基于深度学习与数据增强技术的小样本岩石分类

在油气勘探中,利用深度学习技术对岩石进行识别与分类能极大提高工作效率。岩石采样并制作样本图像费时费力,因此岩石样本通常较少。有鉴于此,基于深度学习技术设计一个新的神经网络模型MyNet,该模型能对小样本进行学习并完成岩石样本的分类。使用数据增强技术通过Python编程将314张岩石样本扩充成28 272张图像,为了充分利用现有数据,取其中的27 384张作为训练集,剩余888张作为测试集。将数据分别导入MyNet、ResNet50、Vgg16进行训练和测试。实验结果表明,加载、不加载预训练参数的ResNet50、Vgg16的岩石分类结果因受有无迁移学习影响会有所不同;MyNet的总体分类准确率为75.6%,均优于有无迁移学习的ResNet50、Vgg16,且MyNet、ResNet50、Vgg16所需训练的参数量分别为919 278、25 503 912、138 357 544,显然,MyNet模型的复杂度与训练代价明显低于其他对比模型,但性能最优,说明新模型应用于小样本的岩石分类可行有效且经济安全,更容易推广应用。     

基于深度学习的Stack Overflow问题帖分类方法

针对基于正则表达式和传统机器学习的分类方法分别存在模式手工提取困难和性能瓶颈的问题,提出一种基于深度学习的问题帖分类方法,采用深度文本挖掘模型TextCNN和融合注意力机制的TextRNN构建分类模型.实验结果表明,基于深度学习的方法在多数问题目的类别上的分类性能优于已有基准方法,且使用的Adam优化器优于SGD优化器...     

低速冲击下钢筋混凝土深梁抗冲击性能及其损伤评估

为研究钢筋混凝土深梁在低速冲击下的抗冲击性能和损伤机理,采用有限元软件ANSYS/LS-DYNA对不同冲击速度下深梁动力响应进行模拟.分析深梁的动态损伤过程及横截面的损伤分布,采用截面损伤因子对钢筋混凝土深梁的损伤程度进行定量评估;进一步分析边界条件、冲击位置对深梁抗冲击性能和损伤的影响.分析结果表明:建立的模型可以合...     

融合动作剔除的深度竞争双Q网络智能干扰决策算法

为解决战场通信干扰决策问题,设计了一种融合动作剔除的深度竞争双Q网络智能干扰决策方法.该方法在深度双Q网络框架基础上采用竞争结构的神经网络决策最优干扰动作,并结合优势函数判断各干扰动作的相对优劣,在此基础上引入无效干扰动作剔除机制加快学习最佳干扰策略.当面对未知的通信抗干扰策略时,该方法能学习到较优的干扰策略.仿真结果...     

基于大津算法和深度学习的开集声纹识别自适应阈值计算方法

针对开集声纹识别的自适应阈值计算问题,提出一种基于大津算法和深度学习的阈值计算方法.首先,采用三层受限Boltzmann机堆叠而成的深度置信网络从Mel倒谱系数中提取语音深层特征;其次,通过Gauss混合模型计算特征的相似度值,对特征的相似度值使用大津算法计算阈值.实验结果表明,该方法识别效果较理想,与等错误率计算阈值...     

基于深度残差网络的医学超声图像多尺度边缘检测算法

为提高医学超声图像在临床诊断的效果,需先对图像进行优化检测和识别,提出一种基于深度残差网络的医学超声图像多尺度边缘检测算法.首先,通过对原始医学超声图像进行自动标注,构建医学超声图像灰度分布矩阵,利用分布矩阵完成医学超声图像的多尺度分割;其次,构建医学超声图像多尺度边缘的轮廓模型,提取多尺度图像边缘特征;再次,构建深度...     

Forecasting COVID-19 Epidemic Trends by Combining a Neural Network with Rt Estimation

On 31 December 2019, a cluster of pneumonia cases of unknown etiology was reported in Wuhan (China). The cases were declared to be Coronavirus Disease 2019 (COVID-19) by the World Health Organization (WHO). COVID-19 has been defined as SARS Coronavirus 2 (SARS-CoV-2). Some countries, e.g., Italy, France, and the United Kingdom (UK), have been subjected to frequent restrictions for preventing the spread of infection, contrary to other ones, e.g., the United States of America (USA) and Sweden. The restrictions afflicted the evolution of trends with several perturbations that destabilized its normal evolution. Globally, Rt has been used to estimate time-varying reproduction numbers during epidemics. Methods: This paper presents a solution based on Deep Learning (DL) for the analysis and forecasting of epidemic trends in new positive cases of SARS-CoV-2 (COVID-19). It combined a neural network (NN) and an Rt estimation by adjusting the data produced by the output layer of the NN on the related Rt estimation. Results: Tests were performed on datasets related to the following countries: Italy, the USA, France, the UK, and Sweden. Positive case registration was retrieved between 24 February 2020 and 11 January 2022. Tests performed on the Italian dataset showed that our solution reduced the Mean Absolute Percentage Error (MAPE) by 28.44%, 39.36%, 22.96%, 17.93%, 28.10%, and 24.50% compared to other ones with the same configuration but that were based on the LSTM, GRU, RNN, ARIMA (1,0,3), and ARIMA (7,2,4) models, or an NN without applying the Rt as a corrective index. It also reduced MAPE by 17.93%, the Mean Absolute Error (MAE) by 34.37%, and the Root Mean Square Error (RMSE) by 43.76% compared to the same model without the adjustment performed by the Rt. Furthermore, it allowed an average MAPE reduction of 5.37%, 63.10%, 17.84%, and 14.91% on the datasets related to the USA, France, the UK, and Sweden, respectively.     

Deep Image Steganography Using Transformer and Recursive Permutation

Image steganography, which usually hides a small image (hidden image or secret image) in a large image (carrier) so that the crackers cannot feel the existence of the hidden image in the carrier, has become a hot topic in the community of image security. Recent deep-learning techniques have promoted image steganography to a new stage. To improve the performance of steganography, this paper proposes a novel scheme that uses the Transformer for feature extraction in steganography. In addition, an image encryption algorithm using recursive permutation is proposed to further enhance the security of secret images. We conduct extensive experiments to demonstrate the effectiveness of the proposed scheme. We reveal that the Transformer is superior to the compared state-of-the-art deep-learning models in feature extraction for steganography. In addition, the proposed image encryption algorithm has good attributes for image security, which further enhances the performance of the proposed scheme of steganography.     

Compound buried layer SOI high voltage device with a step buried oxide

A silicon-on-insulator (SOI) high performance lateral double-diffusion metal oxide semiconductor (LDMOS) on a compound buried layer (CBL) with a step buried oxide (SBO CBL SOI) is proposed.The step buried oxide locates holes in the top interface of the upper buried oxide (UBO) layer.Furthermore,holes with high density are collected in the interface between the polysilicon layer and the lower buried oxide (LBO) layer.Consequently,the electric fields in both the thin LBO and the thick UBO are enhanced by these holes,leading to an improved breakdown voltage.The breakdown voltage of the SBO CBL SOI LDMOS increases to 847 V from the 477 V of a conventional SOI with the same thicknesses of SOI layer and the buried oxide layer.Moreover,SBO CBL SOI can also reduce the self-heating effect.     

玻璃中CdSeS纳米晶体的生长及其性能

对掺有镉、硒、硫的玻璃在500—800℃退火2—24h,生长了不同尺寸的CdSxSe1x纳米晶体.用分光光度计和光致发光光谱(PL)分析了纳米晶体的性能.退火温度低于550℃,纳米晶体处于成核阶段,600—625℃处于正常扩散生长阶段,700—800℃处于竞争生长阶段;而650℃处于两种生长阶段之间.虽然650℃下生长的纳米晶体的尺寸分布比较窄,但纳米晶体的尺寸随退火时间的延长几乎不变,在该温度改变退火时间很难改变纳米晶体的平均尺寸.在所有样品中出现了深能级缺陷,在650℃退火时间小于4h或大于16h有利 关键词： 纳米晶体 生长机理 深能级缺陷