The motor imagery-based brain-computer interface (BCI) using electroencephalography (EEG) has been receiving attention from neural engineering researchers and is being applied to various rehabilitation applications. However, the performance degradation caused by motor imagery EEG with very low single-to-noise ratio faces several application issues with the use of a BCI system. In this paper, we propose a novel motor imagery classification scheme based on the continuous wavelet transform and the convolutional neural network. Continuous wavelet transform with three mother wavelets is used to capture a highly informative EEG image by combining time-frequency and electrode location. A convolutional neural network is then designed to both classify motor imagery tasks and reduce computation complexity. The proposed method was validated using two public BCI datasets, BCI competition IV dataset 2b and BCI competition II dataset III. The proposed methods were found to achieve improved classification performance compared with the existing methods, thus showcasing the feasibility of motor imagery BCI.

The Internet of Things (IoT) is considered a milestone for the realization of intelligent services through the interaction of smart things. Constrained Application Protocol (CoAP) was proposed by the Internet Engineering Task Force (IETF) as a web transfer protocol in the IoT. CoAP inherits the properties of the Representational State Transfer (REST) model to realize communications with low overhead. It is characterized by a small overhead and it uses the stateless UDP protocol in the transport layer. As the IoT has attracted more attention, the demands for various multimedia applications based on the IoT have increased. Video applications and IoT objects communicate through CoAP. CoAP defines a simple congestion control mechanism that can provide reliable communication between IoT endpoints. However, the congestion control mechanism was not proposed considering video streaming applications. In this paper, we evaluate the performance of video streaming applications for reliable CoAP communications between devices over a wireless network. To evaluate the performance, we perform multiple experiments by adjusting the CoAP transmission parameters. Moreover, we analyzed the effect of segment duration of a video being streamed over CoAP. The results show that the default CoAP parameters do not fulfill the stringent Quality of Experience (QoE) constraints. The experiments show that the default retransmission RTO is extremely high for the video streaming application. A small increase in the packet loss can significantly affect the video download time which increases the risk of playback interruption. Through experiments, we show that the performance of video streaming applications can be improved by tuning the congestion control parameters according to the network conditions. A smaller RTO value can ensure significant reduction in the segment download time. Similarly, the video can be downloaded quickly by increasing the number of unacknowledged transactions. Furthermore, the experiments show that the risk of playback interruption can be mitigated by downloading longer segments.

Electrocardiogram (ECG) signal has been commonly used to analyze the complexity of heart rate variability (HRV). For this, various entropy methods have been considerably of interest. The multiscale entropy (MSE) method, which makes use of the sample entropy (SampEn) calculation of coarse-grained time series, has attracted attention for analysis of HRV. However, the SampEn computation may fail to be defined when the length of a time series is not enough long. Recently, distribution entropy (DistEn) with improved stability for a short-term time series has been proposed. Here, we propose a novel multiscale DistEn (MDE) for analysis of the complexity of short-term HRV by utilizing a moving-averaging multiscale process and the DistEn computation of each moving-averaged time series. Thus, it provides an improved stability of entropy evaluation for short-term HRV extracted from ECG. To verify the performance of MDE, we employ the analysis of synthetic signals and confirm the superiority of MDE over MSE. Then, we evaluate the complexity of short-term HRV extracted from ECG signals of congestive heart failure (CHF) patients and healthy subjects. The experimental results exhibit that MDE is capable of quantifying the decreased complexity of HRV with aging and CHF disease with short-term HRV time series.

This paper presents a new approach of the normalized subband adaptive filter (NSAF) which directly exploits the sparsity condition of an underlying system for sparse system identification. The proposed NSAF integrates a weightedl1-norm constraint into the cost function of the NSAF algorithm. To get the optimum solution of the weightedl1-norm regularized cost function, a subgradient calculus is employed, resulting in a stochastic gradient based update recursion of the weightedl1-norm regularized NSAF. The choice of distinct weightedl1-norm regularization leads to two versions of thel1-norm regularized NSAF. Numerical results clearly indicate the superior convergence of thel1-norm regularized NSAFs over the classical NSAF especially when identifying a sparse system.

Among various methods for frequency recognition of the steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) study, a task-related component analysis (TRCA), which extracts discriminative spatial filters for classifying electroencephalogram (EEG) signals, has gathered much interest. The TRCA-based SSVEP method yields lower computational cost and higher classification performance compared to existing SSVEP methods. In spite of its utility, the TRCA-based SSVEP method still suffers from the degradation of the frequency recognition rate in cases where EEG signals with a short length window are used. To address this issue, here, we propose an improved strategy for decoding SSVEPs, which is insensitive to a window length by carrying out two-step TRCA. The proposed method reuses the spatial filters corresponding to target frequencies generated by the TRCA. Followingly, the proposed method accentuates features for target frequencies by correlating individual template and test data. For the evaluation of the performance of the proposed method, we used a benchmark dataset with 35 subjects and confirmed significantly improved performance comparing with other existing SSVEP methods. These results imply the suitability as an efficient frequency recognition strategy for SSVEP-based BCI applications.