Adversarial Data Hiding in Digital Images

In recent studies of generative adversarial networks (GAN), researchers have attempted to combine adversarial perturbation with data hiding in order to protect the privacy and authenticity of the host image simultaneously. However, most of the studied approaches can only achieve adversarial perturbation through a visible watermark; the quality of the host image is low, and the concealment of data hiding cannot be achieved. In this work, we propose a true data hiding method with adversarial effect for generating high-quality covers. Based on GAN, the data hiding area is selected precisely by limiting the modification strength in order to preserve the fidelity of the image. We devise a genetic algorithm that can explore decision boundaries in an artificially constrained search space to improve the attack effect as well as construct aggressive covert adversarial samples by detecting “sensitive pixels” in ordinary samples to place discontinuous perturbations. The results reveal that the stego-image has good visual quality and attack effect. To the best of our knowledge, this is the first attempt to use covert data hiding to generate adversarial samples based on GAN.     

Conserved Control Path in Multilayer Networks

The determination of directed control paths in complex networks is important because control paths indicate the structure of the propagation of control signals through edges. A challenging problem is to identify them in complex networked systems characterized by different types of interactions that form multilayer networks. In this study, we describe a graph pattern called the conserved control path, which allows us to model a common control structure among different types of relations. We present a practical conserved control path detection method (CoPath), which is based on a maximum-weighted matching, to determine the paths that play the most consistent roles in controlling signal transmission in multilayer networks. As a pragmatic application, we demonstrate that the control paths detected in a multilayered pan-cancer network are statistically more consistent. Additionally, they lead to the effective identification of drug targets, thereby demonstrating their power in predicting key pathways that influence multiple cancers.     

基于独立组分分析和BP神经网络的可见/近红外光谱蜂蜜品牌的鉴别

提出了一种基于独立组分分析的可见/近红外光谱透射技术快速鉴别蜂蜜品牌的新方法。用独立组分分析方法获取蜂蜜的可见/近红外光谱载荷图,将载荷图中相关性最大的波段,作为人工神经网络的输入建立蜂蜜品牌的鉴别模型。建立了一个三层的BP神经网络模型,各层传递函数采用S型(Sigmoid)函数,并设置网络输入层节点数为9,隐含层节点数为10,输出层节点数为3。每个品牌25个样本,3个品牌共75个样本,用来建立BP神经网络模型,剩余的3个品牌各５个样本用于预测,鉴别准确率达100%,模型的拟合残差为8.245 365×10-5。说明基于独立组分分析的方法具有很好的鉴别效果,为蜂蜜的品牌鉴别提供了一种新方法。     

血液可见吸收光谱与血氧参数神经网络估算法

总血红蛋白浓度和血氧饱和度是两个基本的血氧参数。文章提出了利用内置双光纤微创探头在位测量大鼠脑组织血氧参数的新方法。首先,利用悬乳液(Intralipid)和全血配置不同总血红蛋白浓度的混合溶液,模拟生物组织模型,用光纤光谱仪测试系统测量组织模型在加氧和去氧时的实时吸收光谱,同时用血氧分析仪(OXI meter)对血氧参数定标,建立测试光谱和定标数据样本集。然后,利用人工神经网络建立血液吸收光谱与血氧参数的神经网络模型,训练后的网络模型能根据吸收光谱输出生物组织的血氧参数值,总血红蛋白浓度和血氧饱和度的平均输出误差分别为±4μmol·L-1和±5%。最后,利用神经网络模型对大鼠脑组织血氧参数进行了在位测试实验,测得脑灰质的血氧饱和度为0.60~0.70,脑白质血氧饱和度为0.45~0.55;总血红蛋白浓度在脑皮层(深度1mm)附近最高,平均110μmol·L-1,其余深度脑组织的总血红蛋白浓度为70~90μmol·L-1。这种方法对脑外科微创手术中实时在位测试脑组织血氧参数具有重要的参考意义。     

An Improvement to Conformer-Based Model for High-Accuracy Speech Feature Extraction and Learning

Owing to the loss of effective information and incomplete feature extraction caused by the convolution and pooling operations in a convolution subsampling network, the accuracy and speed of current speech processing architectures based on the conformer model are influenced because the shallow features of speech signals are not completely extracted. To solve these problems, in this study, we researched a method that used a capsule network to improve the accuracy of feature extraction in a conformer-based model, and then, we proposed a new end-to-end model architecture for speech recognition. First, to improve the accuracy of speech feature extraction, a capsule network with a dynamic routing mechanism was introduced into the conformer model; thus, the structural information in speech was preserved, and it was input to the conformer blocks via sequestered vectors; the learning ability of the conformed-based model was significantly enhanced using dynamic weight updating. Second, a residual network was added to the capsule blocks, thus, the mapping ability of our model was improved and the training difficulty was reduced. Furthermore, the bi-transformer model was adopted in the decoding network to promote the consistency of the hypotheses in different directions through bidirectional modeling. Finally, the effectiveness and robustness of the proposed model were verified against different types of recognition models by performing multiple sets of experiments. The experimental results demonstrated that our speech recognition model achieved a lower word error rate without a language model because of the higher accuracy of speech feature extraction and learning using our model architecture with a capsule network. Furthermore, our model architecture benefited from the advantage of the capsule network and the conformer encoder, and also has potential for other speech-related applications.     

光纤CAN总线接口设计

基于CAN控制器SJAl000提出了光纤CAN(Fiber—CAN)总线网络的设计方案。采用光纤作为传输介质提高电动汽车CAN通信网抗干扰能力。详细分析了双绞线CAN(Wire—CAN)总线的接口协议，设计了基于此协议的Fiber—CAN总线接口电路和相应的接口驱动，以及光纤CAN总线和双绞线CAN总线间转换接口。通过3个节点的Fiber-CAN总线组网，验证了接口协议和接口电路设计的正确性。     

基于园区网络的主动安全模型设计与研究

从现行典型园区网络安全设计方案入手，结合其在安全防范解决方案上存在的问题，提出了一种网络主动安全模型；在全局网络安全认识的基础上．阐述了模型组成部件的功能定义和网络主动安全实现流程；采用统一网络入口认证、网络知识发现及资源有效控制、沟通等手段，解决了现行网络安全设计中存在的恶意攻击行为源头定位困难，以及信息安全司法取证不准、网络资源安全被动防护、网络灾难快速反映能力差等问题．实验结果表明，该设计方案具有较好的可行性和实用性．     

出境旅游网络关注度时空演变及影响因素研究——以泰国为例

网络关注度是测量潜在旅游者对目的地旅游关注情况及需求变化的重要手段之一。基于百度指数,以我国31个省（区、市）（不含港、澳、台）的泰国旅游网络关注度为研究对象,运用季节性强度指数、地理集中度指数、赫芬达尔-赫希曼指数、地理探测器等方法,探讨我国居民对泰国旅游网络关注度的时空演化规律及其影响因素。结果表明：从时序演化上看,2011—2019年泰国旅游网络关注度呈波动上升态势,可划分为快速上升期和平稳发展期2个阶段,地区季节性差异显著,3月、7月、12月为泰国旅游网络关注度的高峰时段;从空间分异上看,泰国旅游网络关注度空间分异变化不大,空间集聚趋于分散状态,整体呈“东高-西低”的阶梯状递减特征,高关注度地区主要集中在东部地区及四川省,低关注度地区则主要分布于除四川省外的西部省份;从影响因素上看,经济发展水平（人均可支配收入、GDP）、交通便利程度、贸易开放度以及国际旅游开放度共同影响泰国旅游网络关注度的空间分布格局。     

人工神经网络对VOCs的自动识别

利用人工神经网络(ANN)对严重混叠的傅里叶变换红外光谱图进行了定性和定量解析。通过大量模拟数据训练神经网络后,引用了新的评价标准——逼近度来选择最优网络模型。利用此优化网络对两类光谱图进行了解析,考察了网络的泛化能力。结果表明：该网络不仅能够对两组分同时存在时的样本进行准确解析,而且对于未知单组分光谱图,也能够进行准确鉴别和定量分析。可见, 该研究为人工神经网络在单组分和多组分未知物的定性和定量分析方面提供了一种新思路。     

基于反向传播神经网络的阻抗断层图像重建新方法

电阻抗成像是通过对物体表面电压、电流的测量来重建物体内部阻抗分布或变化图像的一种新颖计算机断层成像技术。阻抗断层图像重建是一种病态的、非线性的逆问题。提出了一种全新的阻抗断层图像重建方法，它利用反向传播神经网络来表征物体内部阻抗变化位置与物体表面电压变化大小的非线性映射关系，从而可以根据对物体表面测量电压的变化先准确定位阻抗变化区域，再用线性近似方法重建阻抗变化图像，这种方法不仅具有一定的抗噪能力，而且成像精度和空间分辨率都大大好于逆投影方法。