During the navigation process of unmanned ships, unmanned ships must be able to plan a reasonable path between the starting and the end point, and on the basis of this, the tracking tasks need to be ...completed. In response to this issue, this article proposes the planning method and tracking control method based on the improved artificial potential method and the unmanned ship path of the A-star algorithm. Adding a scaling factor to the repulsion function and combining the two algorithms effectively solves the problem that traditional artificial potential field methods are prone to local minima. After smoothing the planned path, it is used as the input of the controller. Based on the backstepping sliding mode method, the controller of the underactuated unmanned ship is designed, which solves the problem that the external environment cannot be considered in the traditional path planning. The effectiveness of path planning and tracking control of unmanned ships based on the improved artificial potential field method and A-star algorithm is verified by simulation experiments.
Sequential recommender models typically generate predictions in a single step during testing, without considering additional prediction correction to enhance performance as humans would. To improve ...the accuracy of these models, some researchers have attempted to simulate human analogical reasoning to correct predictions for testing data by drawing analogies with the prediction errors of similar training data. However, there are inherent gaps between testing and training data, which can make this approach unreliable. To address this issue, we propose an \textit{Abductive Prediction Correction} (APC) framework for sequential recommendation. Our approach simulates abductive reasoning to correct predictions. Specifically, we design an abductive reasoning task that infers the most probable historical interactions from the future interactions predicted by a recommender, and minimizes the discrepancy between the inferred and true historical interactions to adjust the predictions.We perform the abductive inference and adjustment using a reversed sequential model in the forward and backward propagation manner of neural networks. Our APC framework is applicable to various differentiable sequential recommender models. We implement it on three backbone models and demonstrate its effectiveness. We release the code at https://github.com/zyang1580/APC.
Ocean temperature has an important influence on the distribution and migration of marine fishes, and with the improvement of modern remote sensing information acquisition technology, ocean data are ...constantly being improved. Sea surface temperature (SST) around the Korean Peninsula is influenced by several complex factors. In this paper, an improved long short-term memory network (LSTM) model with attention mechanism is proposed to predict the SST for the next 5 days, which extracts more temporal and spatial information by assigning new weights through the attention mechanism. The experimental results show that the root mean square error (RMSE) of the proposed model on day 1 is 0.2181°C and the prediction accuracy (PACC) is 99.14%, which is a 20% reduction in RMSE compared to the existing similar networks.
With the development of deep learning technology, a large number of new technologies for video anomaly detection have emerged. This paper proposes a video anomaly detection algorithm based on the ...future frame prediction using Generative Adversarial Network (GAN) and attention mechanism. For the generation model, a U-Net model, is modified and added with an attention module. For the discrimination model, a Markov GAN discrimination model with self-attention mechanism is proposed, which can affect the generator and improve the generation quality of the future video frame. Experiments show that the new video anomaly detection algorithm improves the detection performance, and the attention module plays an important role in the overall detection performance. It is found that the more the attention modules are appliedthe deeper the application level is, the better the detection effect is, which also verifies the rationality of the model structure used in this project.
With the popularization of rail transit, the number of people who choose rail transit as a travel mode has increased, resulting in the long-term gathering of passengers at some hubs and insufficient ...capacity at stations. These increase the duration of passengers and have a more significant impact on the carrying capacity of urban rail transit. In order to find a reasonable number of people flow limit, and at the same time meet the urban rail carrying capacity and maximize passenger demand. Based on the AFC data of Beijing commuter lines, this paper puts forward a current limiting model of urban rail transit. Firstly, based on the AFC data, the influence of passenger demand and OD structure in the station can be described more accurately after the passenger route is identified. At the same time, compared with the previous peak data, the model can have better redundancy in the face of changes in passenger demand. Using the multi-objective optimization idea, fully consider the carrying capacity of urban rail transit and personalized passenger demand two factors. Finally, taking the single line of urban rail transit as an example, the objective function is established. On the basis of considering the dynamic change of passenger flow, the optimization of the urban rail transit transportation system and the maximization of passenger flow demand are realized.
Using life events scale, self-transcendence scale and meaning in life scale, 1019 college students were investigated to explore the relationship between self-transcendence wisdom, negative life ...events and meaning in life. The results showed that there was a significant negative correlation between negative life events and self-transcendence wisdom, and a significant negative correlation between meaning in life and wisdom. The relationship between negative life events and self-transcendence wisdom was moderated by meaning in life as a moderating variable.
The purpose of this work was to explore the application of microwaves for the regeneration of activated carbon fibers saturated with ethanol. The efficacy of the regeneration was analyzed by the rate ...of desorption and mass loss. When the microwave power was 528W , the dosage of activated carbon fiber was 3.0g , the nitrogen gas flow rate was 1.4m3/h and the microwave irradiation time was 180s, the desorption rate was up to 90.2% and the outlet concentration of ethanol was 95.6%. The adsorption of activated carbon fiber after microwave regeneration for many times was larger than the fresh activated carbon fiber. And the rate of total mass loss was 4.74%.
The purpose of this work was to explore the application of microwaves for the regeneration of activated carbon fibers saturated with ethanol under vacuum condition. The efficacy of the regeneration ...was analyzed by the rate of desorption and mass loss. When the microwave power was 680W , the dosage of activated carbon fiber was 3.5g , the degree of vacuum is 0.05MPa and the microwave irradiation time was 180s, the desorption rate was up to 95.3% and the outlet concentration of ethanol was 97.5%. The adsorption of activated carbon fiber after microwave regeneration for many times was larger than the fresh activated carbon fiber. And the rate of total mass loss was 3.54%.
With the widespread deployment of location-aware mobile devices, a mass of trajectory data is being generated and collected. Mining co-movement patterns of people and vehicles from streaming and ...massive trajectory data has attracted much attention due to its wide applications in various fields. As a typical co-movement pattern, convoys describe objects moving together in consecutive timestamps. There are two challenges for efficient distributed convoy mining: object clustering and workload balancing. Clustering objects in each time snapshot is a time-consuming operation. In addition, on the basis of practical application scenarios, load balancing is an important consideration for distributed algorithms. To tackle the above challenges, we propose a novel method for distributed convoy mining via sliding window-based indexing and sub-track partitioning, abbreviated SWISP. We offer three major advancements. First, we develop a grid-based DBSCAN clustering algorithm named Grid-DBSCAN for distributed scenarios. It avoids the exhaustive calculation of pairwise distances for neighborhood search and thus improves computational efficiency in the clustering stage. Second, we propose a sliding window-based indexing scheme to filter out sub-tracks with less than k consecutive time snapshots, significantly reducing the number of candidate sub-tracks for convoy mining. Third, we develop a distributed convoy mining algorithm based on sub-track partitioning. It exploits both temporal and spatial information of sub-tracks for data partitioning and solves the data skewness problem caused by uneven data distributions. We conduct extensive experiments on four real-world datasets. The experimental results show that our distributed algorithm can handle large-scale trajectory data and is more efficient than state-of-the-art approaches.
Accurate prediction of drug molecule solubility is crucial for therapeutic effectiveness and safety. Traditional methods often miss complex molecular structures, leading to inaccuracies. We introduce ...the YZS-Model, a deep learning framework integrating Graph Convolutional Networks (GCN), Transformer architectures, and Long Short-Term Memory (LSTM) networks to enhance prediction precision. GCNs excel at capturing intricate molecular topologies by modeling the relationships between atoms and bonds. Transformers, with their self-attention mechanisms, effectively identify long-range dependencies within molecules, capturing global interactions. LSTMs process sequential data, preserving long-term dependencies and integrating temporal information within molecular sequences. This multifaceted approach leverages the strengths of each component, resulting in a model that comprehensively understands and predicts molecular properties. Trained on 9,943 compounds and tested on an anticancer dataset, the YZS-Model achieved an \(R^2\) of 0.59 and an RMSE of 0.57, outperforming benchmark models (\(R^2\) of 0.52 and RMSE of 0.61). In an independent test, it demonstrated an RMSE of 1.05, improving accuracy by 45.9%. The integration of these deep learning techniques allows the YZS-Model to learn valuable features from complex data without predefined parameters, handle large datasets efficiently, and adapt to various molecular types. This comprehensive capability significantly improves predictive accuracy and model generalizability. Its precision in solubility predictions can expedite drug development by optimizing candidate selection, reducing costs, and enhancing efficiency. Our research underscores deep learning's transformative potential in pharmaceutical science, particularly for solubility prediction and drug design.