Advances in machine learning (ML) and deep learning (DL) have led to automated sleep staging approaches that achieve high accuracy but often require extensive computational resources and/or highdensity electroencephalograms (EEG).This paper presents a method for sleep staging using features extracted via the Discrete Wavelet Transform (DWT) and Power Spectral Density (PSD), followed by the Gradient Boosting (GB) classifier.The study employs a private dataset and the sleep-EDF dataset, comprising EEG and electrooculograms (EOG) channels.The analysis includes configurations with varying numbers of subjects (75, 20, and 12), and the results demonstrate that the proposed method achieves competitive performance with existing approaches that use complex DL architectures, even with fewer subjects.Feature importance analysis highlights the importance of detail coefficients from DWT and PSD-based features from EEG signals.The findings suggest that simplified methods using low-density EEG and EOG with wellselected features and GB classification can offer a viable alternative to DL approaches for sleep staging.

Visual inspection of Polysomnography (PSG) recordings by sleep experts, based on established guidelines, has been the gold standard in sleep stage classification. This approach is expensive, time-consuming, and mostly limited to experimental research and clinical cases of major sleep disorders. Various automatic approaches to sleep scoring have been emerging in the past years and are opening the way to a quick computational assessment of sleep architecture that may find its way to the clinics. With the hope to make sleep scoring a fully automated process in the clinics, we report here an ensemble algorithm that aims at not only predicting sleep stages but of doing so with an optimized minimal number of EEG channels. For that, we combine a genetic algorithm-based optimization with a classification framework that minimizes the number of channels used by the machine learning algorithm to quantify sleep stages. This resulted in a sleep scoring with an F1 score of 0.793 for the fully automated model and 0.82 for the model trained on 10 percent of the unseen subject, both with only 3 EEG channels. The ensemble algorithm is based on a combination of extremely randomized trees and MiniRocket classifiers. The algorithm was trained, validated, and tested on night sleep PSG data collected from 7 subjects. Our approach’s novelty lies in using the minimum information needed for automated sleep scoring, based on a systematic search that concurrently selects the optimal-minimum number of EEG channels and the best-performing features for the machine learning classifier. The optimization framework presented in this work may enable new flexible designs for sleep scoring devices suited to studies in the comfort of homes, easily and inexpensively. In this way facilitate experimental and clinical studies in large populations.

The paper reports defect detection techniques using X-rays in order to find three dimensional defects such as funnels in printed circuit board (PCB) patterns. X-ray images of fine PCB patterns, however, show patterns on more than one layer, having degrees of distortion that vary over an image, are subject to intensity variation due to fluctuations in the intensity of the X-ray source, and so on. To overcome these problems, we examined distortion caused by perspective transforms on the sphere surface of an X-ray detector and developed a defect detection algorithm based on feature extraction. Fluctuation of X-ray strength and heavy shading of the acquired image are compensated by signal processing. Evaluation of the system confirmed that the system could detect defects deeper than 20 /spl mu/m and with surface areas greater than 70/spl times/35 /spl mu/m/sup 2/ in fine PCB patterns and that the inspection time for a 600/spl times/800 mm/sup 2/ PCB was only 20 minutes.>