In this paper, an antenna for ultra-wideband multiple-input and multiple-output (UWB-MIMO) is designed. The design comprises two hexagonal monopole antennas. In order to achieve ultra-wideband characteristics and miti...
详细信息
The growing interest in generating recipes from food images has drawn substantial research attention in recent years. Existing works for recipe generation primarily utilize a two-stage training method - first predicti...
详细信息
作者:
Zhang, JingWang, XinCui, JieLi, RuZhong, HongAnhui University
School of Computer Science and Technology Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Hefei230039 China Anhui University
Anhui Engineering Laboratory of IoT Security Technologies Hefei230039 China Anhui University
School of Computer Science and Technology Hefei230039 China
In Vehicular Ad-hoc Networks (VANETs), vehicles must authenticate their identities before accessing services. However, existing authentication schemes based on anonymous credentials still face single-point failure in ...
详细信息
A compact coplanar waveguide multiband antenna based on an open resonant ring is proposed in this paper. The proposed antenna is fabricated on FR-4 substrate with a dielectric constant of 4.4 and a small size of 23 &#...
详细信息
In order to miniaturize microwave devices in RF systems, a power divider with filtering performance is designed. The filter power divider is based on the LTCC process, and miniaturization is achieved by cascading a ba...
详细信息
It has been widely recognized that the efficient training of neural networks (NNs) is crucial to classification performance. While a series of gradient-based approaches have been extensively developed, they are critic...
详细信息
It has been widely recognized that the efficient training of neural networks (NNs) is crucial to classification performance. While a series of gradient-based approaches have been extensively developed, they are criticized for the ease of trapping into local optima and sensitivity to hyperparameters. Due to the high robustness and wide applicability, evolutionary algorithms (EAs) have been regarded as a promising alternative for training NNs in recent years. However, EAs suffer from the curse of dimensionality and are inefficient in training deep NNs (DNNs). By inheriting the advantages of both the gradient-based approaches and EAs, this article proposes a gradient-guided evolutionary approach to train DNNs. The proposed approach suggests a novel genetic operator to optimize the weights in the search space, where the search direction is determined by the gradient of weights. Moreover, the network sparsity is considered in the proposed approach, which highly reduces the network complexity and alleviates overfitting. Experimental results on single-layer NNs, deep-layer NNs, recurrent NNs, and convolutional NNs (CNNs) demonstrate the effectiveness of the proposed approach. In short, this work not only introduces a novel approach for training DNNs but also enhances the performance of EAs in solving large-scale optimization problems.
An ultra-wideband filter with wide stopband performance with single notch using E-shaped resonator is proposed. Based on a U-shaped MMR structure loaded by an open-circuited stub connected at its center, the loaded ba...
详细信息
This work proposes a high-performance broadband orbital angular momentum (OAM) beam-generating metasurface based on optically transparent media. A broadband polarization-converting transmissive metasurface, which oper...
详细信息
A beamforming microstrip array antenna for K-band is proposed. The antenna array is a 4∗4 array, the array elements are composed of slotted rectangular microstrip antennas, and the feed network is a combination of ser...
详细信息
In addressing the challenges posed by low-frequency airborne transient electromagnetics (ATEM), it is necessary to take into account the considerations of accuracy, computational efficiency, and the scale and intricac...
详细信息
In addressing the challenges posed by low-frequency airborne transient electromagnetics (ATEM), it is necessary to take into account the considerations of accuracy, computational efficiency, and the scale and intricacy of the physical domain. This becomes particularly crucial when dealing with large-scale, complex issues, with the aim of mitigating the computational resource burden associated with managing such complexities. In order to further meet the aforementioned criteria, a Perfectly Matched Monolayer (PMM) model has been introduced into the Random Forest Regression (RFR) framework. The RFR-based PMM model has demonstrated exceptional accuracy through the utilization of Bagging's integrated learning methodology, while also reducing the computational resource requirements for processing time. In comparison to traditional machine learning models, our model has exhibited significant advantages in terms of training stability, model efficiency, and parallelization capabilities. To verify and establish the reliability of this approach, three-dimensional numerical simulations of the ATEM problem were conducted. The proposed model in this study has exhibited superior accuracy, efficiency, and versatility in addressing the low-frequency ATEM problem, integrating with the FDTD method.
暂无评论