Validation of wastewater data using artificial intelligence tools and the evaluation of their performance regarding annotator agreement

被引:3
|
作者
Zidaoui, Imane [1 ,2 ]
Wemmert, Cedric [3 ]
Dufresne, Matthieu [2 ]
Joannis, Claude [4 ]
Isel, Sandra [2 ]
Wertel, Jonathan [2 ]
Vazquez, Jose [1 ]
机构
[1] ICube Lab, Dept Fluid Mech, 2 Rue Boussingault, F-67000 Strasbourg, France
[2] 3D EAU, 3 Quai Kleber, F-67000 Strasbourg, France
[3] ICube Lab, Data Sci & Knowledge Dept, 300 Bd Sebastien Brant, F-67400 Illkirch Graffenstaden, France
[4] CJ Conseil, 37 Rue Coteau, F-44100 Nantes, France
关键词
annotator agreement; artificial intelligence; data validation; matrix profile; one-class SVM; wastewater; REAL-TIME CONTROL; FAULT-DETECTION; URBAN;
D O I
10.2166/wst.2023.174
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
To prevent the pollution of water resources, the measurement and the limitation of wastewater discharges are required. Despite the progress in the field of data acquisition systems, sensors are subject to malfunctions that can bias the evaluation of the pollution flow. It is therefore essential to identify potential anomalies in the data before any use. The objective of this work is to deploy artificial intelligence tools to automate the data validation and to assess the added value of this approach in assisting the validation performed by an operator. To do so, we compare two state-of-the-art anomaly detection algorithms on turbidity data in a sewer network. On the one hand, we conclude that the One-class SVM model is not adapted to the nature of the studied data which is heterogeneous and noisy. The Matrix Profile model, on the other hand, provides promising results with a majority of anomalies detected and a relatively limited number of false positives. By comparing these results to the expert validation, it turns out that the use of the Matrix Profile model objectifies and accelerates the validation task while maintaining the same level of performance compared to the annotator agreement rate between two experts.
引用
收藏
页码:2957 / 2970
页数:14
相关论文
共 50 条
  • [21] Interpreting ECG data by integrating statistical and artificial intelligence tools
    Tatara, E
    Cinar, A
    IEEE ENGINEERING IN MEDICINE AND BIOLOGY MAGAZINE, 2002, 21 (01): : 36 - 41
  • [22] Current evaluation and recommendations for the use of artificial intelligence tools in education
    Sagin, Ferhan Girgin
    Ozkaya, Ali Burak
    Tengiz, Funda
    Geyik, Oyku Gonul
    Geyik, Caner
    TURKISH JOURNAL OF BIOCHEMISTRY-TURK BIYOKIMYA DERGISI, 2024, 48 (06): : 620 - 625
  • [23] Prediction and Validation of Fatigue loads using Artificial Intelligence on Real World Measurement Data
    Venu, Anish
    Luedde, Mike
    Omole, John
    SCIENCE OF MAKING TORQUE FROM WIND (TORQUE 2020), PTS 1-5, 2020, 1618
  • [24] Artificial intelligence and machine learning tools for high-performance microalgal wastewater treatment and algal biorefinery: A critical review
    Oruganti, Raj Kumar
    Biji, Alka Pulimoottil
    Lanuyanger, Tiamenla
    Show, Pau Loke
    Sriariyanun, Malinee
    Upadhyayula, Venkata K. K.
    Gadhamshetty, Venkataramana
    Bhattacharyya, Debraj
    SCIENCE OF THE TOTAL ENVIRONMENT, 2023, 876
  • [25] Fund performance evaluation with explainable artificial intelligence
    Kovvuri, Veera Raghava Reddy
    Fu, Hsuan
    Fan, Xiuyi
    Seisenberger, Monika
    FINANCE RESEARCH LETTERS, 2023, 58
  • [26] A thermodynamic evaluation of chilled water central air conditioning systems using artificial intelligence tools
    Carlos Armas, Juan
    Lapido Rodriguez, Margarita
    Rafael Gomez, Julio
    Valdivia Nodal, Yarelis
    INGENIERIA E INVESTIGACION, 2011, 31 (02): : 134 - 142
  • [27] ASSESSING THE SUCCESS OF ARTIFICIAL INTELLIGENCE TOOLS: AN EVALUATION OF CHATGPT USING THE INFORMATION SYSTEM SUCCESS MODEL
    Marjanovic, Ugljesa
    Mester, Gyula
    Marjanovic, Bojana Milic
    INTERDISCIPLINARY DESCRIPTION OF COMPLEX SYSTEMS, 2024, 22 (03) : 266 - 275
  • [28] Development and validation pathways of artificial intelligence tools evaluated in randomised clinical trials
    Siontis, George C. M.
    Sweda, Romy
    Noseworthy, Peter A.
    Friedman, Paul A.
    Siontis, Konstantinos C.
    Patel, Chirag J.
    BMJ HEALTH & CARE INFORMATICS, 2021, 28 (01)
  • [29] Performance Evaluation of a GM-Type Double Inlet Pulse Tube Refrigerator Using Artificial Intelligence Approach with Experimental Validation
    Debashis Panda
    Manoj Kumar
    A. K. Satapathy
    S. K. Sarangi
    R. K. Sahoo
    Arabian Journal for Science and Engineering, 2020, 45 : 9579 - 9597
  • [30] Performance Evaluation of a GM-Type Double Inlet Pulse Tube Refrigerator Using Artificial Intelligence Approach with Experimental Validation
    Panda, Debashis
    Kumar, Manoj
    Satapathy, A. K.
    Sarangi, S. K.
    Sahoo, R. K.
    ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING, 2020, 45 (11) : 9579 - 9597