For tourists, planning their own travel itinerary to a strange city is really challenging. Although there are many researches on Point of Interests (POIs) recommendation and itinerary planning, two problems occur in c...
详细信息
Zero-shot learning (ZSL) recently has drawn widespread attention due to the demand for scalability of object recognition in real scenes. Existing approaches typically focus on directly learning various mapping functio...
详细信息
In order to meet the cloud side requirements of various traffic business scenarios, the construction of traffic cloud side collaboration platform realizes the collaboration and unification of various business resource...
详细信息
To deal with the discrepancy between global and local objectives in the federated learning invoked by the non-independent, identically distributed (non-IID) data and mitigate the impact of catastrophic forgetting in t...
详细信息
Current semi-supervised learning-based sample selection methods for noisy label image classification typically utilize all clean and noisy samples for model training. However, not all noisy samples contribute positive...
详细信息
ISBN:
(数字)9798350352214
ISBN:
(纸本)9798350352221
Current semi-supervised learning-based sample selection methods for noisy label image classification typically utilize all clean and noisy samples for model training. However, not all noisy samples contribute positively to model training. This paper introduces a novel semi-supervised image data granulation method that employs adaptively generated granular noisy sample subsets in place of the original noisy samples to enhance classification efficiency. The granular data generated retain the essential features of the original data, thereby improving efficiency without compromising classification accuracy. The quality of the granular data is assessed using coverage and specificity criteria, standard metrics for evaluating information granules. The proposed method consists of three main components: (i)selecting clean and noisy samples through network co-training, (ii)calculating granular noisy sample subsets by adaptive granulation, and (iii)optimizing the network model using a semi-supervised strategy. Experimental results on benchmark datasets with varying noise rates demonstrate that our method significantly improves the efficiency of noisy label image classification while maintaining accuracy.
In this paper, we explore and establish several necessary and sufficient conditions that are instrumental in achieving consensus within second-order discrete-time multi-agent systems (SDMAS). Different with previous r...
详细信息
ISBN:
(数字)9798331510138
ISBN:
(纸本)9798331510145
In this paper, we explore and establish several necessary and sufficient conditions that are instrumental in achieving consensus within second-order discrete-time multi-agent systems (SDMAS). Different with previous research, this study addresses the more intricate scenario where the velocity coupling matrix is distinct from the position coupling matrix. We introduce a novel eigenvector condition tailored to this challenge. Furthermore, in response to the burgeoning interest in multiweighted networks, this study is extended to SDMAS with multiple weights. We employ a technique, that rearranges the order of variables, to effectively simplify the analysis of multiweighted networks by transforming them into single-weighted equivalents. The efficacy of our method is substantiated through three numerical examples, which illustrate the practical value in elucidating consensus dynamics within SDMAS featuring diverse coupling matrices.
Currently, many works regarded extractive summarization as a binary classification problem. However, the metric of the summary classification is always too singular and cannot fully utilize sentence features. To addre...
详细信息
Kubernetes has become the basic platform for building cloud native applications. However, existing horizontal scaling methods based on Kubernetes have problems with resource redundancy. Furthermore, the combined horiz...
详细信息
Traffic forecasting plays a crucial role in intelligent transportation systems and finds application in various domains. Accurate traffic forecasting remains challenging due to the time-varying correlations within the...
Traffic forecasting plays a crucial role in intelligent transportation systems and finds application in various domains. Accurate traffic forecasting remains challenging due to the time-varying correlations within the data and the heterogeneous correlations between regions. Although various dynamic spatial-temporal graph models have been proposed to address these challenges in recent years, most of them are burdened by high computation costs and not intuitive to understand. In this paper, we propose a spatial-temporal graph model, Spatial-Temporal Dynamic Graph Diffusion Convolutional Network (SDGDN) that provides an effective and efficient approach to traffic forecasting. From the perspective of traffic flow transition probabilities, SDGDN learns dynamic graph structures to capture the time-varying traffic transition relationships. Besides dynamic graph structures, static node features are employed in diffusion convolution to better capture heterogeneous regional features. Furthermore, we utilize temporal encoding and also generate varying graphs in each stacked layer to enhance the forecasting performance. Experiments results on five real-world datasets demonstrate that SDGDN outperforms most baseline models in terms of both performance and computation efficiency.
In recent years, the travel time prediction has been receiving sustained attention because of the prevalence of location based applications, smart city engineering and online car-hailing. In this paper, a Self-organiz...
In recent years, the travel time prediction has been receiving sustained attention because of the prevalence of location based applications, smart city engineering and online car-hailing. In this paper, a Self-organizing Graph Embedding Deep Network (SGED-Net) model is proposed to address the challenging Origin-Destination(OD) based travel time estimation (TTE). Specifically, SGED-Net comprises four modules, involving travel feature extraction, spatial association graph generation, graph embedding, and travel time deep learning prediction modules. First, we comprehensively extract three travel characteristics and feed them into a modified LightGBM component for learning the importance sort of features for different trips. Second, considering the lack of intermediate trajectories in the OD-based TTE, we employ a self-organizing feature mapping (SOM) approach to obtain the prominent nodes among pick-up and drop-off locations. Meanwhile clustering algorithm is used to divide a city into n-clusters districts of variant sizes. The topology learned by SOM is combined with the districts divided by clustering algorithm to obtain a district-based spatial association graph. Moreover, an improved SDNE algorithm is leveraged to gain a low-dimension spatial association representation while preserving the global and local structure of the graph. Then, we design a deep neural network for learning the captured spatial association representation. Finally, a series of experiments in two real-world large-scale datasets demonstrate the SGED-Net's excellent performance.
暂无评论