Search

To study the acoustic characteristics of sound scattered from laminated structures such as elastic plates and shells, it is usually required to solve the Lamb waves’ dispersion equations. Many traditional root-finding methods such as bisection, the Newton–Raphson method, and the Muller method are not able to tackle the problem completely. A simple but powerful method named local peaks search (LPS) is proposed to overcome their drawbacks. Firstly, the non-zero part of the dispersion equation is defined as the dispersion function, and its reciprocal is used to transform the zeros (i.e., roots) into local peaks. Secondly, the chosen complex domain is discretized, and the coarse local domains where the local peaks exist are determined by the direct search method globally. Thirdly, the Muller method is applied to obtain the refined locations of local peaks. Lastly, in order to refine the results, a hierarchical scheme is designed and the iteration of the above procedures is implemented; the error is set to be 10−16 as the stop criteria. The accuracy of the LPS method is validated by comparing it with the bisection method for the problem of elastic plates in the vacuum. The acoustic echo structures are analyzed experimentally. By computation of Lamb waves’ phase velocity, the critical angles are derived numerically and compared with the results acquired by an experiment using monostatic sound transducers. In this way, it is validated that the elastic scattered wave components are the highlights shown in the time-angle figure. Furthermore, the work can be applied for non-destructive testing, especially underwater structural health monitoring.

Neural architecture search (NAS) is a popular branch of automatic machine learning (AutoML), which aims to search for efficient network structures. Many prior works have explored a wide range of search algorithms for classification tasks, and have achieved better performance than manually designed network architectures. However, few works have explored NAS for object detection tasks due to the difficulty to train convolution neural networks from scratch. In this paper, we propose a framework, named as FastDARTSDet, to directly search on a larger-scale object detection dataset (MS-COCO). Specifically, we propose to apply differentiable architecture search method (DARTS) to jointly search backbone and feature pyramid network (FPN) architectures for object detection task. Extensive experimental results on MS-COCO show the efficient and efficacy of our method. Specifically, our method achieves 40.0% mean average precision (mAP) on the test set, outperforming many recent NAS methods.

Recently, Artificial intelligence (AI) has emerged as a revolutionary field, providing a great opportunity in shaping modern crop breeding, and is extensively used indoors for plant science. Advances in crop phenomics, enviromics, together with the other “omics” approaches are paving ways for elucidating the detailed complex biological mechanisms that motivate crop functions in response to environmental trepidations. These “omics” approaches have provided plant researchers with precise tools to evaluate the important agronomic traits for larger-sized germplasm at a reduced time interval in the early growth stages. However, the big data and the complex relationships within impede the understanding of the complex mechanisms behind genes driving the agronomic-trait formations. AI brings huge computational power and many new tools and strategies for future breeding. The present review will encompass how applications of AI technology, utilized for current breeding practice, assist to solve the problem in high-throughput phenotyping and gene functional analysis, and how advances in AI technologies bring new opportunities for future breeding, to make envirotyping data widely utilized in breeding. Furthermore, in the current breeding methods, linking genotype to phenotype remains a massive challenge and impedes the optimal application of high-throughput field phenotyping, genomics, and enviromics. In this review, we elaborate on how AI will be the preferred tool to increase the accuracy in high-throughput crop phenotyping, genotyping, and envirotyping data; moreover, we explore the developing approaches and challenges for multiomics big computing data integration. Therefore, the integration of AI with “omics” tools can allow rapid gene identification and eventually accelerate crop-improvement programs.

In the field of structural health monitoring (SHM), vibration-based structural damage detection is an important technology to ensure the safety of civil structures. By taking advantage of deep learning, this study introduces a data-driven structural damage detection method that combines deep convolutional neural networks (DCNN) and fast Fourier transform (FFT). In this method, the structural vibration data are fed into FFT method to acquire frequency information reflecting structural conditions. Then, DCNN is utilized to automatically extract damage features from frequency information to identify structural damage conditions. To verify the effectiveness of the proposed method, FFT-DCNN is carried out on a three-story building structure and ASCE benchmark. The experimental result shows that the proposed method achieves high accuracy, compared with classic machine-learning algorithms such as support vector machine (SVM), random forest (RF), K-Nearest Neighbor (KNN), and eXtreme Gradient boosting (xgboost).

To investigate the effect of 14,15-EET on the parthanatos in neurons induced by cerebral ischemia and reperfusion, middle cerebral artery occlusion and reperfusion (MCAO/R) and oxygen glucose deprivation/reoxygenation (OGD/R) were used to simulate cerebral ischemia reperfusion in vivo and in vitro, respectively. TTC staining and the Tunel method were used to detect cerebral infarct volume and neuronal apoptosis. Western blot and immunofluorescence were used to detect poly (ADP-ribose) polymerase-1 (PARP-1) activation and AIF nuclear translocation. The production of reactive oxygen species (ROS) and the expression of antioxidant genes were detected by Mito SOX, DCFH-DA and qPCR methods. MCAO/R increased cerebral infarct volume and neuronal apoptosis in mice, while 14,15-EET pretreatment increased cerebral infarct volume and neuronal apoptosis. OGD/R induced reactive oxygen species generation, PARP-1 cleavage, and AIF nuclear translocation in cortical neurons. 14,15-EET pretreatment could enhance the antioxidant gene expression of glutathione peroxidase (GSH-Px), heme oxygenase-1 (HO-1) and superoxide dismutase (SOD) in cortical neurons after ischemia and reperfusion. 14,15-EET inhibits the neuronal parthanatos induced by MCAO/R through upregulation of the expression of antioxidant genes and by reducing the generation of reactive oxygen species. This study advances the EET neuroprotection theory and provides a scientific basis for targeted clinical drugs that reduce neuronal parthanatos following cerebral ischemia and reperfusion.