http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Hubner, David,Verhoeven, Thibault,Muller, Klaus-Robert,Kindermans, Pieter-Jan,Tangermann, Michael IEEE 2018 IEEE computational intelligence magazine Vol.13 No.2
<P>One of the fundamental challenges in brain-computer interfaces (BCIs) is to tune a brain signal decoder to reliably detect a user's intention. While information about the decoder can partially be transferred between subjects or sessions, optimal decoding performance can only be reached with novel data from the current session. Thus, it is preferable to learn from unlabeled data gained from the actual usage of the BCI application instead of conducting a calibration recording prior to BCI usage. We review such unsupervised machine learning methods for BCIs based on event-related potentials of the electroencephalogram. We present results of an online study with twelve healthy participants controlling a visual speller. Online performance is reported for three completely unsupervised learning methods: (1) learning from label proportions, (2) an expectation-maximization approach and (3) MIX, which combines the strengths of the two other methods. After a short ramp-up, we observed that the MIX method not only defeats its two unsupervised competitors but even performs on par with a state-of-the-art regularized linear discriminant analysis trained on the same number of data points and with full label access. With this online study, we deliver the best possible proof in BCI that an unsupervised decoding method can in practice render a supervised method unnecessary. This is possible despite skipping the calibration, without losing much performance and with the prospect of continuous improvement over a session. Thus, our findings pave the way for a transition from supervised to unsupervised learning methods in BCIs based on eventrelated potentials.</P>
Basse Pierre,Morisson Louis,Barthélémy Romain,Julian Nathan,Kindermans Manuel,Collet Magalie,Huot Benjamin,Gayat Etienne,Mebazaa Alexandre,Chousterman Benjamin G. 대한중환자의학회 2023 Acute and Critical Care Vol.38 No.2
Background The role of positive pressure ventilation, central venous pressure (CVP) and inflammation on the occurrence of acute kidney injury (AKI) have been poorly described in mechanically ventilated patient secondary to coronavirus disease 2019 (COVID-19). Methods This was a monocenter retrospective cohort study of consecutive ventilated COVID-19 patients admitted in a French surgical intensive care unit between March 2020 and July 2020. Worsening renal function (WRF) was defined as development of a new AKI or a persistent AKI during the 5 days after mechanical ventilation initiation. We studied the association between WRF and ventilatory parameters including positive end-expiratory pressure (PEEP), CVP, and leukocytes count. Results Fifty-seven patients were included, 12 (21%) presented WRF. Daily PEEP, 5 days mean PEEP and daily CVP values were not associated with occurrence of WRF. 5 days mean CVP was higher in the WRF group compared to patients without WRF (median [IQR], 12 mm Hg [11-13] vs. 10 mm Hg [9–12]; P=0.03). Multivariate models with adjustment on leukocytes and Simplified Acute Physiology Score (SAPS) II confirmed the association between CVP value and risk of WRF (odd ratio, 1.97; 95% confidence interval, 1.12–4.33). Leukocytes count was also associated with occurrence of WRF in the WRF group (14 G/L [11–18]) and the no-WRF group (9 G/L [8–11]) (P=0.002). Conclusions In mechanically ventilated COVID-19 patients, PEEP levels did not appear to influence occurrence of WRF. High CVP levels and leukocytes count are associated with risk of WRF.
Improving zero-training brain-computer interfaces by mixing model estimators
Verhoeven, T,Hü,bner, D,Tangermann, M,Mü,ller, K R,Dambre, J,Kindermans, P J IOP 2017 Journal of neural engineering Vol.14 No.3
<P> <I>Objective</I>. Brain-computer interfaces (BCI) based on event-related potentials (ERP) incorporate a decoder to classify recorded brain signals and subsequently select a control signal that drives a computer application. Standard supervised BCI decoders require a tedious calibration procedure prior to every session. Several unsupervised classification methods have been proposed that tune the decoder during actual use and as such omit this calibration. Each of these methods has its own strengths and weaknesses. Our aim is to improve overall accuracy of ERP-based BCIs without calibration. <I>Approach</I>. We consider two approaches for unsupervised classification of ERP signals. Learning from label proportions (LLP) was recently shown to be guaranteed to converge to a supervised decoder when enough data is available. In contrast, the formerly proposed expectation maximization (EM) based decoding for ERP–BCI does not have this guarantee. However, while this decoder has high variance due to random initialization of its parameters, it obtains a higher accuracy faster than LLP when the initialization is good. We introduce a method to optimally combine these two unsupervised decoding methods, letting one method’s strengths compensate for the weaknesses of the other and vice versa. The new method is compared to the aforementioned methods in a resimulation of an experiment with a visual speller. <I>Main results</I>. Analysis of the experimental results shows that the new method exceeds the performance of the previous unsupervised classification approaches in terms of ERP classification accuracy and symbol selection accuracy during the spelling experiment. Furthermore, the method shows less dependency on random initialization of model parameters and is consequently more reliable. <I>Significance</I>. Improving the accuracy and subsequent reliability of calibrationless BCIs makes these systems more appealing for frequent use.</P>