Accurate load prediction ensures edge cluster stability, which is crucial for resource allocation and task scheduling. However, varied service levels in multi-service clusters cause uneven resource distribution, overloading some devices. To address this issue, this paper introduces a multiservice, multitask transformer framework for edge load prediction, referred to as MSM-TFL. This framework applies dual encoders to capture variations in service features over time and leverages the Continuous Time Screening (CTS) method to calculate adjacent time points or identify the most similar time points as inputs to the dual encoders using the Similarity Search Using Service Features (SSUSF) method. In tests conducted on 30 server clusters with five loads, MSM-TFL-Continue outperforms the SOTA approach in terms of prediction errors for 1-, 5-, and 15-minute loads, total CPU time, and user CPU time. Compared with iTransformer, MSM-TFL-Continue reduces the prediction error in terms of the MAE, RSE, RMSE, and MAPE by 77.29%, 70.06%, 73.90%, and 77.47%, respectively, when a 5-minute load is used as an example. The prediction errors in terms of the MAE, RSE, RMSE, and MAPE are decreased by 74.46%, 64.75%, 69.31%, and 72.45%, respectively, by applying MSM-TFL-Similarity.

Recently, deep learning has achieved remarkable breakthroughs in hyperspectral image (HSI) classification tasks, particularly with methods based on convolutional neural networks (CNNs) and transformers. However, these methods have several limitations: 1) the limited receptive field inherent in the convolutional layer greatly hampers capturing feature contextual information on a large scale and 2) transformers cannot establish strong local relationships, making it challenging to characterize complex dependencies between distant pixels and different bands in HSIs. Moreover, as the network complexity increases, so does the number of network parameters. We propose a novel network called the spectral-spatial convolutional fusion long-range dependence transformer network (LRDTN) for HSI classification to address these challenges. LRDTN comprises three key components: dynamic-dependent convolutional (DDC) module, the multiscale enhanced fusion (MsEF) module, and the local–global perception transformer (LGPT). Specifically, the DDC dynamically models local features, while the MsEF integrates information from different scales to capture contextual relationships in HSI features effectively. Additionally, the ability to mine and utilize HSI local-global features and complex long-range dependencies is enhanced by the proposed transformer variant, LGPT. Ultimately, through the ingeniously designed structure of the LRDTN, the model effectively maintains its performance while reducing the number of network parameters. Extensive experiments conducted on four typical HSI datasets, including urban areas, agricultural areas, and swamps, demonstrate the superiority of LRDTN over other state-of-the-art networks. The code is available athttps://github.com/ybyangjing/LRDTN.

Abstract Crack is a common form of road distress and a key study of an intelligent transportation system. However, automatic pavement crack detection is a very challenging task due to noisy texture background, intensity inhomogeneity, and topology complexity. In this paper, a new pavement crack detection algorithm to address these issues is proposed. First, non‐local block matching strategy and local statistical mean are put together to generate the probability map of cracks, which has advantages on automatic threshold choosing and strong resistance to intensity inhomogeneity. Second, an iterative seed points sampling algorithm is proposed, which makes full use of the area and shape of connected regions where the seeds lie in, thus exploiting high reliable crack seeds for following curves extraction. Finally, a minimum spanning tree (MST) is adopted to connect points into crack curves and employ a crack growth method to find out the cracks, which is specified to deal with complex topology of cracks. For parameters, a robust and optimal parameters selection rule is obtained by data driven method. The algorithm is compared with other state‐of‐the‐art algorithms on two datasets. The experiment result shows that the proposed method has a better detection performance on ‐measure score over other methods.