Port cargo throughput forecasting is an essential issue in port planning and management.Owing to that cargo throughput is affected by many factors; a single model is often difficult to get an accurate prediction.On the basis of discussing single modeling principle, the combination forecasting model based on Minimum-variance is therefore proposed for forecasting cargo throughput.By comparing the performance evaluation indexes, the results of examples imply that the combination model has higher precision than a single model.
Many clustering ensemble algorithms need to predesign initial thresholds before partition data points, which is supervised learning and directly influence the efficiency of clustering. In order to cluster data points under fully unsupervised situation, the hierarchical partition is introduced in this paper. The proposed algorithm makes use of the distribution of results of all clustering memberships by constructing the m-subset of Descartes with the support degree. The theorems and definitions advanced in this paper are detailed proved. Finally, the proposed algorithm is applied in practice and results show that it is effective.
The subjects of literature are the direct expression of the author’s research results. Mining valuable knowledge helps to save time for the readers to understand the content and direction of the literature quickly. Therefore, the co-occurrence network of high-frequency words in the bioinformatics literature and its structural characteristics and evolution were analysed in this paper. First, 242,891 articles from 47 top bioinformatics periodicals were chosen as the object of the study. Second, the co-occurrence relationship among high-frequency words of these articles was analysed by word segmentation and high-frequency word selection. Then, a co-occurrence network of high-frequency words in bioinformatics literature was built. Finally, the conclusions were drawn by analysing its structural characteristics and evolution. The results showed that the co-occurrence network of high-frequency words in the bioinformatics literature was a small-world network with scale-free distribution, rich-club phenomenon and disassortative matching characteristics. At the same time, the high-frequency words used by authors changed little in 2–3 years but varied greatly in four years because of the influence of the state-of-the-art technology.
With the continuous development of mobile internet, smart mobile terminal is now tightly integrated in the information system. As the extension of the traditional information system, the real-time problem of data transfer for mobile terminal has become particularly important. In the process of development based on Android platform, traditional method of pulling can keep the data synchronization between the Android terminal and server-side. Each Android terminal has to poll the server to see whether data is updated, which wastes a lot of unnecessary network traffic and mobile-phone battery. In order to overcome the weakness of pulling method, we create an application using the cloud pushing based on Android GCM service, which is integrated into our information management system. The new data is sent to Android client-side by the server. The result shows that it enhances the timeliness and effectiveness of the information, reduces online traffic and saves Android terminals' power.
Abstract In order to enhance the safety of maritime transportation and improve the accuracy of maritime traffic accident prediction, an unbiased grey forecast model based on residual error is applied to predict maritime traffic accident. Based on the historical data of maritime traffic accidents from 2008 to 2017, the traditional unbiased grey model prediction and residual error unbiased grey model prediction are carried out, and the fitting curves of actual value and predicted value of the two models are drawn. The results show that the prediction accuracy and fitting curve of residual error unbiased grey model are better than those of traditional unbiased grey model, which can truly reflect the development trend of comprehensive safety of maritime traffic, and the prediction results have certain reliability and practicability.
In international trade, the most widely used transportation form is the ocean freight. Port throughput forecasting is a important index for port construction and layout. In this paper, on the basis of Pearl Curve Model, GM (1,1) and Exponential Smoothing, we introduced the combinatorial forecasting model that incorporated the three. In the case of the cargo throughput of Dalian port as the example, carried out a forecasting of the development of the regional port throughput in China. Finally, we can see from the example analysis that the combination forecasting accuracy can be improve by this model, which is a feasible and effective combination forecasting method of forecasting cargo throughput.
With the fast development of World Wide Wed, Web-based applications and services should allow user to get the right personalized information quickly and effectively. Collaborative Filtering acts a very important role in web service personalization and Recommender System. In this paper, Stability Degree was proposed to improve the accuracy of User based collaboration filtering, three kinds of Stability Degree were introduced into similarity computation, and the results show that the prediction accuracy can be improved by 11 percents, and MAE can be reduced faster than classic method.
One essential issue in skeleton-based driver action recognition is that incomplete skeletons collected from real scenes would degrade model performance. However, existing models often ignore the missing joint preprocessing and tend to be over-parameterized. In this work, we propose 1) a padding strategy SmoothNode and 2) a skeleton-based Multi-Scale Excitation Graph Convolution Network (MSE-GCN). Firstly, SmoothNode, as a part of preprocessing, fills both missing frames and nodes in a smooth style and repairs the incomplete skeletons to a relatively complete state. Secondly, inspired by the efficient modeling ability of EfficientGCN in dynamic skeletons, the MSE-GCN model is designed to reason multi-scale spatial-temporal features through two improvements, i.e., Spatial Graph Convolution layer based on the Independent Self-connecting formulation mode (SGC-IS) and Multi-Scale Wrapper Fused Spatial-Temporal Excitation layer (MSW-FSTE). SGC-IS optimizes the normalized adjacency matrix formulation mode and strengthens connections between each pair of nodes, while MSW-FSTE excites temporal patterns with the global spatiotemporal features in a hierarchical residual-like style and learns multi-scale features in the temporal domain. By coupling these proposals, we develop SMOMS, a driver behavior recognition framework. Extensive experiments on three released datasets, i.e., Drive&Act, 3MDAD, and EBDD, demonstrate that the proposed SMOMS framework outperforms other methods.
In order to ensure logistics system security, an access control model based on RBAC is proposed in this paper. With the combination of the practical logistics business needs, the paper makes a deep research on the access control process, and gives detailed analysis of the relationship among system users, roles and permissions. Then, we discuss the design and implementation of the access control process from four aspects-system development environment, the construction of the system architecture, database design and system implementation framework. Finally the access control model based on this paper is successfully applied in the actual hazard chemicals logistics system. It has a great impact on enhancing the security and flexibility of logistics system managements and enables logistics companies achieve more profits.
In order to grasp the factors affecting road traffic safety and discharge the potential hazard fundamentally, an AHP (Analytic Hierarchy Process) method, which suits for solving complex decision making was proposed in this paper. Started from the view of system science, this paper calculated the weights of the causes of road traffic accidents by establishing the AHP model of the major factors affecting road traffic safety. The results of the experiment showed that factors of drivers accounted for a large proportion of traffic accidents, in which speeding was the most active factor. The AHP method overcome the drawbacks of the traditional analytical measures which only considered one single factor, the number of traffic accidents, and obtained objectively the major causes of road traffic accidents with a comprehensive consideration of people, vehicles, roads and environmental influence. Finally, several corresponding preventive measures were proposed, which will play a guiding role on the development of road traffic safety.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)