In this paper we proposed a wearable electrocardiogram (ECG) telemonitoring system for atrial fibrillation (AF) detection based on a smartphone and cloud computing. A wearable ECG patch was designed to collect ECG signals and send the signals to an Android smartphone via Bluetooth. An Android APP was developed to display the ECG waveforms in real time and transmit every 30 s ECG data to a remote cloud server. A machine learning (CatBoost)-based ECG classification method was proposed to detect AF in the cloud server. In case of detected AF, the cloud server pushed the ECG data and classification results to the web browser of a doctor. Finally, the Android APP displayed the doctor’s diagnosis for the ECG signals. Experimental results showed the proposed CatBoost classifier trained with 17 selected features achieved an overall F₁ score of 0.92 on the test set (n = 7270). The proposed wearable ECG monitoring system may potentially be useful for long-term ECG telemonitoring for AF detection.

Objective . Computerized classification of sleep stages based on single-lead electroencephalography (EEG) signals is important, but still challenging. In this paper, we proposed a deep neural network called MRASleepNet for automatic sleep stage classification using single-channel EEG signals. Approach . The proposed MRASleepNet model consisted of a feature extraction (FE) module, a multi-resolution attention (MRA) module, and a gated multilayer perceptron (gMLP) module, as well as a direct pathway for computing statistical features. The FE, MRA, and gMLP modules were used to extract features, establish feature attention, and obtain temporal relationships between features, respectively. EEG signals were normalized and cut into 30 s segments, and enhanced by incorporating contextual information from adjacent data segments. After data enhancement, the 40 s data segments were input to the MRASleepNet model. The model was evaluated on the SleepEDF and the cyclic alternating pattern (CAP) databases, using such metrics as the accuracy, Kappa, and macro-F1 (MF1). Main results. For the SleepEDF-20 database, the proposed model had an accuracy of 84.5%, an MF1 of 0.789, and a Kappa of 0.786. For the SleepEDF-78 database, the model had an accuracy of 81.4%, an MF1 of 0.754, and a Kappa of 0.743. For the CAP database, the model had an accuracy of 74.3%, an MF1 of 0.656, and a Kappa of 0.652. The proposed model achieved satisfactory performance in automatic sleep stage classification tasks. Significance . The time- and frequency-domain features extracted by the FE module and filtered by the MRA module, together with the temporal features extracted by the gMLP module and the statistical features extracted by the statistical highway, enabled the proposed model to obtain a satisfying performance in sleep staging. The proposed MRASleepNet model may be used as a new deep learning method for automatic sleep stage classification. The code of MRASleepNet will be made available publicly on https://github.com/YuRui8879/ .

Objective. Steady-state visual evoked potential (SSVEP) based brain–computer interface (BCI) has the characteristics of fast communication speed, high stability, and wide applicability, thus it has been widely studied. With the rapid development in paradigm, algorithm, and system design, SSVEP-BCI is gradually applied in clinical and real-life scenarios. In order to improve the ease of use of the SSVEP-BCI system, many studies have been focusing on developing it on the hairless area, but due to the lack of redesigning the stimulation paradigm to better adapt to the new area, the electroencephalography response in the hairless area is worse than occipital region. Approach . This study first proposed a phase difference estimation method based on stimulating the left and right visual field separately, then developed and optimized a left and right visual field biphasic stimulation paradigm for SSVEP-based BCIs with hairless region behind the ear. Main results. In the 12-target online experiment, after a short model estimation training, all 16 subjects used their best stimulus condition. The paradigm designed in this study can increase the proportion of applicable subjects for the behind-ear SSVEP-BCI system from 58.3% to 75% and increase the accuracy from 74.6 ± 20.0% (the existing best SSVEP stimulus with hairless region behind the ear) to 84.2 ± 14.7%, and the information transfer rate from 14.2 ± 6.4 bits min ⁻¹ to 17.8 ± 5.7 bits min ⁻¹ . Significance. These results demonstrated that the proposed paradigm can effectively improve the BCI performance using the signal from the hairless region behind the ear, compared with the standard SSVEP stimulation paradigm.

By three multi-channel linear descriptors, i.e. spatial complexity (omega), field power (sigma) and frequency of field changes (phi), event-related EEG data within 8-30 Hz were investigated during imagination of left or right hand movement. Studies on the event-related EEG data indicate that a two-channel version of omega, sigma and phi could reflect the antagonistic ERD/ERS patterns over contralateral and ipsilateral areas and also characterize different phases of the changing brain states in the event-related paradigm. Based on the selective two-channel linear descriptors, the left and right hand motor imagery tasks are classified to obtain satisfactory results, which testify the validity of the three linear descriptors omega, sigma and phi for characterizing event-related EEG. The preliminary results show that omega, sigma together with phi have good separability for left and right hand motor imagery tasks, which could be considered for classification of two classes of EEG patterns in the application of brain computer interfaces.

The early detection of hepatic fibrosis is of critical importance. Ultrasound backscattered radiofrequency signals from the liver contain abundant information about its microstructure. We proposed a method for characterizing human hepatic fibrosis using one-dimensional convolutional neural networks (CNNs) based on ultrasound backscattered signals. The proposed CNN model was composed of four one-dimensional convolutional layers, four one-dimensional max-pooling layers, and four fully connected layers. Ultrasound radiofrequency signals collected from 230 participants (F0: 23; F1: 46; F2: 51; F3: 49; F4: 61) with a 3-MHz transducer were analyzed. Liver regions of interest (ROIs) that contained most of the liver ultrasound backscattered signals were manually delineated using B-mode images reconstructed from the backscattered signals. ROI signals were normalized and augmented by using a sliding window technique. After data augmentation, the radiofrequency signal segments were divided into training sets, validation sets and test sets at a ratio of 80%:10%:10%. In the test sets, the proposed algorithm produced an area under the receive operating characteristic curve of 0.933 (accuracy: 91.30%; sensitivity: 92.00%; specificity: 90.48%), 0.997 (accuracy: 94.29%; sensitivity: 94.74%; specificity: 93.75%), 0.818 (accuracy: 75.00%; sensitivity: 69.23%; specificity: 81.82%), and 0.934 (accuracy: 91.67%; sensitivity: 88.89%; specificity: 94.44%) for diagnosis liver fibrosis stage ≥F1, ≥F2, ≥F3, and ≥F4, respectively. Experimental results indicated that the proposed deep learning algorithm based on ultrasound backscattered signals yields a satisfying performance when diagnosing hepatic fibrosis stages. The proposed method may be used as a new quantitative ultrasound approach to characterizing hepatic fibrosis.