Visual Analytics for Extracting Trends from Spatio-temporal Data

Dhont, Michiel; Tsiporkova, Elena; Tourwé, Tom; Gonzaléz-Deleito, Nicolás

doi:10.1007/978-3-030-65742-0_9

Cited by 3 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast to line plots, this approach is able to intuitively convey the transition between 12 pm and 1 am. Dhont et al [7] built further on this idea by constructing weekly fingerprints. In this approach, seven circles are compressed into one circular heat map, where the inner circle represents the typical Monday pattern (e.g., hourly), and the outer circle represents the typical Sunday pattern.…”

Section: Visual Analyticsmentioning

confidence: 99%

“…In [7], Dhont et al illustrated how label maps can be exploited to reveal complex patterns and irregularities in temporal data. The visualisation is constructed by positioning the timestamp labels in a matrix-like plot, where the time axis is arranged in a wellconsidered manner.…”

Section: Label Mapsmentioning

confidence: 99%

“…. , K of turbine i, is thus expressed as the weighted sum of the prototypical profiles observed across the fleet, as shown in Equation (7).…”

Section: Prototypical Fleet Profilingmentioning

confidence: 99%

“…The latter is an essential prerequisite for being able to apply non-negative matrix factorisation. In addition, the circular binning facilitates the application of some advanced visual analytics techniques for spatio-temporal data, which we introduced in [7].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Advanced Discretisation and Visualisation Methods for Performance Profiling of Wind Turbines

2021

Self Cite

View full text Add to dashboard Cite

Wind turbines are typically organised as a fleet in a wind park, subject to similar, but varying, environmental conditions. This makes it possible to assess and benchmark a turbine’s output performance by comparing it to the other assets in the fleet. However, such a comparison cannot be performed straightforwardly on time series production data since the performance of a wind turbine is affected by a diverse set of factors (e.g., weather conditions). All these factors also produce a continuous stream of data, which, if discretised in an appropriate fashion, might allow us to uncover relevant insights into the turbine’s operations and behaviour. In this paper, we exploit the outcome of two inherently different discretisation approaches by statistical and visual analytics. As the first discretisation method, a complex layered integration approach is used. The DNA-like outcome allows us to apply advanced visual analytics, facilitating insightful operating mode monitoring. The second discretisation approach is applying a novel circular binning approach, capitalising on the circular nature of the angular variables. The resulting bins are then used to construct circular power maps and extract prototypical profiles via non-negative matrix factorisation, enabling us to detect anomalies and perform production forecasts.

show abstract

Section: Visual Analyticsmentioning

confidence: 99%

Section: Label Mapsmentioning

confidence: 99%

“…. , K of turbine i, is thus expressed as the weighted sum of the prototypical profiles observed across the fleet, as shown in Equation (7).…”

Section: Prototypical Fleet Profilingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Advanced Discretisation and Visualisation Methods for Performance Profiling of Wind Turbines

2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Additionally, in [14] heatmaps were designed to present the differences between true speed and predicted speed. Analogous to this research, an analysis that incorporates k-means clustering and heatmaps visualization was also applied in [15] in order to extract trends from spatiotemporal traffic data.…”

mentioning

confidence: 99%

Analyzing Motorway Operator Data for Spatiotemporal Insights into Speed Dynamics

Koliou,

Spyropoulou

2023

Preprint

View full text Add to dashboard Cite

Advances in technology have introduced remarkable capabilities, particularly in the realm of gathering and accessing vast amounts of data, which has led to the emergence of the "Big Data" era, presenting exciting opportunities to harness the wealth of the generated information. Traffic management centers comprise a stakeholder that can exploit such data towards improving road network operation. This research, explores the utilization of real traffic data, collected by distinct sources on an interurban motorway: static location based aggregate traffic data and probe vehicle data. The first is collected by traffic detectors, while the second involves patrol vehicles’ GNSS data. The traffic quantity analysed is vehicle speed, while specific emphasis has been given on the ap-plication of heatmaps to represent daily traffic patterns and the utilization of k-means clustering. The performed analysis demonstrates the importance of considering spatiotemporal variables as a unified entity when analysing speed in transportation networks. The limitations of using patrol vehicles as estimators of ambient speed, especially in low and heavy traffic conditions, are deline-ated, while the dual purpose of data gathered from these vehicles towards enhancing driving performance and enabling detector maintenance is emphasized. Valuable traffic insights are offered through comprehensive spatiotemporal speed behavior analysis and data combination. The inte-gration of these techniques enhances decision-making for a streamlined and secure transportation system

show abstract