Surface electromyography (sEMG)-based gesture recognition can achieve high intra-session performance. However, the inter-session performance of gesture recognition decreases sharply due to the shift in data distribution. Therefore, developing a robust model to minimize the data distribution difference is crucial to improving the user experience. In this work, based on the inter-session gesture recognition task, we propose a novel algorithm called locality preserving and maximum margin criterion (LPMM). The LPMM algorithm integrates three main modules, including domain alignment, pseudo-label selection, and iteration result selection. Domain alignment is designed to preserve the neighborhood structure of the feature and minimize the overlap of different classes. The pseudo-label selection and iteration result selection can avoid the decrease in accuracy caused by mislabeled samples. The proposed algorithm was evaluated on two of the most widely used EMG databases. It achieves a mean accuracy of 98.46% and 71.64%, respectively, which is superior to state-of-the-art domain adaptation methods.

Gaze estimation based on electrooculograms (EOGs) has been widely explored. However, the inter-subject variability of EOGs still leaves a significant challenge for practical applications. It contributes to performance degradation when handling inter-subject issues. In this paper, an unsupervised transfer learning approach with an adaptive reweighting and resampling (ARR) strategy to fully consider individual variability is proposed for EOG-based gaze angle estimation. It allows quantifying domain shifts by leveraging the source-target similarities, reweighting and resampling the source data to retain relevant instances and disregard irrelevant instances during adaptation. Specifically, our proposed methodology first assesses the domain shifts via decomposing transformation matrices, which are estimated between the training subjects (denoted as multi-source domains) and the test subject (denoted as target domain). Then, the multi-domain shifts are assigned as weighted indicators to resample the multi-source domains for model training. Comparative experiments with several prevailing transfer learning methods including CORrelation ALignment (CORAL), Geodesic Flow Kernel (GFK), Joint Distribution Adaptation (JDA), Transfer component analysis (TCA), and Balanced distribution adaption (BDA) using two different normalization processes were conducted on a realistic scenario across 18 subjects. Experimental results demonstrate that the ARR strategy can significantly improve performance (mean absolute error (MAE) reduction: 7.0%, root mean square error (RMSE) reduction: 6.3%), outperforming the prevailing methods. Besides, the impacts of data diversity and data size on ARR strategy are further investigated. It exhibits that data size is more important than data diversity for EOG-based gaze angle estimation, and also presents the benefits of the ARR strategy for dealing with practical scenarios.

Sleep staging plays a critical role in evaluating the quality of sleep. Currently, most studies are either suffering from dramatic performance drops when coping with varying input modalities or unable to handle heterogeneous signals. To handle heterogeneous signals and guarantee favorable sleep staging performance when a single modality is available, a pseudo-siamese neural network (PSN) to incorporate electroencephalography (EEG), electrooculography (EOG) characteristics is proposed (PSEENet). PSEENet consists of two parts, spatial mapping modules (SMMs) and a weight-shared classifier. SMMs are used to extract high-dimensional features. Meanwhile, joint linkages among multi-modalities are provided by quantifying the similarity of features. Finally, with the cooperation of heterogeneous characteristics, associations within various sleep stages can be established by the classifier. The evaluation of the model is validated on two public datasets, namely, Montreal Archive of Sleep Studies (MASS) and SleepEDFX, and one clinical dataset from Huashan Hospital of Fudan University (HSFU). Experimental results show that the model can handle heterogeneous signals, provide superior results under multimodal signals and show good performance with single modality. PSEENet obtains accuracy of 79.1%, 82.1% with EEG, EEG and EOG on Sleep-EDFX, and significantly improves the accuracy with EOG from 73.7% to 76% by introducing similarity information.

Despite the recent advances in automatic sleep staging, few studies have focused on real-time sleep staging to promote the regulation of sleep or the intervention of sleep disorders. In this paper, a novel network named SwSleepNet, that can handle both precisely offline sleep staging, and online sleep stages prediction and calibration is proposed. For offline analysis, the proposed network coordinates sequence broadening module (SBM), sequential CNN (SCNN), squeeze and excitation (SE) block, and sequence consolidation module (SCM) to balance the operational efficiency of the network and the comprehensive feature extraction. For online analysis, only SCNN and SE are involved in predicting the sleep stage within a short-time segment of the recordings. Once more than two successive segments have disparate predictions, the calibration mechanism will be triggered, and contextual information will be involved. In addition, to investigate the appropriate time of the segment that is suitable to predict a sleep stage, segments with five-second, three-second, and two-second data are analyzed. The performance of SwSleepNet is validated on two publicly available datasets Sleep-EDF Expanded and Montreal Archive of Sleep Studies (MASS), and one clinical dataset Huashan Hospital Fudan University (HSFU), with the offline accuracy of 84.5%, 86.7%, and 81.8%, respectively, which outperforms the state-of-the-art methods. Additionally, for the online sleep staging, the dedicated calibration mechanism allows SwSleepNet to achieve high accuracy over 80% on three datasets with the short-time segments, demonstrating the robustness and stability of SwSleepNet. This study presents a real-time sleep staging architecture, which is expected to pave the way for accurate sleep regulation and intervention.

Tedious parameter settings and poor performances seriously affect the entropy estimation's effectiveness in time series analysis. To solve these limits, we propose a conceptually novel definition, cumulative diversity pattern entropy (CDEn), focusing on eliminating parameter selections and improving quantization accuracy, stability, and robustness. The CDEn algorithm consists of three steps: 1) improved phase-space reconstruction (IPSR) with constant embedding dimension$m= 2$and time delay$\tau =1$; 2) diversity pattern partition generated by the cosine similarity between adjacent vectors; and 3) entropy calculation based on the normalized cumulative probability distribution. Numerical experiments are performed using 7 synthetic datasets and 15 baseline entropy methods for comparative validation. The results confirm CDEn's best description of chaotic/stochastic dynamics with the highest quantization accuracy and the lowest error rate of 2.04%. The coefficient of variation (CV) results also verify CDEn's excellent quantization stability with CV lower than 10−2. The relative change rate results demonstrate that CDEn achieves the best robustness to data length and noise. Finally, the entropy algorithms are applied to a real-world dataset, i.e., neonatal sleep EEG analysis. The results further confirm that suggested CDEn outperforms the state-of-the-art entropy methods, with the minimum outliers and best statistical significance (highest mean of effect size, 1.22) in characterizing the neurodynamics of different sleep stages.

Deep learning methods have become an important tool for automatic sleep staging in recent years. However, most of the existing deep learning-based approaches are sharply constrained by the input modalities, where any insertion, substitution, and deletion of input modalities would directly lead to the unusable of the model or a deterioration in the performance. To solve the modality heterogeneity problems, a novel network architecture named MaskSleepNet is proposed. It consists of a masking module, a multi-scale convolutional neural network (MSCNN), a squeezing and excitation (SE) block, and a multi-headed attention (MHA) module. The masking module consists of a modality adaptation paradigm that can cooperate with modality discrepancy. The MSCNN extracts features from multiple scales and specially designs the size of the feature concatenation layer to prevent invalid or redundant features from zero-setting channels. The SE block further optimizes the weights of the features to optimize the network learning efficiency. The MHA module outputs the prediction results by learning the temporal information between the sleeping features. The performance of the proposed model was validated on two publicly available datasets, Sleep-EDF Expanded (Sleep-EDFX) and Montreal Archive of Sleep Studies (MASS), and a clinical dataset, Huashan Hospital Fudan University (HSFU). The proposed MaskSleepNet can achieve favorable performance with input modality discrepancy, e.g. for single-channel EEG signal, it can reach 83.8%, 83.4%, 80.5%, for two-channel EEG+EOG signals it can reach 85.0%, 84.9%, 81.9% and for three-channel EEG+EOG+EMG signals, it can reach 85.7%, 87.5%, 81.1% on Sleep-EDFX, MASS, and HSFU, respectively. In contrast the accuracy of the state-of-the-art approach which fluctuated widely between 69.0% and 89.4%. The experimental results exhibit that the proposed model can maintain superior performance and robustness in handling input modality discrepancy issues.

In this article, an adaptive neural piecewise implicit inverse control strategy is proposed to effectively compensate for butterfly hysteresis effectively. First, a new butterfly Krasnoselskii–Pokrovskii (BKP) model is developed for the double-loop butterfly hysteresis characteristics. Second, an adaptive neural piecewise implicit inverse control strategy is designed to mitigate the butterfly-like hysteresis without constructing its analytical inverse model. Finally, experimental results on the dielectric elastomer actuator (DEA) motion control platform demonstrate the effectiveness of the adaptive neural piecewise implicit inverse control strategy.

Maglev systems using reluctance actuators (RAs) are increasingly being used in ultra-precision motion platforms due to the non-contact feature of the guide rails. However, because the control system of RAs suffers from strong nonlinearity and uncertainty, it is challenging to realize the high-precision position control of RAs. In this paper, a fractional-order sliding mode control with adaptive neural network (ANN-FSMC) approach is proposed to achieve high-precision position control of RAs. Based on the basic sliding mode control (SMC) approach, the proposed ANN-FSMC introduces the sliding surface with the term of fractional-order calculus. It guarantees that the state converges to the sliding manifold with fast response and small overshoot, and enhances the positioning precision of RAs. Besides, the radial basis function (RBF) neural network is utilized to compensate for the lumped disturbances including magnetic flux leakage, fringe flux, eddy currents, and uncompleted hysteresis compensation, etc. The stability of ANN-FSMC is analyzed and proved according to the Lyapunov Theorem. Finally, experiments are conducted on an RA-based maglev-guided system, and results show that ANN-FSMC can improve the position control performance and disturbance suppression capability of RAs more effectively than the conventional SMC method combined with RBF neural networks.

Magnetic encoders have been widely used in many industrial fields due to their appealing features such as working in harsh environment, anti-interference, low cost and so on. Ideally, the output of a magnetic encoder is a pair of quadrature sinusoidal signals. The raw signals of magnetic encoders, however, are often composed of various sources of disturbances and noises, and consequently the measurement accuracy is deteriorated. In this paper, we propose a new method by combining an adaptive neural network and a phase-locked loop (ADNN-PLL). In the proposed method, the non-ideal factors are first estimated and eliminated by ADNN, and then PLL, as a closed-loop system, is used to track signals. The ADNN-PLL method can compensate for a variety of commonly seen disturbances including amplitude mismatch, phase deviation, low and high order harmonics, dc offsets and random noises. In addition, the adaptive learning rate in the neural network accelerates the speed of convergence and ensures better system stability. Simulation results are provided to demonstrate the effectiveness of the proposed ADNN-PLL method.

Tracking and synchronization accuracies are key performance indicators for advanced wafer scanners. In this paper, we propose a new Parallel Inverse-Model-based Iterative Learning Control (PIMILC) method in which the tracking and synchronization accuracies of the master-slave wafer scanners are jointly considered. In PIMILC, a parallel ILC structure is adopted and the tracking error of the wafer stage filtered by a compensation filter is fed into the reticle stage to decouple the learning system. Furthermore, an inverse-model-based learning law with robustness enhancement techniques is used to trade-off among robustness, accuracy and convergence rate. Simulation results confirm that the PIMILC method can significantly reduce the tracking and synchronization errors compared to prior work.

A novel wearable sensor system for seizure monitoring of neonates comprised of smart clothing, video recording and cloud platform is presented. Textile electrodes and Inertial Measurement Unit (IMU) are embedded in the smart clothing to obtain ECG signal and motion signal whereby epileptic seizure detection algorithm is performed. Moreover, a video monitoring module provides real-time information about patients. The cloud platform receives the pre-processed data and enables remote monitoring, centralized signal processing and data management. Comparison with commercial instruments shows that the smart clothing is capable of acquiring high-quality signals. Pilot tests under disinfection operations at Children's Hospital of Fudan University confirm clinical feasibility of the proposed system. The scalability and modularity of the unobtrusive wearable front end and the design of system architecture based on cloud enable the whole system with great potential in clinical practice and home monitoring scenarios.

We address ranging energy optimization for an unsynchronized localization system, which features robust sensor positioning, in the sense that specific accuracy requirements are fulfilled within a prescribed service area. Optimization problems related to the ranging energy of a sensor and beacons are proposed, after which a practical algorithm based on semidefinite programming is presented. The effectiveness of the algorithm is illustrated by a numerical experiment.

To address system goodput and energy efficiency enhancement, this paper studies packet size optimization for IEEE 802.15.4 networks. Taking into account of the CSMA-CA contention, protocol overhead, and channel condition, new analytical models are proposed to calculate the goodput and the energy consumption. Optimal packet sizes are derived from the new models for different network scenarios. The analytical results are validated by the simulation results. The results from our work can be used to facilitate efficient packet segmentation.

Energy efficiency has become one of the major considerations for protocol design in wireless networks, especially sensor networks. Carrier sense multiple access with collision avoidance (CSMA-CA) mechanisms that incorporate energy saving features have been proposed for contention-based medium access for such networks (e.g., in IEEE 802.15.4 standard). In this paper, we develop a new analytical model for the performance of an energy conserving CSMA-CA in both saturated and periodic traffic conditions. The accuracy of the throughput predicted by the analysis is confirmed via comparison with simulation.

This paper presents a framework to minimize energy consumption in the medium access control (MAC) layer for wireless sensor networks. While satisfying a range of quality of service (QoS) requirements, such as the packet transmission success rate and maximum delay constraint, we optimally choose the lengths of periods in which sensors are active and inactive, such that the energy consumption per unit time in the entire network is minimized. We first use our framework to optimize the values of the MAC attributes macBeaconOrder and macSuperframeOrder in an IEEE 802.15.4 beacon-enabled star network. Then we consider a much simpler protocol, which we call "select-and-transmit" (S&T), and the same framework is applied to find the optimal lengths of the active and inactive portions. Finally, we compare the minimal energy consumption of the IEEE 802.15.4 MAC and S&T under the same QoS requirements and show that the IEEE 802.15.4 MAC outperforms S&T in most cases. However, the S&T MAC performs better than the standard under our framework in certain scenarios, e.g., event-driven sensor networks where the packet transmission success rate is usually low.

We propose a new low-complexity MAC solution for multimedia CDMA cellular networks considering packet reservation and scheduling jointly. The proposed MAC, which we call joint PRMA and packet scheduling (JPPS), treats real-time traffic and non-real-time traffic separately. Once a real-time traffic flow (a continuous packet burst) is admitted to the system, its code channel(s) will be implicitly reserved until its last packet is transmitted, as in PRMA. Real-time traffic has delay priority over non-real-time, and we also prioritize within various non-real-time traffic flows. Packet scheduling techniques are then used to schedule all the real-time and non-real-time packets. Furthermore, an optimal channel access scheme based on a simple linear program is proposed. Simulation results comparing the performance of JPPS versus the well-known MAC protocol WISPER demonstrate lower delay for real time traffic and lower overall packet loss ratio for JPPS