Search

Recently, motor imagery brain–computer interfaces (BCIs) have been developed for use in motor function assistance and rehabilitation engineering. In particular, lower-limb motor imagery BCI systems are receiving increasing attention in the field of motor rehabilitation, because these systems could accurately and rapidly identify a patient's lower-limb movement intention, which could improve the practicability of the motor rehabilitation. In this study, a novel lower-limb BCI system combining visual stimulation, auditory stimulation, functional electrical stimulation, and proprioceptive stimulation was designed to assist patients in lower-limb rehabilitation training. In addition, the Riemannian local linear feature construction (RLLFC) algorithm is proposed to improve the performance of decoding by using unsupervised basis learning and representation weight calculation in the motor imagery BCI system. Three in-house experiment were performed to demonstrate the effectiveness of the proposed system in comparison with other state-of-the-art methods. The experimental results indicate that the proposed system can learn low-dimensional features and correctly characterize the relationship between the testing trial and its k-nearest neighbors. [ABSTRACT FROM AUTHOR]

A tilt integrator of the tilt‐integral‐derivative (TID) controller is an integrator to the power of a fraction. The current state of the art of TID controller is difficult to satisfy prespecified frequency‐domain specifications and is not able to build the connection between the frequency‐domain synthesis and time‐domain analysis. To fill the gap in TID control theory, a systematic tuning method of robust TID controller for first order plus time delay (FOPTD) and higher‐order processes is proposed, which is based on combining frequency‐ and time‐domain specifications synthesis. The TID controller parameters Kt$$ {K}_t $$, Ki$$ {K}_i $$, and optimal fractional order 1/n$$ 1/n $$ are settled to meet frequency‐domain specifications including phase margin, gain crossover frequency, and flat phase constraint that guarantee systemic stability and robustness. The parameter Kd$$ {K}_d $$ can be determined under the time‐domain specification including the smallest ITAE that achieves optimal dynamic performance. In addition, the steps of the proposed robust TID controller design process are given in detail, and an example is given to illustrate the corresponding steps. At last, the control and gain variation performances of the obtained TID controller are compared with some other controllers (PID, FOPI, and FOPID). Simulation results for FOPTD and higher‐order systems illustrate the superior robustness as well as the transient performance of the proposed control tuning procedure. To verify the practical usefulness of the outcomes of this paper, some experimental results on temperature control of a Peltier cell are presented. [ABSTRACT FROM AUTHOR]

Achieving high-performance numerical weather prediction (NWP) is important for people's livelihoods and for socioeconomic development. However, NWP is obtained by solving differential equations with globally observed data without capturing enough local and spatial information at the observed station. To improve the forecasting performance, we propose a novel spatial lightGBM (Light Gradient Boosting Machine) model to correct the numerical forecast results at each observation station. By capturing the local spatial information of stations and using a single-station single-time strategy, the proposed method can incorporate the observed data and model data to achieve high-performance correction of medium-range predictions. Experimental results for temperature and wind prediction in Hainan Province show that the proposed correction method performs well compared with the ECWMF model and outperforms other competing methods. [ABSTRACT FROM AUTHOR]

Abstract: The semantic web inherent the dynamic feature of the web we used today, and applications on the semantic web have to adapt themselves when the ontology they depended on had evolved. In order to adapt the ontology based data access system under dynamic environment, one of the most important problems is detecting and repairing the broken mappings when ontology (which acts as a concept view) evolved to a new state. In this paper, we provide two effective methods for detecting the broken mappings in time, namely structural way and logic way. The structural way of detecting broken mappings refers to element changes in ontology, and the logical way refers to axiom changes in ontology. [Copyright &y& Elsevier]

The non-destructive detection method of nitrogen content in rubber tree leaves based on visible/near infrared spectroscopy was studied. A total of 176 rubber tree leaf samples were collected, and the visible/near infrared data from 350~2 500 nm was used as experimental data. Firstly, a novel interval random frog (iRF) algorithm was used to select the wavelength interval combination with smallest root mean square error of cross-validation (RMSECV). Secondly, the successive projections algorithm (SPA) was used to further select the characteristic wavelength. Thirdly, the selected characteristic wavelength was taken as the input variable to establish a partial least squares (PLS) model. The results show that the wavelength selection is carried out by two-step strategy. The 714 variables from full-spectrum 2 151 are selected by rough selection of iRF algorithm. Then the 20 optimal variables further was selected from the 714 variables refined selection by SPA algorithm, which reduces the information redundancy, and significantly reduces the number of variables of 99.07%. The root mean square error of calibration (RMSEC), correlation coefficient of correlation (Rc), root mean square error of prediction (RMSEP) and correlation coefficient of prediction (Rp) are respectively 0.091 3%, 0.956 5, 0.123 8%, and 0.901 8 which have lower root mean square errors and higher correlation coefficients than PLS, iPLS, iRF, and SPA. Therefore, iRF-SPA can be used as the strategy for wavelength selection to detect the nitrogen content of rubber tree leaves. [ABSTRACT FROM AUTHOR]

The nutritional status of rubber trees ( Hevea brasiliensis ) is inseparable from the production of natural rubber. Nitrogen (N) and potassium (K) levels in rubber leaves are 2 crucial criteria that reflect the nutritional status of the rubber tree. Advanced hyperspectral technology can evaluate N and K statuses in leaves rapidly. However, high bias and uncertain results will be generated when using a small size and imbalance dataset to train a spectral estimaion model. A typical solution of laborious long-term nutrient stress and high-intensive data collection deviates from rapid and flexible advantages of hyperspectral tech. Therefore, a less intensive and streamlined method, remining information from hyperspectral image data, was assessed. From this new perspective, a semisupervised learning (SSL) method and resampling techniques were employed for generating pseudo-labeling data and class rebalancing. Subsequently, a 5-classification spectral model of the N and K statuses of rubber leaves was established. The SSL model based on random forest classifiers and mean sampling techniques yielded optimal classification results both on imbalance/balance dataset (weighted average precision 67.8/78.6%, macro averaged precision 61.2/74.4%, and weighted recall 65.7/78.5% for the N status). All data and code could be viewed on the:Github https://github.com/WeehowTang/SSL-rebalancingtest. Ultimately, we proposed an efficient way to rapidly and accurately monitor the N and K levels in rubber leaves, especially in the scenario of small annotation and imbalance categories ratios., Competing Interests: Competing interests: The authors declare no conflicts of interest in this study., (Copyright © 2024 Wenfeng Hu et al.)