Measuring the Accuracy Levels Regarding the Dual Business Function Criticality Classifier

Podaras, Athanasios

doi:10.1109/access.2018.2860976

Cited by 6 publications

(1 citation statement)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used the confusion matrix [40], [41] to show the performance of the classification results for the 102 events. Specifically, we calculated classification accuracy for three class labels using the following metrics: TP (true positive); FN (false negative), Precision; Recall [42], [43]; and F1 Score [44] for each class label.…”

Section: Event Severity Classification Methodsmentioning

confidence: 99%

Enhancing Weather-Related Power Outage Prediction by Event Severity Classification

et al. 2020

View full text Add to dashboard Cite

The accuracy of machine learning-based power outage prediction models (OPMs) is sensitive to how well event severity is represented in their training datasets. Unbalanced or overly dispersed event severity can result in random errors in outage predictions and underestimation in severe events or overestimation in weak ones. To improve accuracy in the prediction of storm-caused power outages, we introduce a novel method called ''Conditioned OPM'' that divides an OPM training dataset into subsets of events representative of the predicted event's severity by calculating the quantile weight distance (QWD) between severe weather-related events in the dataset and the predicted event. Based on 102 storm events (including two hurricanes, Irene and Sandy), that have occurred since 2005 over Eversource Energy's Connecticut service territory, we quantified the weather differences among predicted events, which we classified into three groups of severity: low, moderate, and high. The Conditioned OPM creates a subset of the historical events based on their classified severity group and uses that subset as the training dataset to predict the power outages. The study shows that the accuracy of event severity classification was 0.76, and the mean absolute percentage error (MAPE) decreased by about 30%; this method was also tested on forecast events and exhibited a low (20%) MAPE.

show abstract

Section: Event Severity Classification Methodsmentioning

confidence: 99%

Enhancing Weather-Related Power Outage Prediction by Event Severity Classification

et al. 2020

View full text Add to dashboard Cite

show abstract

Data-Based Agricultural Business Continuity Management Policies

Podaras

2022

Information and Communication Technologies for Agriculture—Theme II: Data

View full text Add to dashboard Cite

A Business Intelligence Solution for Business Continuity and Safety Management in Public Universities

Podaras¹,

ŽIŽKA²,

Nejedlová³

et al. 2020

AD ALTA: Journal of Interdisciplinary Research

View full text Add to dashboard Cite

The article introduces a modern business intelligence solution for facilitating business continuity and safety management proactive decisions in public organizations and units, which is currently tested in a public university for its effectiveness. The tool’s data dimensions, hierarchies and facts are based on the business continuity points method which is a modern approach for estimating proactively the recovery time and predicting the criticality level for individual business functions. From the constructed dataset, selected safety – related and highly critical business functions are used to validate the proposed contribution. The same functions are further used for estimating their availability rates and compare the results with the rates proposed by the university business continuity experts. The conducted research results indicated high accuracy when predicting criticality levels as well as computing availability rates for safety critical functions in the public university. The proposed BI tool facilitates both online analytical processing operations as well as machine learning activities.

show abstract

Measuring the Accuracy Levels Regarding the Dual Business Function Criticality Classifier

Cited by 6 publications

References 30 publications

Enhancing Weather-Related Power Outage Prediction by Event Severity Classification

Enhancing Weather-Related Power Outage Prediction by Event Severity Classification

Data-Based Agricultural Business Continuity Management Policies

A Business Intelligence Solution for Business Continuity and Safety Management in Public Universities

Contact Info

Product

Resources

About