[1] A confined coastal aquifer usually extends under the sea for some distance with its submarine outlet covered by a thin layer of sediment with properties dissimilar from the aquifer. Previous theoretical studies neglected this outlet capping. In this paper an analytical solution is derived for a confined aquifer subject to tidal fluctuations with a leaky boundary condition at the outlet capping. For the cases that offshore length of the aquifer and/or the leakance of the outlet capping are either zero or infinity, existing solutions in literature are obtained. It is shown that our analytical solution can also be used to describe the tidal wave propagation in a confined aquifer extending infinitely under a tidal river. The full solution agreed well with the observations in a piezometer in the Jahe River Basin in China, 200 m inland from the coastline where the tide-induced head fluctuations without delay were observed but cannot be explained using previous analytical and numerical solutions ignoring the effect of the outlet capping. The sensitivity analysis showed that the combined actions of the tidal loading and outlet capping lead to complex dependency of the head fluctuation on the outlet capping's leakance. When the offshore confined aquifer is short, the inland head fluctuation increases with the outlet capping's leakance. In this case significant negative phase shift occurs if the leakance is small. For offshore aquifer length greater than a threshold value the inland head fluctuations are independent of this length and the outlet capping's leakance.

In the wake of developments in remote sensing, the application of target detection of remote sensing is of increasing interest. Unfortunately, unlike natural image processing, remote sensing image processing involves dealing with large variations in object size, which poses a great challenge to researchers. Although traditional multi-scale detection networks have been successful in solving problems with such large variations, they still have certain limitations: (1) The traditional multi-scale detection methods note the scale of features but ignore the correlation between feature levels. Each feature map is represented by a single layer of the backbone network, and the extracted features are not comprehensive enough. For example, the SSD network uses the features extracted from the backbone network at different scales directly for detection, resulting in the loss of a large amount of contextual information. (2) These methods combine with inherent backbone classification networks to perform detection tasks. RetinaNet is just a combination of the ResNet-101 classification network and FPN network to perform the detection tasks; however, there are differences in object classification and detection tasks. To address these issues, a cross-scale feature fusion pyramid network (CF2PN) is proposed. First and foremost, a cross-scale fusion module (CSFM) is introduced to extract sufficiently comprehensive semantic information from features for performing multi-scale fusion. Moreover, a feature pyramid for target detection utilizing thinning U-shaped modules (TUMs) performs the multi-level fusion of the features. Eventually, a focal loss in the prediction section is used to control the large number of negative samples generated during the feature fusion process. The new architecture of the network proposed in this paper is verified by DIOR and RSOD dataset. The experimental results show that the performance of this method is improved by 2%-12% in the DIOR dataset and RSOD dataset compared with the current SOTA target detection methods.

No abstract

No abstract

Nanosecond pulsed surface dielectric barrier discharge (SDBD) is a hot topic in many fields, but the mechanisms of discharge evolution and micro-channel propagation are still not clearly understood. In this paper, a plasma fluid model of nanosecond pulsed SDBD is established, and the deductions of the two current spikes are verified and improved by simulation. The two current spikes correspond to the two stages of the discharge: the ionization wave propagation and the repeated re-ignition in the gap between the ionization wave and the dielectric surface. In the first stage, the ionization wave develops rapidly at first and propagates very slowly in the end, which produces the first current spike with a very short rise time and a tailing falling edge. The curve profile of the ionization wave velocity is very similar to that of the first current spike. A certain distance is maintained between the bottom of the ionization wave and the dielectric surface in this stage, which forms the gap for the next stage. In the second stage, the charged particle cloud induced by the quasi-uniform electric field in the middle of the gap and the new micro-channel from the edge of the high-voltage electrode propagate at first, and then merge together to establish a new discharge channel. The reverse electric field in the gap induced by the accumulated charges on the dielectric surface restricts the expansion velocity of the second discharge channel, which results in a longer rise time and falling time of the second current spike.

No abstract

In recent years, the lightweight neural network models have been gradually applied to fault diagnosis. In order to solve the problems about computation bottleneck of the pointwise convolution module which is widely used in lightweight networks, and explore how to effectively evaluate the quality of extracted features as well as deeply merge traditional fault diagnosis methods into deep learning, this paper proposed a diagnosis model named butterfly-transform (BFT)-MobileNet V3. BFT-MobileNet V3 was based on MobileNet V3, and consisted of BFT module and a novel algorithm called Deep-SHAP. This model not only had the advantages of low time complexity and high accuracy compared with the original network, but also had a novel feature that was able to automatically figure out the fault characteristic frequency and visualize the quality of extracted features. The experimental results showed that the time complexity of the BFT-MobileNet V3 model proposed in this paper decreases from to while keeping a high accuracy rate. With the same time complexity, BFT-MobileNet V3 also had a higher accuracy rate than other networks. Meanwhile, with the Deep SHAP algorithm, the proposed model can accurately calculate the fault feature frequency of the roller bearings as well as intuitively visualize the quality of extracted features.

Survey/review study Deep Learning Attention Mechanism in Medical Image Analysis: Basics and Beyonds Xiang Li 1, Minglei Li 1, Pengfei Yan 1, Guanyi Li 1, Yuchen Jiang 1, Hao Luo 1,*, and Shen Yin 2 1 Department of Control Science and Engineering, Harbin Institute of Technology, Harbin 150001, China 2 Department of Mechanical and Industrial Engineering, Faculty of Engineering, Norwegian University of Science and Technology, Trondheim 7034, Norway * Correspondence: hao.luo@hit.edu.cn     Received: 16 October 2022 Accepted: 25 November 2022 Published:    Abstract: With the improvement of hardware computing power and the development of deep learning algorithms, a revolution of "artificial intelligence (AI) + medical image" is taking place. Benefiting from diversified modern medical measurement equipment, a large number of medical images will be produced in the clinical process. These images improve the diagnostic accuracy of doctors, but also increase the labor burden of doctors. Deep learning technology is expected to realize an auxiliary diagnosis and improve diagnostic efficiency. At present, the method of deep learning technology combined with attention mechanism is a research hotspot and has achieved state-of-the-art results in many medical image tasks. This paper reviews the deep learning attention methods in medical image analysis. A comprehensive literature survey is first conducted to analyze the keywords and literature. Then, we introduce the development and technical characteristics of the attention mechanism. For its application in medical image analysis, we summarize the related methods in medical image classification, segmentation, detection, and enhancement. The remaining challenges, potential solutions, and future research directions are also discussed.