Semantic segmentation with deep learning networks has become an important approach to the extraction of objects from very high-resolution remote sensing images. Vision Transformer networks have shown significant improvements in performance compared to traditional convolutional neural networks (CNNs) in semantic segmentation. Vision Transformer networks have different architectures to CNNs. Image patches, linear embedding, and multi-head self-attention (MHSA) are several of the main hyperparameters. How we should configure them for the extraction of objects in VHR images and how they affect the accuracy of networks are topics that have not been sufficiently investigated. This article explores the role of vision Transformer networks in the extraction of building footprints from very-high-resolution (VHR) images. Transformer-based models with different hyperparameter values were designed and compared, and their impact on accuracy was analyzed. The results show that smaller image patches and higher-dimension embeddings result in better accuracy. In addition, the Transformer-based network is shown to be scalable and can be trained with general-scale graphics processing units (GPUs) with comparable model sizes and training times to convolutional neural networks while achieving higher accuracy. The study provides valuable insights into the potential of vision Transformer networks in object extraction using VHR images.

The international roughness index (IRI) can be employed to evaluate the smoothness of pavement. The previously proposed mechanical-empirical pavement design guide (MEPDG), which is used to model the IRI of joint plain concrete pavement (JPCP), has been modified in this study considering its disadvantage of low prediction accuracy. To improve the reliability of the prediction effect of the IRI for JPCP, this study compares the prediction accuracy of the IRI of JPCP by using the machine-learning methods of support vector machine (SVM), decision tree (DT), and random forest (RF), optimized by the hyperparameter of the beetle antennae search (BAS) algorithm. The results from the machine-learning process show that the BAS algorithm can effectively improve the effectiveness of hyperparameter tuning, and then improve the speed and accuracy of optimization. The RF model proved to be the one with the highest prediction accuracy among the above three models. Finally, this study analyzes the importance score of input variables to the IRI, and the results show that the IRI was proportional to all the input variables in this study, and the importance score of initial smoothness (IRII) and total joint faulting cumulated per km (TFAULT) were the highest for the IRI of JPCP.

BACKGROUND: The side-channel cryptanalysis method based on convolutional neural network (CNNSCA) can effectively carry out cryptographic attacks. The CNNSCA network models that achieve cryptanalysis mainly include CNNSCA based on the VGG variant (VGG-CNNSCA) and CNNSCA based on the Alexnet variant (Alex-CNNSCA). The learning ability and cryptanalysis performance of these CNNSCA models are not optimal, and the trained model has low accuracy, too long training time, and takes up more computing resources. In order to improve the overall performance of CNNSCA, the paper will improve CNNSCA model design and hyperparameter optimization.
METHODS: The paper first studied the CNN architecture composition in the SCA application scenario, and derives the calculation process of the CNN core algorithm for side-channel leakage of one-dimensional data. Secondly, a new basic model of CNNSCA was designed by comprehensively using the advantages of VGG-CNNSCA model classification and fitting efficiency and Alex-CNNSCA model occupying less computing resources, in order to better reduce the gradient dispersion problem of error back propagation in deep networks, the SE (Squeeze-and-Excitation) module is newly embedded in this basic model, this module is used for the first time in the CNNSCA model, which forms a new idea for the design of the CNNSCA model. Then apply this basic model to a known first-order masked dataset from the side-channel leak public database (ASCAD). In this application scenario, according to the model design rules and actual experimental results, exclude non-essential experimental parameters. Optimize the various hyperparameters of the basic model in the most objective experimental parameter interval to improve its cryptanalysis performance, which results in a hyper-parameter optimization scheme and a final benchmark for the determination of hyper-parameters.
RESULTS: Finally, a new CNNSCA model optimized architecture for attacking unprotected encryption devices is obtained-CNNSCAnew. Through comparative experiments, CNNSCAnew\'s guessing entropy evaluation results converged to 61. From model training to successful recovery of the key, the total time spent was shortened to about 30 min, and we obtained better performance than other CNNSCA models.

OBJECTIVE: The Bayesian first-order antedependence models, which specified single nucleotide polymorphisms (SNP) effects as being spatially correlated in the conventional BayesA/B, had more accurate genomic prediction than their corresponding classical counterparts. Given advantages of BayesCπ over BayesA/B, we have developed hyper-BayesCπ, ante-BayesCπ, and ante-hyper-BayesCπ to evaluate influences of the antedependence model and hyperparameters for vg and sg2 on BayesCπ.
METHODS: Three public data (two simulated data and one mouse data) were used to validate our proposed methods. Genomic prediction performance of proposed methods was compared to traditional BayesCπ, ante-BayesA and ante-BayesB.
RESULTS: Through both simulation and real data analyses, we found that hyper-BayesCπ, ante-BayesCπ and ante-hyper-BayesCπ were comparable with BayesCπ, ante-BayesB, and ante-BayesA regarding the prediction accuracy and bias, except the situation in which ante-BayesB performed significantly worse when using a few SNPs and π = 0.95.
CONCLUSIONS: Hyper-BayesCπ is recommended because it avoids pre-estimated total genetic variance of a trait compared with BayesCπ and shortens computing time compared with ante-BayesB. Although the antedependence model in BayesCπ did not show the advantages in our study, larger real data with high density chip may be used to validate it again in the future.