Home > Research > Publications & Outputs > Novel Methods for the Detection of Emergent Phe...

Research

Associated organisational unit

Electronic data

Text available via DOI:

View graph of relations

Novel Methods for the Detection of Emergent Phenomena in Streaming Data

Research output: Thesis › Doctoral Thesis

Published

Standard

Novel Methods for the Detection of Emergent Phenomena in Streaming Data. / Austin, Edward.
Lancaster University, 2022. 183 p.

Research output: Thesis › Doctoral Thesis

Harvard

Austin, E 2022, 'Novel Methods for the Detection of Emergent Phenomena in Streaming Data', PhD, Lancaster University. https://doi.org/10.17635/lancaster/thesis/1918

APA

Austin, E. (2022). Novel Methods for the Detection of Emergent Phenomena in Streaming Data. [Doctoral Thesis, Lancaster University]. Lancaster University. https://doi.org/10.17635/lancaster/thesis/1918

Vancouver

Austin E. Novel Methods for the Detection of Emergent Phenomena in Streaming Data. Lancaster University, 2022. 183 p. doi: 10.17635/lancaster/thesis/1918

Author

Austin, Edward. / Novel Methods for the Detection of Emergent Phenomena in Streaming Data. Lancaster University, 2022. 183 p.

Bibtex

@phdthesis{4f47c051127c496b9531323bdb6366bf,
title = "Novel Methods for the Detection of Emergent Phenomena in Streaming Data",
abstract = "In the fast paced and data rich world of today there is an increased demand formethods that analyse a stream of data in real time. In particular, there is a desirefor methods that can identify phenomena in the data stream as they are emerging.These emergent phenomena can be viewed as observations being received that are surprising when compared to the history of the data. Motivated by challenges in the telecommunications sector, we develop methods that operate when the stream does not follow classical assumptions. This includes when the data are not independent or identically distributed, or when the phenomena occur gradually over time.This thesis makes three contributions to the field of anomaly detection for streaming data. The first, Non-Parametric Unbounded Change (NUNC), provides a non-parametric method for identifying changes in the distribution of a data stream. The second, Functional Anomaly Sequential Test (FAST), provides a method for identifying deviations from an expected shape in a stream of partially observed functional data. The third, mvFAST, extends FAST to the multivariate functional data setting.",
author = "Edward Austin",
year = "2022",
month = nov,
day = "29",
doi = "10.17635/lancaster/thesis/1918",
language = "English",
publisher = "Lancaster University",
school = "Lancaster University",

}

RIS

TY - BOOK

T1 - Novel Methods for the Detection of Emergent Phenomena in Streaming Data

AU - Austin, Edward

PY - 2022/11/29

Y1 - 2022/11/29

N2 - In the fast paced and data rich world of today there is an increased demand formethods that analyse a stream of data in real time. In particular, there is a desirefor methods that can identify phenomena in the data stream as they are emerging.These emergent phenomena can be viewed as observations being received that are surprising when compared to the history of the data. Motivated by challenges in the telecommunications sector, we develop methods that operate when the stream does not follow classical assumptions. This includes when the data are not independent or identically distributed, or when the phenomena occur gradually over time.This thesis makes three contributions to the field of anomaly detection for streaming data. The first, Non-Parametric Unbounded Change (NUNC), provides a non-parametric method for identifying changes in the distribution of a data stream. The second, Functional Anomaly Sequential Test (FAST), provides a method for identifying deviations from an expected shape in a stream of partially observed functional data. The third, mvFAST, extends FAST to the multivariate functional data setting.

AB - In the fast paced and data rich world of today there is an increased demand formethods that analyse a stream of data in real time. In particular, there is a desirefor methods that can identify phenomena in the data stream as they are emerging.These emergent phenomena can be viewed as observations being received that are surprising when compared to the history of the data. Motivated by challenges in the telecommunications sector, we develop methods that operate when the stream does not follow classical assumptions. This includes when the data are not independent or identically distributed, or when the phenomena occur gradually over time.This thesis makes three contributions to the field of anomaly detection for streaming data. The first, Non-Parametric Unbounded Change (NUNC), provides a non-parametric method for identifying changes in the distribution of a data stream. The second, Functional Anomaly Sequential Test (FAST), provides a method for identifying deviations from an expected shape in a stream of partially observed functional data. The third, mvFAST, extends FAST to the multivariate functional data setting.

U2 - 10.17635/lancaster/thesis/1918

DO - 10.17635/lancaster/thesis/1918

M3 - Doctoral Thesis

PB - Lancaster University

ER -