Anomaly detection; Clustering; Data analytics; Early warning system; Prediction; Radiation; Refining incoming monitored incidents; Artificial Intelligence; Environmental Chemistry; Pollution; Health, Toxicology and Mutagenesis; General Medicine
Abstract :
[en] Although radiation level is a serious concern which requires continuous monitoring, many existing systems are designed to perform this task. Radiation early warning system (REWS) is one of these systems which monitor the gamma radiation level in air. Such system requires high manual intervention, depends totally on experts' analysis, and has some shortcomings that can be risky sometimes. In this paper, the approach called RIMI (refining incoming monitored incidents) will be introduced which aims to improve this system while becoming more autonomous with keeping the final decision to the experts. A new method is presented which will help in changing this system to become more intelligent while learning from past incidents of each specific system.
Disciplines :
Computer science
Author, co-author :
Al Saleh, Mohammed ; David Laboratory, University of Versailles (UVSQ), 45 avenue des Etats-Unis, 78035, Versailles, France. mhdalsaleh@gmail.com ; Lebanese University, Rafic Hariri University Campus, Al Hadath, Beirut, Lebanon. mhdalsaleh@gmail.com ; Lebanese Atomic Energy Commission (LAEC), National Council for Scientific Research (CNRS), Airport Road, P.O.Box 11-8281, Beirut, Lebanon. mhdalsaleh@gmail.com
Finance, Béatrice; David Laboratory, University of Versailles (UVSQ), 45 avenue des Etats-Unis, 78035, Versailles, France
Taher, Yehia; David Laboratory, University of Versailles (UVSQ), 45 avenue des Etats-Unis, 78035, Versailles, France
Haque, Rafiqul; Intelligencia R&D, Paris, France
Jaber, Ali; Lebanese University, Rafic Hariri University Campus, Al Hadath, Beirut, Lebanon
Bachir, Nourhan ; Université de Liège - ULiège > Sphères ; Lebanese University, Rafic Hariri University Campus, Al Hadath, Beirut, Lebanon
Language :
English
Title :
Introducing artificial intelligence to the radiation early warning system.
Publication date :
February 2022
Journal title :
Environmental Science and Pollution Research
ISSN :
0944-1344
eISSN :
1614-7499
Publisher :
Springer Science and Business Media Deutschland GmbH, Germany
CNRS - Centre National de la Recherche Scientifique
Funding text :
We would like to express our thankful to the National Council for Scientific Research (CNRS) in Lebanon for supporting this work. We would like to express our gratitude to the Federal Office for Radiation Protection (Bfs) in Germany for giving us the permission for using the data collected by their REWS for more than 15 years ago. The data sets used and/or analyzed during the current study are available from the corresponding author on reasonable request.We would like to express our thankful to the National Council for Scientific Research (CNRS) in Lebanon for supporting this work. We would like to express our gratitude to the Federal Office for Radiation Protection (Bfs) in Germany for giving us the permission for using the data collected by their REWS for more than 15 years ago.
Alanazi H, Abdullah A, Qureshi K (2017) A critical review for developing accurate and dynamic predictive models using machine learning methods in medicine and health care. Journal of Medical Systems 41:69. 10.1007/s10916-017-0715-6 DOI: 10.1007/s10916-017-0715-6
Arathi M, Govardhan A (2014) Accurate time series classification using shapelets. International Journal of Data Mining & Knowledge Management Process 4:39–47. 10.5121/ijdkp.2014.4204 DOI: 10.5121/ijdkp.2014.4204
Barde P, Barde P (2012) What to use to express the variability of data: standard deviation or standard error of mean? Perspectives in Clinical Research 3:113–116. 10.4103/2229-3485.100662 DOI: 10.4103/2229-3485.100662
Biegalski S, Shipman G, Mason L, Pickering M, Altman S (2001) Caribbean radiation early warning system (CREWS). Journal of Radioanalytical and Nuclear Chemistry 248:637–642. 10.1023/A%3A1010624224587 DOI: 10.1023/A%3A1010624224587
Casanovas R, Morant J, López M, Hernández-Girón I, Batalla E, Salvadó M (2011) Performance of data acceptance criteria over 50 months from an automatic real-time environmental radiation surveillance network. Journal of Environmental Radioactivity 102(8):742–748. 10.1016/j.jenvrad.2011.04.001 DOI: 10.1016/j.jenvrad.2011.04.001
Dombrowski H, Bleher M, De Cort M, Dabrowski R, Neumaier S, Stöhlker U (2017) Recommendations to harmonize European early warning dosimetry network systems. Journal of Instrumentation 12:12024. 10.1088/1748-0221/12/12/P12024 DOI: 10.1088/1748-0221/12/12/P12024
El Samad O, Baydoun R, Aoun M, Zaidan W, El Jeaid H (2016) Public exposure to radioactivity levels in the Lebanese environment. Environmental Science and Pollution Research 24(2):2010–2018. 10.1007/s11356-016-7911-7 DOI: 10.1007/s11356-016-7911-7
Farid M, Prawito SI, Yuniarto A (2017) Design of early warning system for nuclear preparedness case study at Serpong. AIP Conference Proceedings. 10.1063/1.4991171
Ghalwash M, Obradovic Z (2012) Early classification of multivariate temporal observations by extraction of interpretable shapelets. BMC Bioinformatics 13:195–206. 10.1186/1471-2105-13-195 DOI: 10.1186/1471-2105-13-195
Guiling L, Wenhe Y, Zongda W (2019) Discovering shapelets with key points in time series classification. Expert Systems with Applications 132:76–86. 10.1016/j.eswa.2019.04.062 DOI: 10.1016/j.eswa.2019.04.062
Gujarati D, Porter D (2009) Basic econometrics. McGraw-Hill Irwin, USA
Han J, Kamber M (2006) Data mining concepts and techniques, 2nd edn. Morgan Kaufmann, USA
Hõrrak U, Chen X, Hõrrak K, Rand U, Komsaare K, Vana M, Luts A, Junninen H (2021) The rain induced gamma-radiation dose rate enhancement at Järvselja SMEAR station. EGU General Assembly 2021:EGU21–EGU15644. 10.5194/egusphere-egu21-15644 DOI: 10.5194/egusphere-egu21-15644
Huiqing W, Li C, Sun H, Guo Z, Bai Y (2018) Shapelet classification algorithm based on efficient subsequence matching. Data Science Journal 17:1–12. 10.5334/dsj-2018-006 DOI: 10.5334/dsj-2018-006
International Atomic Energy Agency (2015) The FukushimaDaiichi accident. IAEA, Vienna
Jelewska A, Krawczak M (2018) The spectrality of nuclear catastrophe: the case of Chernobyl. politics of the machines - art and after. 10.14236/ewic/EVAC18.30
Julazadeh A, Marsousi M, Alirezaie J (2012) Classification based on sparse representation and Euclidian distance. IEEE Visual Communications and Image Processing (VCIP). 10.1109/VCIP.2012.6410815
Kaufmann L, Rousseeuw P (1987) Clustering by means of medoids. data analysis based on the L1-norm and related methods 405-416
Kendall M (1976) Time-series. Charles Griffin, London
Kessler P, Behnke B, Dabrowski R, Dombrowski H, Röttger A, Neumaier S (2018) Novel spectrometers for environmental dose rate monitoring. Journal of Environmental Radioactivity 187:115–121. 10.1016/j.jenvrad.2018.01.020 DOI: 10.1016/j.jenvrad.2018.01.020
Kramer A (2019) Russia orders evacuation of village near site of nuclear explosion. The New YorkTimes. https://www.nytimes.com/2019/08/13/world/europe/russia-nuclear-explosion-accident.html. Accessed 13 August 2019
Küçükarslan N, Erdoğan A, Güven A, Gülay Y (2004) Early warning environmental radiation monitoring system. In: Zaidi MK, Mustafaev I (eds) Radiation safety problems in the caspian region. Nato Science Series: IV: Earth and Environmental Sciences, vol 41. Springer, Dordrecht. 10.1007/1-4020-2378-2_7 DOI: 10.1007/1-4020-2378-2_7
Liao T (2005) Clustering time series data – a survey. Pattern Recognition 38(11):1857–1874. 10.1016/j.patcog.2005.01.025 DOI: 10.1016/j.patcog.2005.01.025
MacQueen, J (1967) Some methods for classification and analysis of multivariate observations. In: BSMSP 281–297.
Ounacer S, Talhaoui M, Ardchir S, Daif A, Azouazi M (2017) A new architecture for real time data stream processing. International Journal of Advanced Computer Science and Applications 8(11). 10.14569/IJACSA.2017.081106
Pyle D (1999) Data preparation for data mining. Morgan Kaufmann, USA
Rakthanmanon T, Campana B, Mueen A, Batista G, Westover B, Zhu Q, Zakaria J, Keogh E (2012) Searching and mining trillions of time series subsequences under dynamic time warping. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 10.1145/2339530.2339576
Sarda-Espinosa A (2018) Comparing time-series clustering algorithms in r using the dtwclust package. In: Manual of the R package dtwclust
Stöhlker U, Bleher M, Doll H, Dombrowski H, Harms W, Hellmann I, Luff R, Prommer B, Seifert S, Weiler F (2019) The German dose rate monitoring network and implemented data harmonization techniques. Radiation Protection Dosimetry 183(4):405–417. 10.1093/rpd/ncy154 DOI: 10.1093/rpd/ncy154
Szegvary T, Conen F, Stöhlker U, Dubois G, Bossew P, Vries G (2007) Mapping terrestrial gamma-dose rate in Europe based on routine monitoring data. Radiation Measurements 42(9):1561–1572. 10.1016/j.radmeas.2007.09.002 DOI: 10.1016/j.radmeas.2007.09.002
Tan P, Steinbach M, Kumar V (2005) Introduction to data mining, First edn. Addison Wesley Longman, USA
Tan C, Petitjean F, Keogh E, Webb G (2019) Time series classification for varying length series. Researchgate. https://www.researchgate.net/publication/336411021_Time_series_classification_for_varying_length_series. Accessed 10 October 2019
Thieu D, Toan T, My N, Sy N, Tien V, Mai N, Cuong L (2012) Study, design and construction of an early warning environmental radiation monitoring station. Communications in Physics 22:375–382. 10.15625/0868-3166/22/4/2665 DOI: 10.15625/0868-3166/22/4/2665
Wang H, Li C, Sun H, Guo Z, Bai Y (2018) Shapelet classification algorithm based on efficient subsequence matching. Data Science Journal 17:1–12. 10.5334/dsj-2018-006 DOI: 10.5334/dsj-2018-006
Zähringer M, Sempau J (1996) The assessment of the representativeness of data from dose rate monitoring stations. Radiation Protection Dosimetry 64:275–288. 10.1093/oxfordjournals.rpd.a031584 DOI: 10.1093/oxfordjournals.rpd.a031584
