Feature selection methods for root-cause analysis among top-level product attributes

Manufacturing companies not only strive to deliver flawless products but also monitor product failures in the field to identify potential quality issues. When product failures occur, quality engineers must identify the root cause to improve any affected product and process. This root-cause analysis can be supported by feature selection methods that identify relevant product attributes, such as manufacturing dates with an increased number of product failures. In this paper, we present different methods for feature selection and evaluate their ability to identify relevant product attributes in a root-cause analysis. First, we compile a list of feature selection methods. Then, we summarize the properties of product attributes in warranty case data and discuss these properties regarding the challenges they pose for machine learning algorithms. Next, we simulate datasets of warranty cases, which emulate these product properties. Finally, we compare the feature selection methods based on these simulated datasets. In the end, the univariate filter information gain is determined to be a suitable method for a wide range of applications. The comparison based on simulated data provides a more general result than other publications, which only focus on a single use case. Due to the generic nature of the simulated datasets, the results can be applied to various root-cause analysis processes in different quality management applications and provide a guideline for readers who wish to explore machine learning methods for their analysis of quality data.     

A hybrid knowledge and ensemble classification approach for prediction of venous thromboembolism

Clinical narratives such as progress summaries, lab reports, surgical reports, and other narrative texts contain key biomarkers about a patient's health. Evidence-based preventive medicine needs accurate semantic and sentiment analysis to extract and classify medical features as the input to appropriate machine learning classifiers. However, the traditional approach of using single classifiers is limited by the need for dimensionality reduction techniques, statistical feature correlation, a faster learning rate, and the lack of consideration of the semantic relations among features. Hence, extracting semantic and sentiment-based features from clinical text and combining multiple classifiers to create an ensemble intelligent system overcomes many limitations and provides a more robust prediction outcome. The selection of an appropriate approach and its interparameter dependency becomes key for the success of the ensemble method. This paper proposes a hybrid knowledge and ensemble learning framework for prediction of venous thromboembolism (VTE) diagnosis consisting of the following components: a VTE ontology, semantic extraction and sentiment assessment of risk factor framework, and an ensemble classifier. Therefore, a component-based analysis approach was adopted for evaluation using a data set of 250 clinical narratives where knowledge and ensemble achieved the following results with and without semantic extraction and sentiment assessment of risk factor, respectively: a precision of 81.8% and 62.9%, a recall of 81.8% and 57.6%, an F measure of 81.8% and 53.8%, and a receiving operating characteristic of 80.1% and 58.5% in identifying cases of VTE.     

A new reverse reduce-error ensemble pruning algorithm

Although greedy algorithms possess high efficiency, they often receive suboptimal solutions of the ensemble pruning problem, since their exploration areas are limited in large extent. And another marked defect of almost all the currently existing ensemble pruning algorithms, including greedy ones, consists in: they simply abandon all of the classifiers which fail in the competition of ensemble selection, causing a considerable waste of useful resources and information. Inspired by these observations, an interesting greedy Reverse Reduce-Error (RRE) pruning algorithm incorporated with the operation of subtraction is proposed in this work. The RRE algorithm makes the best of the defeated candidate networks in a way that, the Worst Single Model (WSM) is chosen, and then, its votes are subtracted from the votes made by those selected components within the pruned ensemble. The reason is because, for most cases, the WSM might make mistakes in its estimation for the test samples. And, different from the classical RE, the near-optimal solution is produced based on the pruned error of all the available sequential subensembles. Besides, the backfitting step of RE algorithm is replaced with the selection step of a WSM in RRE. Moreover, the problem of ties might be solved more naturally with RRE. Finally, soft voting approach is employed in the testing to RRE algorithm. The performances of RE and RRE algorithms, and two baseline methods, i.e., the method which selects the Best Single Model (BSM) in the initial ensemble, and the method which retains all member networks of the initial ensemble (ALL), are evaluated on seven benchmark classification tasks under different initial ensemble setups. The results of the empirical investigation show the superiority of RRE over the other three ensemble pruning algorithms.     

Chemical-Shift Perturbations Reflect Bile Acid Binding to Norovirus Coat Protein: Recognition Comes in Different Flavors

Bile acids have been reported as important cofactors promoting human and murine norovirus (NoV) infections in cell culture. The underlying mechanisms are not resolved. Through the use of chemical shift perturbation (CSP) NMR experiments, we identified a low-affinity bile acid binding site of a human GII.4 NoV strain. Long-timescale MD simulations reveal the formation of a ligand-accessible binding pocket of flexible shape, allowing the formation of stable viral coat protein–bile acid complexes in agreement with experimental CSP data. CSP NMR experiments also show that this mode of bile acid binding has a minor influence on the binding of histo-blood group antigens and vice versa. STD NMR experiments probing the binding of bile acids to virus-like particles of seven different strains suggest that low-affinity bile acid binding is a common feature of human NoV and should therefore be important for understanding the role of bile acids as cofactors in NoV infection.     

Expression of Main Toll-Like Receptors in Patients with Different Types of Colorectal Polyps and Their Relationship with Gut Microbiota

Abnormal activation of Toll-like receptor (TLRs) signaling can result in colon cancer development. The aim of this study was to investigate the expression of important TLRs in different histological types of colorectal polyps and evaluate their relationship with intestinal microbiota. The expression levels of TLR2, 3, 4, and 5 were analyzed in intestinal biopsy specimens of 21 hyperplastic polyp (HP), 16 sessile serrated adenoma (SSA), 29 tubular adenoma (TA), 21 villous/tubulovillous (VP/TVP) cases, and 31 normal controls. In addition, selected gut bacteria including Streptococcus bovis, Enterococcus faecalis, Enterotoxigenic Bacteroides fragilis (ETBF), Fusobacterium nucleatum, Porphyromonas spp., Lactobacillus spp., Roseburia spp., and Bifidobacterium spp. were quantified in fecal samples using absolute qRT PCR, and, finally, the association between TLRs and these gut microbiota- was evaluated by Spearman’s correlation coefficient. Higher expression of TLR2 and TLR4 in VP/TVP and TA, and lower expression levels of TLR3 and TLR5 in all type of polyps were observed. The differences in TLR expression patterns was not only dependent on the histology, location, size, and dysplasia grade of polyps but also related to the intestinal microbiota patterns. TLR2 and TLR4 expression was directly associated with the F. nucleatum, E. faecalis, S. bovis, Porphyromonas, and inversely to Bifidobacterium, Lactobacillus, and Roseburia quantity. Furthermore, TLR3 and TLR5 expression was directly associated with Bifidobacterium, Roseburia, and Lactobacillus quantity. Our results suggest a possible critical role of TLRs during colorectal polyp progression. An abnormal regulation of TLRs in relation to gut microbial quantity may contribute to carcinogenesis.     

基于张量分解融合RGB-D图像的物体识别

为了充分利用RGB-D图像的深度图像信息，提出了基于张量分解的物体识别方法。首先将RGB-D图像构造成一个四阶张量，然后将该四阶张量分解为一个核心张量和四个因子矩阵，再利用相应的因子矩阵将原张量进行投影，获得融合后的RGB-D数据，最后输入到卷积神经网络中进行识别。RGB-D数据集中三组相似物体的识别结果表明，利用张量分解融合RGB-D图像的物体识别准确率高于未采用张量分解的物体识别准确率，并且单一错分实例的准确率最高可提升99%。     

基于微博用户兴趣话题的相似用户挖掘

相似用户挖掘是提高社交网络服务质量的重要途径，在面向大数据的社交网络时代，准确的相似用户挖掘对于用户和互联网企业等都有重要的意义，而根据用户自己的兴趣话题挖掘的相似用户更符合相似用户的要求。提出了一种基于用户兴趣话题进行相似用户挖掘的方法。该方法首先使用TextRank话题提取方法对用户进行兴趣话题提取，再对用户发表内容进行训练，计算出所有词之间的相似度。提出CP（Corresponding Position similarity）、CPW（Corresponding Position Weighted similarity）、AP（All Position similarity）、APW（All Position Weighted similarity）四种用户兴趣话题词相似度计算方法，通过用户和相似用户间关注、粉丝重合率验证相似用户挖掘效果，APW similarity的相似用户的关注/粉丝重合百分比为1.687%，优于提出的其他三种算法，分别提高了26.3%、2.8%、12.4%，并且比传统的文本相似度方法Jaccard相似度、编辑距离算法、余弦相似度分别提高了20.4%、21.2%、45.0%。因此APW方法可以更加有效地挖掘出用户的相似用户。     

基于查询的新闻多文档自动摘要技术研究

针对新闻文本领域,该文提出一种基于查询的自动文本摘要技术,更加有针对性地满足用户信息需求。根据句子的TF-IDF、与查询句的相似度等要素,计算句子权重,并根据句子指示的时间给定不同的时序权重系数,使得最近发生的新闻内容具有更高的权重,最后使用最大边界相关的方法选择摘要句。通过与基于TF-IDF、Text-Rank、LDA等六种方法的对比,该摘要方法ROUGE评测指标上优于其他方法。从结合评测结果及摘要示例可以看出,该文提出的方法可以有效地从新闻文档集中摘取核心信息,满足用户查询内容的信息需求。     

Supramolecular Zn(II)-Dipicolylamine-Azobenzene-Aminocyclodextrin-ATP Complex: Design and ATP Recognition in Water

Cyclodextrins (CyDs) are water-soluble host molecules possessing a nanosized hydrophobic cavity. In the realm of molecular recognition, this cavity is used not only as a recognition site but also as a reaction medium, where a hydrophobic sensor recognizes a guest molecule. Based on the latter concept, we have designed a novel supramolecular sensing system composed of Zn(II)-dipicolylamine metal complex-based azobenzene (1-Zn) and 3A-amino-3A-deoxy-(2AS,3AS)-γ-cyclodextrin (3-NH₂-γ-CyD) for sensing adenosine-5′-triphosphate (ATP). 1-Zn showed redshifts in the UV-Vis spectra and induced circular dichroism (ICD) only when both ATP and 3-NH₂-γ-CyD were present. Calculations of equilibrium constants indicated that the amino group of 3-NH₂-γ-CyD was involved in the formation of supramolecular 1-Zn/3-NH₂-γ-CyD/ATP. The Job plot of the ICD spectral response revealed that the stoichiometry of 1-Zn/3-NH₂-γ-CyD/ATP was 2:1:1. The pH effect was examined and 1-Zn/3-NH₂-γ-CyD/ATP was most stable in the neutral condition. The NOESY spectrum suggested the localization of 1-Zn in the 3-NH₂-γ-CyD cavity. Based on the obtained results, the metal coordination interaction of 1-Zn and the electrostatic interaction of 3-NH₂-γ-CyD were found to take place for ATP recognition. The “reaction medium approach” enabled us to develop a supramolecular sensing system that undergoes multi-point interactions in water. This study is the first step in the design of a selective sensing system based on a good understanding of supramolecular structures.