Method for predicting the occurrence of an event from measured data

Abstract

Method for predicting the occurrence of an event comprising: a) creation of a database, comprising at least one pattern, the or each pattern being a series of values ​​of the physical quantity, representative of an event; b) acquisition of measurements of the physical quantity by at least one detector and formation of a time series of measurements; c) at each measurement instant, a test for detecting the occurrence of an event at an event occurrence instant; d) - in the event of detection of the occurrence of an event, identification of the event based on each pattern stored in the database, the identification of the event occurring at an identification instant; - in the absence of detection of the occurrence of an event, repetition of steps a) to c); e) after the event has been identified, prediction of measurements at times subsequent to the identification instant.

Description

Title of the invention: Method for predicting the occurrence of an event from measured data Technical field

[0001] The technical field of the invention is the processing of data, in particular data from measurements, with a view to predicting the occurrence of an event. PRIOR ART

[0002] It is common practice for detectors to be deployed in the vicinity of nuclear facilities in order to detect the occurrence of a radiological event. According to common practice, a detection threshold is taken into account. An alert situation is detected when the irradiation measured by a detector exceeds a predetermined threshold.

[0003] Such a solution assumes taking into account an arbitrarily fixed threshold. However, the radiological background noise can be subject to fluctuations. Thus, a simple comparison with a threshold can generate false positives, when the threshold is too low, or false negatives, when the threshold is too high.

[0004] Furthermore, the occurrence of a radiological event is detected after it has occurred. It is therefore not a question of prevention, but of observation.

[0005] The inventors propose a method for anticipating the occurrence of a radiological event. This makes it possible to put in place appropriate measures, prior to the occurrence of the incident. The method proposed by the inventors is not limited to radiological monitoring. It can be applied in other types of application, for example the measurement of gas or pollutant particle concentrations, or measurements carried out for non-destructive testing purposes, for example an abnormal vibration of a component, or to measurements carried out for diagnostic purposes. Statement of the invention

[0006] A first object of the invention is a method for predicting the occurrence of an event from at least one measurement of a physical quantity carried out at different times, the method comprising the following steps: • a) creation of a database, comprising at least one pattern, the or each pattern being a series of values ​​of the physical quantity, at different successive times, each pattern being representative of an event; • b) acquisition of measurements of the physical quantity by at least one detector at different successive measurement times, so as to form a time series of measurements; • c) at each measurement time, from the time series of measurements, ap application of a test for detecting the occurrence of an event at an event occurrence time, the event occurrence time corresponding to the measurement time or to a time subsequent to the measurement time; • d) in the event of detection of the occurrence of an event, identification of the event based on each pattern in the database, identification of the event occurring at an identification time;

[0007] - in the absence of detection of the occurrence of an event, repetition of steps a) to c); • e) after the event has been identified, prediction of measurements at times subsequent to the time of identification.

[0008] Steps c) to e) can be implemented by a processing unit.

[0009] According to one possibility, during step c), the detection test can be applied to at least the physical quantity measured at the time of measurement, so that the time of occurrence of the event corresponds to the time of measurement.

[0010] According to one possibility, step c) comprises: - ci) from measurements acquired at times prior to the measurement time, application of a prediction algorithm, so as to predict measurements at times subsequent to the measurement time; - c-ii) application of the event occurrence detection test using the measurements predicted at times subsequent to the measurement time, so that the event occurrence time is subsequent to the measurement time.

[0011] According to one possibility, step a) comprises: • ai) carrying out measurements of the physical quantity during an observation period, the observation period comprising different observation times; • aii) application of an event occurrence detection test at each observation time; • aiii) in the event of detection of the occurrence of an event, storage of the physical quantities measured after detection, so as to form an observation time series; • aiv) application of a classification algorithm to each observation time series, so as to define at least one class representative of an event, said class being associated with a pattern.

[0012] Step aiv) may comprise a definition of several classes, the classes being respectively associated with different patterns.

[0013] During step a), at least one pattern in the database may be a pattern obtained by modeling.

[0014] In step e), the prediction of the measurements can be carried out using the pattern associated with the event identified in step d).

[0015] During step c), the test can be based on detecting a crossing of a threshold.

[0016] Following a step e), the method may include an acquisition of the measurements corresponding to the identified event, said measurements forming a series of values ​​feeding the database.

[0017] The physical quantity can be a quantity chosen from: - a level of irradiation; - a concentration of an analyte in a gaseous or liquid medium; - a level of temperature or humidity or pressure; - an electrical or electrostatic or magnetic or acoustic measurement.

[0018] A second object of the invention is a measuring system, comprising: - a detector, configured to measure a physical quantity by at least one detector at different successive measurement times, so as to form a time series of measurements; - a processing unit, configured to implement steps c) to e) of a method according to the first subject of the invention, from measurements of the physical magnitude resulting from the detector, the processing unit being connected to a memory storing a database, comprising at least one pattern, the or each pattern being a series of values ​​of the physical magnitude, at different successive times, each pattern being representative of an event.

[0019] The invention will be better understood upon reading the description of the exemplary embodiments presented in the remainder of the description, in conjunction with the figures listed below. FIGURES

[0020] [Fig.l] illustrates the presence of events in a measurement series.

[0021] [Fig.2] shows an example of a system suitable for implementing the invention.

[0022] [Fig.3A] shows schematically the main steps of a method according to a first embodiment of the invention.

[0023] [Fig.3B] shows schematically the main steps of a method according to a second embodiment of the invention.

[0024] [Fig.4] shows an acquisition of measurements of a physical quantity, corresponding to an irradiation level, during an observation phase, as well as the identification of patterns in said data.

[0025] [Fig.5A] shows classes resulting from a classification of the patterns identified during the observation phase.

[0026] [Fig.5B] represents the center of classes represented in [Fig.5A].

[0027] Figures 6A to 6C illustrate an application of the invention to a measurement of a irradiation level.

[0028] [Fig.7] shows an acquisition of measurements of a physical quantity, corresponding to ECG (electrocardiogram) type measurements, during an observation phase.

[0029] [Fig.8] shows clusters resulting from a classification of the patterns identified during the observation phase shown in [Fig.7].

[0030] Figures 9A and 9B illustrate an application of the invention to an ECG type measurement. PRESENTATION OF SPECIAL METHODS OF IMPLEMENTATION

[0031] [Fig.l] represents an evolution, as a function of time (abscissa axis unit minutes), of a radiation level (y-axis). In [Fig.l], the gray area corresponds to a situation of no concern. The time ranges designated by braces correspond to events E, during which the radiation level is higher than a threshold. One objective of the invention is to anticipate the occurrence of such events, so as to estimate certain characteristics, for example the magnitude or duration.

[0032] [Fig. 2] shows a system suitable for implementing the invention. The system comprises a detector 10 connected to a processing unit 20. In the example shown, the detector is a gamma radiation detector deployed in an environment, for example near a nuclear facility IN. The detector may for example be an ionization chamber. The detector is configured to generate, at different measurement times, measured data, corresponding to irradiation levels.

[0033] The detector 10 is connected to a processing unit 20. The processing unit is programmed to implement the steps described below, in connection with FIGS. 3A to 3B. The processing unit may in particular comprise a microprocessor. The objective of these steps is to anticipate the occurrence of an event, so as to anticipate its consequences. The term event designates a temporal sequence of measured data corresponding to a particular situation. This may be a particular normal situation or an anomaly, for example temporary exposure to a high level of irradiation, or a gradual increase in the level of irradiation.

[0034] In other fields of application, an anomaly may be a vibration whose amplitude is abnormal, or, more generally, a measurement of a physical quantity representative of an anomaly, for example a concentration of a gaseous species in the air or more generally a concentration of a chemical or biological species in a liquid or gaseous medium.

[0035] [Fig.3A] shows schematically the main steps of an embodiment of the invention.

[0036] The method assumes a preliminary learning phase, intended to define patterns representative of an event. The learning phase corresponds to steps 70 to 90.

[0037] Step 70: acquisition of learning data. During this step, the detector acquires data, called learning data, by being subjected to events as previously defined. [Fig.4] represents data acquired over several days. The abscissa axis corresponds to time (unit minutes) and the ordinate axis corresponds to dose equivalent rates (unit nSv / h). The learning phase extends over an observation period, grouping together observation times during which the physical quantity is measured.

[0038] Step 80: Pattern detection.

[0039] During this step, a pattern detection algorithm is implemented. This may, for example, involve detecting the crossing of a threshold. The threshold may be calculated on the basis of a moving average and standard deviation. For example, at each instant, the threshold Thn is such that: Thn = fl + k(J„ (1), where

[0040] is the standard deviation calculated in a time interval of length /

[0041] is the moving average calculated in a time interval of length N. N is for example equal to 20.

[0042] A pattern corresponds to data measured at observation times extending between two threshold crossings. It comprises adjacent times 11 at which the measured data is greater than the threshold.

[0043] In [Fig.4], detected patterns are shown in gray.

[0044] Other pattern extraction techniques are conceivable, for example methods of the type - Matrix profile, described in C.-CM Yeh, Y. Zhu, L. Ulanova, N. Begum, Y. Ding, HA Dau, DF Silva, A. Mueen and E. Keogh, “Matrix profile i: ail pairs similarity joins for time series: a unifying view that includes motifs, discords and shapelets,” in IEEE 16th international conference on data mining (ICDM), pp. 1317-1322, leee, 2016. - Crossmatch, described in M. Toyoda, Y. Sakurai, and Y. Ishikawa, “Pattern discovery in data streams under the time warping distance,” in The VLDB Journal, vol. 22, no. 3, pp. 295-318, 2013. - Autoencoder, described in K. Bascol, R. Emonet, E. Fromont and JM Odobez, “Unsupervised interpretable pattern discovery in time series using autoencoders,” in: Joint IAPR International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (SSPR). Springer, Cham, 2016. P. 427-438

[0045] Step 90: Pattern classification

[0046] During this step, the patterns detected during step 80 are classified. sification, so as to form groups of patterns, usually referred to as clusters or classes. A group of patterns corresponds to patterns whose characteristics are considered similar. The classification is based on the temporal form of the patterns.

[0047] The classification algorithm may for example be a K-means type algorithm. Preferably, the implementation of this algorithm is preceded by a phase aimed at bringing the detected patterns together over the same duration. This may be a linear interpolation.

[0048] The patterns, placed on the same time scale, are then classified by the iterative K-means algorithm, aiming to define K classes. The publication Artur, David “K-means++: the advantages of Careful Seeding.”, SODA'07: Proceedings of the Eighteenth Annual ACM-SIAM Sympsium of Discrète Algorithms. 2007 pp. 1027-1035, describes, in particular in part 2.2, a K-means++ classification algorithm suitable for the application. According to this approach, each class is represented by a class center, which corresponds to an average of all the patterns forming said class.

[0049] The classification algorithm can be implemented using a method different from the K-means methods. For example, it can be: - k Medoids, described in Kaufman, L., and Rousseeuw, PJ (2009). Finding Groups in Data: An Introduction to Cluster Analysis. Hoboken, NJ: John Wiley & Sons, Inc. - Hierarchical clustering, described in Sibson, Robin. “SLINK: an optimally efficient algorithm for the single-link cluster method.” The computer journal 16.1 (1973): 30-34.

[0050] According to one possibility, the learning phase includes taking into account additional patterns, which result not from measurements taken, but from simulations resulting from models. For example, it is possible to simulate a pattern representative of the evolution of irradiation levels following an abnormal event. This corresponds to step 80' shown in FIGS. 3A and 3B.

[0051] [Fig.5A] shows different clusters of patterns. Each pattern has been previously interpolated, so as to be represented according to the same duration. The patterns are normalized in amplitude. The patterns belonging to the same cluster (i.e. the same class) are considered to have a comparable temporal form. Each class corresponds to a type of event. In [Fig.5B], the class centers corresponding to the patterns represented in [Fig.5B] are shown. In Figures 5A and 5B, each class is identified by an index k between 1 and 8.

[0052] The patterns are stored. The number of classes and their centers may vary over time. The database formed in steps 70 to 90 may be supplemented by data measured during step 100 described below, so as to allow continuous adjustment of the number and parameters of each class.

[0053] Step 100: Data acquisition. During this step, the physical quantity is measured at different measurement times. In the example described, the physical quantities are gamma irradiation measurements from a radiation detector suitable for environmental monitoring. In Figure 6A, an acquisition of measurements is shown, which corresponds to the curve x(n). The abscissa axis corresponds to time n (unit minutes) and the ordinate axis corresponds to an irradiation level (arbitrary units). The data shown in Figure 6A are simulated data. The dotted curve corresponds to the evolution of the physical quantity after the measurement time n.

[0054] In Figure 6A, the evolution, as a function of time, of the threshold Tht, as defined in (1) is also shown.

[0055] Step 110: Detection of the occurrence of an event. During step 110, a test for detecting the occurrence of the event is applied. In this example, the test for detecting the occurrence of an event is carried out as described in connection with step 80. In FIG. 6A, the crossing of the threshold Thn (x(n) > Thn) is shown by a solid vertical line, corresponding to the instant n = 1000.

[0056] When the occurrence of an event is detected, the time at which the event occurs is an event occurrence time. In this first embodiment, the event occurrence time corresponds to the measurement time, or is determined from the measurement time. For example, it can be considered that the event occurs y time increments before the threshold crossing time, which is shown in FIG. 6A, with y = 10. In a second embodiment, described below, the event occurrence time is later than the measurement time.

[0057] As long as a pattern has not been detected, steps 100 and 110 are repeated.

[0058] Detecting the occurrence of an event by a moving average and standard deviation is only one example. Step 110 may be implemented with other methods, as discussed in step 80.

[0059] Step 120: Identification of the event detected during step 110, among the stored patterns. During this step, the identified event is identified from the first moments following the moment of detection of the occurrence of the event. This involves determining a pattern, among the patterns stored in the database, closest to the identified event.

[0060] The first values ​​measured after crossing the threshold are compared with the first values ​​of each class center of the previously stored patterns. The comparison is a distance calculation with respect to one of the K stored patterns. Each pattern is designated by an index k, such as 1 <k<K. On identifie le motif k en déterminant, parmi les K motifs celui qui est à la plus petite distance des signaux mesurés depuis le franchissement du seuil. La distance dk entre la grandeur physique mesurée par rapport à chaque motif k est par exemple calculée par rapport au centre de classe de chaque motif. Il peut par exemple s’agir d’une distance euclidienne, auquel cas : 100611 dt

[0062] Where z is a time index from the instant of crossing the pattern (i = n'-n, n' corresponding to the instant of crossing the threshold), n corresponds to the instant of measurement, and c' corresponds to the center of the class at instant i. x ( i ) is the measurement at instant i.

[0063] The pattern k identified is the one that minimizes dk.

[0064] In [Fig.6B], an example is shown in which the identified profile corresponds to the class k = 7 of [Fig.5A]. The measured physical quantities used to identify the pattern are those corresponding to the brace 120.

[0065] The identification of the pattern occurs at a time of identification of the event, coincident with or subsequent to the time of detection of the occurrence of the event.

[0066] Pattern identification may be performed by a distance measurement-based identification algorithm, as previously described, or by a classification algorithm, for example LSTM (Long Short Term Memory), as described in Hochreiter, Sepp, and Jurgen Schmidhuber. “Long short-term memory.” Neural computation 9.8 (1997): 1735-1780.

[0067] Step 130: Prediction. After the class of the pattern has been identified, the physical quantity, at times P subsequent to the time of identification of the event, is predicted, based on the first values ​​of the pattern and the learning data of the class associated with the pattern. Thus, the estimation of the physical quantity, at times P subsequent to the time of identification of the event, is carried out thanks to the identification of the pattern resulting from step 120, as quickly as possible after crossing the threshold. In this example, the time of identification of the event corresponds to a measurement time, because it is on the basis of measurements carried out between the time of detection of the occurrence of the event and the time of identification that the event was identified.

[0068] In [Fig.6C], the physical quantity predicted on the basis of the identified pattern is shown under bracket 130. It can be seen that the predicted physical quantity is close to the actual values ​​of the dotted curve. Step 140: Reinforcing Learning

[0069] At the end of step 130, the class of the pattern detected at time n is known and can feed the learning database by integrating it into the group of patterns associated with the same class. Thus, the center of the class is re-evaluated by taking into account the new pattern. In the case where this pattern does not correspond to any known class, then a new class is created and is taken into account in the learning data to identify the future patterns. This new class therefore obtains its unique pattern as its class center. This allows for reinforcement of the learning.

[0070] During this step, the identified event can be analyzed: duration, typology. Preventive or curative measures can be determined, in order to limit the impact of the event.

[0071] [Fig.3B] shows schematically the main steps of a second embodiment of the invention.

[0072] Steps 70 to 90 are similar to those described in connection with [Fig.3A]. Step 200 is similar to step 100 described in connection with [Fig.3A].

[0073] Steps 200, 210, 220, 230 are respectively similar to steps 100, 110, 120, 130 described in connection with [Fig.3A].

[0074] In parallel with steps 210, 220, 230 the method comprises:

[0075] Step 205: Prediction. This is a step of predicting the physical quantity measured at times P subsequent to the measurement time n. The prediction can be carried out by implementing a prediction algorithm, for example a supervised learning artificial intelligence algorithm, of the LSTM neural network type. During this step, physical quantities measured during the acquisition period are used as input data for the prediction algorithm. Other Machine Learning type algorithms can be applied, for example the statistical model for predicting time series ARIMA (Autoregressive integrated moving average) or ARMA (Autoregressive moving average).

[0076] The prediction algorithm allows for example a prediction of the physical quantity measured during a prediction period subsequent to the measurement instant (n to n+10), from signals acquired at the measurement instant and / or at instants prior to the measurement instant. For example, the prediction period extends between n and n+10, from the signals acquired during the instants n-10 and n.

[0077] Following step 205, a step 210' of testing for detecting the occurrence of an event is implemented. The test for detecting the occurrence of a pattern is carried out according to the principles described in step 110 of the first embodiment. A difference is that the detection of patterns is carried out from measured physical quantities (10 values) but also from the predicted values ​​resulting from step 205 (10 values). Thus, the time of occurrence of the event is later than the time of measurement of the prediction.

[0078] If no event has been detected, steps 200 to 210' are repeated. When an event has been detected, a step 220' of identifying the event, among the stored patterns, is performed. This step is performed in a similar manner to step 220 described in connection with the first embodiment. Unlike step 220, the identification of the pattern corresponding to the event is performed from the measured physical quantities (10 values) and from the predicted physical quantities (10 values) during step 205.

[0079] Step 230': After the pattern has been identified, a step 230' is implemented, so as to complete the prediction. This step is similar to step 230 except that it is based on a pattern identified from predicted values. As with step 230, the prediction is based on the first values ​​of the pattern and the training data of its associated class.

[0080] Following step 230', preventive or curative actions can be launched, for example an evacuation of a site Step 240

[0081] As with step 140, during step 240, measures may be taken to limit the impact of the detected event.

[0082] In [Fig.3B], steps 210', 220' and 230' are implemented partly on the basis of predicted measurements. They are therefore carried out with a certain time advance, compared to steps 210, 220 and 230, which are carried out taking into account measured values.

[0083] Thus, compared to the first embodiment, the detection of the event occurs in an anticipated manner. The measures for limiting the impact of the event can be taken with greater anticipation.

[0084] Step 240 may comprise a comparison between the event resulting from step 230', based on partially predicted data, and the event resulting from step 230, which is defined on the basis of only measured data. The comparison makes it possible to determine a level of accuracy of the event resulting from step 230' with respect to the event resulting from step 230.

[0085] The event can then be injected into the database, for learning reinforcement purposes.

[0086] Whatever the embodiment, an important aspect of the invention is to be able to predict, as quickly as possible, the occurrence of an event as well as its identification. This allows a forecast of the evolution of the measurements. It is then possible to anticipate actions, as accurately and as early as possible, on the causes and consequences of the phenomena, for example protective actions, such as putting in installation of physical protective barriers, maintenance, etc.

[0087] In Figures 6A to 6C, a simulation representing irradiation measurements has been described. The invention can be applied to other measurements, resulting from a sensor. It can be an acoustic sensor, for example in the field of non-destructive testing. It can be a vibration sensor, or in a non-limiting manner, an optical, magnetic, electrical, chemical sensor.

[0088] Figures 7, 8, 9A and 9B represent an example of implementation of the invention in electrocardiogram type measurements. In these figures, data from the LTAF (Long Term Asset Funds) database, described in PETRUTIU, Simona, SAHAKIAN, Alan V., and SWIRYN, Steven, have been taken into account. Abrupt changes in fibrillatory wave characteristics at the termination of paroxysmal atrial fibrillation in humans. Europace, 2007, vol. 9, no. 7, p. 466-470.

[0089] In Figure 7, examples of acquired physical quantities are shown, so as to constitute classes of patterns. The recorded signal comprises three successive calibration signals, designated calib in Figure 7, then a transient signal, and measurement signals x(n) corresponding to 6 successive heartbeats. This is an example of application of step 70 previously described.

[0090] In [Fig.8], 5 classes of patterns obtained from the database as represented in [Fig.7] are shown. This is an example of application of step 90 previously described.

[0091] Classes 3 and 5 each represent a distinct signal form. We notice a misclassified pattern in class 3, this error is explained by the fact that the classification method used (K-means) is not optimized. The patterns in classes 1, 2 and 4 are isolated patterns and classified in classes containing a single unique pattern since they do not resemble the shapes of the other patterns.

[0092] Figures 9A and 9B illustrate an application of steps 100 to 130 described in connection with [Fig.3A]. In [Fig.9A], a physical quantity measured up to a threshold crossing is represented, the moment of crossing being materialized by a vertical line. The moment of crossing corresponds to the moment of detection of the occurrence of an event. The exact measurements corresponding to the moments after the moment of detection of the occurrence of the event are represented by dotted lines.

[0093] In [Fig.9A], the measurements allowing identification of the event that triggered the crossing of the threshold are shown. These measurements correspond to bracket 120. This is an event corresponding to pattern 5 of [Fig.8]. The last instant of bracket 120 corresponds to the instant of identification of the event.

[0094] In [Fig.9B], the predicted measurements from the identified event are shown. The predicted measurements, at times subsequent to the identification time of the event, correspond to brace 130. The dotted curve shows the actual measurements. We observe a good fit between the actual measurements and the predicted measurements.

Claims

1.

2.

3. Claims Method for predicting the occurrence of an event from at least one measurement of a physical quantity carried out at different times, the method comprising the following steps: - a) creation of a database, comprising at least one pattern, the or each pattern being a series of values ​​of the physical quantity, at different successive times, each pattern being representative of an event; - b) acquisition of measurements of the physical quantity (xQîj) by at least one detector (10) at different successive measurement times, so as to form a time series of measurements; - c) at each measurement time, from the time series of measurements, application of a test for detecting the occurrence of an event at an event occurrence time, the event occurrence time corresponding to the measurement time or to a time subsequent to the measurement time; - d) - in the event of detection of the occurrence of an event, identification of the event based on each pattern in the database, identification of the event occurring at an identification time; - in the absence of detection of the occurrence of an event, repetition of steps a) to c); - e) after the event has been identified, forecasting measurements at times subsequent to the time of identification. steps c) to e) being implemented by a processing unit (20). Method according to claim 1, in which during step c), the detection test is applied to at least the physical quantity measured at the measurement time, so that the time of occurrence of the event corresponds to the measurement time. The method of claim 1, wherein step c) comprises: - ci) from measurements acquired at times prior to the measurement time, application of a prediction algorithm, so as to predict measurements at times subsequent to the measurement time; - c-ii) application of the event occurrence detection test using the measurements predicted at times subsequent to the measurement time, so that the event occurrence time is subsequent to the measurement time.

4. Method according to any one of the preceding claims, in which step a) comprises: • ai) carrying out measurements of the physical quantity during an observation period, the observation period comprising different observation times; • aii) applying an event occurrence detection test at each observation time; • aiii) in the event of detection of the occurrence of an event, storing the physical quantities measured after the detection, so as to form an observation time series; • aiv) applying a classification algorithm to each observation time series, so as to define at least one class representative of an event, said class being associated with a pattern.

5. Method according to claim 4, in step aiv) comprises a definition of several classes, the classes being respectively associated with different patterns.

6. Method according to any one of the preceding claims, wherein during step a), at least one pattern of the database is a pattern obtained by modeling.

7. Method according to any one of the preceding claims, wherein during step e), the prediction of the measurements is carried out using the pattern associated with the event identified during step d).

8. Method according to any one of the preceding claims in which during step c), the test is based on a detection of a crossing of a threshold.

9. Method according to any one of the preceding claims, in which following a step e), an acquisition of the measurements corresponding to the identified event, said measurements forming a series of values feeding the database.

10. Method according to any one of the preceding claims, in which the physical quantity is a quantity chosen from: - an irradiation level; - a concentration of an analyte in a gaseous or liquid medium; - a temperature or humidity or pressure level; - an electrical or electrostatic or magnetic or acoustic measurement.

11. Measuring system, comprising: - a detector (10), configured to measure a physical quantity by at least one detector at different successive measurement times, so as to form a time series of measurements; - a processing unit (20), configured to implement steps c) to e) of a method according to any one of the preceding claims, from measurements of the physical quantity resulting from the detector, the processing unit being connected to a memory storing a database, comprising at least one pattern, the or each pattern being a series of values ​​of the physical quantity, at different successive times, each pattern being representative of an event.

Images