Microbial induced calcium carbonate precipitation (MICP) technology is an emerging green reinforcement technology for geotechnical engineering, which has a good application prospect in the reinforcement of loess slopes. The reinforcement of loess by MICP is affected by a variety of factors, in addition to the external environment, material properties and reinforcement methods and other factors, the calcium source, the concentration of binder, the age of the maintenance and the maintenance methods also play a decisive role in the microbial reinforcement of loess. The loess in Longxi area was taken as the research object, bacillus subtilis-induced calcium carbonate precipitation technology was adopted to consolidate loess, and a comparative experimental study on the shear strength of MICP-consolidated loess under the conditions of different calcium sources, binder concentration, age of maintenance and maintenance methods was carried out. The results show that the MICP technology is more effective in consolidating loess specimens when the calcium source is calcium chloride, the binder concentration is 1.0 mol/L and the specimens are cured for 7 d. The cohesion and internal friction are increased by 4.95 and 1.34 times, respectively, compared with the vegetal loess soil. The research results have certain reference value for the roadbed reinforcement and slope management in the Loess Plateau area.

In order to facilitate the counting of turning traffic flow and to enhance the detection speed and accuracy of turning traffic flow at intersections, a deep learning-based method was suggested for detecting, tracking, and counting turning traffic flow at urban crossings. Initially, the YOLOv5s, which was lightweight and efficient, was chosen as the target detection framework after conducting a comparative analysis. Unmanned aerial vehicle (UAV) aerial photography was utilized to record video footage of traffic movement at urban intersections, resulting in the development of a dataset of vehicle aerial photography photos. The pre-training weights and the most recent weight files were utilized to conduct training and testing on the self-constructed dataset. The model evaluation shows that the vehicle detection model using YOLOv5 exhibits great detection speed and accuracy. The model’s box_loss value declines rapidly and stabilizes at 0.038, while the mAP_0.5 value climbs swiftly and stays near 0.91.After that, the DeepSORT model was used as the backend multi-vehicle tracking technique, and a corner-to-centroid coordinate transformation was used to simplify the extraction of vehicle trajectories. The precision of the driving trajectory line was evaluated thereafter. To improve the robustness of trajectory points’ coordinate information, a corner-point-center-of-mass point coordinate transformation was suggested to tackle the issue of corner points in the detection frame. A sixth-degree polynomial was used to model the vehicle trajectory. Unsuitable trajectory lines were rotated and optimized to meet the function mapping requirements and ensure good fitting of all trajectories. Turning vehicles were detected and counted by using a predetermined threshold to determine the turning angle. Ultimately, to validate the performance of the proposed turning vehicle flow detection method, vehicle detection experiments were conducted at a city intersection as an illustration. The manual counting values were compared and analyzed against the detection results obtained using this method. The results show that the average detection accuracy for the four flow directions is 92.9%, with a maximum of 95.7%, meeting the standard detection requirements for turning vehicle flow in real intersection scenarios.

In order to realize the automatic optimization of hyperparameters of YOLO model, the hyperparameter optimization of you only look once (YOLO) model based on orthogonal optimization strategy (OOS) was proposed. Firstly, based on the principle of statistical orthogonal test, the orthogonal search method of population and the hyperparameter contribution analysis strategy were proposed to improve the optimization efficiency of the algorithm. Then, the uniform orthogonal search strategy and the neighborhood orthogonal search strategy were designed to alleviate the problem of the YOLO model falling into the local optimum and premature convergence. Finally, YOLOv5, YOLOv5s-Transformer and YOLOv7 were used as optimization objects to test on two target detection datasets, NWPU VHR-10 and Pascal VOC. Test results show that the recognition accuracy of the YOLO model is improved by the OOS hyperparameter optimization method in all cases. The average recognition accuracy mAP@0.5 on two datasets is improved to 93.94%, 93.18%, 93.45%, and 85.81%, 84.59%, 89.96%. The mAP@0.5-0.95 is improved to 60.00%, 60.08%, 56.98%,and 62.27%, 58.89%, 70.77%. It can provide a new intelligent method for hyperparameter optimization of object detection model.

According to the requirements of rain ingestion of airworthiness regulations, the rain ingestion calculation was carried out for the no booster fan part. The movement trajectory of water droplets with different water speeds was studied based on Lagrangian particle tracking, and the separation amount of water droplets ingested to inner duct was obtained. Further more, the requirements for water spray speed from the rain ingestion test rig in the certification for turbofan engine was discussed,which can support the design and verification of rain ingestion airworthiness of turbofan engine. The results show that with the decrease of water speed, the amount of rain impacting on the fan blade and other walls increases, and no water droplets can pass through the fan blade and enter the inner duct. The water entering the engine inner duct at 250 m/s is 15.3 percent of the total amount of water, about 19.1 times of that at 10 m/s. Under the same water velocity, as the distance between the splitter and the fan blade decreases, the increase in water ingested to inner duct increases. At different fan rotational speeds, the change trend of the water ratio ingested to inner duct with initial water velocity is consistent, basically increasing with the increase in water drop velocity, and then remaining or slightly decreasing.

Remote sensing image target detection is one of great significance in military reconnaissance, intelligent agriculture and other fields, especially small target detection has been gaining continuous attention. However, small targets in remote sensing images face the problems of insufficient feature information and difficult detection, which have become the biggest obstacles plaguing the development of remote sensing applications. To this end, the you only look once-hybrid feature(YOLO-HF) algorithm was proposed, which introduced a hybrid attention mechanism of channel attention and self-attention in the network of the traditional YOLOv7 model to extract the target’s deep features, and fused the shallow and deep features to increase the richness of local features; to further strengthen the attention to the global information, a global attention mechanism was added for the small-scale targets after the extraction of the features, to achieve the ability of global feature expression enhancement. In order to avoid that the traditional loss function was sensitive to the positional deviation of small targets, which leaded to poor detection effect, a new metric was selected for use, which was embedded into the computation of the bounding box loss function, so as to accelerated the convergence of the loss function and realized the enhancement of the detection accuracy of small targets. The experimental results show that compared with the traditional YOLOv7 algorithm, the proposed algorithm shows superiority on both RSOD and NWPU VHR-10 datasets, and in particular, the mean average accuracy on RSOD dataset is improved by 2.90%, and the mean average accuracy on NWPU VHR-10 dataset realizes an improvement of 3.61%.

In the contemporary digital healthcare setting, the dissemination and sharing of medical imagery are integral to routine medical operations. However, medical images often contain sensitive patient information, and without adequate protection, there is a risk of illegal acquisition or leakage, which brings unnecessary troubles. To address this issue, an encryption algorithm based on Zigzag scrambling and a new four-dimensional hyperchaotic system was proposed. Firstly, the Zigzag algorithm was used to scramble the image once, roughly hiding the obvious contours of the image. Then, an improved cat mapping algorithm was used to perform secondary scrambling on the image, removing obvious texture features. Finally, the scrambling factor generated from the plaintext image was applied to the initial value generation process of the hyperchaotic system. The generated hyperchaotic sequence was transformed into a hyperchaotic matrix for the subsequent diffusion process of the encryption algorithm. The simulation results show that the proposed algorithm can effectively conceal plaintext information based on the characteristics of medical images and resist common types of attacks. The robustness of the proposed algorithm has been demonstrated through testing, confirming its capability to address the issue of image interference in remote healthcare.

In order to study the influence of the tank environment on the results of the seaplane model test, for the first time in this field, a series of whole aircraft model tests were conducted using the same seaplane model in two towing tanks to study the aerodynamic and hydrodynamic characteristics of the whole aircraft model in the two towing tanks, the test results and environmental differences were analyzed. The results show that the towing tank environment has a significant impact on the aerodynamic characteristics of the seaplane model, but by compensating the aerodynamic characteristics of the seaplane model in each towing tank during the test, the interference of the test environment on the water resistance results could be avoided, so as to obtain a more satisfactory water resistance test result. Among the boundary effects of the towing tank, the blockage effect has the greatest impact on the aerodynamic characteristics of the seaplane model. Compared with 2.51% relative blockage ratio 0.67%, the aerodynamic drag coefficient of the seaplane model is 0.1~0.2 larger, and the lift coefficient is at least 0.2.Because the typical high-speed coasting state is used for aerodynamic compensation to calculate, so the compensation effect is only achieved at the corresponding speed and produce some deviation at other speeds, resulting in a certain deviation in the test result, but it will not have a significant impact on the test result because the deviation is so small. The research findings provide guidance for model hydrodynamic tests and performance analysis of seaplanes in China.

To explore the reasonable lining section thickness of shallow buried soft soil excavation channels under vehicle loads, two-dimensional finite element models were established using load structure method and strata structure method, respectively. The stress characteristics and safety factors of subway excavation channels under different burial depths, vehicle loads, and lining thicknesses were quantified. The research results indicate that regardless of the presence or absence of vehicle loads, the maximum bending moment of the tunnel is located at the arch foot or arch shoulder, and the minimum safety factor is located at the arch crown. According to the original design reinforcement, regardless of whether there is vehicle load, the safety factor decreases with increasing burial depth and increases with increasing secondary lining. Under shallow burial conditions, the safety factors calculated by the load structure method are smaller than those calculated by the stratum structure method. The calculation results of load structure method show that under vehicle load and surrounding rock pressure, the secondary lining thickness is 60, 90, 100 cm respectively, and the burial depth does not exceed 8, 12, 14.6 m respectively, meeting the safety factor requirements of the specifications. The calculation results of the stratum structure method show that under vehicle load and surrounding rock pressure, when the thickness of the secondary lining is 60, 80, 100 cm respectively, its burial depth does not exceed 12, 15.5, 19 m, which can meet the safety factor requirements of the specifications.

In order to improve the engineering characteristics of silty soil in yellow plain area with low strength, easy deformation and poor bonding ability, mechanical testing and scanning electron microscope (SEM) were used to add different contents of xanthan gum(XG), The mechanical properties and improvement mechanism of XG, lignin fiber (LF) and curing age were studied. The results show that both XG and LF as improved materials can increase the compressive strength of silty sand. With the increase of XG content, the compressive strength of silty sand first increases and then decreases. With the increase of LF content, the compressive strength of silt will increase, and the improvement effect will be weakened by adding too much LF. When the two materials are added to the silt simultaneously, the compressive strength of the silt is higher than that of one material alone. XG produces high viscosity gel when it encounters water, the loose silty soil is tightly cemented together, and the strength of the soil is improved. LF contains large molecular groups, forming a spatial network structure with surrounding soil particles, which strengthens the joint force between soils. The research results can provide reference values for the silty soil subgrade improvement project in the yellow plain area.

Dynamic graph link prediction aims to predict the formation or disappearance of links between nodes in a graph based on their historical interactions. To address the issue of high energy consumption associated with modeling dynamic networks using recurrent neural networks at fine-grained temporal graphs, a dynamic graph link prediction model optimized by spiking neural networks was proposed. By the node memory updater incorporated spiking neural networks and the spiking update process of node memory, the evolving dynamics of dynamic graphs were learned by graph neural networks and the model achieved link prediction. The results on three publicly available classic datasets show that the proposed model exhibits improved runtime efficiency while maintaining accuracy, showcasing favorable performance in dynamic graph link prediction tasks.