Set Of Input Samples Research Articles

A Fuzzy Neural Network-Based Intelligent Warning Method for Financial Risk of Enterprises

The fast warning for financial risk of enterprises has always been a realistic demand for their managers. Currently, this mainly relies on expert experience to make comprehensive analysis from massive business data. Benefitting from the strong computational performance of deep learning, this paper proposes a fuzzy neural network (FNN)-based intelligent warning method for financial risk of enterprises. An improved FNN structure with time-varying coefficients and time-varying time lags is established to extract features of enterprises from complex financial context. The algorithm of fuzzy C-means and fuzzy clustering based on sample data are studied. In this paper, the fuzzy C-means algorithm is used to cluster the samples, the input sample set is preprocessed, a new set of learning samples is formed, and then the neural network is trained. The enterprise financial risk sample and its modular FNN model are established, and the evaluation of the enterprise financial risk sample is simulated. Then, a decision part is added following the FNN part to output the warning results. After that, we have also conducted a case study as simulation experiments to evaluate the proposed technical framework. The obtained results show that it can perform well in the fast warning of financial risk for enterprises.

A novel reliability updating based method for efficient estimation of failure-probability global sensitivity

Failure-probability (FP) global sensitivity (FP-GS) can measure the average effect of random input on FP, and it is significant in reliability-based design optimization. The key of FP-GS is estimating the conditional FPs on the different realizations of random inputs, which usually requires a time-demanding double-loop structure analysis. This paper originally discovers a reliability updating perspective to efficiently estimate FP-GS, in which all required conditional FPs can be approximated by the posterior FPs based on reliability updating strategy, and the double-loop structure is avoided in estimating the conditional FPs required by FP-GS. In the proposed novel reliability updating based FP-GS analysis method, all conditional FPs required by FP-GS are derived with the likelihood function on the given quasi observations, and they can be simultaneously estimated by a single random input sample set for analyzing the unconditional FP. To reduce the computational cost further, adaptive Kriging model is updated to replace the performance function for efficiently estimating the unconditional FP and all conditional FPs required by FP-GS. Several examples are presented to verify the efficiency and accuracy of the proposed novel reliability updating method for estimating the FP-GS.

A Data-Driven Kernel Principal Component Analysis–Bagging–Gaussian Mixture Regression Framework for Pulverizer Soft Sensors Using Reduced Dimensions and Ensemble Learning

In light of the nonlinearity, high dimensionality, and time-varying nature of the operational conditions of the pulverizer in power plants, as well as the challenge of the real-time monitoring of quality variables in the process, a data-driven KPCA–Bagging–GMR framework for soft sensors using reduced dimensions and ensemble learning is proposed. Firstly, the methodology employs a Kernel Principal Component Analysis to effectively reduce the dimensionality of the collected process data in a nonlinear manner. Secondly, the reduced principal components are then utilized to reconstruct a refined set of input samples, followed by the application of the Bagging algorithm to obtain multiple subsets of the samples and develop corresponding Gaussian Mixture Regression models. Ultimately, the fusion output is achieved by calculating the weights of each local model based on Bayesian posterior probabilities. By conducting simulation experiments on the coal mill, the proposed approach has been validated as demonstrating superior predictive accuracy and excellent generalization capabilities.

Learning Semantic Context from Normal Samples for Unsupervised Anomaly Detection

Unsupervised anomaly detection aims to identify data samples that have low probability density from a set of input samples, and only the normal samples are provided for model training. The inference of abnormal regions on the input image requires an understanding of the surrounding semantic context. This work presents a Semantic Context based Anomaly Detection Network, SCADN, for unsupervised anomaly detection by learning the semantic context from the normal samples. To achieve this, we first generate multi-scale striped masks to remove a part of regions from the normal samples, and then train a generative adversarial network to reconstruct the unseen regions. Note that the masks are designed in multiple scales and stripe directions, and various training examples are generated to obtain the rich semantic context . In testing, we obtain an error map by computing the difference between the reconstructed image and the input image for all samples, and infer the abnormal samples based on the error maps. Finally, we perform various experiments on three public benchmark datasets and a new dataset LaceAD collected by us, and show that our method clearly outperforms the current state-of-the-art methods.

A Monte Carlo Simulation Approach in Non-linear Structural Dynamics Using Convolutional Neural Networks

The evaluation of the structural response statistics constitutes one of the principal tasks in engineering. However, in the tail region near structural failure, engineering structures behave highly non-linear, making an analytic or closed form of the response statistics difficult or even impossible. Evaluating a series of computer experiments, the Monte Carlo method has been proven a useful tool to provide an unbiased estimate of the response statistics. Naturally, we want structural failure to happen very rarely. Unfortunately, this leads to a disproportionately high number of Monte Carlo samples to be evaluated to ensure an estimation with high confidence for small probabilities. Thus, in this paper, we present a new Monte Carlo simulation method enhanced by a convolutional neural network. The sample-set used for this Monte Carlo approach is provided by artificially generating site-dependent ground motion time histories using a non-linear Kanai-Tajimi filter. Compared to several state-of-the-art studies, the convolutional neural network learns to extract the relevant input features and the structural response behavior autonomously from the entire time histories instead of learning from a set of hand-chosen intensity inputs. Training the neural network based on a chosen input sample set develops a meta-model that is then used as a meta-model to predict the response of the total Monte Carlo sample set. This paper presents two convolutional neural network-enhanced strategies that allow for a practical design approach of ground motion excited structures. The first strategy enables for an accurate response prediction around the mean of the distribution. It is, therefore, useful regarding structural serviceability. The second strategy enables for an accurate prediction around the tail end of the distribution. It is, therefore, beneficial for the prediction of the probability of failure.

Research on reducing fuzzy test sample set based on heuristic genetic algorithm

Fuzzy testing is the most effective method for vulnerability mining, which can deal with complex programmes better than other vulnerability mining techniques and has strong scalability. However, in the large-scale vulnerability analysis test, the fuzzy test input sample set faces the challenges of low quality, high repeatability and low availability etc. Therefore, this paper studies the input sample set and proposes heuristic genetic algorithm. By using 0–1 matrix, the genetic algorithm is improved with a consideration of practical problems and the execution path for sample set is selected and compressed through approximation algorithm, thus obtaining a smallest sample set and accelerating the efficiency of fuzzy test. Experimental results show that the proposed method is effective.

EdgeScaping: Mapping the spatial distribution of pairwise gene expression intensities.

Gene co-expression networks (GCNs) are constructed from Gene Expression Matrices (GEMs) in a bottom up approach where all gene pairs are tested for correlation within the context of the input sample set. This approach is computationally intensive for many current GEMs and may not be scalable to millions of samples. Further, traditional GCNs do not detect non-linear relationships missed by correlation tests and do not place genetic relationships in a gene expression intensity context. In this report, we propose EdgeScaping, which constructs and analyzes the pairwise gene intensity network in a holistic, top down approach where no edges are filtered. EdgeScaping uses a novel technique to convert traditional pairwise gene expression data to an image based format. This conversion not only performs feature compression, making our algorithm highly scalable, but it also allows for exploring non-linear relationships between genes by leveraging deep learning image analysis algorithms. Using the learned embedded feature space we implement a fast, efficient algorithm to cluster the entire space of gene expression relationships while retaining gene expression intensity. Since EdgeScaping does not eliminate conventionally noisy edges, it extends the identification of co-expression relationships beyond classically correlated edges to facilitate the discovery of novel or unusual expression patterns within the network. We applied EdgeScaping to a human tumor GEM to identify sets of genes that exhibit conventional and non-conventional interdependent non-linear behavior associated with brain specific tumor sub-types that would be eliminated in conventional bottom-up construction of GCNs. Edgescaping source code is available at https://github.com/bhusain/EdgeScaping under the MIT license.

Online Evaluation Method for Low Frequency Oscillation Stability in a Power System Based on Improved XGboost

Low frequency oscillation in an interconnected power system is becoming an increasingly serious problem. It is of great practical significance to make online evaluation of actual power grid’s stability. To evaluate the stability of the power system quickly and accurately, a low frequency oscillation stability evaluation method based on an improved XGboost algorithm and power system random response data is proposed in this paper. Firstly, the original input feature set describing the dynamic characteristics of the power system is established by analyzing the substance of low frequency oscillation. Taking the random response data of power system including the disturbance end time feature and the dynamic feature of power system as the input sample set, the wavelet threshold is applied to improve its effectiveness. Secondly, using the eigenvalue analysis method, different damping ratios are selected as threshold values to judge the stability of the system low-frequency oscillation. Then, the supervised training with improved XGboost algorithm is performed on the characteristics of stability. On this basis, the training model is obtained and applied to online low frequency oscillation stability evaluation of a power system. Finally, the simulation results of the eight-machine 36-node test system and Hebei southern power grid show that the proposed low frequency oscillation online evaluation method has the features of high evaluation accuracy, fast evaluation speed, low error rate of unstable sample evaluation, and strong anti-noise ability.

Estimated confidence interval from single blood pressure measurement based on algorithmic fusion

Background: Current oscillometric blood pressure measurement devices generally provide only single-point estimates for systolic and diastolic blood pressures and rarely provide confidence ranges for these estimates. A novel methodology to obtain confidence intervals (CIs) for systolic blood pressure (SBP) and diastolic blood pressure (DBP) estimates from a single oscillometric blood pressure measurement is presented.Methods: The proposed methodology utilizes the multiple regression technique to fuse optimally a set of SBP and DBP estimates obtained through different algorithms. However, the set of SBP and DBP estimates is a small number to determine the CI of each individual subject. To address this issue, the weighted bootstrap approach based on the multiple regression technique was used to generate a pseudo sample set for the SBP and the DBP. In this paper, the multiple regression technique can estimate the best-fitting surface of an efficient function that relates the input sample set as an independent vector to the auscultatory nurse measurement as a dependent vector to estimate regression coefficients. Consequently, the coefficients are assigned to an eight-sample set obtained from the fusion of different algorithms as optimally weighted parameters. CIs are also estimated using the conventional methods on the set of fused SBP and DBP estimates for comparison purposes.Results: The proposed method was applied to an experimental dataset of 85 patients. The results indicated that the proposed approach provides better blood pressure estimates than the existing algorithms and, in addition, is able to provide CIs for a single measurement.Conclusions: The CIs derived from the proposed scheme are much smaller than those calculated by conventional methods except for the pseudo maximum amplitude-envelope algorithm for both the SBP and the DBP, probably because of the decrease in the standard deviation through the increase in the pseudo measurements using the weighted bootstrap method for each subject. The proposed methodology is likely the only one currently available that can provide CIs for single-sample blood pressure measurements.

Massive-Scale Gene Co-Expression Network Construction and Robustness Testing Using Random Matrix Theory

The study of gene relationships and their effect on biological function and phenotype is a focal point in systems biology. Gene co-expression networks built using microarray expression profiles are one technique for discovering and interpreting gene relationships. A knowledge-independent thresholding technique, such as Random Matrix Theory (RMT), is useful for identifying meaningful relationships. Highly connected genes in the thresholded network are then grouped into modules that provide insight into their collective functionality. While it has been shown that co-expression networks are biologically relevant, it has not been determined to what extent any given network is functionally robust given perturbations in the input sample set. For such a test, hundreds of networks are needed and hence a tool to rapidly construct these networks. To examine functional robustness of networks with varying input, we enhanced an existing RMT implementation for improved scalability and tested functional robustness of human (Homo sapiens), rice (Oryza sativa) and budding yeast (Saccharomyces cerevisiae). We demonstrate dramatic decrease in network construction time and computational requirements and show that despite some variation in global properties between networks, functional similarity remains high. Moreover, the biological function captured by co-expression networks thresholded by RMT is highly robust.

Multiway kernel independent component analysis based on feature samples for batch process monitoring

Most batch processes generally exhibit the characteristics of nonlinear variation. In this paper, a nonlinear monitoring technique is proposed using a multiway kernel independent component analysis based on feature samples (FS-MKICA). This approach first unfolds the three-way dataset of a batch process into the two-way one and then chooses representative feature samples from the large two-way input training dataset. The nonlinear feature space abstracted from the unfolded two-way data space is then transformed into a high-dimensional linear space via kernel function and an independent component analysis (ICA) model is established in the mapped linear space. The proposed FS-MKICA method can significantly reduce the computational cost in extracting the kernel ICA model since it is based on the small subset of feature samples rather than on the entire input sample set. We supply two statistics, the I 2 statistic of process variation and the squared prediction error statistic of residual, for on-line monitoring of batch processes. The proposed method is applied to detecting faults in the fed-batch penicillin fermentation process. The standard linear ICA method for batch process monitoring, known as the multiway independent component analysis (MICA), is also applied to the same benchmark batch process. The simulation results obtained in this nonlinear batch process application clearly demonstrate the power and superiority of the new nonlinear monitoring method over the linear one. The FS-MKICA approach can extract the nonlinear features of the batch process while the MICA method cannot.

Construction of a Neurofuzzy Network Capable of Extrapolating (and Interpolating) With Respect to the Convex Hull of a Set of Input Samples in ${{\bb R}}^n$

The problem of regression estimation is considered with a specific regard for the distinction between interpolation and extrapolation. A neurofuzzy network named NFECH is proposed that is capable of extrapolating (and interpolating) with respect to the convex hull of a finite set of input samples X sub Ropfn. The geometrical construction of the proposed network is explained both mathematically and graphically. The illustrations explain how the particular parts of the construction work, and also show the final surfaces of the obtained models. The method is tested on artificial datasets generated from mathematical functions according to various statistical distributions. Also, comparisons to the commonly used radial basis function (RBF), multilayered perceptron (MLP) neural networks, and to fuzzy rule interpretation (FRI)/fuzzy rule extrapolation (FRE) approach are presented.

How to make large self-organizing maps for nonvectorial data

The self-organizing map (SOM) represents an open set of input samples by a topologically organized, finite set of models. In this paper, a new version of the SOM is used for the clustering, organization, and visualization of a large database of symbol sequences (viz. protein sequences). This method combines two principles: the batch computing version of the SOM, and computation of the generalized median of symbol strings.

Performance Improvement of DPLL's in Non-Gaussian Noise Using Robust Estimators

This paper deals with the analysis of DPLL's operating in the presence of non-Gaussian noise. The loop model developed here allows for multiple input samples each loop sampling period, complex processing of the input sample set, and various noise distributions. In particular, six different robust estimators are used as processors of the input: these are the trimmed mean estimator, a one-step Huber M -type estimator, a new M -type estimator, and three versions of a zero-memory nonlinear (ZNL) estimator: hole punch, limiter, and sign detector. The tracking performance of a second-order DPLL is simulated and analyzed for five different types of noise: Gaussian, contaminated Gaussian, Laplace, Middleton Class A , and generalized exponential. Comparisons are made for signal-to-noise ratios ranging from 0 to - 10 dB. It is found that the ZNL estimators provide performance superior to that of the other robust estimators, especially for noise densities that are heavy tailed.

Microwave Hyperthermic Distributions in a Layered Living Body with Nonlinear Thermoregulatory Properties (Short Papers)

In this paper, the microwave heating of biological systems with nonlinear thermoregulatory properties is considered. Temperature distributions are calculated in a layered biological model exposed to uniform plane waves. The external surfaces of such a model are cooled and its thermoregulatory properties are assumed to be nonlinear functions of the local temperature. The calculation of the space-time evolution of the temperature is performed using a numerical program that has been developed by applying the finite-difference method. In this numerical program, the nonlinear thermoregulatory functions are given either by a segment-linearization process or by an arbitrary analytical form or by a transformation of an input sample set. The mean power density of the incident electromagnetic wave and the coolant temperature are also taken time-dependent.

A “Logical Pattern” Recognition Program

A description is given of an IBM 7090 program which searches for “logical patterns” in a set of input samples. The program was tested on a character recognition problem, where it designed a recognition system whose error rate and hardware requirements are compared to those of a system designed by humans. This program is intended to be used as a research tool to discover certain kinds of patterns in data and as a step in the direction of automatic logic design for some character recognition problems.