Method for determining an objective fatigue level of an operator performing a task, associated determination system, and method for estimating and determining such a fatigue level

Abstract

Method for determining an objective fatigue level of an operator performing a mission, associated determination system, and method for estimating and determining such a fatigue level. The present invention relates to a method (200) for determining an objective fatigue level of an operator performing a mission, the method comprising the following steps: - acquisition (210) of a first fatigue estimate determined by a biomathematical fatigue prediction model from a plurality of mission data relating to the mission; - acquisition (220) of a second fatigue estimate determined by a physiological fatigue prediction model from the operator's physiological data; and - determination (230) of an objective fatigue level by merging the two fatigue estimates. Figure for the abstract: Figure 3

Description

Title of the invention: Method for determining an objective fatigue level of an operator performing a task, associated determination system and method for estimating and determining such a fatigue level

[0001] The present invention relates to a method for determining an objective level of fatigue of an operator performing a mission.

[0002] The present invention further relates to a determination system implementing such a determination method.

[0003] The present invention also relates to a method for estimating and determining such a level of fatigue.

[0004] The invention is more particularly situated in the technical field of determining the fatigue of an operator.

[0005] The operator, for example, operates in a critical operational environment. In other words, operator fatigue in this critical environment can lead to significant consequences. This is particularly the case in the aeronautical, aerospace, railway, nuclear, and medical fields, among others.

[0006] In the aeronautical field, biomathematical models for predicting fatigue are well known. These models provide tools for predicting crew member fatigue levels. The predictions are based on scientific knowledge of the factors that generate fatigue and on mission planning information. These models are used as a solution for predicting fatigue and are currently available on the market.

[0007] However, existing biomathematical fatigue models cannot accurately and objectively estimate fatigue levels for all types of missions and operators. This is because these biomathematical models are generally based on average fatigue levels and other data from ad hoc surveys, such as polls or statements obtained from a limited number of individuals. These polls and statements, however, are generally based on the operators' personal experiences, which may be biased by cultural, professional, or operational factors. They do not constitute an objective way to estimate fatigue levels.

[0008] Furthermore, existing biomathematical models rely on generic principles and do not always reflect the reality of operations. They do not take into account certain operational factors such as weather, season, or the type of means of transport used for the mission.

[0009] The aim of the invention is therefore to propose a means of objectively and precisely determining the level of fatigue of an operator.

[0010] To this end, the invention relates to a method for determining an objective fatigue level of an operator performing a mission, the method comprising the following steps:

[0011] - acquisition of a first fatigue estimate determined by a model biomathematics for predicting fatigue from a plurality of mission data related to the mission;

[0012] - acquisition of a second fatigue estimate determined by a model physiological prediction of fatigue based on the operator's physiological data; and

[0013] - determination of an objective fatigue level by merging the two estimates of fatigue.

[0014] According to other advantageous aspects of the invention, the determination method comprises one or more of the following features, taken individually or in all technically possible combinations:

[0015] - the fusion is performed by recalibrating the first fatigue estimate by the second fatigue estimate;

[0016] - the calibration is done using an optimal filter;

[0017] - the optimal filter is a Kalman filter and / or a particle filter;

[0018] - the implementation of the optimal filter comprises the following sub-steps:

[0019] + calculation of an initial weighting for a time T from the first fatigue estimate acquired for a previous instant Tl, the initial weighting corresponding to the uncertainty of the first fatigue estimate;

[0020] + prediction of a first theoretical fatigue estimate for time T from of the initial weighting for time T, of the first estimate of fatigue acquired for the previous time Tl and of a theoretical evolution function of fatigue;

[0021] + modification of the initial weighting based on a conditional probability of the second fatigue estimate acquired for time T, given the first theoretical fatigue estimate for time T; and

[0022] + estimation of an objective fatigue level for time T based on the weighting initial for time T modified and the first theoretical fatigue estimate for time T;

[0023] - the implementation of the optimal filter further includes a generation substep of a set of particles, each particle having a first estimate of fatigue acquired for a previous instant Tl and a previously undefined initial weighting associated with the first estimate of fatigue;

[0024] said sub-steps of calculation, prediction, modification and estimation being implemented for each of the particles;

[0025] the method further comprising a substep of estimating an objective fatigue level resulting from a weighted average of the estimates of the fatigue level for the different particles.

[0026] - the fusion is performed by a supervised learning algorithm capable of extracting a supervised set of signature(s) linked to the objective fatigue level from the two fatigue estimates, a model of the supervised learning algorithm being chosen from the group consisting of: neural networks, logistic regression, support vector machine, and k nearest neighbors method;

[0027] -the fusion is performed by an unsupervised learning algorithm capable of extracting an unsupervised set of signature(s) related to the objective fatigue level from the two fatigue estimates, a model of the unsupervised learning algorithm being chosen from the group consisting of: hierarchical clustering, K-means partitioning, self-organizing maps, and Gaussian mixtures;

[0028] - the biomathematical model is constructed from subjective and / or data statistics relating to a plurality of individuals.

[0029] - the operator's mission is the piloting of an aircraft and in which the plurality of Mission data includes at least one data type chosen from the group comprising:

[0030] + data relating to the scheduling of a crew of which the operator is a part;

[0031] + data relating to the configuration of an airline.

[0032] - the physiological data include at least one type of data selected from the group comprising:

[0033] + images of the operator;

[0034] + a heartbeat;

[0035] + blood pressure;

[0036] + an inspiration of oxygen;

[0037] + sweating;

[0038] + oxygen saturation;

[0039] + a rate of dehydration;

[0040] - the operator's physiological data are measured during the mission.

[0041] The invention also relates to a system for determining an objective level of fatigue comprising technical means configured to implement the method according to any one of the characteristics described above.

[0042] The invention also relates to a method for estimating and determining the fatigue level of an operator, comprising the following steps:

[0043] - determination of a first fatigue estimate determined by a model biomathematics for predicting fatigue from a plurality of mission data related to the mission;

[0044] - determination of a second fatigue estimate determined by a model physiological prediction of fatigue based on the operator's physiological data;

[0045] - implementation of the determination method according to any one of the characteristics described above.

[0046] The invention will become clearer upon reading the following description, given solely by way of non-limiting example, and made with reference to the drawings in which:

[0047] [Fig-1] [Fig.1] is a schematic representation of an estimation architecture and determining the level of fatigue of an operator, according to the invention;

[0048] [Fig.2] [Fig.2] is a schematic representation of a determination system of an objective fatigue level, the determination system being part of the estimation and determination architecture of [Fig. 1]; and

[0049] [Fig.3] [Fig.3] is a flowchart of an estimation and determination process of a level of fatigue, the process being implemented by the architecture of the [Fig.l].

[0050] Figure 1 represents an architecture 10 for estimating and determining the fatigue level of an operator. The architecture 10 allows for estimating and determining the fatigue level of an operator.

[0051] Advantageously, architecture 10 is usable in the aeronautical field. In such a case, the operator is part of the flight crew, specifically the commercial flight crew. In other examples, the operator may be part of the flight planning team, the maintenance team, the aircraft control team, or the air traffic controllers.

[0052] Advantageously, the operator is a pilot capable of flying an aircraft.

[0053] By aircraft, we mean any flying machine that can be piloted from its cockpit, as is the case, for example, with an airplane or a helicopter, or at a distance from it, as is the case, for example, with a drone.

[0054] In general, the concept of operator can be applied to any other person carrying out a critical mission, for example in the field of transport (rail or heavy goods vehicle or any transport for example) or in the nuclear or space field, or in medicine.

[0055] As previously stated, the operator carries out a mission which is determined by the field of its activity.

[0056] In particular, the operator's mission includes a plurality of tasks defined according to the operator's skills.

[0057] When the operator is an aircraft pilot, his mission generally consists of piloting the aircraft from a starting point to a point of its destination.

[0058] The estimation and determination architecture 10 includes a first fatigue estimation system 12, a second fatigue estimation system 14 and an objective fatigue determination system 16.

[0059] The first fatigue estimation system 12 is configured to determine a first fatigue estimate from mission data, by implementing a biomathematical fatigue prediction model.

[0060] To this end, the first fatigue estimation system 12 is connected to one or more databases 18 containing mission data. This system 12 can, for example, be connected to this or these database(s) 18 directly or indirectly, for example via a computer network.

[0061] Mission data describes the mission to be performed by the operator.

[0062] This mission data includes, for example, the mission schedule (i.e. start, end, duration), the position to be occupied by the operator during this mission (pilot, co-pilot or other critical position for example in nuclear or air traffic control), team composition (for example the number of pilots required for the flight to be carried out), the position of the work day in the period (i.e. the day number in the work sequence), information on the planning of the mission (mission planned, replanned and in the latter case, prior to this replanning), time frame of the mission (morning, daytime, evening, night), type of aircraft or any other work position on which the mission will be carried out.

[0063] Advantageously, when the operator's mission is piloting an aircraft, the mission data 18 includes at least one data type selected from the group comprising:

[0064] - data relating to the scheduling of a crew of which the operator is a part;

[0065] - data relating to the configuration of an airline.

[0066] Advantageously, the mission data originates from the airline for which the operator is performing the mission. In such a case, the database(s) 18 are advantageously made available to the first estimation system 12 by the airline.

[0067] The biomathematical fatigue prediction model is, for example, a model known in itself that makes it possible to determine a fatigue level from mission data, as defined above. The biomathematical model is, for example, constructed from subjective and / or statistical data relating to a plurality of individuals. Each of these individuals, for example, has an operator performing a mission identical or similar to that of the operator for whom the level of fatigue is determined by the estimation and determination architecture 10.

[0068] Advantageously, the data used to construct the biomathematical model are determined beforehand from subjective and / or statistical data relating to the individuals in question. This data is collected, for example, through self-reporting by these individuals and / or through ad hoc survey campaigns. This data can also be statistically processed to make it applicable to other individuals.

[0069] By way of example, a biomathematical model can be constructed or adjusted from data reported by pilots after each flight. For instance, the pilot can report their subjective fatigue level after each flight. The model can then associate different flight durations with different levels of fatigue experienced by the pilots. Thus, such a model is capable of determining a perceived fatigue level for a given moment during the flight.

[0070] A simple biomathematical model may, for example, take the form of abacuses associating one value with another. A more complex biomathematical model may take the form of a formula associating one value with a plurality of other values ​​and comprising coefficients determined beforehand from subjective and / or statistical data relating to individuals.

[0071] The level of fatigue determined by the biomathematical model has a value (for example a number or a character) determined on a scale specific to this model.

[0072] The second fatigue estimation system 14 is configured to determine a second fatigue estimate from the operator's physiological data, by implementing a physiological fatigue prediction model.

[0073] The operator's physiological data includes all types of data that allow the operator's physical state to be characterized. This physiological data is advantageously acquired during the mission, or just before the mission, or just after the mission.

[0074] Advantageously, the operator's physiological data includes at least one type of data selected from the group comprising:

[0075] - images of the operator;

[0076] - a heartbeat;

[0077] - blood pressure;

[0078] - an inspiration of oxygen;

[0079] - a breathing rate;

[0080] - a breathing amplitude;

[0081] - perspiration;

[0082] - oxygen saturation;

[0083] - a rate of dehydration.

[0084] To acquire physiological data, the second estimation system 14 is connected directly or indirectly to a plurality of sensors 20 located, for example, in the operator's workstation. For example, these sensors 20 are located in a fixed and / or removable manner in the cockpit of the aircraft piloted by the operator. These sensors 20 can, for example, be connected to the second estimation system 14 via a computer network.

[0085] In particular, the plurality of sensors 20 includes any sensor enabling the acquisition of the operator's physiological data.

[0086] For example, the plurality of sensors 20 includes a camera (not shown) configured to acquire images of the operator and a heart rate sensor (not shown) for measuring the operator's heart rate.

[0087] The camera is for example oriented towards the operator or has means allowing it to be oriented according to the position of the operator.

[0088] The operator's heart rate sensor is configured, for example, to be positioned around the operator's wrist.

[0089] For this purpose, the heart rate sensor includes, for example, a bracelet that can be attached to the operator's wrist and a sensitive part that is intended to measure the operator's heart rate when the bracelet is attached to his wrist.

[0090] Heart rate measurement is performed, for example, by the sensitive part, using the technique called photoplethysmography, or PPG. Alternatively, the sensitive part is configured to perform heart rate measurement from an analysis of the electrical response via the operator's wrist or by analyzing radar signals propagating through the operator's wrist.

[0091] In some examples, the heart rate sensor is configured to measure other physiological parameters of the operator such as blood pressure, oxygen inspiration, sweating, dehydration rate, etc.

[0092] For oxygen saturation, the heart rate sensor is configured, for example, to emit and receive a light signal comprising at least two wavelengths towards the operator's skin. The first wavelength corresponds to a wavelength absorbed by saturated red blood cells, and the second wavelength corresponds to a wavelength absorbed by unsaturated red blood cells. To determine oxygen saturation, the heart rate sensor is then configured to compare the light intensity received in response to each of the two wavelengths.

[0093] Generally speaking, the heart rate sensor can take the form of a smartwatch to, for example, measure one's heart rate.

[0094] Of course, the aforementioned functionalities of the heart rate sensor can form separate sensors.

[0095] The physiological fatigue prediction model is configured to determine an operator's fatigue level using their physiological data as described above. This fatigue level has a value (for example, a number or a character) determined on a scale specific to this model.

[0096] To determine the level of fatigue, the physiological model analyzes physiological data according to predetermined algorithms and associates a level of fatigue in accordance with this analysis.

[0097] For example, the physiological model can analyze images of the operator to determine the number of blinks, the frequency of yawning, and / or any other gesture likely to be caused by fatigue. The physiological model can, for example, analyze the operator's heart rate and link it to information relating to their gestures.

[0098] Each of the estimation systems 12, 14 described above includes, for example, at least partially a hardware component (such as an FPGA-type programmable logic circuit) and / or a software component. In the latter case, the software component is, for example, implemented by a computer comprising at least one processor and RAM. The corresponding model is, for example, stored in non-volatile memory of this computer.

[0099] Figure 2 illustrates in detail the objective fatigue determination system 16. This system 16 is configured to fuse the first and second fatigue estimates in order to determine an objective fatigue level. To do this, the objective fatigue determination system 16 comprises an acquisition module 22, a processing module 24, and an output module 26.

[0100] The acquisition module 22 is configured to acquire data from the first and second fatigue estimation systems 12, 14. In other words, the acquisition module 22 is configured to acquire the first fatigue estimation from the first fatigue estimation system 12 and the second fatigue estimation from the second fatigue estimation system 14.

[0101] The processing module 24 is connected to the output of the acquisition module 22 and is configured to determine an objective fatigue level by merging the first fatigue estimate and the second fatigue estimate, as will be explained in more detail later.

[0102] As an optional addition, the processing module 24 is also capable of identifying a set of risk factor(s) associated with the objective level of fatigue.

[0103] The output module 26 is connected to the output of the processing module 24. This output module 26 is capable of transmitting the objective fatigue level to a system external to the architecture 10.

[0104] Each of the modules 22, 24, 26 of the objective fatigue determination system 16 described above includes, for example, at least partially a hardware component (such as an FPGA-type programmable logic circuit) and / or a software component. In the latter case, the software component is, for example, implemented by a computer comprising at least one processor and random access memory.

[0105] The operation of the estimation and determination architecture 10 according to the invention will now be described with reference to [Fig. 3], which represents a flowchart of the method 100, according to the invention, for estimating and determining the operator's fatigue level. This method is implemented by the architecture 10.

[0106] During step 110 of this estimation and determination process 100, the first fatigue estimation system 12 determines a first estimate corresponding to the fatigue level determined by the biomathematical model, as described previously.

[0107] This fatigue level is determined using mission data relating to the operator's mission.

[0108] This step 110 is, for example, implemented before the operator's mission. In some embodiments, this step 110 can also be implemented during the mission, for example, throughout the mission. In such a case, the first estimate may present a sequence of data generated at different times by the biomathematical model.

[0109] During step 120 of this estimation and determination process 100, the second fatigue estimation system 14 determines a second estimate corresponding to the fatigue level determined by the physiological model, as described above. Step 120 can be implemented following step 110 or in parallel with step 120.

[0110] This step 120 is, for example, implemented during the operator's mission using physiological data also acquired during the mission. For example, this step is implemented continuously throughout the operator's mission. Thus, the second estimation can present a series of data generated at different times by the physiological model.

[0111] During step 130 of this estimation and determination process 100, the objective fatigue determination system 16 implements a method 200 for determining the objective fatigue level. This method 200 is based on the two estimates determined during steps 110 and 120. During step 210 of this determination process 200, the objective fatigue determination system 16 acquires, via its acquisition module 22, the first fatigue estimate determined during step 110.

[0112] During step 220, which can be implemented following step 210 or in parallel with this step 220, the acquisition module 22 acquires the second estimate determined during step 120.

[0113] In the next step 230, the processing module 24 processes the received estimates in order to determine an objective fatigue level.

[0114] To this end, according to certain embodiments, the processing module 24 can first normalize the received estimates. This may be the case, for example, when the biomathematical and physiological models do not use the same scale for determining fatigue.

[0115] Then, the processing module 24 merges the received estimates.

[0116] This fusion is, for example, carried out by recalibrating the first estimate of fatigue as measured by the second fatigue assessment.

[0117] Preferably, the registration is done using an optimal filter such as a Kalman filter or a particle filter.

[0118] According to one embodiment, the optimal filter is a Kalman filter.

[0119] The Kalman filter first calculates an initial weighting for a time T from the first fatigue estimate acquired for a previous time TL. The initial weighting corresponds to the uncertainty of the first fatigue estimate.

[0120] Next, the Kalman filter predicts a first theoretical fatigue estimate for time T from the initial weighting for time T, the first fatigue estimate acquired for the previous time T1 and a theoretical fatigue evolution function.

[0121] The theoretical fatigue evolution function is used to estimate the evolution of the initial fatigue estimate over time. For example, the theoretical fatigue evolution function corresponds to a piecewise linear function according to the operator's sleep or wake phases.

[0122] Alternatively, the theoretical evolution function of the fatigue of the Kalman filter corresponds to a more complex function depending on the data relating to the schedule of a crew which includes the operator such as the duration of the mission, or the time of the mission carried out during the night.

[0123] The theoretical fatigue evolution model of the Kalman filter is, for example, modeled according to the following equation:

[0124] XbioT = f( ) +WT

[0125] where

[0126] xbioj-ï corresponds to the first fatigue estimate at the time preceding Tl;

[0127] xbio:i: corresponds to the first theoretical fatigue estimate at time T;

[0128] f corresponds to the theoretical fatigue evolution function; and

[0129] wt corresponds to the initial weighting at time T.

[0130] The Kalman filter subsequently modifies the initial weighting based on a conditional probability of the second fatigue estimate acquired for the previous time Tl knowing the first theoretical fatigue estimate for the previous time Tl.

[0131] Finally, the Kalman filter estimates an objective fatigue level for time T from the initial weighting for time T modified and the first theoretical fatigue estimate for time T.

[0132] Alternatively, the optimal filter is a particle filter.

[0133] The process with the particle filter first generates a set of particles. Each particle includes a first fatigue estimate acquired for a previous instant Tl and a previously undefined initial weighting associated with the first fatigue estimate.

[0134] The process with the particle filter has steps partly similar to the Kalman filter. Thus, the process with the particle filter implements the calculation, prediction, and modification steps of the Kalman filter as described above.

[0135] Following the modification, the process with the particle filter performs, for example, the step of resizing the particle set, retaining certain particles based on their modified initial weights. Resizing allows, for example, the creation of a modified particle set with fewer particles than the original set, where particles with higher weights are more likely to be selected.

[0136] The calculation, prediction, modification and estimation steps are implemented for each of the particles.

[0137] In such a case, the implementation of the optimal filter further includes a substep of estimating a resulting objective fatigue level from a weighted average of the fatigue level estimates for the different particles. It is this resulting objective fatigue level that is subsequently considered the objective fatigue level determined by the determination process 200.

[0138] Alternatively, the fusion is performed by machine learning on the data used by the biomathematical model 12 applied to new cases of the fatigue prediction system 14.

[0139] Preferably, the fusion is performed by a supervised learning algorithm capable of extracting a supervised set of signature(s) related to the objective fatigue level from the two fatigue estimates, a model of the supervised learning algorithm being chosen from the group consisting of: neural networks, logistic regression, support vector machine, and k nearest neighbors method.

[0140] For example, the supervised learning method is a symbolic learning method based on the initial knowledge of the biomathematical model. The initial knowledge is constantly evolving since new rules can be added to the initial knowledge while maintaining consistency with the initial knowledge and generalizing the learned knowledge. For example, the type of symbolic learning is learning by detecting similarities from examples and counterexamples. For example, the type of symbolic learning is learning by searching for explanations from examples and counterexamples.

[0141] According to another example, the learning method is numerical learning. For example, the type of numerical learning is carried out via one or more statistical models.

[0142] Alternatively, the fusion is performed by an unsupervised learning algorithm capable of extracting an unsupervised set of signature(s) related to the objective fatigue level from the two fatigue estimates, a model of the unsupervised learning algorithm being chosen from the group consisting of: hierarchical clustering, K-means partitioning, self-organizing maps, and Gaussian mixing.

[0143] According to some examples, the determination process 200 further includes an optional step in which the processing module 24 identifies a set of risk factor(s) associated with the objective fatigue level.

[0144] During step 240 of the determination process 200, the processing module 24 transmits to the output module 26 the determined objective fatigue level, possibly accompanied by associated risk factors.

[0145] The output module 26 then transmits this data to any interested system. Such a system may, for example, include a display, a database, and / or a remote server. In some examples, the objective fatigue level and possibly risk factors may also be communicated to the operator.

[0146] It is therefore conceivable that the present invention has a number of advantages. In particular, the invention makes it possible to determine the objective fatigue level objectively and precisely. Thus, independently of the database or databases used to determine a first estimate of fatigue and independently of the sensors 20 used to determine a second estimate of fatigue, the invention makes it possible to determine an objective level of fatigue which is standardized and therefore comparable among several operators and to subsequently identify all the risk factors associated with the objective level of fatigue.

[0147] Supervised learning makes it possible to further improve the accuracy of the objective fatigue level due to considerable experience merging the two estimates.

[0148] Unsupervised learning makes it possible to improve the computational speed by merging the two estimates.

[0149] The use of an optimal filter also allows for control over the merging of estimates. When the optimal filter is a particle filter, the determined objective fatigue level is particularly accurate. The Kalman filter allows for obtaining a good approximation more quickly by simplifying the calculation steps.

Claims

1.

2.

3.

4.

5. Demands Method for determining (200) an objective fatigue level of an operator performing a mission, the method comprising the following steps: - acquisition (210) of a first estimate of fatigue determined by a biomathematical fatigue prediction model from a plurality of mission data relating to the mission; - acquisition (220) of a second fatigue estimate determined by a physiological fatigue prediction model from the operator's physiological data; and - determination (230) of an objective fatigue level by merging the two fatigue estimates. Method (200) according to claim 1, wherein the fusion is carried out by recalibrating the first fatigue estimate by the second fatigue estimate. Method (200) according to claim 2, wherein the calibration is done using an optimal filter. Method (200) according to claim 3, wherein the optimal filter is a Kalman filter and / or a particle filter. Method (200) according to claim 4, wherein the implementation of the optimal filter comprises the following substeps: - calculation of an initial weighting for a time T from the first fatigue estimate acquired for a previous time Tl, the initial weighting corresponding to the uncertainty of the first fatigue estimate; - prediction of a first theoretical fatigue estimate for time T from the initial weighting for time T, the first fatigue estimate acquired for the previous time T1 and a theoretical fatigue evolution function; - modification of the initial weighting based on a conditional probability of the second fatigue estimate acquired for time T, given the first theoretical fatigue estimate for time T; and - estimation of an objective fatigue level for time T from the initial weighting for time T modified and the first theoretical fatigue estimate for time T.

6. Method (200) according to claim 5, wherein the implementation of the optimal filter further comprises a substep of generating a set of particles, each particle having a first estimate of fatigue acquired for a previous instant Tl and a previously undefined initial weighting associated with the first estimate of fatigue; said calculation, prediction, modification and estimation substeps being implemented for each of the particles; the implementation of the optimal filter further comprising a substep of estimating an objective fatigue level resulting from a weighted average of the estimates of the fatigue level for the different particles.

7. Method (200) according to claim 1, wherein the fusion is performed by a supervised learning algorithm capable of extracting a supervised set of signature(s) related to the objective fatigue level from the two fatigue estimates, a model of the supervised learning algorithm being chosen from the group consisting of: neural networks, logistic regression, support vector machine, and k nearest neighbors method.

8. Method (200) according to claim 1, wherein the fusion is performed by an unsupervised learning algorithm capable of extracting an unsupervised set of signature(s) related to the objective fatigue level from the two fatigue estimates, a model of the unsupervised learning algorithm being chosen from the group consisting of: hierarchical clustering, K-means partitioning, self-organizing maps, and Gaussian mixing.

9. A method (200) according to any one of the preceding claims, wherein the biomathematical model is constructed from subjective and / or statistical data relating to a plurality of individuals.

10. A method (200) according to any one of the preceding claims, wherein the operator's mission is piloting an aircraft and wherein the plurality of mission data includes at least one type of data selected from the group comprising: - data relating to the scheduling of a crew of which the operator is a part; - data relating to the configuration of an airline.

11. A method (200) according to any one of the preceding claims, wherein the physiological data includes at least one type of data selected from the group comprising: - operator images; - heart rate; - blood pressure; - oxygen inspiration; - sweating; - oxygen saturation; - dehydration rate.

12. A method (200) according to any one of the preceding claims, wherein the operator's physiological data are measured during the mission.

13. System for determining (16) an objective fatigue level comprising technical means configured to implement the method according to any one of the preceding claims.

14. Method for estimating and determining (100) an operator's fatigue level, comprising the following steps: - determining (110) a first fatigue estimate determined by a biomathematical fatigue prediction model from a plurality of mission data relating to the mission; - determining (120) a second fatigue estimate determined by a physiological fatigue prediction model from the operator's physiological data; - implementing (130) the determination method (200) according to any one of claims 1 to 12.

Images