In recent years, driver fatigue has become one of the main causes of road accidents. As a result, fatigue detection systems have been developed to warn drivers, and, among the available methods, EEG signal analysis is recognized as the most reliable method for detecting driver fatigue. This study presents an automated system for a two-stage classification of driver fatigue, using a combination of compressed sensing (CS) theory and deep neural networks (DNNs), that is based on EEG signals. First, CS theory is used to compress the recorded EEG data in order to reduce the computational load. Then, the compressed EEG data is fed into the proposed deep convolutional neural network for automatic feature extraction/selection and classification purposes. The proposed network architecture includes seven convolutional layers together with three long short-term memory (LSTM) layers. For compression rates of 40, 50, 60, 70, 80, and 90, the simulation results for a single-channel recording show accuracies of 95, 94.8, 94.6, 94.4, 94.4, and 92%, respectively. Furthermore, by comparing the results to previous methods, the accuracy of the proposed method for the two-stage classification of driver fatigue has been improved and can be used to effectively detect driver fatigue.

In recent years, detecting driver fatigue has been a significant practical necessity and issue. Even though several investigations have been undertaken to examine driver fatigue, there are relatively few standard datasets on identifying driver fatigue. For earlier investigations, conventional methods relying on manual characteristics were utilized to assess driver fatigue. In any case study, such approaches need previous information for feature extraction, which could raise computing complexity. The current work proposes a driver fatigue detection system, which is a fundamental necessity to minimize road accidents. Data from 11 people are gathered for this purpose, resulting in a comprehensive dataset. The dataset is prepared in accordance with previously published criteria. A deep convolutional neural network–long short-time memory (CNN–LSTM) network is conceived and evolved to extract characteristics from raw EEG data corresponding to the six active areas A, B, C, D, E (based on a single channel), and F. The study’s findings reveal that the suggested deep CNN–LSTM network could learn features hierarchically from raw EEG data and attain a greater precision rate than previous comparative approaches for two-stage driver fatigue categorization. The suggested approach may be utilized to construct automatic fatigue detection systems because of their precision and high speed.

In this paper, we proposed a 2-channel demultiplexer based on photonic crystal ring resonator (PCRR). For performing wavelength selection, we used two ring resonators, two different wavelengths were obtained by using two resonant rings with different values for the radius of dielectric rods. All the simulations and calculations have been done using Rsoft Photonic CAD software, which employs finite difference time domain (FDTD) method. The output channels were respectively at 1590.8 and 1593.8 nm, correspondingly had the quality factors of 7954 and 3984, the crosstalk values of − 22 and − 11 dB separately. The total footprint of our proposed structure is 681.36 μm². Results suggest that 2-channels in the proposed structure are characterized with high transmission efficiency and low band width, resulting in a very sharp output spectrum and high quality factor values.

Exhaled breath analysis (EBA) is an advanced, non-invasive diagnostic technique that utilizes volatile organic compounds (VOCs) to detect and monitor various diseases. This review examines EBA’s historical development and current status as a promising diagnostic tool. It highlights the significant contributions of modern methods such as gas chromatography–mass spectrometry (GC-MS), ion mobility spectrometry (IMS), and electronic noses in enhancing the sensitivity and specificity of EBA. Furthermore, it emphasizes the transformative role of nanotechnology and machine learning in improving the diagnostic accuracy of EBA. Despite challenges such as standardization and environmental factors, which must be addressed for the widespread adoption of this technique, EBA shows excellent potential for early disease detection and personalized medicine. The review also highlights the potential of photonic crystal fiber (PCF) sensors, known for their superior sensitivity, in the field of EBA.

Hydrogen cyanide gas is a dangerous and fatal gas that is one of the causes of air pollution in the environment. A small percentage of this gas causes poisoning and eventually death. In this paper, a new PCF is designed that offers high sensitivity and low confinement loss in the absorption wavelength of hydrogen cyanide gas. The proposed structure consists of circular layers that are located around the core, which is also composed of circular microstructures. The finite element method (FEM) is used to simulate the results. According to the results, the PCF gives a high relative sensitivity of 65.13% and a low confinement loss of 1.5 × 10⁻³ dB/m at a wavelength of 1.533 µm. The impact of increasing the concentration of hydrogen cyanide gas on the relative sensitivity and confinement loss is investigated. The high sensitivity and low confinement losses of the designed PCF show that this optical structure could be a good candidate for the detection of this gas in industrial and medical environments.