Functional near‐infrared spectroscopy (fNIRS) is a low‐cost and noninvasive method to measure the hemodynamic responses of cortical brain activities and has received great attention in brain‐computer interface (BCI) applications. In this paper, we present a method based on deep learning and the time‐frequency map (TFM) of fNIRS signals to classify the three motor execution tasks including right‐hand tapping, left‐hand tapping, and foot tapping. To simultaneously obtain the TFM and consider the correlation among channels, we propose to utilize the two‐dimensional discrete orthonormal Stockwell transform (2D‐DOST). The TFMs for oxygenated hemoglobin (HbO), reduced hemoglobin (HbR), and two linear combinations of them are obtained and then we propose three fusion schemes for combining their deep information extracted by the convolutional neural network (CNN). Two CNNs, LeNet and MobileNet, are considered and their structures are modified to maximize the accuracy. Due to the lack of enough signals for training CNNs, data augmentation based on the Wasserstein generative adversarial network (WGAN) is performed. Several simulations are performed to assess the performance of the proposed method in three‐class and binary scenarios. The results present the efficiency of the proposed method in different scenarios. Also, the proposed method outperforms the recently introduced methods.

Traditional approaches for emotion recognition utilize unimodal physiological signals. The effectiveness of such systems is affected by some limitations. To overcome them, this paper proposes a new method based on time‐frequency maps that extract the features from multimodal biological signals. At first, the fusion of electroencephalogram (EEG) and peripheral physiological signal (PPS) is performed, and then, the two‐dimensional discrete orthonormal Stockwell transform (2D‐DOST) of the multimodal signal matrix is calculated to obtain time‐frequency maps. A convolutional neural network (CNN) is then utilized to extract the local deep features from the absolute output of the 2D‐DOST. Since there are uninformative deep features, the semisupervised dimension reduction scheme reduces them by balancing the generalization and discrimination. Finally, the classifier recognizes the emotion. The Bayesian optimizer finds the proper SSDR and classifier parameter values to maximize the recognition accuracy. The performance of the proposed method is evaluated on the DEAP dataset considering the two‐ and four‐class scenarios through extensive simulations. This dataset consists of electroencephalograph (EEG) signals in 32 channels and peripheral physiological signals (PPSs) in eight channels from 32 subjects. The proposed method reaches the accuracy of 0.953 and 0.928 for two‐ and four‐class scenarios, respectively. The results indicate the efficiency of the multimodal signals for detecting emotions compared to that of unimodal signals. Also, the results indicate that the proposed method outperforms the recently introduced ones.

Identification of modulation and space‐time block code (STBC) is an important task of receivers in applications such as military, civilian, and commercial communications. Here, we consider multiple‐input multiple‐output (MIMO) systems. We propose two methods for STBC identification when the modulation is known. We also introduce a method for joint identification of code and modulation. Additionally, we present an enhanced zero‐forcing (ZF) equaliser to improve the separation between the features of different classes. Higher order cumulants are used as the statistical features. In the first method of STBC identification, after the proposed equalisation, received data samples are segmented, and then using the mean and Frobenius norm of the covariance matrix of extracted cumulants as threshold values, the STBCs are detected. This method requires the knowledge of the threshold values for each modulation type and noise power. In the second method, the knowledge of noise power and the type of modulation are not needed. After the proposed ZF equalisation, feature vector based on the cumulants is calculated, and then support vector machine (SVM) classifier is used to classify different STBCs. In the third method, joint detection of STBC and modulation type is performed using the proposed ZF equaliser and mapping the received samples. This method deals with the theoretical values calculated from the cumulants of four STBCs and four modulations, where there is no need to know the noise power. The results indicate that the proposed methods perform well even at low signal‐to‐noise ratios (SNRs).

Sleep has great effect on physical health and quality of life. Electroencephalogram (EEG) signal is used in studying sleep process and recently, time–frequency transforms are increasingly utilised in EEG signal analysis. This study proposes an efficient method for sleep stages classification based on a time–frequency transform, namely Stockwell transform. In the introduced method, at first, the Stockwell transform is used to map each 30 s epoch of EEG signal into the time–frequency domains, which results in a complex‐valued matrix. Then, the frequency domain is divided into different non‐overlapping segments, leading to several matrices. After that, entropy features are extracted from the obtained matrices. In order to determine the sleep stage of each epoch, the computed features are applied to classifier. Support vector machine, weighted K ‐nearest neighbour, and ensemble bagged tree classifiers are considered. The Pz–Oz and Fpz–Cz channels of EEG signal from Sleep‐EDF data set and C3–A2 channel from ISRUC‐Sleep data set are used in this research. The results indicate that the proposed method outperforms the recently introduced methods.

Static bandwidth allocation for variable bit rate (VBR) video traffic forfeits the available bandwidth. Prediction of the next frame size is thus useful in dynamic bandwidth allocation. It has been shown that VBR video traces are long-range dependent, which makes one-frame-ahead prediction insufficient for dynamic bandwidth allocation. Several studies have been conducted based on the linear autoregressive (AR) model to address VBR traffic prediction. In this paper, we propose the use of a nonlinear model from the AR family called logistic smooth transition autoregressive (LSTAR) to predict VBR video traffic. Furthermore, we introduce adaptive algorithms, including least mean square (LMS), normalized LMS (NLMS), kernel LMS (KLMS), and normalized KLMS (NKLMS), to obtain the parameters of the LSTAR model used in long-range VBR traffic prediction. In the proposed model, we do not separate traffic of different frame types and use only one predictor, which results in lower computational complexity. The performance of the proposed predictor for different prediction steps was evaluated and compared with recently introduced predictors. The results indicate that the proposed nonlinear LSTAR-based predictor yields better results than the optimum linear AR predictor, i.e., Wiener-Hopf and others.

This study presents an efficient handoff algorithm for heterogeneous networks comprising macrocells, microcells, picocells, and femtocells. The proposed algorithm is based on call admission control (CAC) for selecting target base station (BS) from a list of neighbouring candidate BSs, as well as using the technique for order of preference by similarity to ideal solution (TOPSIS) as decision method. The introduced algorithm takes into account multiple criteria including measured received signal strength (RSS) and signal‐to‐interference‐plus noise ratio (SINR), predicted RSS and SINR, and number of free resource blocks of neighbouring BSs. With the use of TOPSIS, neighbouring BSs are ordered based on their priority determined using the five mentioned criteria. Selection of target BS from ordered list is then performed using CAC. Also, coverage expansion is used to retain the connection when there is not any BS for handoff. In addition, in order to predict the RSS and SINR samples, the logistic smooth transition autoregressive model is used. Performance of the proposed algorithm is evaluated in terms of ping‐pong rate, outage probability, and throughput. The results indicate efficiency of the proposed algorithm in reducing number of unnecessary handoffs while significantly increasing throughput and decreasing connection dropping when compared with conventional algorithms.

The aim of this study is to improve the performance of two‐tier macro/femtocell networks using a power control approach. In wireless networks, power control plays an important role in improving a number of performance parameters such as co‐channel interference and outage probability reduction, throughput increasing, and power saving. This study explores the evolution of centralised power control algorithm based on femtocell base station (FBS) clustering and predicted signal‐to‐interference‐plus‐noise ratio (SINR) of users. To reduce the computational complexity of centralised algorithm, dense deployed femtocells are considered in different clusters. In this case, femtocells inside one cluster make considerable interference to each other, while the interferences from femtocells of other clusters are negligible. Moreover, because of the non‐linearity of SINR samples, non‐linear logistic smooth transition autoregressive (LSTAR) model is used to model the SINR data, and then the next SINR samples are predicted from the previous samples. According to the clustered FBSs and predicted SINR, the proposed power control scheme is applied to femtocell network in the downlink. The results demonstrate that the introduced method improves the outage probability and throughput and outperforms previous methods significantly.

This study presents an efficient fractional frequency reuse scheme for macrocell network which uses six directional antennas to cover the outer region and analyses the performance. Cross‐tier interference between macrocell and femtocell networks leading to throughput and outage probability degradation is a major issue in two‐tier networks when femtocells are deployed in co‐channel with macrocells. In this study, the received interference from the macrocell network to femtocell network is analysed. Then, based on the degree of received interference, an algorithm for orthogonal resource allocation to femtocells with low cross‐tier interference is presented. According to the introduced scheme, macrocell uses all resource blocks along with a portion of the spectrum allocated to femtocell while both networks operate simultaneously. Closed‐form expressions for downlink throughput and outage probability of femtocells are also attained as well as the throughput of macrocell network. The results demonstrate that the proposed hierarchical cellular network achieves higher throughput and lower outage probability for femtocell when compared to other hierarchical macro–femto cellular networks.

In this study, the problem of variable bit rate (VBR) video traffic prediction is addressed. VBR traffic prediction is necessary in dynamic bandwidth allocation for multimedia quality of service control strategies. Autoregressive (AR) models have been widely used in VBR traffic prediction where the least mean square (LMS)‐based methods were utilised for parameter estimation. However, they are ineffective when the traffic is dynamic in nature. In this study, using the Brock, Dechert, and Scheinkman (BDS) test, it is shown that the video traffic is non‐linear. Kernel is an efficient tool to convert non‐linear data into linear one in a higher‐dimensional space. The kernel LMS (KLMS) method is proposed to forecast the next frame sizes of I, B and P frames as well as the next group‐of‐pictures (GOP) size of video traffic. Extensive simulations were performed on different video traces where different performance metrics were considered. KLMS results were very close to those of the Wiener–Hopf optimum solution and better than the results of commonly used normalised LMS and other algorithms such as the least mean kurtosis (LMK), wavelet LMK, adaptive network fuzzy inference system (ANFIS) and neural networks.

The aim of this paper is to present a non‐linear statistical model to fit and forecast the signal‐to‐interference plus noise ratio (SINR) in two‐tier heterogeneous cellular networks which consist of macrocells and femtocells. Since in these networks the number and locations of femtocell base stations (FBS) are variable, SINR forecasting can be useful in some areas such as power control and handover management. So far, linear autoregressive (AR) models have commonly been used in forecasting the received signal strength (rss) in macrocellular networks. However, AR modelling results in high mean square error (MSE) when data are non‐linear. This paper focuses on SINR which takes into account signal strength, interference and noise effects. Moreover, macro‐femto cellular network is considered. The F ‐test results show that the SINR data are non‐linear, leading to use non‐linear models instead of AR model. A non‐linear logistic smooth threshold AR (LSTAR) model is utilised to model and forecast the SINR data. Kolmogorov–Smirnov (K‐S) test demonstrates that LSTAR provides good fitness to the SINR samples. The results indicate that LSTAR model achieves much better performance in modelling and forecasting of SINR data than the AR model.

In this study, an efficient handover algorithm based on the received signal strength (RSS) prediction is presented for two‐tier macro–femtocell networks in which, because of the fading effects of channel and short coverage range of femtocells, ping‐pong handovers may take place. In the proposed approach, first each mobile station (MS) uses the recursive least square algorithm for predicting the RSS from the candidate base stations (BSs) including both femtocell and macrocell BSs. Then, according to the predicted RSS values, several future values of signal‐to‐interference plus noise ratio (SINR) are calculated. Afterwards, the candidate list of BSs is pruned according to the estimated future SINR values and the predicted RSS of each BS. Finally, the target BS which yields the highest throughput, is opted for handover. Through extensive simulations, the effects of speed of MSs and the density of femtocell BSs on the outage probability (OP), throughput and the ping‐pong rate of MSs are studied. The results show that the proposed handover algorithm outperforms the previous ones and improves the throughput of MS while it reduces the OP and the number of ping‐pong handovers.

Eye state analysis (open or closed) is an important step in fatigue detection. In this study, an efficient algorithm for eye state detection is proposed. At first, a new face detection method is presented for noisy images that finds the face area in the input image well. Then, novel algorithms for detection of eye region and eye state are introduced. The performance of the proposed method is evaluated on four different databases namely FERET, Aberdeen, IMM and CVL which contain more than 5700 images with different descents, positions, light conditions and glasses. The results show that the new method achieves more accuracy rate than the previously presented algorithms, while it does not need training data and is also computationally efficient.