The lower limb exoskeleton provides assistance by following the lower limb joints’ desired motion trajectory. However, angle control is not enough to meet the requirements in some special circumstances such as encountering obstacles. In the swing phase of the attached leg with the exoskeleton, there is a different contact force between the sole and the road surface in different road conditions. Therefore, it is particularly important to control the joint angle and contact force simultaneously, that is, it is not only necessary to follow the desired angle but also to minimize the influence of external contact force. In this article, a novel scheme is proposed to adjust the trajectory dynamically in the swing phase. First of all, the physical model is streamlined and the Lagrangian principle is carried out to dynamic analysis and established a model of lower limb exoskeleton in the swing phase. Furthermore, the angle dynamics equation is transformed into a Cartesian coordinate system to calculate the end contact force for the impedance model. Finally, the impedance control strategy together with a disturbance observer is designed which is suitable for nonlinear and strong coupling characteristics. The simulation result shows that the control system can follow the angle accurately in the condition of minimizing external constraints. Hardware experiment shows that lower extremity exoskeleton can adjust motion trajectory actively when encountering obstacles and complete the movement trajectory tracking at the same time.
Accurate estimation of tropical cyclone (TC) intensity is the key to understanding and forecasting the behavior of TC and is crucial for initialization in forecast models and disaster management in the meteorological industry. TC intensity estimation is a challenge because it requires domain knowledge to manually extract TC cloud structure features and form various sets of parameters obtained from satellites. In this paper, a novel hybrid model is proposed based on convolutional neural networks (CNNs) for TC intensity estimation with satellite remote sensing. According to the intensity of TCs, we divide them into three types and use three different models for intensity regression, respectively. The results show that the use of piecewise thinking can improve the model's fitting speed on small samples. A classification network is provided to classify unlabeled TC samples before TC regression, whose results would determine which regression network to estimate these samples. Finally, the estimation values are sent to the backpropagation (BP) neural network to fit the suitable intensity values. Experimental results demonstrate that our model achieves high accuracy and low root-mean-square error (RMSE up to 8.91 kts) by just using inferred images. INDEX TERMS Convolutional neural networks, hybrid model, tropical cyclone intensity estimation, infrared imagery.
With the deterioration of the ecological environment and the depletion of fossil energy, fuel cells, representing a new generation of clean energy, have received widespread attention. This review summarized recent progress in noble metal-based core–shell catalysts for oxygen reduction reactions (ORRs) in proton exchange membrane fuel cells (PEMFCs). The novel testing methods, performance evaluation parameters and research methods of ORR were briefly introduced. The effects of the preparation method, temperature, kinds of doping elements and the number of shell layers on the ORR performances of noble metal-based core–shell catalysts were highlighted. The difficulties of mass production and the high cost of noble metal-based core–shell nanostructured ORR catalysts were also summarized. Thus, in order to promote the commercialization of noble metal-based core–shell catalysts, research directions and prospects on the further development of high performance ORR catalysts with simple synthesis and low cost are presented.
Mild Cognitive Impairment (MCI) is an early stage of dementia, which may lead to Alzheimer’s disease (AD) in older adults. Therefore, early detection of MCI and implementation of treatment and intervention can effectively slow down or even inhibit the progression of the disease, thus minimizing the risk of AD. Currently, we know that published work relies on an analysis of awake EEG recordings. However, recent studies have suggested that changes in the structure of sleep may lead to cognitive decline. In this work, we propose a sleep EEG-based method for MCI detection, extracting specific features of sleep to characterize neuroregulatory deficit emergent with MCI. This study analyzed the EEGs of 40 subjects (20 MCI, 20 HC) with the developed algorithm. We extracted sleep slow waves and spindles features, combined with spectral and complexity features from sleep EEG, and used the SVM classifier and GRU network to identify MCI. In addition, the classification results of different feature sets (including with sleep features from sleep EEG and without sleep features from awake EEG) and different classification methods were evaluated. Finally, the MCI classification accuracy of the GRU network based on features extracted from sleep EEG was the highest, reaching 93.46%. Experimental results show that compared with the awake EEG, sleep EEG can provide more useful information to distinguish between MCI and HC. This method can not only improve the classification performance but also facilitate the early intervention of AD.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.