Search

Lodging is one of the primary factors that reduce wheat yield; therefore, rapid and accurate monitoring of wheat lodging helps to provide data support for crop loss and damage response and the subsequent settlement of agricultural insurance claims. In this study, we aimed to address two problems: (1) calculating the wheat lodging area. Through comparative experiments, the SegFormer-B1 model can achieve a better segmentation effect of wheat lodging plots with a higher prediction rate and a stronger generalization ability. This model has an accuracy of 96.56%, which realizes the accurate extraction of wheat lodging plots and the relatively precise calculation of the wheat lodging area. (2) Analyzing wheat lodging areas from various growth stages. The model established, based on the mixed-stage dataset, generally outperforms those set up based on the single-stage datasets in terms of the segmentation effect. The SegFormer-B1 model established based on the mixed-stage dataset, with its mIoU reaching 89.64%, was applicable to wheat lodging monitoring throughout the whole growth cycle of wheat. [ABSTRACT FROM AUTHOR]

The emergence of deep learning methods has driven the widespread use of brain–machine interface motor imagery classification in machine control and medical rehabilitation, and has achieved classification accuracy superior to those of traditional machine learning methods. However, models trained using current mainstream deep learning methods show a maximum variation in accuracy of over 20% when using data from different subjects in the same dataset for classification. The large variation indicates the weak robustness of such models and the difficulties in feature extraction for some subjects. As motor imagery classification is aimed at individual users, it is not conducive to the diffusion of the technique if the results vary too much from one user to another. In our research, we have found the accuracy differences between different subjects are caused by the data differ in spatial characteristics and training difficulty. Therefore, exploring the differences between different subjects' data and weakening these differences can reduce the accuracy gap between subjects and ensure that the model can have good classification accuracy for each subject. We call this operation of reducing the accuracy gap individual differences weakening. To implement this operation, we propose a Double-branch Graph Convolutional Attention Neural Network (DGCAN), which uses a graph neural network to filter channels that are less disturbed by spatial location factors, and uses spatial–temporal domain convolution to focus on extracting features contained in the filtered channels, weakening the influence of spatial features contributes to individual differences weakening. We also design a loss function, EegLoss, which focuses on training hard samples and can effectively reduce the model-insensitive data contained in different subjects. We test model performance on the BCI Competition IV datasets 2a and 2b, achieving accuracies of 84% and 86%. We also compare the accuracy gap between subjects, showing that our model is effective in reducing the accuracy gap between subjects and has higher robustness than previous models. [ABSTRACT FROM AUTHOR]

Traffic prediction has drawn considerable attention due to its potential to optimize the operational efficiency of road networks. Existing methods commonly combine graph neural network (GNN) and recurrent neural network (RNN) to model spatio-temporal correlations. However, the above models still face challenges, including an inability to capture time-varying spatial correlations, inadequate consideration of spatio-temporal heterogeneity and inefficient iterative operations. To address the above challenges, in this paper, we propose a novel framework for traffic prediction, named time-based adaptive graph neural network (TAGNN). First, a novel graph learning module was developed to generate time-based adaptive graph dependency matrices, which capture hidden spatial correlations at different time steps. Second, two embedding matrices are proposed to assist the model in capturing spatio-temporal heterogeneity by attaching essential external features. Third, a temporal convolution module is proposed to capture temporal correlations by stacking grouped convolution. The receptive field expands exponentially with each additional layer, reducing parameters and improving prediction efficiency. Extensive experimental results demonstrate that our model adequately extracts the spatio-temporal correlation of nodes while ensuring prediction efficiency. • A time-based adaptive adjacency matrix capturing time-varying spatial correlations. • A novel temporal convolutional module with superior prediction efficiency. • Adding external features to capture spatio-temporal heterogeneity of traffic flows. [ABSTRACT FROM AUTHOR]

• We propose a novel multi-branch hybrid neural network which is called MBHNN. Since we split the input signal into different frequency bands for processing, the EEG classification accuracy is improved compared to the single branch structure of our proposed model. • In order to make full use of the rich information in the forward and backward directions, we introduce a bidirectional attention mechanism into the BGRU block of the EEG feature decoding model, which improves the efficiency of decoding. • Since the EEG field lacks a large amount of training data, deep learning is a data research methodology that requires a large number of training samples, this paper proposes a novel data augmentation method for expanding EEG datasets, which is called frequency domain segmentation swap (Seg-Swap). • It is worth noting that comparing the classification performance of the state-of-the-art models with the proposed model, better results are obtained on the BCI Competition IV dataset 2a and HGD, respectively. As a typical spontaneous brain-computer interface system, motor imagery has been widely used in areas such as robot control and stroke rehabilitation. Recently, researchers have started to study and propose various Convolutional Neural Network (CNN) structures based on motor imagery signals and have obtained better decoding accuracy compared with traditional machine learning algorithms. In this paper, we focus on a four-class motor imagery task. Therefore, we propose an end-to-end novel multi-branch hybrid neural network for motor imagery EEG signal classification. Notably, we divide the input signal into four frequency bands associated with the motor imagery signal. Meanwhile, we also introduced a Bidirectional Gated Recurrent Unit (BGRU) to identify EEG features. Nevertheless, it is extremely difficult to collect high-quality EEG data and the classification accuracy is degraded due to the strict requirements of the subjects and the experimental environment. To address this issue, we propose a novel data augmentation approach for frequency domain segmentation swap (Seg-Swap) for improving EEG motor imagery signal classification accuracy. We make use of the publicly available BCI IV 2a dataset and High Gamma dataset to evaluate the decoding performance of the model. The proposed multi-branch hybrid neural network (MBHNN) achieves 86.15% and 95.04% on the both datasets. Compared with several state-of-the-art (SOA) algorithms, our proposed model has a slight improvement in classification accuracy. Experimental results show that our proposed MBHNN has higher decoding classification and stronger robustness. [ABSTRACT FROM AUTHOR]

With the rapid development of information technology, the problem of the network security of unmanned aerial vehicles (UAVs) has become increasingly prominent. In order to solve the intrusion detection problem of massive, high-dimensional, and nonlinear data, this paper proposes an intrusion detection method based on the deep belief network (DBN) optimized by particle swarm optimization (PSO). First, a classification model based on the DBN is constructed, and the PSO algorithm is then used to optimize the number of hidden layer nodes of the DBN, to obtain the optimal DBN structure. The simulations are conducted on a benchmark intrusion dataset, and the results show that the accuracy of the DBN-PSO algorithm reaches 92.44%, which is higher than those of the support vector machine (SVM), artificial neural network (ANN), deep neural network (DNN), and Adaboost. It can be seen from comparative experiments that the optimization effect of PSO is better than those of the genetic algorithm, simulated annealing algorithm, and Bayesian optimization algorithm. The method of PSO-DBN provides an effective solution to the problem of intrusion detection of UAV networks. [ABSTRACT FROM AUTHOR]

• The proposed model is adaptively adjusted. • The average accuracy of the proposed model exceeds 85% on several datasets. • The model ensures better accuracy for each subject. • The proposed data augmentation method is applicable to many types of data. • The proposed model captures both intra- and inter-channel features of EEG. Background and objective: The development of deep learning has led to significant improvements in the decoding accuracy of Motor Imagery (MI) EEG signal classification. However, current models are inadequate in ensuring high levels of classification accuracy for an individual. Since MI EEG data is primarily used in medical rehabilitation and intelligent control, it is crucial to ensure that each individual's EEG signal is recognized with precision. Methods: We propose a multi-branch graph adaptive network (MBGA-Net), which matches each individual EEG signal with a suitable time-frequency domain processing method based on spatio-temporal domain features. We then feed the signal into the relevant model branch using an adaptive technique. Through an enhanced attention mechanism and deep convolutional method with residual connectivity, each model branch more effectively harvests the features of the related format data. Results: We validate the proposed model using the BCI Competition IV dataset 2a and dataset 2b. On dataset 2a, the average accuracy and kappa values are 87.49 % and 0.83, respectively. The standard deviation of individual kappa values is only 0.08. For dataset 2b, the average classification accuracies obtained by feeding the data into the three branches of MBGA-Net are 85.71 % , 85.83 % , and 86.99 % , respectively. Conclusions: The experimental results demonstrate that MBGA-Net could effectively perform the classification task of motor imagery EEG signals, and it exhibits strong generalization performance. The proposed adaptive matching technique enhances the classification accuracy of each individual, which is beneficial for the practical application of EEG classification. [ABSTRACT FROM AUTHOR]

• A parallel NLOS identification method is proposed using the multiple input neural network model. • The raw CIR and its time-frequency diagram are effectively employed. • Five different typical obstacles are tested to validate the identification method within 1–4 m. • The UWB-based positioning results of LS and WLS algorithms are compared using the proposed NLOS identification method. Ultra wide band (UWB) radio positioning technology is widely used in indoor high-precision positioning scenes, while obstacles in the wireless signal propagation path will cause the non-line of sight (NLOS) propagation of UWB signal and the reduction of positioning reliability. In this paper, an efficient NLOS identification scheme based on multiple input learning (MIL) neural network model with channel impulse response (CIR) and time-frequency diagram of CIR (TFDOCIR) is proposed by direct detection in UWB positioning system. It is experimentally demonstrated that the average NLOS identification accuracies reach 86.82%, 92.53%, 91.61%, 92.91%, 92.02% corresponding to five different obstacles including wooden door, concrete wall, metal plate, human body and glass window, respectively. Additionally, the overall NLOS identification accuracy achieves 91.74%. Through the proposed NLOS identification scheme with weight least squares (WLS), the indoor UWB-based positioning tests are performed with the average error 7.35 cm, thereby proving its ability of ranging error preventation. [ABSTRACT FROM AUTHOR]