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.
收藏资源简介：
Dataset of the 'Internet of Things: Online Event Detection for Drinking Water Quality Control' competition hosted at The Genetic and Evolutionary Computation Conference (GECCO) July 13th-17th 2019, Prague, Czech Republic The task of the competition was to develop an anomaly detection algorithm for a water- and environmental data set. Included in zenodo: 1. Original train dataset of water quality data provided to participants (identical to gecco2019_train_water_quality.csv) 2. Call for Participation 3. Rules and Description of the Challenge 4. Resource Package provided to participants 5. The complete dataset, consisting of train, test and validation merged together (gecco2019_all_water_quality.csv) 6. The test dataset, which was used for creating the leaderboard on the server (gecco2019_test_water_quality.csv) 7. The train dataset, which participants had available for training their models (gecco2019_train_water_quality.csv) 8. The validation dataset, which was used for the end results for the challenge (gecco2019_valid_water_quality.csv) 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). 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. The competition was organized by: F. Rehbach, S. Moritz, T. Bartz-Beielstein (TH Köln) The dataset was provided by: Thüringer Fernwasserversorgung and IMProvT research project Internet of Things: Online Event Detection for Drinking Water Quality Control 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 "Thüringer Fernwasserversorgung" 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. <br> Competition Opens: End of January/Start of February 2019<br> Final Submission: 30 June 2019 Official webpage: https://www.th-koeln.de/informatik-und-ingenieurwissenschaften/gecco-challenge-2019_63244.php
本数据集对应2019年7月13日至17日于捷克共和国布拉格举办的遗传与进化计算会议（Genetic and Evolutionary Computation Conference, GECCO）上的"物联网：饮用水水质控制在线事件检测"竞赛。本次竞赛的任务为针对水质与环境数据集开发异常检测算法。 Zenodo收录的内容包括： 1. 向参赛选手提供的原始水质训练数据集（与gecco2019_train_water_quality.csv完全一致） 2. 竞赛征集通知 3. 竞赛规则与赛题说明 4. 向参赛选手提供的资源包 5. 完整数据集，包含合并后的训练、测试与验证集（gecco2019_all_water_quality.csv） 6. 用于生成线上排行榜的测试数据集（gecco2019_test_water_quality.csv） 7. 参赛选手可用于模型训练的训练数据集（gecco2019_train_water_quality.csv） 8. 用于生成竞赛最终结果的验证数据集（gecco2019_valid_water_quality.csv） 竞赛要求参赛选手提交事件检测程序。参赛选手可使用训练数据集（gecco2019_train_water_quality.csv）开展模型训练。竞赛期间，选手可将其开发的程序版本上传至线上平台，平台将基于测试数据集（gecco2019_test_water_quality.csv）对该程序进行评分，由此生成阶段性排行榜。为避免针对该测试数据集过拟合，竞赛最终结果将基于验证数据集（gecco2019_valid_water_quality.csv）的评分结果生成。训练、测试与验证数据集均取自同一监测站点，且按时间顺序排列：测试数据集的时间戳紧随训练数据集之后，验证数据集的时间戳则紧随测试数据集之后。 本次竞赛的主办方为：F. Rehbach、S. Moritz、T. Bartz-Beielstein（科隆应用技术大学，TH Köln）。数据集由图林根远程供水公司（Thüringer Fernwasserversorgung）与IMProvT研究项目提供。 数据集背景说明：这是GECCO历史上第八次由SPOTSeven实验室联合多家行业合作伙伴举办的产业挑战赛。本届赛事基于2018年的赛题，与"图林根远程供水公司（Thüringer Fernwasserversorgung）"合作举办，后者提供了真实世界的数据集。本次竞赛的任务为针对水质与环境数据集开发异常检测算法。对水质数据中的异常进行早期识别是一项极具挑战性的工作：不仅需要准确识别水质中真正的不良变化，同时必须将误报率控制在极低水平。 竞赛相关信息如下： - 竞赛开放报名：2019年1月末/2月初 - 最终提交截止日期：2019年6月30日 - 官方网页：https://www.th-koeln.de/informatik-und-ingenieurwissenschaften/gecco-challenge-2019_63244.php
