基于细胞神经网络和网格特征的碑刻文字识别

碑刻作为文字的载体,具有极其重要的历史价值和艺术价值。但是,因为时间的久远,其拓本大量的噪声对碑刻文字的辨识产生一定的影响。针对这种情况,提出了一种新方法,首先利用细胞神经网络（CNN）技术,去除单个碑刻文字的噪声,然后用网格特征提取方法对其进行识别。本文在MATLAB平台上进行了实例模拟,取得了较好的效果。     

基于细胞神经网络的视频分割算法研究

细胞神经网络（CNN）是一种局部互连的非线性并行模拟视觉处理系统,具有适合硬件实现处理速度快的优点,被广泛地应用于图像处理的各个方面。针对目前大多数视频分割算法难以满足实时性要求的缺点,将细胞神经网络应用到视频分割当中．提出了一种改进的基于细胞神经网络的视频分割算法,并通过仿真实验证明了其可行性。     

基于transformer自适应特征向量融合的图像分类

针对目前基于transformer的图像分类模型直接应用在小数据集上性能较差的问题,本文提出了transformer自适应特征向量融合网络,该网络在特征提取器中将不同阶段的特征进行融合,减少特征信息丢失的同时获得更多不同感受野下的信息,同时利用最大池化来去除特征中的冗余信息,从而使提取的特征更具有判别性。此外,为了充分利用图像的各级特征信息来进行分类预测,本文将网络各阶段产生的特征向量进行融合,使融合后的特征向量更具有表征能力,从而减少网络对大数据集的依赖,使网络在小数据集中也能获得很好的性能。实验表明,本文提出的 算法在数据集Mini-ImageNet-100、CIFAR-100和ImageNet-1k上的TOP-1准确率分别达到了74.22%、85.86%和81.4%。在没有增加计算量的情况下,在baseline上分别提高了6.0%、3.0%和0.1%,且参数量减少了18.3%。本文代码开源在“https://github.com/xhutongxue/afvf”。     

基于图卷积的视网膜血管轮廓及高不确定度区域细化框架

针对传统卷积神经网络(convolutional neural network, CNN)受感受野大小的限制,无法直接有效地获取空间结构及全局语义等关键信息,导致宽血管边界及毛细血管区域特征提取困难,造成视网膜血管分割表现不佳的问题,提出一种基于图卷积的视网膜血管分割细化框架。该框架通过轮廓提取及不确定分析方法,选取CNN粗分割结果中潜在的误分割区域,并结合其提取的特征信息构造出合适的图数据,送入残差图卷积网络(residual graph convolutional network, Res-GCN)二次分类,得到视网膜血管细化分割结果。该框架可以作为一个即插即用模块接入任意视网膜血管分割网络的末端,具有高移植性和易用性的特点。实验分别选用U型网络(U-neural network, U-Net)及其代表性改进网络DenseU-Net和AttU-Net作为基准网络,在DRIVE、STARE和CHASEDB1数据集上进行测试,本文框架的Sp分别为98.28%、99.10%和99.04%,Pr分别为87.97%、88.87%和90.25%,证明其具有提升基准网络分割效果的细化能力。     

基于CTCNet对球结膜进行糖尿病视网膜病变分类

糖尿病视网膜病变(diabetic retinopathy, DR)是一种糖尿病性微血管病变,会在球结膜微血管上有所体现,球结膜血管图像的获取比眼底图像更加便捷,但微血管的特征变化微小且难以量化。为了能够对患者进行早期辅助诊断,本文依据球结膜微血管形态与DR的关联,首先对球结膜图像进行预处理,使用限制对比度自适应直方图均衡(contrast limited adaptive histogram equalization, CLAHE)算法进行图像增强,随机处理使数据增强,然后结合卷积神经网络(convolutional neural network, CNN)和Transformer各自的网络优势构建CTCNet,对处理后的球结膜血管图像进行DR分类,分类准确率达到了97.44%,敏感度97.69%,特异性97.11%,精确度97.69%,通过实验对比CNN和Transformer, CTCNet网络性能优于其他模型,能够有效识别DR。     

Optimized deep learning-based intrusion detection for wireless sensor networks

The technological innovations and wide use of Wireless Sensor Network (WSN) applications need to handle diverse data. These huge data possess network security issues as intrusions that cannot be neglected or ignored. An effective strategy to counteract security issues in WSN can be achieved through the Intrusion Detection System (IDS). IDS ensures network integrity, availability, and confidentiality by detecting different attacks. Regardless of efforts by various researchers, the domain is still open to obtain an IDS with improved detection accuracy with minimum false alarms to detect intrusions. Machine learning models are deployed as IDS, but their potential solutions need to be improved in terms of detection accuracy. The neural network performance depends on feature selection, and hence, it is essential to bring an efficient feature selection model for better performance. An optimized deep learning model has been presented to detect different types of attacks in WSN. Instead of the conventional parameter selection procedure for Convolutional Neural Network (CNN) architecture, a nature-inspired whale optimization algorithm is included to optimize the CNN parameters such as kernel size, feature map count, padding, and pooling type. These optimized features greatly improved the intrusion detection accuracy compared to Deep Neural network (DNN), Random Forest (RF), and Decision Tree (DT) models.     

Detection of COVID-19 from chest X-ray images: Boosting the performance with convolutional neural network and transfer learning

Coronavirus disease (COVID-19) is a pandemic that has caused thousands of casualties and impacts all over the world. Most countries are facing a shortage of COVID-19 test kits in hospitals due to the daily increase in the number of cases. Early detection of COVID-19 can protect people from severe infection. Unfortunately, COVID-19 can be misdiagnosed as pneumonia or other illness and can lead to patient death. Therefore, in order to avoid the spread of COVID-19 among the population, it is necessary to implement an automated early diagnostic system as a rapid alternative diagnostic system. Several researchers have done very well in detecting COVID-19; however, most of them have lower accuracy and overfitting issues that make early screening of COVID-19 difficult. Transfer learning is the most successful technique to solve this problem with higher accuracy. In this paper, we studied the feasibility of applying transfer learning and added our own classifier to automatically classify COVID-19 because transfer learning is very suitable for medical imaging due to the limited availability of data. In this work, we proposed a CNN model based on deep transfer learning technique using six different pre-trained architectures, including VGG16, DenseNet201, MobileNetV2, ResNet50, Xception, and EfficientNetB0. A total of 3886 chest X-rays (1200 cases of COVID-19, 1341 healthy and 1345 cases of viral pneumonia) were used to study the effectiveness of the proposed CNN model. A comparative analysis of the proposed CNN models using three classes of chest X-ray datasets was carried out in order to find the most suitable model. Experimental results show that the proposed CNN model based on VGG16 was able to accurately diagnose COVID-19 patients with 97.84% accuracy, 97.90% precision, 97.89% sensitivity, and 97.89% of F1-score. Evaluation of the test data shows that the proposed model produces the highest accuracy among CNNs and seems to be the most suitable choice for COVID-19 classification. We believe that in this pandemic situation, this model will support healthcare professionals in improving patient screening.     

基于场景先验及注意力引导的跌倒检测算法

已有跌倒检测工作主要关注室内场景,且大多偏重对人员身体姿态特征进行建模,而忽略了场景背景信息以及人员与地面的交互信息。针对这个问题,从实际电梯场景应用入手,提出一种基于场景先验及注意力引导的跌倒检测算法。首先,利用电梯历史数据,以高斯概率分布建模的方式从人员的活动轨迹中自动化地学习场景先验信息;随后,把场景先验信息作为空间注意力掩膜与神经网络的全局特征融合,以此聚焦地面区域的局部信息;然后,将融合后的局部特征与全局特征采用自适应加权的方式进一步聚合,从而形成更具鲁棒性和判别力的特征;最后,将特征送入由全局平均池化层和全连接层构成的分类模块中进行跌倒类别预测。在自构建的电梯场景Elevator Fall Detection和公开的UR Fall Detection数据集上的实验结果表明,所提算法的检测准确率分别达到了95.36%和99.01%,相较于网络结构复杂的ResNet50算法,分别提高了3.52个百分点和0.61个百分点。可见所构建的高斯场景先验引导的注意力机制可使网络关注地面区域的特征,更有利于对跌倒的识别,由此得到的检测模型准确率高且算法满足实时性应用要求。     

抑制图像非语义信息的通用后门防御策略

目的 后门攻击已成为目前卷积神经网络所面临的重要威胁。然而,当下的后门防御方法往往需要后门攻击和神经网络模型的一些先验知识,这限制了这些防御方法的应用场景。本文依托图像分类任务提出一种基于非语义信息抑制的后门防御方法,该方法不再需要相关的先验知识,只需要对网络的输入进行编解码处理就可以达到后门防御的目的。方法 核心思想是在保持图像语义不改变的同时,尽量削弱原始样本中与图像语义不相关的信息,以此抑制触发器。通过在待保护模型前添加一个即插即用的U型网络(即信息提纯网络)来实现对图像非语义信息的抑制。其输入是干净的初始样本,输出命名为强化样本。具体的训练过程中,首先用不同的训练超参数训练多个结构不一的干净分类器,然后在保持强化样本被上述分类器正确分类的前提下,优化信息提纯网络使强化样本和原始样本之间的差异尽可能地大。结果 实验在MNIST、CIFAR10和Image Net10数据集上进行。实验结果显示,经过信息提纯网络编解码后,干净样本的分类准确率略有下降,后门攻击成功率大幅降低,带有触发器的样本以接近干净样本的准确率被正确预测。结论 提出的非语义信息抑制防御方法能够在不需要相关先验知识的...     

引入分组注意力的医学图像分割模型

目的 卷积神经网络结合U-Net架构的深度学习方法广泛应用于各种医学图像处理中,取得了良好的效果,特别是在局部特征提取上表现出色,但由于卷积操作本身固有的局部性,导致其在全局信息获取上表现不佳。而基于Transformer的方法具有较好的全局建模能力,但在局部特征提取方面不如卷积神经网络。为充分融合两种方法各自的优点,提出一种基于分组注意力的医学图像分割模型（medical image segmentation module based on group attention,GAU-Net）。方法 利用注意力机制,设计了一个同时集成了Swin Transformer和卷积神经网络的分组注意力模块,并嵌入网络编码器中,使网络能够高效地对图像的全局和局部重要特征进行提取和融合;在注意力计算方式上,通过特征分组的方式,在同一尺度特征内,同时进行不同的注意力计算,进一步提高网络提取语义信息的多样性;将提取的特征通过上采样恢复到原图尺寸,进行像素分类,得到最终的分割结果。结果 在Synapse多器官分割数据集和ACDC （automated cardiac diagnosis challenge）数据集上进行了相关实验验证。在Synapse数据集中,Dice值为82.93%,HD（Hausdorff distance）值为12.32%,相较于排名第2的方法,Dice值提高了0.97%,HD值降低了5.88%;在ACDC数据集中,Dice值为91.34%,相较于排名第2的方法提高了0.48%。结论 本文提出的医学图像分割模型有效地融合了Transformer和卷积神经网络各自的优势,提高了医学图像分割结果的精确度。