Priyanga Dilini Talagala
PhD, Monash University, Australia




 



Avatar

Priyanga Dilini Talagala

PhD in Statistics

Monash University, Australia

I am a Lecturer at the University of Moratuwa. I completed my PhD in Statistics at Monash University, Australia, under the supervision of Professor Rob J. Hyndman and Professor Kate Smith-Miles.

I am also an Associate Investigator of the Australian Research Council (ARC) Centre of Excellence for Mathematical and Statistical Frontiers (ACEMS), Australia. Further, I am a co-founder of R-Ladies Colombo, a local chapter of the R-Ladies Global Organization.

My research focuses on statistical machine learning and data mining, and in particular the development of novel methods and tools for analyzing complex data. I am also strongly committed to develop open source software tools to facilitate reproducible research. You can find some of my projects here. Visit me on twitter, I post mostly about R, Statistics, Data Science and science in nature.

Thiyanga Talagala, PhD in Statistics, Monash University, Australia is my sister.

Interests

  • Computational statistics
  • Statistical machine learning
  • Machine learning interpretability
  • Anomaly detection
  • Functional data analysis
  • Time series analysis and forecasting
  • High dimensional data visualization
  • Streaming data mining
  • Applied statistics
  • R programming

Education

  • PhD in Statistics, 2019

    Monash University, Australia

  • BSc (Hons) Special Degree in Statistics, 2013

    University of Sri Jayewardenepura, Sri Lanka

  • Batch first and Professor R A Dayananda Gold Medalist, 2013

Featured Publications




Featured Publications Anomaly Detection in Streaming Nonstationary Temporal Data

This article proposes a framework that provides early detection of anomalous series within a large collection of non-stationary streaming time series data.






Recent Publications

Quickly discover relevant content by filtering publications.

Anomaly Detection in High Dimensional Data

The algorithm, stray, which is specially designed for high-dimensional data, addresses the limitations of the state-of-art-method, the …

Anomaly Detection in Streaming Nonstationary Temporal Data

This article proposes a framework that provides early detection of anomalous series within a large collection of non-stationary …











Recent & Upcoming Talks

Anomaly Detection in R

useR! 2019, Toulouse , France.

A feature-based framework for detecting technical outliers in water-quality data from in situ sensors

39th International Symposium on Forecasting, Thessaloniki, Greece

Outlier Detection in Non-Stationary Data Streams

Joint International Society for Clinical Biostatistics and Australian Statistical Conference 2018, Melbourne, Australia

Outlier Detection in Non-Stationary Data Streams

2018 Joint Statistical Meetings - American Statistical Association, Vancouver, Canada

oddstream and stray-Anomaly Detection in Streaming Temporal Data with R

useR! 2018, Brisbane, Australia











Projects

*

CRAN Task View: Anomaly Detection with R

CRAN Task View: Anomaly Detection with R

oddstream - R package

oddstream {Outlier Detection in Data STREAMs}

oddwater - R package

oddwater{Outlier Detection in Data from WATER-quality sensors}

R-Ladies Colombo

R-Ladies is a worldwide organization whose mission is to promote diversity in the R community. R-Ladies Colombo chapter is a part of …

staplr - R package

A package containing a toolkit for PDF files

stray - R package

stray {Search and TRace AnomalY}

Contact