Detection and Classification of ECG Chaotic Components Using ANN Trained by Specially Simulated Data

2012 ◽  
pp. 193-202 ◽  
Author(s):  
Polina Kurtser ◽  
Ofer Levi ◽  
Vladimir Gontar
Keyword(s):  
Simulated Data

scholarly journals Supervised linear classification of Gaussian spatio-temporal data

2021 ◽  
Vol 62 ◽  
pp. 9-15
Author(s):  
Marta Karaliutė ◽  
Kęstutis Dučinskas
Keyword(s):  
Time Moment ◽  
Gaussian Random Field ◽  
Covariance Structure ◽  
Simulated Data ◽  
Spatial Location ◽  
Error Rates ◽  
Prior Probabilities ◽  
Structure Factors ◽  
Spatio Temporal

In this article we focus on the problem of supervised classifying of the spatio-temporal Gaussian random field observation into one of two classes, specified by different mean parameters. The main distinctive feature of the proposed approach is allowing the class label to depend on spatial location as well as on time moment. It is assumed that the spatio-temporal covariance structure factors into a purely spatial component and a purely temporal component following AR(p) model. In numerical illustrations with simulated data, the influence of the values of spatial and temporal covariance parameters to the derived error rates for several prior probabilities models are studied.

scholarly journals Sequence Classification Using Third-Order Moments

2018 ◽  
Vol 30 (1) ◽  
pp. 216-236
Author(s):  
Rasmus Troelsgaard ◽  
Lars Kai Hansen
Keyword(s):  
Hidden Markov Models ◽  
Markov Models ◽  
Sequence Data ◽  
Hidden Markov ◽  
Score Function ◽  
Simulated Data ◽  
Discrete Observations ◽  
Third Order ◽  
Leibler Divergence

Model-based classification of sequence data using a set of hidden Markov models is a well-known technique. The involved score function, which is often based on the class-conditional likelihood, can, however, be computationally demanding, especially for long data sequences. Inspired by recent theoretical advances in spectral learning of hidden Markov models, we propose a score function based on third-order moments. In particular, we propose to use the Kullback-Leibler divergence between theoretical and empirical third-order moments for classification of sequence data with discrete observations. The proposed method provides lower computational complexity at classification time than the usual likelihood-based methods. In order to demonstrate the properties of the proposed method, we perform classification of both simulated data and empirical data from a human activity recognition study.

scholarly journals Fault Classification and Fault Zone Identification in a Thyristor Controlled Series Compensator Based Transmission Line by using Decision Tree

2020 ◽  
Vol 9 (3) ◽  
pp. 1502-1506
Keyword(s):  
Decision Tree ◽  
Simulated Data ◽  
Fault Classification ◽  
Network Systems ◽  
Thyristor Controlled Series Capacitor ◽  
Decision Tree Method ◽  
Thyristor Controlled Series Compensator ◽  
Types Of Faults ◽  
Tree Method

A new method has been introduced for classification of fault and to identify zone of fault in Thyristor Controlled Series Capacitor based line by utilizing Decision Tree method. PSACD/EMTDC software is used in this paper for the simulation of TCSC. Voltage and current samples after fault are used in this method as input against predicted output vectors for zone identification of fault. Decision Tree based classification algorithm also used to classify all ten types of faults in the TCSC based line. This method is being tested on simulated data and the results indicate that this method can classify different types of faults and also identify zone of fault more accurately than any neural network systems in a TCSC based line.

scholarly journals Rapid classification of TESS planet candidates with convolutional neural networks

2020 ◽  
Vol 633 ◽  
pp. A53 ◽  
Author(s):  
H. P. Osborn ◽  
M. Ansdell ◽  
Y. Ioannou ◽  
M. Sasdelli ◽  
D. Angerhausen ◽  
...  
Keyword(s):  
Simulated Data ◽  
Real Data ◽  
Eclipsing Binaries ◽  
Average Precision ◽  
Class Model ◽  
Data Rates ◽  
Threshold Crossing ◽  
Deep Learning Model

Aims. Accurately and rapidly classifying exoplanet candidates from transit surveys is a goal of growing importance as the data rates from space-based survey missions increase. This is especially true for the NASA TESS mission which generates thousands of new candidates each month. Here we created the first deep-learning model capable of classifying TESS planet candidates. Methods. We adapted an existing neural network model and then trained and tested this updated model on four sectors of high-fidelity, pixel-level TESS simulations data created using the Lilith simulator and processed using the full TESS pipeline. With the caveat that direct transfer of the model to real data will not perform as accurately, we also applied this model to four sectors of TESS candidates. Results. We find our model performs very well on our simulated data, with 97% average precision and 92% accuracy on planets in the two-class model. This accuracy is also boosted by another ~4% if planets found at the wrong periods are included. We also performed three-class and four-class classification of planets, blended and target eclipsing binaries, and non-astrophysical false positives, which have slightly lower average precision and planet accuracies but are useful for follow-up decisions. When applied to real TESS data, 61% of threshold crossing events (TCEs) coincident with currently published TESS objects of interest are recovered as planets, 4% more are suggested to be eclipsing binaries, and we propose a further 200 TCEs as planet candidates.

Complex Similarity and Fluctuation Dynamics of Financial Markets on Voter Interacting Dynamic System

2018 ◽  
Vol 28 (13) ◽  
pp. 1850156 ◽  
Author(s):  
Rui Li ◽  
Jun Wang ◽  
Guochao Wang
Keyword(s):  
Financial Markets ◽  
Cross Correlation ◽  
Simulated Data ◽  
Intrinsic Mode Functions ◽  
Dynamical Behaviors ◽  
Mode Decomposition ◽  
Proposed Model ◽  
Fluctuation Dynamics ◽  
Random Property

A financial price dynamics is developed based on the voter interacting system, in an attempt to investigate and reproduce the complex similarity and the fluctuation dynamics of financial markets. The complexity-invariance distance (CID) is applied to study the similarity of each stock pairs. A simple classification of seven real indexes and the simulated data is obtained according to the CID values for each stock pairs. The corresponding multiscale dynamical behaviors of CID values are also studied by combining CID with the multiscale method. Further, the similarity of the newest data and the historical data of the returns is investigated by a novel auto-CID analysis, and a corresponding exponent relationship is exhibited. Moveover, the cross correlation function (CCF) is applied to study the correlation of each stock pairs and the causalities of these stock pairs are investigated by the Granger causality method. Besides, the complexity and the randomness of fluctuations of returns, surrogate returns, shuffled returns and intrinsic mode functions (derived from empirical mode decomposition) are also explored at different thresholds with Lempel–Ziv complexity. The empirical study shows complex similarity and similar random property between the proposed price model and the real stock markets, which exhibits that the proposed model is feasible to some extent.

scholarly journals Unsupervised Spike Detection and Sorting with Wavelets and Superparamagnetic Clustering

2004 ◽  
Vol 16 (8) ◽  
pp. 1661-1687 ◽  
Author(s):  
R. Quian Quiroga ◽  
Z. Nadasdy ◽  
Y. Ben-Shaul
Keyword(s):  
Simulated Data ◽  
New Method ◽  
Data Sets ◽  
Improved Method ◽  
Spike Detection ◽  
Gaussian Distributions ◽  
Conventional Methods ◽  
Simulated Data Sets

This study introduces a new method for detecting and sorting spikes from multiunit recordings. The method combines the wave let transform, which localizes distinctive spike features, with super paramagnetic clustering, which allows automatic classification of the data without assumptions such as low variance or gaussian distributions. Moreover, an improved method for setting amplitude thresholds for spike detection is proposed. We describe several criteria for implementation that render the algorithm unsupervised and fast. The algorithm is compared to other conventional methods using several simulated data sets whose characteristics closely resemble those of in vivo recordings. For these data sets, we found that the proposed algorithm outperformed conventional methods.

scholarly journals A Robust Procedure for Machine Learning Algorithms Using Gene Expression Data

2021 ◽  
Vol 12 (2) ◽  
pp. 2422-2439
Keyword(s):  
Gene Expression ◽  
Machine Learning ◽  
Gene Expression Data ◽  
Learning Algorithms ◽  
Simulated Data ◽  
Cancer Classification ◽  
Machine Learning Algorithms ◽  
Expression Data ◽  
Traditional Procedure

Cancer classification is one of the main objectives for analyzing big biological datasets. Machine learning algorithms (MLAs) have been extensively used to accomplish this task. Several popular MLAs are available in the literature to classify new samples into normal or cancer populations. Nevertheless, most of them often yield lower accuracies in the presence of outliers, which leads to incorrect classification of samples. Hence, in this study, we present a robust approach for the efficient and precise classification of samples using noisy GEDs. We examine the performance of the proposed procedure in a comparison of the five popular traditional MLAs (SVM, LDA, KNN, Naïve Bayes, Random forest) using both simulated and real gene expression data analysis. We also considered several rates of outliers (10%, 20%, and 50%). The results obtained from simulated data confirm that the traditional MLAs produce better results through our proposed procedure in the presence of outliers using the proposed modified datasets. The further transcriptome analysis found the significant involvement of these extra features in cancer diseases. The results indicated the performance improvement of the traditional MLAs with our proposed procedure. Hence, we propose to apply the proposed procedure instead of the traditional procedure for cancer classification.

scholarly journals Cancellation of Towing Ship Interference in Passive SONAR in a Shallow Ocean Environment

2022 ◽  
Vol 72 (1) ◽  
pp. 122-132
Author(s):  
Remadevi M. ◽  
N. Sureshkumar ◽  
R. Rajesh ◽  
T. Santhanakrishnan
Keyword(s):  
Long Range ◽  
Simulated Data ◽  
Interference Signal ◽  
Spectral Leakage ◽  
Low Snr ◽  
Eigenvector Analysis ◽  
Spatio Temporal ◽  
Ocean Environment ◽  
Space Time Adaptive Processing

Towed array sonars are preferred for detecting stealthy underwater targets that emit faint acoustic signals in the ocean, especially in shallow waters. However, the towing ship being near to the array behaves as a loud target, introducing additional interfering signals to the array, severely affecting the detection and classification of potential targets. Canceling this underlying interference signal is a challenging task and is investigated in this paper for a shallow ocean operational scenario where the problem is more critical due to the multipath phenomenon. A method exploiting the eigenvector analysis of spatio-temporal covariance matrix based on space time adaptive processing is proposed for suppressing tow ship interference and thus improving target detection. The developed algorithm learns the interference patterns in the presence of target signals to mitigate the interference across azimuth and to remove the spectral leakage of own-ship. The algorithm is statistically analyzed through a set of relevant metrics and is tested on simulated data that are equivalent to the data received by a towed linear array of acoustic sensors in a shallow ocean. The results indicate a reduction of 20-25dB in the tow ship interference power while the detection of long-range low SNR targets remain largely unaffected with minimal power-loss. In addition, it is demonstrated that the spectral leakage of tow ship, on multiple beams across the azimuth, due to multipath, is also alleviated leading to superior classification capabilities. The robustness of the proposed algorithm is validated by the open ocean experiment in the coastal shallow region of the Arabian Sea at Off-Kochi area of India, which produced results in close agreement with the simulations. A comparison of the simulation and experimental results with the existing PCI and ECA methods is also carried out, suggesting the proposed method is quite effective in suppressing the tow ship interference and is immensely beneficial for the detection and classification of long-range targets.

Sign in / Sign up

Export Citation Format

Share Document