurate early detection of drowsiness should be based on multichannel frequency-domain features.

Intra-body communication (IBC) uses the human body as the transmission medium for electrical signals, and it features the following advantages: low power consumption, strong anti-interference ability, high data security, and broad application scenarios. However, some technical issues still need to be addresses, such as the choice of the best modulation and demodulation scheme in different application scenarios, influence of human activity on IBC performance, variable signal-to-noise ratio (SNR), and influence of transmission distance change on different modulation and demodulation methods. This paper adopts direct sequence spread spectrum (DSSS) communication and phase modulation to realize DSSS-differential phase shift keying (DPSK) and DPSK modulation transmission of baseband data. Moreover, the Costas loop method is employed to achieve reliable symbol recovery. Under the same conditions, in vivo experiments were conducted to compare the performance of DSSS-DPSK and DPSK galvanic coupling IBC transceivers. Notably, these transceivers are affected by the changes in SNR, transmission distance, and human activities. Results show that the bit error rate (BER) of the DPSK scheme is 40 times larger than the DSSS-DPSK scheme in a 30 cm channel length and different SNR experiments. When the BER performance changes from extremely poor (1.40×10-1) to excellent (1.51×10-6), the SNR of DSSS-DPSK scheme only needs to be improved by 16 dB. In contrast, when the BER performance changes from extremely poor (1.54×10-1) to good (1.65×10-5), the SNR of DPSK scheme needs to be improved by 25 dB. With a SNR of –5 dB, the BER ratios of the DPSK scheme is 7 times larger than the DSSS-DPSK scheme. Also, DSSS-DPSK scheme is more sensitive to changes in motion status than DPSK.