While piezoelectric impedance/admittance measurements have been used for fault detection and identification, the actual identification of fault location and severity remains to be a challenging topic. On one hand, the approach that uses these measurements entertains high detection sensitivity owing to the high-frequency actuation/sensing nature. On the other hand, high-frequency analysis requires high dimensionality in the model and the subsequent inverse analysis contains a very large number of unknowns which often renders the identification problem under-determined. A new fault identification algorithm is developed in this research for piezoelectric impedance/admittance based measurement. Taking advantage of the algebraic relation between the sensitivity matrix and the admittance change measurement, we devise a pre-screening scheme that can rank the likelihoods of fault locations with estimated fault severity levels, which drastically reduces the fault parameter space. A Bayesian inference approach is then incorporated to pinpoint the fault location and severity with high computational efficiency. The proposed approach is examined and validated through case studies.
A theoretical study was carried out to determine the dielectric response and tunability of a composite consisting of a linear, low-loss dielectric matrix with uniformly sized, randomly distributed paraelectric Ba 0.60 Sr 0.40 TiO 3 ͑BST 60/40͒ particles as functions of the volume fraction and size of the particles. The field dependence of the polarization and the dielectric response of the inclusions are specified through a nonlinear thermodynamic model and then incorporated into a two-dimensional finite element analysis. Near the percolation threshold for BST particles ͑ϳ27% to 45% depending on the particle size͒, high dielectric tunabilities with a lower effective permittivity than monolithic BST can be realized.
Molecularly imprinted polymers (MIPs), often called "synthetic antibodies", are highly attractive as artificial receptors with tailored biomolecular recognition to construct biosensors. Electropolymerization is a fast and facile method to directly synthesize MIP sensing elements in situ on the working electrode, enabling ultra-low-cost and easy-to-manufacture electrochemical biosensors. However, due to the high dimensional design space of electropolymerized MIPs (e-MIPs), the development of e-MIPs is challenging and lengthy based on trial and error without proper guidelines. Leveraging machine learning techniques in building the quantitative relationship between synthesis parameters and corresponding sensing performance, e-MIPs' development and optimization can be facilitated. We herein demonstrate a case study on the synthesis of cortisol-imprinted polypyrrole for cortisol detection, where e-MIPs are fabricated with 72 sets of synthesis parameters with replicates. Their sensing performances are measured using a 12-channel potentiostat to construct the subsequent data-driven framework. The Gaussian process (GP) is employed as the mainstay of the integrated framework, which can account for various uncertainties in the synthesis and measurements. The Sobol index-based global sensitivity is then performed upon the GP surrogate model to elucidate the impact of e-MIPs' synthesis parameters on sensing performance and interrelations among parameters. Based on the prediction of the established GP model and local sensitivity analysis, synthesis parameters are optimized and validated by experiment, which leads to remarkable sensing performance enhancement (1.5-fold increase in sensitivity). The proposed framework is novel in biosensor development, which is expandable and also generally applicable to the development of other sensing materials.
Recent years, many scientists address the research on text sentiment analysis of social media due to the exponential growth of social multimedia content. Natural language ambiguities and indirect sentiments within the social media text have made it hard to classify by using traditional machine learning approaches, such as support vector machines, naive Bayes, hybrid models and so on. This article aims to investigate the sentiment analysis of social media Chinese text by combining Bidirectional Long-Short Term Memory (BiLSTM) networks with a Multi-head Attention (MHAT) mechanism in order to overcome the deficiency of Sentiment Analysis that is performed with traditional machine learning. BiLSTM networks, not only solve the long-term dependency problem, but they also capture the actual context of the text. Due to the fact that the MHAT mechanism can learn the relevant information from a different representation subspace by using multiple distributed calculations, the purpose is to add influence weights to the constructed text sequence. The results of the numerical experiments show that the proposed model achieves better performance than the existing well-established methods.INDEX TERMS Chinese product reviews text, bidirectional LSTM, multi-head attention mechanism.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.