基于变分自编码器的谣言立场分类算法

针对当前谣言检测任务中社交媒体推特平台的推文数据分布复杂且不均衡的特点,提出基于变分自编码器（VAE）的谣言立场分类算法VAE-LSTM。对数据进行预处理后,利用word2vec模型提取推文词向量并输入VAE中进行训练,得到符合简单概率分布的深度特征序列再从中采样获取有效特征,以避免数据量较大的推文类别影响特征向量。在此基础上,使用长短时记忆（LSTM）网络处理向量序列数据进而实现分类。理论分析和实验结果表明,VAE-LSTM算法无须手动提取或添加特征,训练过程简单高效,同时能缓解类间不平衡问题,其应用于实际场景准确率和F1得分分别为0.800和0.494,与时序注意力机制算法、Turing算法、霍克斯过程算法等相比分类性能更好,且较SVM等早期机器学习方法节省了大量数据预处理时间。     

基于多尺度分割的图像识别残差网络研究

深度卷积神经网络能够解决复杂的计算机视觉问题,被广泛应用于图像识别任务中。在基于深度卷积神经网络的图像识别过程中,增加网络的深度和宽度能够产生丰富的特征信息,使用多尺度分割方法能够有效减少冗余的特征信息。然而,增加网络的深度和进行多尺度分割都会影响识别速度。如何在保证精度的同时提高识别速度,成为设计高效网络的关键问题。通过增加网络宽度的方法对ResNet残差网络进行改进,在保证精度的基础上提升识别速度。使用ResNet-D中的残差结构并减少网络长度,得到长度只有7层的残差网络,同时对HS-ResNet中的多尺度分割方法进行优化,只保留最后一次连接合并操作,得到图像识别残差网络SSRNet。在CIFAR 10和CIFAR 100数据集上的实验结果显示,SSRNet速度最高较ResNet网络提升7倍多,同时错误率最高下降8.81%,表明缩短网络长度可大幅加快图像识别速度,同时结合多尺度分割方法能够有效提升识别精度。     

基于节点状态输出的动力学网络的自适应同步

基于微分方程不变原理,针对带有一般耦合函数的动力学网络,设计了实现网络同步的自适应同步方法.与其它的自适应同步方法相比较,该方法的优点是利用网络的一个节点的状态作为控制目标轨道来设计控制器.这一改进可以降低控制系统的维数,并且减少控制过程中各节点间的信息传递量.最后,通过一些数值算例验证所设计控制方法的有效性.     

神经元膜电位噪声取值范围的评估

大脑神经元的活动是在复杂的生理学环境下工作的，而生理学环境中的噪声来源于多个方面．如何定量地正确评估神经系统中的噪声环境是神经信息处理的基本问题．本文通过神经能量的计算给出了噪声对神经元膜电位及对应的能量波形产生显著影响的临界值的估计范围，从而定义了神经元赖以活动的生理学意义上的噪声环境．     

基于直推式学习的网络故障诊断算法

网络故障的及时诊断能够保证日常工作、学习和生活能够正常进行,传统的基于监督式学习的诊断方法依赖于大量具有鉴别意义的样本,这在实际情况中通常难以得到满足;针对上述问题,提出了一种基于直推式学习的诊断算法;针对大规模的网络管理的特征数据,该算法利用主成分分析对特征进行降维,并利用新的度量下的特征数据来构建拉普拉斯矩阵;该矩阵能够很好地描述带检测样本和训练样本之间的关系;在此基础上,设计了基于直推式学习的目标函数,并利用拉格朗日乘子法完成了优化;实验部分证明了本算法能够在有限数目的带标签的样本的前提下获得精确的分类结果,能够显著提高网络故障诊断的检测率。     

Neural Machine Translation by Fusing Key Information of Text

When the Transformer proposed by Google in 2017, it was first used for machine translation tasks and achieved the state of the art at that time. Although the current neural machine translation model can generate high quality translation results, there are still mistranslations and omissions in the translation of key information of long sentences. On the other hand, the most important part in traditional translation tasks is the translation of key information. In the translation results, as long as the key information is translated accurately and completely, even if other parts of the results are translated incorrect, the final translation results’ quality can still be guaranteed. In order to solve the problem of mistranslation and missed translation effectively, and improve the accuracy and completeness of long sentence translation in machine translation, this paper proposes a key information fused neural machine translation model based on Transformer. The model proposed in this paper extracts the keywords of the source language text separately as the input of the encoder. After the same encoding as the source language text, it is fused with the output of the source language text encoded by the encoder, then the key information is processed and input into the decoder. With incorporating keyword information from the source language sentence, the model’s performance in the task of translating long sentences is very reliable. In order to verify the effectiveness of the method of fusion of key information proposed in this paper, a series of experiments were carried out on the verification set. The experimental results show that the Bilingual Evaluation Understudy (BLEU) score of the model proposed in this paper on the Workshop on Machine Translation (WMT) 2017 test dataset is higher than the BLEU score of Transformer proposed by Google on the WMT2017 test dataset. The experimental results show the advantages of the model proposed in this paper.     

Residual Feature Attentional Fusion Network for Lightweight Chest CT Image Super-Resolution

The diagnosis of COVID-19 requires chest computed tomography (CT). High-resolution CT images can provide more diagnostic information to help doctors better diagnose the disease, so it is of clinical importance to study super-resolution (SR) algorithms applied to CT images to improve the resolution of CT images. However, most of the existing SR algorithms are studied based on natural images, which are not suitable for medical images; and most of these algorithms improve the reconstruction quality by increasing the network depth, which is not suitable for machines with limited resources. To alleviate these issues, we propose a residual feature attentional fusion network for lightweight chest CT image super-resolution (RFAFN). Specifically, we design a contextual feature extraction block (CFEB) that can extract CT image features more efficiently and accurately than ordinary residual blocks. In addition, we propose a feature-weighted cascading strategy (FWCS) based on attentional feature fusion blocks (AFFB) to utilize the high-frequency detail information extracted by CFEB as much as possible via selectively fusing adjacent level feature information. Finally, we suggest a global hierarchical feature fusion strategy (GHFFS), which can utilize the hierarchical features more effectively than dense concatenation by progressively aggregating the feature information at various levels. Numerous experiments show that our method performs better than most of the state-of-the-art (SOTA) methods on the COVID-19 chest CT dataset. In detail, the peak signal-to-noise ratio (PSNR) is 0.11 dB and 0.47 dB higher on CTtest1 and CTtest2 at SR compared to the suboptimal method, but the number of parameters and multi-adds are reduced by 22K and 0.43G, respectively. Our method can better recover chest CT image quality with fewer computational resources and effectively assist in COVID-19.     

A decision support tool for the diagnosis of breast cancer based upon Fuzzy ARTMAP

This paper presents research into the application of the fuzzy ARTMAP neural network model to the diagnosis of cancer from fine-needle aspirates of the breast. Trained fuzzy ARTMAP networks are differently pruned so as to maximise accuracy, sensitivity and specificity. The differently pruned networks are then employed in a cascade of networks intended to separate cases into certain and suspicious classes. This mimics the predictive behaviour of a human pathologist. The fuzzy ARTMAP model also provides symbolic rule extraction facilities and the validity of the derived rules for this domain is discussed. Additionally, results are provided showing the effects upon network performance of different input features and different observers. The implications of the findings are discussed.     

车辆四轮转向系统的控制方法

系统地评述了车辆四轮转向系统的原理及其控制方法的发展,在此基础上指出四轮转向系统的研究必须以闭环综合评价为出发点,并与其它主动安全技术相结合才能真正达到实用阶段。