Search

Research on emotion recognition based on electroencephalogram (EEG) signals is important for human emotion detection and improvements in mental health. However, the importance of EEG signals from different brain regions and frequency bands for emotion recognition is different. For this problem, this paper proposes the Capsule–Transformer method for multi-region and multi-band EEG emotion recognition. First, the EEG features are extracted from different brain regions and frequency bands and combined into feature vectors which are input into the fully connected network for feature dimension alignment. Then, the feature vectors are inputted into the Transformer for calculating the self-attention of EEG features among different brain regions and frequency bands to obtain contextual information. Finally, utilizing capsule networks captures the intrinsic relationship between local and global features. It merges features from different brain regions and frequency bands, adaptively computing weights for each brain region and frequency band. Based on the DEAP dataset, experiments show that the Capsule–Transformer method achieves average classification accuracies of 96.75%, 96.88%, and 96.25% on the valence, arousal, and dominance dimensions, respectively. Furthermore, in emotion recognition experiments conducted on individual brain regions or frequency bands, it was observed that the frontal lobe exhibits the highest average classification accuracy, followed by the parietal, temporal, and occipital lobes. Additionally, emotion recognition performance is superior for high-frequency band EEG signals compared to low-frequency band signals. [ABSTRACT FROM AUTHOR]

Twin delayed deep deterministic (TD3) policy gradient has several limitations when applied in planning a path in environment with a number of dilemmas according to our experiment, due to the complexity of the robot path planning task, the rate of convergence of TD3 algorithm is slow and the rate of collision is high. To address this problem, deep dense dueling twin delayed deep deterministic (D3-TD3) architecture is proposed, a method that preserves important information from cross-layer inputs through dense connections and divides the network into a value function and a dominance function, thus, allowing for faster convergence when solving complex tasks. Finally, a spatial model based on three-dimension (3D) point cloud is built, and simulation experimental results show that in static environment, the algorithm proposed in the paper has 40.6% fewer collisions compared to TD3, 30% fewer collisions compared to TD3-BC, 19.2% fewer collisions compared to Dueling TD3 and 17.4% fewer collisions compared to deep dense TD3. In dynamic and static environment, the algorithm proposed in the paper has 34.4% fewer collisions compared to TD3, 24% fewer collisions compared to TD3-BC, 6% fewer collisions compared to Dueling TD3 and 25% fewer collisions compared to deep dense TD3. [ABSTRACT FROM AUTHOR]

Magnetic and inertial measurement units (MIMUs) are mainly used for determining the attitude of moving bodies. The extended Kalman filter (EKF) and the complementary filters (CFs) are the most commonly applied algorithms for calculating the attitude of the body that an MIMU is attached. Despite its much higher accuracy than CFs, the time-consuming EKF may not be competent for the work of attitude calculation if a microcomputer with limited computation power is used. To any attitude calculating algorithm, its posterior attitude (PA) is computed as: PA = prior attitude + gain matrix (GM) $\times $ innovation. The prior attitude and the innovation are derived from the measurements of the gyroscope, the accelerometer, and the magnetometer. The detailed analysis in this study found that the reason for the performance difference between EKF and CFs is their different structures of the GMs, which promotes the authors to construct a new GM. Based on some reasonable assumptions, the GM of EKF is simplified under the principle that the computation accuracy of PA is decreased as little as possible, but its computation burden is reduced as much as possible. After the replacement of the GM of the EKF by the innovatively designed GM, a new CF, named time-efficient complementary Kalman gain filter (TCF), is proposed. The simulation and experimental results show that TCF performs better than two CFs and is close to EKF in terms of attitude estimation accuracy but uses nearly the same computation time as the two CFs and about half of the computation time required by EKF. [ABSTRACT FROM AUTHOR]

In complex driving scenarios, automated vehicles should behave reasonably and respond adaptively with high computational efficiency. In this paper, a computational efficient motion planning method is proposed, which considers traffic interaction and accelerates calculation. Firstly, the behavior is decided by connecting the points on the unequally divided road segments and lane centerlines, which simplifies the decision-making process in both space and time span. Secondly, as the dynamic vehicle model with changeable longitudinal velocity is considered in the trajectory generation module, the C/GMRES algorithm is used to accelerate the calculation of trajectory generation and realize on-line solving in nonlinear model predictive control. Meanwhile, the motion of other traffic participants is more accurately predicted based on the driver's intention and kinematics vehicle model, which enables the host vehicle to obtain a more reasonable behavior and trajectory. The simulation results verify the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Fruit images collected by picking robots in natural environments have problems such as uneven lighting, complex backgrounds, occlusion of branches and leaves, and overlapping fruits and vegetables, which greatly increases the difficulty for picking robots to accurately identify target fruits and vegetables. Meanwhile, most fruits and vegetables have similar‐color backgrounds. Compared with the ones with different colors in the background, fruits and vegetables in similar‐color backgrounds are similar to the colors of their leaves and surrounding weeds, which increases the difficulty of identification. Therefore, realizing the accurate identification of fruits and vegetables in similar‐color backgrounds is vital to realize the dynamic monitoring of the growth of fruits and vegetables and intelligent picking, which has important value and application prospects for optimizing plantation management and automated harvesting operations. The work summarized the specific characteristics of fruits and vegetables with the close‐color background and the different processing procedures in the identification process. The following methods have been summarized, for example, image acquisition, image preprocessing, feature extraction, image segmentation, and fruit and vegetable detection in the process, and some methods were compared. Finally, the current research was discussed, and a solution was proposed for the different processing steps of fruit and vegetable recognition in similar‐color backgrounds. Deep learning methods were combined with some traditional methods to identify fruits and vegetables with close‐color background, which provides references for further research in various aspects. [ABSTRACT FROM AUTHOR]

The accurate trajectory of the train ahead with more dynamic behaviour, such as train position, speed, acceleration, etc., is the critical issue of virtual coupling for future railways, which can drastically reduce their headways and increase line capacity. This paper presents an integrated convolutional neural network (CNN) and long short-term memory (LSTM) hybrid model for the task of trajectory prediction. A CNN–LSTM hybrid algorithm has been proposed. The model employs CNN and LSTM to extract the spatial dimension feature of the trajectory and the long-term dependencies of train trajectory data, respectively. The proposed CNN–LSTM model has superiority in achieving collaborative data mining on spatiotemporal measurement data to simultaneously learn spatial and temporal features from phasor measurement unit data. Therefore, the high-precision prediction of the train trajectory prediction is achieved based on the sufficient fusion of the above features. We use real automatic train operation (ATO) collected data for experiments and compare the proposed method with recurrent neural networks (RNN), recurrent neural networks (GRU), LSTM, and stateful-LSTM models on the same data sets. Experimental results show that the prediction performance of long-term trajectories is satisfyingly accurate. The root mean square error (RMSE) error can be reduced to less than 0.21 m, and the hit rate achieves 93% when the time horizon increases to 4S, respectively. [ABSTRACT FROM AUTHOR]

In this article, we combined a search-based technique with model-based mutation testing to overcome the inherent computational cost that comes with the test-case generation of the Chinese Train Control System Level 3 (CTCS-3) train control system by providing a newly designed fitness function to guide the search process of test cases. First, we defined the test-case inputs as timed input traces, which can easily deal with noninput-enabled systems with both input events and input variables. Because the input sequence of the timed input traces can be potentially infinite, they can be more flexible in dealing with different scales of train control systems than can the traditional model-checking techniques. Furthermore, we proposed a way of encoding timed input traces as blocks of inputs for the genetic algorithm, together with crossover and mutation operators, to reduce the search space and improve algorithm efficiency. By using the encoded input blocks as individuals, the test cases generated from the train control system will be more compact and easier to perform. Finally, we applied the mutation operators to the mode-transition function of the CTCS-3 from which all of the known faults have been considered comprehensively. To evaluate the coverage of the test cases generated and compare the performance of different methods, the benchmarking indicators of conformance relation score (CRS), average CRS, and weighted CRS have all been analyzed. In addition, we performed an experiment to determine the extent to which the maximum block width can influence the search performance as a guidance for parameter selection in practice. [ABSTRACT FROM AUTHOR]

Rail transit plays a significant role in the operation of an efficient and effective urban public transportation system. Safety and capacity are some of the most crucial objectives in railway operations. The communication-based train control (CBTC) system is a continuous and automatic train control system that realizes constant and high-capacity train ground two-way communication. In this study, a dynamic headway model of the 'softwall' moving-block approach is proposed for CBTC to increase the track capacity and improve dispatching efficiency based on the train trajectory prediction. For this precise trajectory prediction task, we introduce a hybrid trajectory prediction model to combine Long Short-term memory (LSTM) and Kalman Filter (KF) to extract the train's local data features and learn the long-term dependencies, respectively. Then we present a dynamic headway model to maximize the train headway and reduce the track distance. The leading trains' information is used to construct the iterative learning control strategy, and the predicted trajectory is input into the algorithm of the headway model. We use a simulation model of the rail network in Chengdu to demonstrate the effectiveness of our proposed approach. The results show the Mean Absolute Error (MAE) of the predicted trajectory retreated to 93.97 cm and reductions in operation headway of at least 64.33% under the dynamic headway model versus the traditional moving-block model. [ABSTRACT FROM AUTHOR]

The work proposed a method for recognising the green grapes in the orchard based on multi-source image fusion. First, the acquired multi-source images were denoised based on median filtering and wavelet transform. After extracting the feature points by the improved SURF (speeded up robust features) method, the registration was completed based on the consistency of feature offset and the affine relationship between images. The registered multi-source images were fused based on the CS (compressed sensing) and NSCT-DWT (non-down sampled contourlet transform-discrete wavelet transform). Then the MI-OPT (mutual-information optimal threshold) and the minimum circumscribed rectangle were used to segment the fused images and recognise fruits. The experimental results showed that the information of the target fruits in the fused images was complete. Therefore, compared with the K-means method using colour components of the visible light image and the OTSU (proposed by Nobuyuki Otsu and named after him) method based on near-infrared image, the fruit region obtained by the algorithm in the work was complete. On this basis, the average recognition rate of green grapes reached 92.1%. [ABSTRACT FROM AUTHOR]

The Chinese Train Control System level 3 (CTCS-3) is an open and real-time safety-critical system. Due to the non-deterministic delay behavior in the environment, there is a large number of stimuli to the train control system with different patterns of arrival times. Control strategies must be well considered, as either the logic of the function fails or the real-time constraints are dissatisfied, may directly lead to significant human injury or financial loss. In this paper, we introduce the notion of test specification and the relativized timed input/output conformance based on timed automata theory. A new test case generation and execution algorithm has been proposed, by which the tester can reset Implementation Under Test (IUT) whenever they want, make it more sense in specific domain fields. We apply UPPAAL-TRON based online conformance testing framework to test nondeterministic delay behavior of Radio Block Center (RBC) handover scenario of CTCS-3 against critical safety, real-time, and liveness properties (defined in the system requirement specification (SRS) documents). Our experiments show that assurance of collision avoidance and train non-derailment can be guaranteed, but emergency brake intervention may happen with low probability in this scenario under the requirements specified in the SRS document. [ABSTRACT FROM AUTHOR]

Patients with attention-deficit/hyperactivity disorder (ADHD) have shown abnormal functional connectivity and network disruptions at the whole-brain static level. However, the changes in brain networks in ADHD patients from dynamic functional connectivity (DFC) perspective have not been fully understood. Accordingly, we executed DFC analysis on resting-state fMRI data of 25 ADHD patients and 27 typically developing (TD) children. A sliding window and Pearson correlation were used to construct the dynamic brain network of all subjects. The k -means+ + clustering method was used to recognize three recurring DFC states, and finally, the mean dwell time, the fraction of time spent for each state, and graph theory metrics were quantified for further analysis. Our results showed that ADHD patients had abnormally increased mean dwell time and the fraction of time spent in state 2, which reached a significant level (p < 0.05). In addition, a weak correlation between the default mode network was associated in three states, and the positive correlations between visual network and attention network were smaller than TD in three states. Finally, the integration of each network node of ADHD in state 2 is more potent than that of TD, and the degree of node segregation is smaller than that of TD. These findings provide new evidence for the DFC study of ADHD; dynamic changes may better explain the developmental delay of ADHD and have particular significance for studying neurological mechanisms and adjuvant therapy of ADHD. • Multiple recurring DFC patterns were first identified from resting state fMRI data of ADHD. • ADHD and TD had significant differences in mean dwell time and the fraction of time spent using DFC. • The degree of network integration and separation is related to different DFC states. [ABSTRACT FROM AUTHOR]

To address the fact that the classical motor imagination paradigm has no noticeable effect on the rehabilitation training of upper limbs in patients after stroke and the corresponding feature extraction algorithm is limited to a single domain, this paper describes the design of a unilateral upper-limb fine motor imagination paradigm and the collection of data from 20 healthy people. It presents a feature extraction algorithm for multi-domain fusion and compares the common spatial pattern (CSP), improved multiscale permutation entropy (IMPE) and multi-domain fusion features of all participants through the use of decision tree, linear discriminant analysis, naive Bayes, a support vector machine, k-nearest neighbor and ensemble classification precision algorithms in the ensemble classifier. For the same subject, the average classification accuracy improvement of the same classifier for multi-domain feature extraction relative to CSP feature results went up by 1.52%. The average classification accuracy improvement of the same classifier went up by 32.87% relative to the IMPE feature classification results. This study's unilateral fine motor imagery paradigm and multi-domain feature fusion algorithm provide new ideas for upper limb rehabilitation after stroke.