The 4D trajectory is a multi-dimensional time series with plentiful spatial-temporal features and has a high degree of complexity and uncertainty. Aiming at these features of aircraft flight trajectory and the problem that it is difficult for existing trajectory prediction methods to extract spatial-temporal features from the trajectory data at the same time, we propose a novel 4D trajectory prediction hybrid architecture based on deep learning, which combined Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM). An 1D convolution is used to extract the spatial dimension feature of the trajectory, and LSTM is used to mine the temporal dimension feature of the trajectory. Hence the highprecision prediction of the 4D trajectory is realized based on the sufficient fusion of the above features. We use real Automatic Dependent Surveillance-Broadcast (ADS-B) historical trajectory data for experiments and compare the proposed method with a single LSTM model and BP model on the same data set. The experimental results show that the trajectory prediction accuracy of the CNN-LSTM hybrid model is superior to a single model. The prediction error is reduced by an average of 21.62% compared to the LSTM model and by an average of 52.45%compared to the BP model. It provides a certain reference for the trajectory prediction research and Air Traffic Management decision-making. INDEX TERMS 4D trajectory prediction, deep learning, CNN-LSTM model, spatial-temporal feature Ma Lan (1966-) Female; Born in Huocheng, Xinjiag Province. Professor. Her main research direction is Air Traffic Information Process, Air Traffic Management Optimization. Shan Tian, born in 1996. Her research interests include data mining and deep learning with recent applications on aircraft 4D trajectory prediction.

Abstract To solve the problem that traditional trajectory prediction methods cannot meet the requirements of high-precision, multi-dimensional and real-time prediction, a 4D trajectory prediction model based on the backpropagation (BP) neural network was studied. First, the hierarchical clustering algorithm and the k-means clustering algorithm were adopted to analyze the total flight time. Then, cubic spline interpolation was used to interpolate the flight position to extract the main trajectory feature. The 4D trajectory prediction model was based on the BP neural network. It was trained by Automatic Dependent Surveillance – Broadcast trajectory from Qingdao to Beijing and used to predict the flight trajectory at future moments. In this paper, the model is evaluated by the common measurement index such as maximum absolute error, mean absolute error and root mean square error. It also gives an analysis and comparison of the predicted over-point time, the predicted over-point altitude, the actual over-point time and the actual over-point altitude. The results indicate that the predicted 4D trajectory is close to the real flight data, and the time error at the crossing point is no more than 1 min and the altitude error at the crossing point is no more than 50 m, which is of high accuracy.

Chinese solar greenhouses are unique facility agriculture buildings and widely used in northeastern China, providing a favorable requirement for crop growth. The north wall configurations play an essential role in heat storage and thermal insulation and directly affect the management of the internal environment. This research is devoted to further improve the thermal performance of the greenhouse and explore the potential of the north wall. A mathematical model was designed to investigate the concave-convex wall configurations based on computational fluid dynamics. Four passive heat-storage north walls were analyzed by using the same constituent materials, including a plane wall, a vertical wall, a horizontal wall and an alveolate wall. The numerical model was validated by experimental measurements. The temperature distributions of the north walls were examined and a comparative analysis of the heat storage-release capabilities was carried out. The results showed that the heatstorage capacity of the north wall is affected by the surface structure. Moreover, the critical factor influencing the air temperature is the sum of the heat load released by the wall and the energy increment of greenhouse air. The results suggested that the alveolate wall has preferable thermal accumulation capacity. The concave-convex wall configurations have a wider range of heat transfer performance along the thickness direction, while the plane wall has a superior thermal environment. This study provides a basic theoretical reference to rationally design the internal surface structures of the north wall. OPEN ACCESSCitation: Liu X, Li H, Li Y, Yue X, Tian S, Li T (2020) Effect of internal surface structure of the north wall on Chinese solar greenhouse thermal microclimate based on computational fluid dynamics. PLoS ONE 15(4): e0231316. https://doi.

Infrared small target detection has been a challenging task due to the weak radiation intensity of targets and the complexity of the background. Traditional methods using hand-designed features are usually effective for specific background and have the problems of low detection rate and high false alarm rate in complex infrared scene. In order to fully exploit the features of infrared image, this paper proposes an infrared small target detection method based on region proposal and convolution neural network. Firstly, the small target intensity is enhanced according to the local intensity characteristics. Then, potential target regions are proposed by corner detection to ensure high detection rate of the method. Finally, the potential target regions are fed into the classifier based on convolutional neural network to eliminate the non-target regions, which can effectively suppress the complex background clutter. Extensive experiments demonstrate that the proposed method can effectively reduce the false alarm rate, and outperform other state-of-the-art methods in terms of subjective visual impression and quantitative evaluation metrics.

In this study, a visual grading system of vegetable grafting machine was developed. The study described key technology of visual grading system of vegetable grafting machine. First, the contrasting experiment was conducted between acquired images under blue background light and natural light conditions, with the blue background light chosen as lighting source. The Visual C++ platform with open-source computer vision library (Open CV) was used for the image processing. Subsequently, maximum frequency of total number of 0-valued pixels was predicted and used to extract the measurements of scion and rootstock stem diameters. Finally, the developed integrated visual grading system was experimented with 100 scions and rootstock seedlings. The results showed that success rate of grading reached up to 98%. This shows that selection and grading of scion and rootstock could be fully automated with this developed visual grading system. Hence, this technology would be greatly helpful for improving the grading accuracy and efficiency.