"Convolutional neural network for high-accuracy functional near-infrared spectroscopy in a braincomputer interface: three-class classification of rest, right-, and left-hand motor execution," Neurophoton. 5(1), 011008 (2017), doi: 10.1117/1.NPh.5.1.011008. Abstract. The aim of this work is to develop an effective brain-computer interface (BCI) method based on functional near-infrared spectroscopy (fNIRS). In order to improve the performance of the BCI system in terms of accuracy, the ability to discriminate features from input signals and proper classification are desired. Previous studies have mainly extracted features from the signal manually, but proper features need to be selected carefully. To avoid performance degradation caused by manual feature selection, we applied convolutional neural networks (CNNs) as the automatic feature extractor and classifier for fNIRS-based BCI. In this study, the hemodynamic responses evoked by performing rest, right-, and left-hand motor execution tasks were measured on eight healthy subjects to compare performances. Our CNN-based method provided improvements in classification accuracy over conventional methods employing the most commonly used features of mean, peak, slope, variance, kurtosis, and skewness, classified by support vector machine (SVM) and artificial neural network (ANN). Specifically, up to 6.49% and 3.33% improvement in classification accuracy was achieved by CNN compared with SVM and ANN, respectively.
Background: An efficient and accurate method of respiratory rate measurement is still missing in hospital general wards and triage. The goal of this study is to propose a method of respiratory rate measurement that has a potential to be used in general wards, triage, and different hospital settings with comparable performance. We propose a method of respiratory rate measurement that combines a unique wearable platform with an adaptive and optical approach. The optical approach is based on a direct-contact optical diffuse reflectance phenomenon. An adaptive algorithm is developed that computes the first respiratory rate and uses it to select a band. The band then chooses a set of unique optimized parameters in the algorithm to calculate and improve the respiratory rate. We developed a study to compare the proposed method against reference manual counts from 82 patients diagnosed with respiratory diseases. Results: We found good agreement between the proposed method of respiratory rate measurement and reference manual counts. The performance of the proposed method highlighted deviations with a 95% confidence interval (C.I.) of − 3.34 and 3.67 breaths per minute (bpm) and a mean bias and standard deviation (STD) of 0.05 bpm and 2.56 bpm, respectively. Conclusions: The performance of the proposed method of respiratory rate measurement is comparable with current manual counting and other respiratory rate devices reported. The method has additional advantages that include ease-of-use, quick setup time, and being mobile for wider clinical use. The proposed method has the potential as a tool to measure respiratory rates in a number of use cases.
Lung function classifies respiratory diseases. However, obtaining them with spirometry is difficult. We present an easy method that combines breathing patterns and machine learning to classify healthy from respiratory conditions at accuracy of 97.7%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.