基于HOG特征与SVM的胶体气泡识别方法研究

本文提出了一种基于HOG特征与支持向量机的分类方法,来代替目前人工检测光纤连接器中的胶体是否存在气泡.该方法先对视频中的胶体部分进行逐帧取样,根据样本制作正、负样本训练集以及测试集,接着选择适当的参数提取了训练集和测试集中胶体气泡HOG特征,并通过支持向量机来进行训练和测试统计的HOG特征,来识别胶体是否存在气泡.最后以人工识别为标准,并与本方法的分类结果进行验证.其实验结果表明该方法能够有效地将有、无气泡的样本进行分类,并在时间和人力上取得明显的优势.     

基于特征关系依赖网络的小样本学习方法

小样本学习任务旨在仅提供少量训练样本的情况下完成对测试样本的正确分类.基于度量学习的小样本学习方法通过将样本映射到嵌入空间中,计算样本间距离得到相似性度量以预测类别,但仅对样本特征进行独立映射,而忽略了对整个任务的观察,同时在小样本场景下通过传统方法计算的原型与期望原型存在偏差,导致在查询集上泛化性较低.针对上述问题,提出了特征关系依赖网络(FRDN).特征关系依赖网络包含两个模块:首先使用关系挖掘模块充分挖掘任务中样本的类内与类间关系,将其作为自注意力值对类簇进行调整,以获得判别性更高的任务自适应嵌入空间,计算初始原型;随后使用偏差抑制模块对初始原型进行校正,得到在查询集上泛化性更高的优化原型,进一步提高模型的分类准确率.在MiniImagenet数据集上,该方法1-shot分类准确率59.17%,5-shot准确率74.11%,分别超过传统度量学习方法6.13%与2.83%;在CUB数据集上分别提升9.3%和2.74%.     

基于用户兴趣集的在线垃圾邮件快速识别新方法

为在不显著降低垃圾邮件识别精度的同时有效提高邮件识别速度,提出了一种在线垃圾邮件快速识别新方法.首先引入用户正、负兴趣集的概念,结合用户兴趣集及支持向量机对邮件进行分类;然后根据主动学习理论,结合训练集样本密度及改进角度差异方法寻找分类最不确定的样本并推荐给用户进行类别标注;最后将标注后样本及分类最确定性样本加入训练集,并使用样本价值评价新函数淘汰冗余样本以生成新的训练集.实验表明,本文方法的用户标注负担小,垃圾邮件识别精度高、速度快,具有较高的在线应用价值.     

基于元学习的少样本红外空中目标分类方法

针对空中红外目标样本数目不足、细粒度分类精度低等问题,提出一种基于元学习的少样本红外空中目标分类的方法.该方法以元学习为基础,结合多尺度特征融合,在减少计算量的同时有效提取不同分类任务之间的共性,再利用微调策略实现对不同任务的分类.实验证明,此方法在提升mini-ImageNet数据集分类精度的同时可减少约70％的计算...     

基于网格法分集和主动学习的高光谱图像分类方法

针对高光谱图像分类过程中分类精度低和样本数量较少的问题,文中提出了一种基于网格法分集和主动学习的图像分类方法。该方法利用网格法将主成分空间划分成若干网格,在每个含有样本的网格中随机挑选一个样本,并将其原始光谱数据归入训练集;随后,采用主动学习方法,在其余样本中用K-近邻法选择不确定性最大的若干样本并入训练集,从而扩充了训练集,并使数据集具有代表性,提升了分类精度。同时,在数据处理过程中,联合运用主成分分析和线性判别分析对光谱数据进行降维,进一步提高了运算速度。实验结果表明,在Indian Pines高光谱数据集中,在少量训练集样本的情况下,该方法相较于随机分集和非主动学习,分别将总体分类精度提升了12.24%和19.76%。     

文本分类中基于K-means的类偏斜KNN样本剪裁

KNN算法是经典的文本分类算法.训练样本的数量和类别密度是影响算法性能的主要瓶颈,合理的样本剪裁可以提高分类器效率.文中提出了一种基于聚类的改进KNN分类模型.首先对训练集进行聚类,基于测试样本与簇之间的相对位置对训练集进行合理裁剪以节约计算开销;然后基于簇内样本分布进行样本赋权,改善大类别样本的密度占优现象.实验结果表明,本文提出的样本剪裁方法提高了KNN算法的分类性能.     

基于影响函数的k-近邻分类

分类是一种监督学习方法,通过在训练数据集学习模型判定未知样本的类标号。与传统的分类思想不同,该文从影响函数的角度理解分类,即从训练样本集对未知样本的影响来判定未知样本的类标号。首先介绍基于影响函数分类的思想;其次给出影响函数的定义,设计3种影响函数;最后基于这3种影响函数,提出基于影响函数的k-近邻(kNN)分类方法。并将该方法应用到非平衡数据集分类中。在18个UCI数据集上的实验结果表明,基于影响函数的k-近邻分类方法的分类性能好于传统的k-近邻分类方法,且对非平衡数据集分类有效。     

基于高维空间典型样本Steiner最小树覆盖模型的一类分类算法

最小生成树数据描述方法在刻画高维空间样本点分布时,将所有图形的边作为新增虚拟样本以提供同类样本分布描述,这种描述存在分支多覆盖模型复杂,且局部覆盖不够合理的问题。针对该问题,依据特征空间中同类样本分布的连续性规律,提出基于高维空间典型样本Steiner最小树覆盖模型的一类分类算法,该算法首先对目标类训练集进行样本修剪,去除冗余信息和噪声信息,选择最具代表性的样本作为训练集,然后对保留的典型样本构建Steiner最小树覆盖模型。算法分析和仿真实验结果表明,相比最小生成树数据描述,文中提出的方法能在较低覆盖模型复杂度的前提下更合理的描述目标类样本空间分布,构建更合理的覆盖模型,在分类正确率和适用样本规模上都表现出一定的优越性。      

基于信息融合的情感词典扩建研究

词语是文本中的情感表达的最小单位,而词语语义的情感倾向性分析是文本情感分类的基础.利用中文情感词构建出一个基础情感词典来判断未知情感词的情感极性.本文即是在HOWNET情感词语集的基础上,利用义原相似度算法,构建了中文基础情感词典,并提出以信息融合方法,将此词典与同济大学的褒贬词典进行整合,建立了特定情感词与特定情感标注以及相应的情感权值的映射关系,实验结果表明,该方法取得不错的分类效果.     

融合注意力机制与神经网络的三维点云分类算法

为了提高三维点云格式的样本分类准确率,将注意力机制与改进后的Pointnet网络相融合,对提取到的局部特征和全局特征进行加权获得对分类任务更加有效的特征,抑制相对无效的特征.该模型首先使用Pointnet网络作为基础架构对点云样本中每一个点进行全局特征的获取,使用k近邻方法为均匀采样得到的中心点选取k个相邻点,对该点到其他相邻点的关系进行建模,作为区域的局部特征.其次,使用squeeze＿excitation＿network中的SE＿block模块完成特征通道间的权重分配,为改进后的Pointnet网络加入注意力机制,使其能够提取出更加精细且更具有分辨能力的特征.最后,通过混合池化层进行聚合,混合池化由最大池化和平均池化按照不同的比例融合,文章实验部分对于比例系数的影响进行了展示.在保证与Pointnet实验环境设置相同的情况下,该模型在Modelnet40数据集上的三维物体分类结果相比Pointnet取得了4.1%的准确率的提升.实验表明,文章提出的融合注意力与神经网络结合的模型能够得到更有区分度的样本特征,从而有效的提高了三维点云物体的分类准确率.     

基于功能磁共振成像技术的情感检测研究

情绪是人对具有积极或消极意义的内或外部事件的主观感受,在人们日常生活中发挥着重要作用.情绪解码通过解码人的情绪反应带来的生理信号,达到自动辨别不同情绪状态的目的,从而解决临床上精神疾病患者与情绪相关的实际难题和实现更加自然友好的人-机交互.基于功能磁共振成像的情绪解码是一种常用且有效的方法.该文从功能磁共振影像的实验设...     

基于改进的蛙跳算法与支持向量机的实用语音情感识别

支持向量机是一种基于统计学习理论的新型机器学习算法,在高维特征空间中寻找最优分类超平面,具有很好的分类精度和泛化性能。支持向量机的训练需要求解一个带约束的二次规划问题,针对数据规模很大情况下经典训练方法变得很困难的缺点,提出一种基于改进混合蛙跳算法的支持向量机分类器参数优化方法,既提高了混合蛙跳算法的收敛速度和精度,又能借助混合蛙跳算法的全局随机搜索能力,为支持向量机参数的优化选择提供一条有效途径。本文提取情感语句的韵律特征、音质特征和混沌特征参数,提出一种基于改进蛙跳算法的数据融合方法,并利用基于改进蛙跳算法的支持向量机进行实用语音情感的识别研究。在实验中比较了PCA方法、BP神经网络和数据融合方法用于语音情感识别的识别率,研究结果表明本文所提的各项改进机制能有效提升情感识别率,为实用语音情感的识别提供一种新方法和新思路。      

Cross-dataset emotion recognition from facial expressions through convolutional neural networks

The face is the window to the soul. This is what the 19th-century French doctor Duchenne de Boulogne thought. Using electric shocks to stimulate muscular contractions and induce bizarre-looking expressions, he wanted to understand how muscles produce facial expressions and reveal the most hidden human emotions. Two centuries later, this research field remains very active. We see automatic systems for recognizing emotion and facial expression being applied in medicine, security and surveillance systems, advertising and marketing, among others. However, there are still fundamental questions that scientists are trying to answer when analyzing a person’s emotional state from their facial expressions. Is it possible to reliably infer someone’s internal state based only on their facial muscles’ movements? Is there a universal facial setting to express basic emotions such as anger, disgust, fear, happiness, sadness, and surprise? In this research, we seek to address some of these questions through convolutional neural networks. Unlike most studies in the prior art, we are particularly interested in examining whether characteristics learned from one group of people can be generalized to predict another’s emotions successfully. In this sense, we adopt a cross-dataset evaluation protocol to assess the performance of the proposed methods. Our baseline is a custom-tailored model initially used in face recognition to categorize emotion. By applying data visualization techniques, we improve our baseline model, deriving two other methods. The first method aims to direct the network’s attention to regions of the face considered important in the literature but ignored by the baseline model, using patches to hide random parts of the facial image so that the network can learn discriminative characteristics in different regions. The second method explores a loss function that generates data representations in high-dimensional spaces so that examples of the same emotion class are close and examples of different classes are distant. Finally, we investigate the complementarity between these two methods, proposing a late-fusion technique that combines their outputs through the multiplication of probabilities. We compare our results to an extensive list of works evaluated in the same adopted datasets. In all of them, when compared to works that followed an intra-dataset protocol, our methods present competitive numbers. Under a cross-dataset protocol, we achieve state-of-the-art results, outperforming even commercial off-the-shelf solutions from well-known tech companies.     

基于HMM和ANN的语音情感识别研究

语音情感识别是语音识别中的重要分支,是和谐人机交互的基础理论。由于单一分类器在语音情感识别中的局限性,本文提出了隐马尔科夫模型（HMM）和人工神经网络（ANN）相结合的方法,对高兴、惊奇、愤怒、悲伤、恐惧、平静六种情感分别设计一个HMM模型,得到每种情感的最佳匹配序列,然后利用ANN作为后验分类器对测试样本进行分类,通...     

A survey on deep learning for textual emotion analysis in social networks

Textual Emotion Analysis (TEA) aims to extract and analyze user emotional states in texts. Various Deep Learning (DL) methods have developed rapidly, and they have proven to be successful in many fields such as audio, image, and natural language processing. This trend has drawn increasing researchers away from traditional machine learning to DL for their scientific research. In this paper, we provide an overview of TEA based on DL methods. After introducing a background for emotion analysis that includes defining emotion, emotion classification methods, and application domains of emotion analysis, we summarize DL technology, and the word/sentence representation learning method. We then categorize existing TEA methods based on text structures and linguistic types: text-oriented monolingual methods, text conversations-oriented monolingual methods, text-oriented cross-linguistic methods, and emoji-oriented cross-linguistic methods. We close by discussing emotion analysis challenges and future research trends. We hope that our survey will assist readers in understanding the relationship between TEA and DL methods while also improving TEA development.     

Context-dependent emotion recognition

Most previous methods for emotion recognition focus on facial emotion and ignore the rich context information that implies important emotion states. To make full use of the contextual information to make up for the facial information, we propose the Context-Dependent Net (CD-Net) for robust context-aware human emotion recognition. Inspired by the long-range dependency of the transformer, we introduce the tubal transformer which forms the shared feature representation space to facilitate the interactions among the face, body, and context features. Besides, we introduce the hierarchical feature fusion to recombine the enhanced multi-scale face, body, and context features for emotion classification. Experimentally, we verify the effectiveness of the proposed CD-Net on the two large emotion datasets, CAER-S and EMOTIC. On the one hand, the quantitative evaluation results demonstrate the superiority of the proposed CD-Net over other state-of-the-art methods. On the other hand, the visualization results show CD-Net can capture the dependencies among the face, body, and context components and focus on the important features related to the emotion.     

情感驱动的自私MANETs节点协商机制

在移动Ad hoc网络(MANETs)中,具有不同工作环境和目标的自私节点追求最大化自身利益,因此需要一种有效的激励手段促进彼此间的协作和资源共享。情感作为影响节点认知和行为决策的重要因素,能够帮助节点在资源有限、不可预知的场景中增强适应性和自治性。该文提出一种情感驱动的自私MANETs节点协商机制(Emotion-driven Negotiation of Selfish Nodes in the MANETs,ENSNM),将情感因素定义为自私MANETs节点内在的能力和属性。协商初始阶段,成就动机的强烈程度支配节点发起或参与一次协商,同时影响初始价的设定。另外,在每轮协商开始前遵循韦伯-费希纳定律对协商最后期限进行修正。仿真实验表明ENSNM机制能够提高MANETs网络的协商效率,并减少网络流量和通信能耗。     

A Clearer Picture: The Contribution of Visuals and Text to Framing Effects

Visuals in news media help define, or frame issues, but less is known about how they influence opinions and behavior. The authors use an experiment to present image and text exemplars of frames from war and conflict news in isolation and in image–text congruent and incongruent pairs. Results show that, when presented alone, images generate stronger framing effects on opinions and behavioral intentions than text. When images and text are presented together, as in a typical news report, the frame carried by the text influences opinions regardless of the accompanying image, whereas the frame carried by the image drives behavioral intentions irrespective of the linked text. These effects are explained by the salience enhancing and emotional consequences of visuals.     

Understanding social viewing through discussion network and emotion: A focus on South Korean presidential debates

With the development of social media, television viewing is perceived no longer as an isolated activity. This study explores the underlying mechanism of the effects of social viewing discussion networks (i.e., bridging and bonding social viewing networks) on emotions (i.e., anger, fear, and enthusiasm), and moreover on opinion consolidation as well as opinion weakening in the context of the 2017 South Korean presidential debates. Overall, the main results are: a) Social viewing discussion networks influenced emotional states of social viewers, b) Emotions influenced attitude formation during social viewing, and c) Enthusiasm served as a catalyst that links bonding and bridging social viewing, and opinion consolidation. Implications and theoretical contributions are discussed.     

Are emotional objects visually salient? The Emotional Maps Database

The visual system prioritizes emotional content in natural scenes, but it is unclear whether emotional objects are systematically more salient. We compare emotional maps - created by averaging multiple manual selections of the most meaningful regions in images of negative, positive, and neutral affective valence - with saliency maps generated by Graph-Based Visual Saliency, Proto-object, and SalGAN models. We found that similarity between emotional and saliency maps is modulated by the scenes’ arousal and valence ratings: the more negative and high-arousing content, the less it was salient. Simultaneously, the negative and high-arousing content was the easiest to identify by the participants, as shown by the highest inter-individual agreement in the selections. Our results support the “affective gap” hypothesis, i.e., decoupling of emotional meaning from image’s formal features. The Emotional Maps Database created for this study, proven useful in gaze fixation prediction, is available online for scientific use.