Feature Selection Using Tree Model and Classification Through Convolutional Neural Network for Structural Damage Detection

Structural damage detection(SDD)remains highly challenging,due to the difficulty in selecting the optimal damage features from a vast amount of information.In this study,a tree model-based method using decision tree and random forest was employed for feature selection of vibration response signals in SDD.Signal datasets were obtained by numerical experiments and vibration experiments,respectively.Dataset features extracted using this method were input into a convolutional neural network to determine the location of structural damage.Results indicated a 5％to 10％improvement in detection accuracy compared to using original datasets without feature selection,demonstrating the feasibility of this method.The proposed method,based on tree model and classification,addresses the issue of extracting effective information from numerous vibration response signals in structural health monitoring.     

Tree-gel and loop-gel conversions in nonlinear polymerization

Ａｓｉｓｗｅｌｌｋｎｏｗｎ,ｔｈｅｔｈｅｏｒｙｆｏｒｎｏｎｌｉｎｅａｒｐｏｌｙｍｅｒｉｚａｔｉｏｎｓｗａｓｉｎｉｔｉａｔｅｄｂｙＦｌｏｒｙａｎｄＳｔｏｃｋｍａｙｅｒ[1—3].ＭｉｌｌｅｒａｎｄＭａｃｏｓｋｏ[4—6]ｐｒｏｐｏｓｅｄａｒｅｃｕｒｓｉｖｅｍｅｔｈｏｄｆｏｒｄｅａｌｉｎｇｗｉｔｈｔｈｅｐｒｏｂｌｅｍｏｆｔｈｅｐｏｓｔｇｅｌｐｒｏｐｅｒｔｉｅｓｏｆｔｈｅｎｅｔｗｏｒｋｆｏｒｍｉｎｇｐｏｌｙｍｅｒｉｚａｔｉｏｎ.Ｓｔｅｐｔｏ[7]ｉｎｖｅｓｔｉｇａｔｅｄｔｈｅｇｅｌｇｅｌｒｅａｃｔｉｏｎｏｆＲＡｆｔ…     

Covariate model-based fault tree analysis for risk assessment in chemical process industries: A case study of a chlorine manufacturing facility

Fault tree analysis (FTA) is a promising quantitative technique for risk analysis in chemical process industries (CPIs). In FTA, a certain sequence of basic events (causes) leads to one specific Top event (critical event of interest). However, the conventional fault tree analysis has the limitations of staticity and uncertainty. The staticity in conventional FTA arises due to its inability to accommodate time-dependent characteristics of the process system. Whereas uncertainty primarily lies in the failure probability data of basic events. This paper proposes an innovative methodology that uses a time-dependent covariate model to update the failure probability values of major contributing basic events in FTA. A novel subclass of the family of phase-type distributions is used to model the covariates corresponding to the basic events. The newly developed methodology is applied for a case study in a chlorine manufacturing facility to estimate the chlorine release probability. The blockage in the pipeline was identified as the significant reason for chlorine release from expert opinion and sensitivity analysis. The results of the proposed model of FTA are compared with that of conventional FTA.     

HPLC in the investigation of taxonomic problems. Classification of poplar genotypes

Summary The RP-HPLC technique has been applied to the analysis of the flavonoid content of leaf extracts from various genotypes ofPopulus nigra andPopulus deltoides and from several of their hybrids. Two elution procedures different either as regards gradient program or the type of organic modifier used were checked to optimize the reliability of the results obtained. Before making any identification, the chromatographic profiles proved so typical of each species as to allow of their use as fingerprints in this type of taxonomic problem. Individual identifications were carried out by spiking real samples with known amounts of standard substances. The presence of flavonoid compounds previously identified was confirmed and a few new identifications were proposed.     

Identification of triacylglycerol using automated annotation of high resolution multistage mass spectral trees

High complexity of identification for non-target triacylglycerols (TAGs) is a major challenge in lipidomics analysis. To identify non-target TAGs, a powerful tool named accurate MSⁿ spectrometry generating so-called ion trees is used. In this paper, we presented a technique for efficient structural elucidation of TAGs on MSⁿ spectral trees produced by LTQ Orbitrap MSⁿ, which was implemented as an open source software package, or TIT. The TIT software was used to support automatic annotation of non-target TAGs on MSⁿ ion trees from a self-built fragment ion database. This database includes 19108 simulate TAG molecules from a random combination of fatty acids and corresponding 500582 self-built multistage fragment ions (MS ≤ 3). Our software can identify TAGs using a “stage-by-stage elimination” strategy. By utilizing the MS¹ accurate mass and referenced RKMD, the TIT software can discriminate unique elemental composition candidates. The regiospecific isomers of fatty acyl chains will be distinguished using MS² and MS³ fragment spectra. We applied the algorithm to the selection of 45 TAG standards and demonstrated that the molecular ions could be 100% correctly assigned. Therefore, the TIT software could be applied to TAG identification in complex biological samples such as mouse plasma extracts.     

Intraday volatility and network topological properties in the Korean stock market

We examine whether the relationship between market volatility and network properties in the low-frequency level can be applied to the high-frequency level. For the analysis, we use the minimum spanning tree (MST) method constructed from intraday Korean stock market data. The results show that the higher the market volatility is, the denser the MST of stocks becomes. The normalized tree length shows a strong negative relationship with market volatility, indicating that the distances between nodes are shorter when the market volatility is high. The mean occupation layer shows the tendency of having a smaller value in a higher volatility market. The maximum number of links becomes larger when the market volatility increases. All these network properties support the network being dense and shrinking in high market volatility conditions; that is, the degree of co-movement in financial market is reinforced in the intraday high-frequency level.     

A novel kernel Fisher discriminant analysis: constructing informative kernel by decision tree ensemble for metabolomics data analysis

Large amounts of data from high-throughput metabolomics experiments become commonly more and more complex, which brings an enormous amount of challenges to existing statistical modeling. Thus there is a need to develop statistically efficient approach for mining the underlying metabolite information contained by metabolomics data under investigation. In the work, we developed a novel kernel Fisher discriminant analysis (KFDA) algorithm by constructing an informative kernel based on decision tree ensemble. The constructed kernel can effectively encode the similarities of metabolomics samples between informative metabolites/biomarkers in specific parts of the measurement space. Simultaneously, informative metabolites or potential biomarkers can be successfully discovered by variable importance ranking in the process of building kernel. Moreover, KFDA can also deal with nonlinear relationship in the metabolomics data by such a kernel to some extent. Finally, two real metabolomics datasets together with a simulated data were used to demonstrate the performance of the proposed approach through the comparison of different approaches.