In this paper, we propose a prototype similarity-based approach of estimating the remaining useful life (RUL) of turbofan engine data using the singular spectrum analysis and the long-short term memory (SSA-LSTM) neural networks algorithm. The algorithm consists of two steps. First, the optimal window length of the trajectory matrix of the dataset is empirically determined from a prototype dataset. Second, the estimation of the RUL of the target datasets is performed using the window length parameter obtained from the first step. The validity of the proposed algorithm is verified by testing with 200 turbofan engine datasets. The results are shown to have a significant improvement in the performance of the RUL estimation over the existing LSTM algorithm.
The adaptive step-size (AS) code-constrained minimum output energy (CMOE) receiver for nonstationary code-division multiple access (CDMA) channels is proposed. The AS-CMOE algorithm adaptively varies the step-size in order to minimise the CMOE criterion. Admissibility of the proposed method is confirmed via the reformulation of the CMOE criterion as an unconstrained optimisation. The ability of the algorithm to track sudden changes of the channel structure in multipath fading channels is assessed. Sensitivity to the initial values ofthe step-size and the adaptation rate of the algorithm is also investigated.
BackgroundIdentification of good metaphase spreads is an important step in chromosome analysis for identifying individuals with genetic disorders. The process of finding suitable metaphase chromosomes for accurate clinical analysis is, however, very time consuming since they are selected manually. The selection of suitable metaphase chromosome spreads thus represents a major bottleneck for conventional cytogenetic analysis. Although many algorithms have been developed for karyotyping, none have adequately addressed the critical bottleneck of selecting suitable chromosome spreads. In this paper, we present a software tool that uses a simple rule-based system to efficiently identify metaphase spreads suitable for karyotyping.ResultsThe chromosome shapes can be classified by the software into four main classes. The first and the second classes refer to individual chromosomes with straight and skewed shapes, respectively. The third class is characterized as those chromosomes with overlapping bodies and the fourth class is for the non-chromosome objects. Good metaphase spreads should largely contain chromosomes of the first and the second classes, while the third class should be kept minimal. Several image parameters were examined and used for creating rule-based classification. The threshold value for each parameter is determined using a statistical model. We observed that the Gaussian model can represent the empirical probability density function of the parameters and, hence, the threshold value can be easily determined. The proposed rules can efficiently and accurately classify the individual chromosome with > 90% accuracy.ConclusionsThe software tool, termed MetaSel, was developed. Using the Gaussian-based rules, the tool can be used to quickly rank hundreds of chromosome spread images so as to assist cytogeneticists to perform karyotyping effectively. Furthermore, MetaSel offers an intuitive, yet comprehensive, workflow to assist karyotyping, including tools for editing chromosome (split, merge and fix) and a karyotyping editor (moving, rotating, and pairing homologous chromosomes). The program can be freely downloaded from "http://www4a.biotec.or.th/GI/tools/metasel".
In this paper, we propose a novel method of generating synthetic datasets by means of singular spectrum analysis (SSA) with the optimal window length for substituting the actual datasets that are needed for remaining useful life (RUL) estimation of turbofan engines. The validity of proposed method is confirmed by testing with 200 actual datasets from turbofan engine datasets and 200 synthetic datasets generated by the proposed method in comparison to those generated by three algorithms: the Fourier Decomposition Method (FDM), the Fast Fourier Transform (FFT) and the Empirical Mode Decomposition (EMD). The performance of the SSA-based synthetic datasets for RUL estimation was compared with those of the FFT, EMD and FDM algorithms by means of the regression performed by the Long Short Term Memory (LSTM) neural networks. All the results were measured in terms of the mean absolute error (MAE) and the root mean squared error (RMSE) of their RUL estimates averaged over 200 datasets. The results were also compared with those of the actual feature dataset which provided the MAE of 23.828 and RMSE of 35.284. For the synthetic datasets, the results showed the MAE of 27.126 and RMSE of 38.472 for the FFT, the MAE of 28.362 and RMSE of 39.402 for the EMD and the MAE of 30.410 and RMSE of 41.705 for the FDM. It was revealed that the synthetic datasets generated by the proposed SSA-based method performed the best with the MAE of 25.123 and RMSE of 36.825 confirming the applicability of the proposed SSA-based synthetic datasets in substitution of the actual datasets for RUL estimation.
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.