Wearable electroencephalogram (EEG) devices have shown great potential in enabling real-time monitoring of subtle changes in brain activity, providing new possibilities for the assessment and management of chronic pain. However, recognizing pain-related biomarkers from EEG data remains a complex, multitask challenge. Most existing research focuses on single-task approaches and rarely addresses this issue within a unified framework. In this article, we propose a novel deep neural network (DNN) model called multiscale frequency domain MetaFormer (MFDFormer), which is designed to simultaneously predict the presence, type, and intensity of chronic pain. The proposed MFDFormer comprises two primary subnetworks: 1) multiscale feature extractor (MFE) and 2) frequency domain MetaFormer (FDFormer) encoder. The MFE extracts diverse EEG features through convolutions with different kernel sizes, while a self-attention mechanism is integrated into MFE to emphasize the importance of interdependency among these features. The FDFormer encoder refines the output MFE features using causal convolutions to capture local patterns and projects them into a higher dimensional representation domain. Additionally, it incorporates spatial and temporal frequency domain learners (TFDLs) in parallel to effectively capture the spatial-temporal information of EEG data. Based on the publicly available brain function in chronic pain (BFCP) dataset, the proposed MFDFormer demonstrates superior performance over state-of-the-art algorithms, achieving accuracies of 97.59%, 96.02%, and 83.48% in pain or nonpain state classification (P/NSC), pain type classification (PTC), and pain intensity classification (PIC) tasks, respectively. This article proposes a unified, end-to-end DNN-based framework for multitask chronic pain recognition, providing a reliable solution with the potential to advance pain diagnosis and management in IoT and smart wearable applications.

Long-term and mobile healthcare applications have increased the use of single-channel electroencephalogram (EEG) systems. However, electromyography (EMG) artifacts often disturb EEGs. The lack of spatial correlation, diversity of waveforms, and time-varying overlap make eliminating EMG interference from a single-channel EEG difficult. To overcome these challenges, we create DSATCN, a dual-stream learning model that makes use of multi-level and multi-scale temporal dependencies in different frequency bands to perform robust EEG reconstruction. The first DSATCN stream extracts low-frequency band EEG features with reduced EMG interference. The second stream selectively combines the high-level features of the first stream with its own low-level features to refine the EEG reconstruction across the entire frequency band, lowering the risk of overfitting. Both streams employ a novel attention-based temporal convolution network (ATCN) to adaptively separate the overlapping features of EEGs and EMGs. The ATCN has multiple stages to represent various temporal dependencies at different levels. Each stage consists of multi-scale dilated convolutions and fast Fourier transform modulations, which efficiently enrich the receptive fields and establish global self-attention mechanisms. The stages’ outputs are merged by relaxed attentional feature fusion modules, which bridge semantic gaps between features at various levels. Extensive experimental results on three semi-simulated datasets containing 318,700 samples show that the proposed model significantly outperforms the existing methods in EEG reconstruction accuracy. And its computational cost meets the criteria for real-time processing. Our code is available at https://github.com/BaenRH/DSATCN.

In this work, a separating function estimation test (SFET) based detector is proposed for the problem of impropriety test of complex signals. With the establishment of closed-form expressions concerning the first two raw moments of the proposed test statistic, we can obtain the analytic form for the probability of false alarm (PFA) based on moment-matching method. Moreover, the threshold can be further obtained for a given user-specified PFA. Numerical examples are provided to verify our theoretical results and demonstrate the performance gain of our proposed detector.

Abstract Unmanned aerial vehicles as an important role for 5G and beyond networks are becoming more and more popular and have been equipped with various sensors to enable diverse emerging applications, e.g. locating sound‐emitting targets. Multi‐channel blind source separation algorithm has been applied into the unmanned aerial vehicles and micro aerial vehicles, where underdetermined mixture blind source separation is a challenging problem, i.e. the number of sources is more than the number of microphones. An optimization underdetermined blind source separation algorithm to separate the multi‐channel audio mixture signals recorded by an unmanned aerial vehicle is proposed. In the algorithm, firstly a hierarchical clustering to estimate channel as the mixing matrix initialization is employed, while using direction of arrival permutation algorithm to deal with the permutation alignment and update the mixing matrix using multiplication update method. Then the model parameters are estimated using improved expectation‐maximization update rules for the fast convergence. Finally, the frequency‐domain sources are estimated through Wiener filtering and time‐domain sources are obtained via inverse short‐time Fourier transform. Experimental results covering synthetic and real‐recorded speech source mixtures show that the proposed algorithm achieves better separation results than the state‐of‐the‐art methods.

In Internet of Things (IoT), physical-level cross-technology communication (CTC) enables IoT gateways to communicate with heterogeneous nodes economically. However, because of bandwidth asymmetry between heterogeneous technologies, many residual frequency resources are often not fully utilized. Without modification on hardware, in this article, we consider the coexistence of ultralow power (ULP) and WiFi nodes, and propose ERFR-CTC that enables an IoT gateway to fully exploit residual frequency resources without adding additional cost. With ERFR-CTC, the gateway can simultaneously communicate with ULP and WiFi nodes only via a single WiFi network interface card (NIC), which is not only economic but also very efficient. In particular, ERFR-CTC enables ULP nodes to correctly demodulate ULP signals without being interfered by WiFi signals. We then develop theoretical models to quantify available residual frequency resources and analyze the system throughput. Finally, extensive simulations verify that our model is very accurate and show that ERFR-CTC can increase the system throughput by up to 51.4%.

This paper elaborates the similarities and differences of impression of pictures between Japanese and Chinese. We conducted a questionnaire survey of 32 Chinese college students, asking them to evaluate 40 pictures from their feelings. By comparing the results of Chinese and Japanese, we found several interesting conclusions. First of all, both Chinese males and Japanese males have come up with 5 identical main factors for pictures, but these main factors have different degrees of influence. Second, Chinese females only have four main factors for pictures. Third, we compared Chinese males with Chinese females and then found their respective main factors. Lastly, by changing the way of the factor rotation, the correlation between the main factors was found.