Sentiment visualization and classification via semi-supervised nonlinear dimensionality reduction

Sentiment analysis, which detects the subjectivity or polarity of documents, is one of the fundamental tasks in text data analytics. Recently, the number of documents available online and offline is increasing dramatically, and preprocessed text data have more features. This development makes analysis more complex to be analyzed effectively. This paper proposes a novel semi-supervised Laplacian eigenmap (SS-LE). The SS-LE removes redundant features effectively by decreasing detection errors of sentiments. Moreover, it enables visualization of documents in perceptible low dimensional embedded space to provide a useful tool for text analytics. The proposed method is evaluated using multi-domain review data set in sentiment visualization and classification by comparing other dimensionality reduction methods. SS-LE provides a better similarity measure in the visualization result by separating positive and negative documents properly. Sentiment classification models trained over reduced data by SS-LE show higher accuracy. Overall, experimental results suggest that SS-LE has the potential to be used to visualize documents for the ease of analysis and to train a predictive model in sentiment analysis. SS-LE can also be applied to any other partially annotated text data sets.     

Integrated Fisher linear discriminants: An empirical study

This paper studies Fisher linear discriminants (FLDs) based on classification accuracies for imbalanced datasets. An optimal threshold is found out from a series of empirical formulas developed, which is related not only to sample sizes but also to distribution regions. A mixed binary–decimal coding system is suggested to make the very dense datasets sparse and enlarge the class margins on condition that the neighborhood relationships of samples are nearly preserved. The within-class scatter matrices being or approximately singular should be moderately reduced in dimensionality but not added with tiny perturbations. The weight vectors can be further updated by a kind of epoch-limited (three at most) iterative learning strategy provided that the current training error rates come down accordingly. Putting the above ideas together, this paper proposes a type of integrated FLDs. The extensive experimental results over real-world datasets have demonstrated that the integrated FLDs have obvious advantages over the conventional FLDs in the aspects of learning and generalization performances for the imbalanced datasets.     

Multidisciplinary design modeling and optimizationfor satellite with maneuver capability

According to the mission of a satellite with maneuver capability, the collaborative optimization (CO) method was introduced for the satellite system design, and the related multidisciplinary design optimization (MDO) model was established. The possessing and needed velocity increments Δv and Δv _{n e e d} were taken as the measurement of maneuvering capability of the studied satellite, which were then combined with total mass of the satellite to form the optimization objective in the systematic level of the MDO problem. The design variables and constraints of the MDO problem dealt with disciplines or subsystems as guidance, navigation and control (GNC), power, and structure, and corresponding engineering analysis models were also built. A program system to solve the MDO problem wasdeveloped by integrating a non-nested CO method, the commercial and user-supplied codes on framework software iSIGHT. The result showed that the satellite performance could be obviously improved, which also indicates MDO technique is feasible and effective for the spacecraft design problem. The modeling and optimization procedure of the work can be referred for further research and engineering design.     

Online stiffness estimation for robotic tasks with force observers

In this paper we propose an online stiffness estimation technique for robotic tasks based only on force data, therefore, not requiring contact position information. This allows estimations to be obtained in robotic tasks involving interactions with unstructured and unknown environments where geometrical data is unavailable or unreliable. Our technique – the Candidate Observer Based Algorithm (COBA) – uses two force observers, configured with different candidate stiffnesses, to estimate online the actual target object stiffness. COBA is embedded in a force control architecture with computed torque in the task space. The theoretical presentation of the algorithm, as well as simulation tests and experimental results with a lightweight robot arm are also presented.     

一种基于聚类加权的文本特征生成算法

目前的文本特征生成算法一般采用加权的文本向量空间模型,该模型使用TF-IDF评价函数来计算单个特征的权值,这种算法生成的文本特征冗余度往往都比较高。针对这一问题,采用了一种基于聚类加权的文本特征生成算法,首先对特征候选集进行初始加权处理;然后通过语义和信息熵对特征进行进一步加权处理;最后使用特征聚类对冗余特征进行剔除。实验表明该算法比传统的TF-IDF算法的平均分类准确率高出5%左右。     

一种利用历史数据构造虚拟标签的定位算法

在RFID定位算法中,利用接收信号强度统计模型进行直接定位的精确度不高,而利用实际参考标签定位存在信号易碰撞、外出部署不便等问题,因此提出一种基于虚拟标签的RFID定位算法VIREH以克服以上缺点.该算法利用历史数据构建虚拟参考标签,然后利用虚拟参考标签代替实际参考标签进行定位.依据VIREH算法,开发基于Android移动设备的RFID定位系统,在系统中使用VIREH算法进行定位,对定位误差进行了统计以测试算法性能.测试结果表明,VIREH算法的定位精度较直接定位有显著提高,较使用实际参考标签没有明显降低,有助于提高RFID定位精度.     

基于多项式拟合的CT图像环状伪影校正

探测器探元的响应不一致性会使CT图像中出现环状伪影,环状伪影是影响CT图像像质的重要因素,影响图像的分析及后续处理。为此提出一种基于分段多项式拟合的环状伪影校正方法,该方法适用于单材质或图像中的材质衰减系数相差不大的情况。采用分段多项式拟合正弦图累加曲线得到修正因子,用修正因子修正不一致的探元,最后重建图像。实验结果证明此方法能有效抑制图像正中间部分环状伪影。     

深度学习在主动脉中膜变性病理图像分类中的应用

胸主动脉瘤和夹层（TAAD）是严重的心血管疾病之一,而中膜变性（MD）的组织学改变对疾病的诊断及早期干预具有重要的临床意义。针对病理图像的高度复杂性使得MD的诊断过程耗时费力且一致性差的问题,提出了一种基于深度学习的病理图像分类方法,并将其应用于四种MD病变类型以进行性能验证。该方法使用了一种改进的基于GoogLeNet的卷积神经网络模型,首先采用迁移学习来将先验知识应用于TAAD病理图像的表达,然后使用Focal loss和L2正则化来解决数据不平衡问题,从而进一步优化模型性能。实验结果表明,所提模型的平均四分类准确率达到98.78%,表现出较好的泛化性能。可见所提方法可以有效地提升病理学家的诊断效率。     

基于深度残差长短记忆网络交通流量预测算法

针对多步交通流量预测任务中时间空间特征提取效果不佳和预测未来时间交通流量精度低的问题,提出一种基于长短时记忆（LSTM）网络、卷积残差网络和注意力机制的融合模型。首先,利用一种基于编解码器的架构,通过在编解码器中加入LSTM网络来挖掘不同尺度的时间域特征;其次,构建基于注意力机制挤压激励（SE）模块的卷积残差网络嵌入到LSTM网络结构中,从而挖掘交通流量数据中的空间域特征;最后,将编码器中获得的隐状态下的信息输入到解码器中,实现高精度多步交通流量的预测。基于真实交通数据进行实验测试和分析,实验结果表明,相较于原始的基于图卷积的模型,所提模型在北京和纽约两个交通流量公开数据集上的均方根误差（RMSE）分别获得了1.622和0.08的下降。所提模型能够高效且精确地对交通流量作出预测。     

The mass,fake news,and cognition security

The widespread fake news in social networks is posing threats to social stability, economic development, and political democracy, etc. Numerous studies have explored the effective detection approaches of online fake news, while few works study the intrinsic propagation and cognition mechanisms of fake news. Since the development of cognitive science paves a promising way for the prevention of fake news, we present a new research area called Cognition Security (CogSec), which studies the potential impacts of fake news on human cognition, ranging from misperception, untrusted knowledge acquisition, targeted opinion/attitude formation, to biased decision making, and investigates the effective ways for fake news debunking. CogSec is a multidisciplinary research field that leverages the knowledge from social science, psychology, cognition science, neuroscience, AI and computer science. We first propose related definitions to characterize CogSec and review the literature history. We further investigate the key research challenges and techniques of CogSec, including humancontent cognition mechanism, social influence and opinion diffusion, fake news detection, and malicious bot detection. Finally, we summarize the open issues and future research directions, such as the cognition mechanism of fake news, influence maximization of fact-checking information, early detection of fake news, fast refutation of fake news, and so on.