An Algorithm for Classification and Outlier Detection of Time-Series Data

Weekley, R. Andrew; Goodrich, Robert K.; Cornman, Larry

doi:10.1175/2009jtecha1299.1

Cited by 23 publications

(7 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Transient heterogeneity, along with a changing baseline, made automatic peak identification challenging. To identify peaks, we adapted an algorithm based on clustering points in delay space (29) to call peaks in the PROPS channel (SI Appendix, Fig. S9 and SI Methods).…”

Section: Resultsmentioning

confidence: 99%

Voltage-gated calcium flux mediates Escherichia coli mechanosensation

Bruni

Weekley

Dodd

et al. 2017

Proc. Natl. Acad. Sci. U.S.A.

Self Cite

131

116

View full text Add to dashboard Cite

Electrically excitable cells harness voltage-coupled calcium influx to transmit intracellular signals, typically studied in neurons and cardiomyocytes. Despite intense study in higher organisms, investigations of voltage and calcium signaling in bacteria have lagged due to their small size and a lack of sensitive tools. Only recently were bacteria shown to modulate their membrane potential on the timescale of seconds, and little is known about the downstream effects from this modulation. In this paper, we report on the effects of electrophysiology in individual bacteria. A genetically encoded calcium sensor expressed in Escherichia coli revealed calcium transients in single cells. A fusion sensor that simultaneously reports voltage and calcium indicated that calcium influx is induced by voltage depolarizations, similar to metazoan action potentials. Cytoplasmic calcium levels and transients increased upon mechanical stimulation with a hydrogel, and single cells altered protein concentrations dependent on the mechanical environment. Blocking voltage and calcium flux altered mechanically induced changes in protein concentration, while inducing calcium flux reproduced these changes. Thus, voltage and calcium relay a bacterial sense of touch and alter cellular lifestyle. Although the calcium effectors remain unknown, these data open a host of new questions about E. coli, including the identity of the underlying molecular players, as well as other signals conveyed by voltage and calcium. These data also provide evidence that dynamic voltage and calcium exists as a signaling modality in the oldest domain of life, and therefore studying electrophysiology beyond canonical electrically excitable cells could yield exciting new findings.alcium is a universal and indispensable signaling ion used in all known eukaryotes (1). Calcium concentration gradients across the plasma membrane and intracellular organelles enable highly dynamic fluxes via orchestrated channel openings to generate tightly controlled spatial and temporal patterns. The dynamics in both space and time are encoded and decoded into varying and sometimes opposing cellular signals (2, 3). In electrically excitable cells, including neurons and muscle cells, voltage-gated calcium channels (VGCCs) couple membrane depolarization to calcium influx, which can then alter cellular physiology. The myriad uses of calcium by cells highlight its crucial role in cellular maintenance.Despite calcium's ubiquity and utility across biological domains, little is known about how calcium is regulated in bacteria, especially at the single cell level (4). Fluorescent calcium dyes used in eukaryotic cells are not able to pass through the cell wall without pretreatment with the chelating agent EDTA, prohibiting studies of calcium with high temporal and spatial resolution in bacteria. Isotope labeling and luminescent probes have contributed population-level measurements of calcium, but were unable to resolve any potential cellular heterogeneity. In population measurements, cytoplasmic ...

show abstract

Section: Resultsmentioning

confidence: 99%

Voltage-gated calcium flux mediates Escherichia coli mechanosensation

Bruni

Weekley

Dodd

et al. 2017

Proc. Natl. Acad. Sci. U.S.A.

Self Cite

131

116

View full text Add to dashboard Cite

show abstract

“…The advantage of neural networks are that they can differentiate between anomalies from different classes. Weekley et al also applied clustering techniques to a reconstructed phase space to detect anomalies [16] . To make valid and efficient inferences about the data, anomalous data needs to be imputed after their detection.…”

Section: Section II Previous Workmentioning

confidence: 99%

Data Improving in Time Series Using ARX and ANN Models

Akouemo

Povinelli

2017

IEEE Trans. Power Syst.

View full text Add to dashboard Cite

Abstract:Anomalous data can negatively impact energy forecasting by causing model parameters to be incorrectly estimated. This paper presents two approaches for the detection and imputation of anomalies in time series data. Autoregressive with exogenous inputs (ARX) and artificial neural network (ANN) models are used to extract the characteristics of time series. Anomalies are detected by performing hypothesis testing on the extrema of the residuals, and the anomalous data points are imputed using the ARX and ANN models. Because the anomalies affect the model coefficients, the data cleaning process is performed iteratively. The models are re-learned on "cleaner" data after an anomaly is imputed. The anomalous data are reimputed to each iteration using the updated ARX and ANN models. The ARX and ANN data cleaning models are evaluated on natural gas time series data. This paper demonstrates that the proposed approaches are able to identify and impute anomalous data points. Forecasting models learned on the unclean data and the cleaned data are tested on an uncleaned out-of-sample dataset. The forecasting model learned on the cleaned data outperforms the model learned on the unclean data with 1.67% improvement in the mean absolute percentage errors and a 32.8% improvement in the root mean squared error. Existing challenges include correctly identifying specific types of anomalies such as negative flows.

show abstract

“…As shown in [3], outlier detection approaches can be roughly fall into supervised, unsupervised and semi supervised models according to the availability of labels. For each category, the common outlier detection models are clustering models [4], [5], [14], [15], [21], nearest neighbor models [6]- [8], statistical models [9], [10] and artificial neural network [11]- [13].…”

Section: Introductionmentioning

confidence: 99%

Stacked Denoising Autoencoder With Density-Grid Based Clustering Method for Detecting Outlier of Wind Turbine Components

Sun

2019

IEEE Access

View full text Add to dashboard Cite

Different types of outliers have existed in the monitoring data of wind turbines, which are not conducive to the follow-up data mining. However, the complex inner characteristics of the monitoring data pose major challenges to detect the outliers. To address this problem, an unsupervised outlier detection approach combining stacked denoising autoencoder (SDAE) and density-grid-based clustering method is proposed. First, the characteristics of the outliers in supervisory control and data acquisition data caused by different reasons are analyzed. Then, the SDAE is utilized to extract features by training the original data. Furthermore, the density-grid-based clustering method is applied to achieve the clustering results. Window width is added to classify the outliers as isolated outliers, missing data, and fault data according to the duration of abnormal data. The monitoring data of four wind turbines are sampled as the training data to demonstrate the effectiveness of the proposed method. The results show that the proposed model can effectively identify the isolated outliers, missing data, and fault information in the high dimensional data set by unsupervised learning.INDEX TERMS Density-grid based clustering, outlier detection, stacked denoising autoencoder, unsupervised learning.

show abstract

An Algorithm for Classification and Outlier Detection of Time-Series Data

Cited by 23 publications

References 8 publications

Voltage-gated calcium flux mediates Escherichia coli mechanosensation

Voltage-gated calcium flux mediates Escherichia coli mechanosensation

Data Improving in Time Series Using ARX and ANN Models

Stacked Denoising Autoencoder With Density-Grid Based Clustering Method for Detecting Outlier of Wind Turbine Components

Contact Info

Product

Resources

About