In this study, a novel spatial filter design method is introduced. Spatial filtering is an important processing step for feature extraction in motor imagery-based brain-computer interfaces. This paper introduces a new motor imagery signal classification method combined with spatial filter optimization. We simultaneously train the spatial filter and the classifier using a neural network approach. The proposed spatial filter network (SFN) is composed of two layers: a spatial filtering layer and a classifier layer. These two layers are linked to each other with non-linear mapping functions. The proposed method addresses two shortcomings of the common spatial patterns (CSP) algorithm. First, CSP aims to maximize the between-classes variance while ignoring the minimization of within-classes variances. Consequently, the features obtained using the CSP method may have large within-classes variances. Second, the maximizing optimization function of CSP increases the classification accuracy indirectly because an independent classifier is used after the CSP method. With SFN, we aimed to maximize the between-classes variance while minimizing within-classes variances and simultaneously optimizing the spatial filter and the classifier. To classify motor imagery EEG signals, we modified the well-known feed-forward structure and derived forward and backward equations that correspond to the proposed structure. We tested our algorithm on simple toy data. Then, we compared the SFN with conventional CSP and its multi-class version, called one-versus-rest CSP, on two data sets from BCI competition III. The evaluation results demonstrate that SFN is a good alternative for classifying motor imagery EEG signals with increased classification accuracy.

No abstract

Our model is effective and available for simulating normal cardiac conditions and cardiovascular diseases, especially the Eisenmenger syndrome.

No abstract

Purpose The purpose of this paper is to provide an in-depth performance evaluation of funds offered by the Turkish pension system. Design/methodology/approach This paper compares aggregate fund index returns with the corresponding asset class returns, estimates a factor model to decompose excess returns to factor exposures, i.e., β return and excess return originating from residual α and analyzes persistence of fund returns using migration tables and Fama–MacBeth regressions and tests for market timing ability. Findings Majority of pension funds are unable to generate excess returns. Majority of funds are unable to generate a positive α and fund returns are predominantly driven factor exposures. There is evidence for slight persistence in returns, mainly due to factor exposures and funds do not exhibit market timing ability. Originality/value In this paper, the authors perform an in-depth analysis of pension fund performance for the Turkish pension fund system. The authors identify weaknesses and strengths of the pension fund industry and provide policy recommendations for a better design of pension fund system.