肠道杆菌的扫描电镜观察

我们用扫描电镜观察肠道杆菌种(Enterobacteriaceae)中的四种细菌,大肠埃希氏杆菌(Escherichiacoli),普通变形杆菌(Proteus vulgaris),伤寒沙门氏菌(Salmonella typhi)和福氏志贺氏菌(Shigella Flexneri)。未处理的菌落标本,菌落表面都可形成一层厚薄不同的表膜(Surface film)。四种细菌菌落的表膜,形状不一,千姿百态。适当处理后的菌落标本,则可显示菌体的本来面目。四种细菌菌体在菌落表面的分布和排列,也是各不相同,千差万别。本文根据扫描电镜的观察,对四种不同菌落进行了讨论。     

ASRNet: Adversarial Segmentation and Registration Networks for Multispectral Fundus Images

Multispectral imaging (MSI) technique is often used to capture images of the fundus by illuminating it with different wavelengths of light. However, these images are taken at different points in time such that eyeball movements can cause misalignment between consecutive images. The multispectral image sequence reveals important information in the form of retinal and choroidal blood vessel maps, which can help ophthalmologists to analyze the morphology of these blood vessels in detail. This in turn can lead to a high diagnostic accuracy of several diseases. In this paper, we propose a novel semi-supervised end-to-end deep learning framework called “Adversarial Segmentation and Registration Nets” (ASRNet) for the simultaneous estimation of the blood vessel segmentation and the registration of multispectral images via an adversarial learning process. ASRNet consists of two subnetworks: (i) A segmentation module S that fulfills the blood vessel segmentation task, and (ii) A registration module R that estimates the spatial correspondence of an image pair. Based on the segmention-driven registration network, we train the segmentation network using a semi-supervised adversarial learning strategy. Our experimental results show that the proposed ASRNet can achieve state-of-the-art accuracy in segmentation and registration tasks performed with real MSI datasets.     

Protect privacy of deep classification networks by exploiting their generative power

Machine Learning - Research showed that deep learning models are vulnerable to membership inference attacks, which aim to determine if an example is in the training set of the model. We propose a...     

Identifying epidemic spreading dynamics of COVID-19 by pseudocoevolutionary simulated annealing optimizers

Neural Computing and Applications - At the end of 2019, a new coronavirus (COVID-19) epidemic has triggered global public health concern. Here, a model integrating the daily intercity migration...     

Visualization-based disentanglement of latent space

Neural Computing and Applications - In recent years, selecting manipulation of data attributes by changing latent code using auto-encoder has received considerable scholarly attention . However,...     

Editorial: Special issue on neural computing and applications in cyber intelligence: ATCI 2020

Neural Computing and Applications -     

DM-CTSA: a discriminative multi-focused and complementary temporal/spatial attention framework for action recognition

Neural Computing and Applications - Video-based human action recognition remains a challenging task. There are three main limitations: (1) Most works are only restricted to single temporal scale...     

An iterative gradient convolutional neural network and its application in endoscopic photoacoustic image formation from incomplete acoustic measurement

Neural Computing and Applications - Endoscopic photoacoustic tomography (EPAT) is a rapidly developing catheter-based imaging technique to provide cross-sectional images of anatomical, functional...     

多频段脑功能网络融合的阿尔茨海默病分类

将图论与机器学习方法相结合的阿尔茨海默病计算机辅助中,脑网络的构建大多是基于滤波去噪后的全频段BOLD信号匹配,忽略了不同脑活动信息的差异.因此,本文提出了一种多频段脑功能网络融合模型.首先将离散小波变换应用于BOLD信号中,得到不同频域下的体素信号,而后计算同频信号的相关性,获取不同频段下相关矩阵.而后计算所有矩阵的网络特征,在特征选择后基于SVM对患者进行分类.从实验结果可以看出,分频下的脑功能网络特征与未分频网络相比能在一定程度上提高分类的准确性;体素级网络由于可以更加详细的表达脑网络的变化,其分类效果要优于脑区级.     

Security flaws in a recent RFID delegation protocol

Radio frequency identification (RFID) tag delegation enables a centralized back-end server to delegate the right to identify and authenticate a tag to specified readers. This should be used to mitigate the computational load on the server side and also to solve the issues in terms of latency and dependency on network connectivity. In this study, we describe a basic RFID delegation architecture and then under this model, we investigate the security of an RFID delegation protocol: Song Mitchell delegation (SMD), which is recently proposed by Song and Mitchell. We point out security flaws that have gone unnoticed in the design and present two attacks namely, a tag impersonation attack and a desynchronization attack against it. We also discover a subtle flaw by which a delegated entity can still keep its delegation rights after the expire of them—this infringes security policy of the scheme. More precisely, we show that the protocol will be still vulnerable to previously mentioned attacks, even if the back-end server ends the delegation right of a delegated reader and update the secrets of the delegated tags. To counteract such flaws, we improve the SMD protocol with a stateful variant so that it provides the claimed security properties.