http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
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>
Examining Temporal Effects of Lifecycle Events on Transport Mode Choice Decisions
Marloes Verhoeven, Theo Arentze, Harry Timmermans, Peter van der Waerden 서울시립대학교 도시과학연구원 2007 International journal of urban sciences (IJUS) Vol. No.
This paper describes the first results of a study on the impact of events on transport mode choice decisions. An Internet-based survey was designed to collect data concerning seven structural lifecycle events. In addition, respondents answered questions about personal and household characteristics, possession and availability of transport modes and their current travel behaviour. In total, 710 respondents completed the online survey. The complexity of transport mode choice is modelled using a Bayesian Decision Network. This paper focuses only on the time influence of events on transport mode choice decisions. We assume that people change or at least reconsider their behaviour after a structural lifecycle event, at times directly after experiencing a change and at times only after a period of time. We estimated a multinomial choice model to estimate the effect of these structural events, and in particular of the length of the time elapsed, on transport mode choice.
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>