<< Go Back

Metadata

Name
GECCO Industrial Challenge 2019 Dataset: A water quality dataset for the 'Internet of Things: Online Event Detection for Drinking Water Quality Control' competition at the Genetic and Evolutionary Computation Conference 2019, Prague, Czech Republic.
Repository
ZENODO
Identifier
doi:10.5281/zenodo.4304080
Description
Dataset &nbsp;of the &#39;Internet of Things: Online Event Detection for Drinking Water Quality Control&#39; competition hosted at&nbsp;The Genetic and Evolutionary Computation Conference (GECCO)&nbsp;July 13th-17th 2019, Prague, Czech Republic

&nbsp;

The task of the&nbsp;competition was&nbsp;to develop an anomaly detection algorithm for a water- and environmental data set.

&nbsp;

Included in zenodo:&nbsp;

1. Original train dataset of water quality data provided to participants (identical to&nbsp;gecco2019_train_water_quality.csv)

2.&nbsp;Call for Participation

3. Rules and Description of the Challenge

4. Resource Package provided to&nbsp;participants

5. The complete dataset, consisting of train, test and validation merged together&nbsp;(gecco2019_all_water_quality.csv)

6.&nbsp;The&nbsp;test&nbsp;dataset, which was used for creating the leaderboard on the server&nbsp; (gecco2019_test_water_quality.csv)

7.&nbsp;The train dataset, which participants had available for training their models&nbsp; (gecco2019_train_water_quality.csv)

8.&nbsp;The&nbsp;&nbsp;validation dataset, which was used for the end results for the challenge (gecco2019_valid_water_quality.csv)

&nbsp;

The challenge required the participants to submit a program for event detection. A training dataset was available to the participants (gecco2019_train_water_quality.csv). During the challenge the participants were able to upload a version of their program to out online platform, where this version was scored against the testing dataset (gecco2019_test_water_quality.csv), thus an intermediate leaderboard was available. To avoid overfitting against this dataset, at the end of the challenge, the end result was created from scoring with the validation dataset (gecco2019_valid_water_quality.csv).&nbsp;

Train, Test, Validation dataset are from the same measuring station and are in chronological order. So the timestamps from the test dataset begin directly after the train timestamps, while the validation timestamps begin directly after the test timestamps.&nbsp;

&nbsp;

The competition was organized by:

F. Rehbach, S. Moritz,&nbsp;T. Bartz-Beielstein (TH K&ouml;ln)

&nbsp;

The dataset was provided by:

Th&uuml;ringer Fernwasserversorgung and&nbsp;IMProvT research project

&nbsp;

&nbsp;

Internet of Things: Online Event Detection for Drinking Water Quality Control

&nbsp;

Description:

For the 8th time in GECCO history, the SPOTSeven Lab is hosting an industrial challenge in cooperation with various industry partners. This years challenge, based on the 2018 challenge, is held in cooperation with &quot;Th&uuml;ringer Fernwasserversorgung&quot; which provides their real-world data set. The task of this years competition is to develop an anomaly detection algorithm for the water- and environmental data set. Early identification of anomalies in water quality data is a challenging task. It is important to identify true undesirable variations in the water quality. At the same time, false alarm rates have to be very low.


Competition Opens: End of January/Start of February 2019
Final Submission: 30 June 2019

Official webpage:

https://www.th-koeln.de/informatik-und-ingenieurwissenschaften/gecco-challenge-2019_63244.php

&nbsp;
Data or Study Types
multiple
Source Organization
Unknown
Access Conditions
available
Year
2020
Access Hyperlink
https://doi.org/10.5281/zenodo.4304080

Distributions