Time Series Analysis research projects

Advisian Digital, Proof of Concept for Application of Advanced Short Term Power Generation Forecasting Technology for Wind and Solar Farms

(2019-2021)

Project lead: Dr Christoph Bergmeir, Dr. Mahsa Salehi


EMOTIV: Hack your brain with a machine that reads minds

(Emotiv, 2018-2019)

Project lead: Dr. Mahsa Salehi

Distracted drivers are 3 times more likely to be involved in a crash than attentive drivers. Our research has developed a device to measure and track brain activities using specialised wearable Emotiv headsets. By designing new machine learning algorithms we can detect human distraction patterns in order to make driving safer. Our current research includes anomaly detection (finding unusual patterns) in huge multi-dimensional time series, spatio-temporal data analysis and data stream mining with a specific application to interpret the human brain.

Browse the EMOTIV website


Highly Scalable Autonomous Time Series Analysis

(AOARD, 2017-2019)

Project lead: Prof.Geoff Webb

Most machine learning systems learn models that apply at a single point in time and take little or no account of the dynamic interactions that have led to the current state-of-affairs. We are developing new autonomous machine learning algorithms that learn from time series data using two exemplar applications; satellite image analysis and railway track maintenance.

It is only possible to distinguish in satellite imagery whether a crop is wheat or barley by considering the evolution of images in each location. No single image in isolation provides sufficient discriminatory detail. When using measurements of railway track performance to assess remedial maintenance, only by considering the evolution of the track condition is it possible to determine whether simple ballast tamping will be effective or whether ballast replacement is required.

Machine learning from information collected at multiple time points is called time series analysis. This project builds on a large body of previous research in this field to produce techniques that scale to orders of magnitude, larger collections of time series than the current state-of-the-art techniques and to much higher-dimensional time series, as is required by our two exemplar applications.

Read the full research report


Time series classification for new-generation Earth observation satellites

(ARC DECRA, 2017-2020)

Project lead: Dr. Francois Petitjean

We are entering a new era in Earth Observation, with latest-generation satellites starting to image Earth frequently, completely, in high-resolution, and at no charge to end-users; introducing unprecedented opportunities to monitor the dynamics of any region of our planet over time and revealing the constant flux that underpins the bigger picture of our world. These satellites produce vast streams of unprecedentedly rich data in the form of time series, enabling the creation of nuanced, temporal land-cover maps that describe the evolution of an area over time. This DECRA project aims to create the machine learning technologies necessary to analyse series of satellite images, and to produce accurate temporal land-cover maps of our planet.

Read the full project report


Efficient and effective analytics for real-world time series forecasting

(ARC DECRA, 2019-2022)

Project lead: Dr. Christoph Bergmeir

This project aims to create efficient, effective techniques that provide accurate forecasts for heterogeneous sets of time series of varying sizes. The project addresses the need to exploit properties of big data, which is transforming many industries. By exploiting similarities between time series, this means using many related series, not larger series when building forecasts. The expected outcomes should be innovative methods that improve accuracy and allow forecasting with shorter time series. This should enable more accurate and reliable forecasts, which have the potential to save billions of dollars across many industries.


Application of Advanced Short Term Power Generation Forecasting

(ARENA, 2019-2021)

Project lead: Dr. Christoph Bergmeir

Read the full project report


Cognitive Buildings Project

(Honeywell, 2018-2019)

Project lead: Dr. Christoph Bergmeir