Search

Abstract The long-term use of a piezoelectric smart structure make it difficult to judge whether the structure or piezoelectric lead zirconate titanate (PZT) is damaged when the signal changes. If the sensor fault occurs, the cases and degrees of the fault are unknown based on the electromechanical impedance method. Therefore, after the principal component analysis (PCA) of six characteristic indexes, a two-component solution that could explain 99.2% of the variance in the original indexes was obtained to judge whether the damage comes from the PZT. Then LibSVM was used to make an effective identification of four sensor faults (pseudo soldering, debonding, wear, and breakage) and their three damage degrees. The result shows that the identification accuracy of damaged PZT reached 97.5%. The absolute scores of PCA comprehensive evaluation for structural damages are less than 0.5 while for sensor faults are greater than 0.6. By comparing the scores of the samples under unknown conditions with the set threshold, whether the sensor faults occur is effectively judged; the intact and 12 possible damage states of PZT can be all classified correctly with the model trained by LibSVM. It is feasible to use LibSVM to classify the cases and degrees of sensor faults.

Every performance, in an officially sanctioned meet, by a registered USA swimmer is recorded into an online database with times dating back to 1980. For the first time, statistical analysis and machine learning methods are systematically applied to 4,022,631 swim records. In this study, we investigate performance features for all strokes as a function of age and gender. The variances in performance of males and females for different ages and strokes were studied, and the correlations of performances for different ages were estimated using the Pearson correlation. Regression analysis show the performance trends for both males and females at different ages and suggest critical ages for peak training. Moreover, we assess twelve popular machine learning methods to predict or classify swimmer performance. Each method exhibited different strengths or weaknesses in different cases, indicating no one method could predict well for all strokes. To address this problem, we propose a new method by combining multiple inference methods to derive Wisdom of Crowd Classifier (WoCC). Our simulation experiments demonstrate that the WoCC is a consistent method with better overall prediction accuracy. Our study reveals several new age-dependent trends in swimming and provides an accurate method for classifying and predicting swimming times.

Every performance, in an officially sanctioned meet, by a registered USA swimmer is recorded into an online database with times dating back to 1980. For the first time, statistical analysis and machine learning methods are systematically applied to 4,022,631 swim records. In this study, we investigate performance features for all strokes as a function of age and gender. The variances in performance of males and females for different ages and strokes were studied, and the correlations of performances for different ages were estimated using the Pearson correlation. Regression analysis show the performance trends for both males and females at different ages and suggest critical ages for peak training. Moreover, we assess twelve popular machine learning methods to predict or classify swimmer performance. Each method exhibited different strengths or weaknesses in different cases, indicating no one method could predict well for all strokes. To address this problem, we propose a new method by combining multiple inference methods to derive Wisdom of Crowd Classifier (WoCC). Our simulation experiments demonstrate that the WoCC is a consistent method with better overall prediction accuracy. Our study reveals several new age-dependent trends in swimming and provides an accurate method for classifying and predicting swimming times.

Accurately predicting drug–target interactions is a critical yet challenging task in drug discovery. Traditionally, pocket detection and drug–target affinity prediction have been treated as separate aspects of drug–target interaction, with few methods combining these tasks within a unified deep learning system to accelerate drug development. In this study, we propose EMPDTA, an end-to-end framework that integrates protein pocket prediction and drug–target affinity prediction to provide a comprehensive understanding of drug–target interactions. The EMPDTA framework consists of three main modules: pocket online detection, multimodal representation learning for affinity prediction, and multi-task joint training. The performance and potential of the proposed framework have been validated across diverse benchmark datasets, achieving robust results in both tasks. Furthermore, the visualization results of the predicted pockets demonstrate accurate pocket detection, confirming the effectiveness of our framework. [ABSTRACT FROM AUTHOR]

The multiple intersecting stiffeners on the chemical milling stiffened panel (CMSP) limit the application of active health monitoring methods on it. An imaging algorithm based on electromechanical impedance (EMI) and probability-weighting is proposed to achieve quantitative evaluation and localization of the damage on CMSP. The proposed algorithm compensates for the difference in sensor performance with coefficients and there is no need to determine the key parameters of the algorithm through prior experiments. In the paper, the applicability of ultrasonic guided wave (GW) and EMI on CMSP was first studied through the finite element method. Based on EMI and the mean absolute percentage deviation (MAPD), the selected damage indicator (DI), a probability-weighted damage imaging algorithm are proposed and experimentally verified. The results indicate that due to the reflection and attenuation effects of stiffeners on GW, the signal characteristics of damage scattering waves are contaminated, making it difficult to quantitatively characterize the damage from GW signals through DIs. MAPD is positively correlated with the damage degree and has consistency in characterizing the signal of different PZTs under the same working condition. The feasibility and accuracy of the proposed algorithm are verified through experiments which show a strong engineering application capability. [ABSTRACT FROM AUTHOR]

It is challenging to obtain reliable and optimal mapping between networks for alignment algorithms when both nodal and topological structures are taken into consideration due to the underlying NP-hard problem. Here, we introduce an adaptive hybrid algorithm that combines the classical Hungarian algorithm and the Greedy algorithm (HGA) for the global alignment of biomolecular networks. With this hybrid algorithm, every pair of nodes with one in each network is first aligned based on node information (e.g., their sequence attributes) and then followed by an adaptive and convergent iteration procedure for aligning the topological connections in the networks. For four well-studied protein interaction networks, i.e., C.elegans, yeast, D.melanogaster, and human, applications of HGA lead to improved alignments in acceptable running time. The mapping between yeast and human PINs obtained by the new algorithm has the largest value of common gene ontology (GO) terms compared to those obtained by other existing algorithms, while it still has lower Mean normalized entropy (MNE) and good performances on several other measures. Overall, the adaptive HGA is effective and capable of providing good mappings between aligned networks in which the biological properties of both the nodes and the connections are important.

The emergency evacuation demonstration test of transport aircraft is an important testing link through the type certification. The test involves a large number of personnel and the items, and types of airworthiness certification check are complicated. In order to formulate a more reasonable test plan, it is necessary to carry out a systematic analysis of documents related to airworthiness requirements for emergency evacuation of transport aircraft and their advisory notices. For the whole process of the aircraft emergency evacuation demonstration test, research is carried out from four aspects: pre-preparation, on-board inspection, test and post-test, test and post-test. Defining the basic process of airworthiness certification, summarizing the airworthiness certification elements and specific verification methods are necessary to support and guarantee the completing of emergency evacuation demonstration test.

Network alignment is an important bridge to understanding human protein-protein interactions (PPIs) and functions through model organisms. However, the underlying subgraph isomorphism problem complicates and increases the time required to align protein interaction networks (PINs). Parallel computing technology is an effective solution to the challenge of aligning large-scale networks via sequential computing. In this study, the typical Hungarian-Greedy Algorithm (HGA) is used as an example for PIN alignment. The authors propose a HGA with 2-nearest neighbours (HGA-2N) and implement its graphics processing unit (GPU) acceleration. Numerical experiments demonstrate that HGA-2N can find alignments that are close to those found by HGA while dramatically reducing computing time. The GPU implementation of HGA-2N optimises the parallel pattern, computing mode and storage mode and it improves the computing time ratio between the CPU and GPU compared with HGA when large-scale networks are considered. By using HGA-2N in GPUs, conserved PPIs can be observed, and potential PPIs can be predicted. Among the predictions based on 25 common Gene Ontology terms, 42.8% can be found in the Human Protein Reference Database. Furthermore, a new method of reconstructing phylogenetic trees is introduced, which shows the same relationships among five herpes viruses that are obtained using other methods.

In the electromechanical impedance-based health monitoring of structures, partial failure of piezoelectric lead zirconate titanate will result in signal changes, which may cause misjudgment of the structure state. Therefore, this paper proposes an evaluation method of the sensor condition based on k-nearest neighbors (kNNs) and least-squares regression (LSR) to make monitoring more reliable. After the analysis of the signal characteristics of three structural changes and four sensor faults, the principal components (PCs) of three indices are extracted by principal component analysis. Next, the kNN classifier is trained with the data represented by PCs and then tested by tenfold cross-validation. To determine the degree of sensor faults, LSR is used to fit the damage degree laws with multivariate nonlinear equations. The results show that the kNN model trained with three PCs has higher classification accuracy than the one trained with two PCs. The accuracy of the former reaches 100%. The R2 values of damage degree regressions of four sensor faults are all greater than 0.85, and the p-values are far less than 0.05, which denotes the effectiveness of the regression in the prediction of damage degree. This method has great application potential in evaluating sensor conditions accurately and quickly.