Method for processing a one-dimensional signal, and corresponding device and program

Abstract

The invention relates to a method and device for characterizing an event occurring within a space comprising an apparatus for receiving WLAN signals, the method being implemented by an electronic processing device. A method of this type comprises: - a step (P_1) of normalizing the input data which aims to reduce the resolution of a plurality of sequences of WLAN signals received by the receiving apparatus, delivering a plurality of compressed sequences; and - a step (P_2) of processing the plurality of compressed sequences by means of an echo state network comprising a predetermined number N of nodes, delivering a probability of each compressed sequence belonging to one class from among a predetermined set of event classes.

Description

Description Title of the invention: one-dimensional signal processing method, device and corresponding program. Technical field

[0001] The disclosure relates to the field of detecting presence and / or movement within an environment. More particularly, the disclosure relates to the field of detecting the presence of moving objects and / or people using existing and / or inexpensive to install equipment. In a particular operating context, the disclosure is implemented from a wireless home communication network, in particular of the Wi-Fi type for example within a home. 1. Prior art

[0002] For many years, keeping vulnerable people at home and monitoring events occurring within their homes has been a major concern for both institutional and industrial stakeholders. This concern stems not only from the increasing cost of housing vulnerable people in specialized institutions, but also from the desire, often for these same people, not to be uprooted from their homes. However, keeping vulnerable people at home is not without its problems, particularly safety issues: vulnerable people, alone at home, are frequently victims of domestic accidents. Solutions have been proposed to prevent or intervene as much as possible in such situations.For example, medallions are available to be worn by the elderly, allowing them to press an emergency button in the event of an accident, which triggers one or more phone calls or transmissions to a monitoring center. Some medallions also offer fall detection functions and can be triggered autonomously. Similarly, new smartphones and smartwatches also have similar functions.

[0003] These devices, although effective, pose a problem in that they must be worn and have sufficient battery life to operate. Thus, other solutions, not requiring a wearable device, have been developed. Among these solutions is the one described in patent application WO2020037313, in which a Wi-Fi network and signals exchanged between Wi-Fi devices in the network are used. More particularly, a system is described comprising multiple Wi-Fi-enabled devices, arranged in an environment and configured to be a transmitter or a receiver for transmitting or receiving data over a Wi-Fi radio frequency communication link. A remote server is configured to receive and analyze the channel state information data transmitted by the receiver, store the channel state information (CSI) data with a corresponding adequate (human presence) label collected for training, train a (human presence) identification classifier using a Convex Clustered Concurrent Shapelet Learning (C3SL) method, and estimate a presence of a user based on the CSI data and the C3SL method. The server is configured to receive and analyze the CSI data transmitted by the receiver, in order to assign a corresponding gesture label and estimate and identify the gesture performed by the user using a trained target encoder and source classifier.

[0004] This solution offers the aforementioned advantage of not requiring additional devices to detect user gestures within a home. This solution, however, suffers from several problems, including the need for a server device processing the Channel Information State (CSI) data, which processes this data remotely. In addition, the described technique implements a complex neural network, which requires significant resources to perform a fine classification of the movements made by the user. 1. Summary of the invention

[0005] The disclosure was designed with these disadvantages of the prior art in mind.

[0006] The disclosure relates more particularly to a one-dimensional signal processing methodology, making it possible to detect the presence or movements made by users. More particularly, the disclosure relates to a method for characterizing an event occurring within a space comprising WLAN signal reception equipment, a method implemented by an electronic processing device. Such a method comprises: - a step of normalizing the input data aimed at reducing the resolution of a plurality of WLAN signal sequences received by said receiving equipment, delivering a plurality of compressed sequences; and - a step of processing the plurality of compressed sequences by an echo state network comprising a predetermined number N of nodes, delivering a probability of belonging of each compressed sequence to a class among a predetermined set of event classes.

[0007] This makes it possible to quickly determine, with little available computing power, the presence or movements made by a user.

[0008] According to a particular characteristic, the step of normalizing the input data for reducing the resolution of the plurality of received WLAN signal sequences, comprises: - a step of obtaining the plurality of signal sequences, each signal sequence comprising a [one-dimensional] signal amplitude variation over time; - a step of compressing each signal sequence of the plurality of signal sequences, in which a sub-sampling of each signal sequence is carried out, so that the number of samples of each resulting compressed sequence is equal to a predetermined number K.

[0009] According to a particular characteristic, the step of compressing each signal sequence of the plurality of signal sequences comprises, for a current signal sequence: - a step of re-encoding the current sequence with reduced precision, delivering a re-encoded sequence; - a step of filtering the re-encoded sequence by a low-pass linear filter, with an upper limit cut-off frequency of 24Hz, delivering a filtered time sequence; - a step of resizing the filtered time sequence to obtain a series of zero mean with values ​​included in the interval [-1, +1]; - a step of padding the resized sequence to produce a sequence of a predetermined length; - a sub-sampling step to the predetermined number K of samples by averaging the values ​​of said padded sequence over a number of intervals corresponding to the number K of samples.

[0010] According to a particular characteristic, the step of processing the plurality of compressed sequences by an echo state network comprises a step of optimizing a predetermined number X of output weights of a predetermined number N of nodes of the echo state network so that each input signal sequence can be assigned to a predetermined event class among the predetermined set of event classes.

[0011] According to a particular characteristic, the step of optimizing the predetermined number X of output weights of the echo state network comprises a step of calculating a linear regression.

[0012] According to a particular characteristic, the step of calculating a linear regression includes: - a step of concatenating a predetermined number of states of the echo state network which are selected from among the K states of the echo state network, delivering a concatenated state; - a step of calculating a linear regression to adjust the output weights of the echo state network according to the concatenated state.

[0013] According to a particular characteristic, the number N of nodes in the echo state network is between 25 and 250.

[0014] According to a particular characteristic, the number of samples K of each sequence is between 10 and 25.

[0015] According to another aspect, the invention also relates to an electronic device for characterizing an event occurring within a space comprising WLAN signal reception equipment. Such a device comprises: - means for reducing the resolution of a plurality of WLAN signal sequences received by said receiving equipment, delivering compressed sequences; and - means for processing the compressed sequences by an echo state network comprising a predetermined number N of nodes, delivering a probability of belonging of each compressed sequence to a class among a predetermined set of event classes.

[0016] According to a preferred implementation, the different steps of the methods according to the present disclosure are implemented by one or more software or computer programs, comprising software instructions intended to be executed by a data processor of an electronic execution device according to the present technique and being designed to control the execution of the different steps of the methods, implemented at the level of an electronic processing device or even communication equipment, for example of the router or "box" type, within the framework of a distribution of the processing to be carried out and determined by a scripted source code or a compiled code.

[0017] Accordingly, the present technique also relates to programs, capable of being executed by a computer or by a data processor, these programs comprising instructions for controlling the execution of the steps of the methods as mentioned above.

[0018] A program may use any programming language, and may be in the form of source code, object code, or code intermediate between source code and object code, such as in a partially compiled form, or in any other desirable form.

[0019] The present technique also aims at an information medium readable by a data processor, and comprising instructions of a program as mentioned above.

[0020] The information carrier can be any entity or terminal capable of store the program. For example, the medium may include a storage medium, such as a ROM, for example a CD-ROM or a microelectronic circuit ROM, or a magnetic recording medium, for example a mobile medium (memory card) or a hard disk or an SSD.

[0021] Furthermore, the information carrier may be a transmissible medium such as an electrical or optical signal, which may be conveyed via an electrical or optical cable, by radio or by other means. The program according to the present technique may in particular be downloaded over a network such as the Internet.

[0022] Alternatively, the information carrier may be an integrated circuit in which the program is incorporated, the circuit being adapted to perform or to be used in the performance of the method in question.

[0023] According to one embodiment, the present technique is implemented by means of software and / or hardware components. In this regard, the term "module" may correspond in this document to a software component, a hardware component or a set of hardware and software components.

[0024] A software component corresponds to one or more computer programs, one or more sub-programs of a program, or more generally to any element of a program or software capable of implementing a function or a set of functions, as described below for the module concerned. Such a software component is executed by a data processor of a physical entity (terminal, server, gateway, set-top-box, router, etc.) and is likely to access the hardware resources of this physical entity (memories, recording media, communication buses, electronic input / output cards, user interfaces, etc.).

[0025] Similarly, a hardware component is any element of a hardware assembly capable of implementing a function or set of functions, as described below for the module concerned. It may be a programmable hardware component or one with an integrated processor for running software, for example an integrated circuit, a smart card, a memory card, an electronic card for running firmware, etc.

[0026] Each component of the system described above of course implements its own software modules.

[0027] The different embodiments mentioned above can be combined with each other for the implementation of the present technique. 1. Brief description of the drawings

[0028] Other aims, characteristics and advantages of the invention will appear more clearly on reading the following description, given as a simple illustrative, and non-limiting, example, in relation to the figures, among which:

[0029] - [Fig.1] represents the characterization process according to the present;

[0030] - [Fig.2] explains the process implemented in more detail;

[0031] - [Fig.3] diagrams an echo state network implemented within the framework of the present;

[0032] - [Fig.4] represents a simplified physical architecture of an electronic device suitable for carrying out the method described. 1. Detailed description 1. Reminder of the principle

[0033] As previously stated, the disclosure is distinguished from the prior art by the frugality of the resources used to perform the classification of user movements.

[0034] More particularly, in relation to [Fig.l], the disclosure relates to a method for characterizing an event occurring within a space (such as a room, a set of communicating rooms, a hospital, an accommodation establishment or even a home) comprising at least one piece of WLAN (Wireless Local Area Network) signal reception equipment, for example Wi-Fi. The method is implemented by an electronic processing device (which may be the Wi-Fi signal reception equipment itself). The method comprises: - a step of normalizing the input data aiming at reducing the resolution (P_l), of a plurality of sequences (Sig_B) of WLAN signals received by said reception equipment (Eqpt), delivering a plurality of compressed sequences (Sig_T); and - a step of processing (P_2) the plurality of compressed sequences (Sig_T) by an echo state network (REE) comprising a predetermined number N of nodes, delivering a membership probability (PA_si g _r) of each compressed sequence (Sig_T) to a class among a set of predetermined event classes (for example “lie down”, “fall”, “walk”, “run”, “sit”, “get up” but also “enter”, “exit”, “open a door”, “close a door”, “open a window”, “close a window”, etc.).

[0035] The characterization method comprises two implementation modes: a learning mode and a usage mode. The learning mode consists of determining operating parameters of the echo-state network and the usage mode consists of implementing the method with a configured echo-state network.

[0036] More particularly, in learning mode, the method implements the step of normalizing the signal data and the processing step which comprises the supervised learning of the normalized data using an echo state network, this processing making it possible to fix the parameters of the echo state network. In learning mode of use, the characterization method also makes it possible to carry out the classification, by implementing a signal data normalization step, similar to the signal data normalization step of the learning mode and a normalized data classification step, using the echo state network configured during an implementation of the method in learning mode.

[0037] More particularly, compared to the prior art, the characterization method comprises a step of normalizing the received signal data. This step delivers, for an input amplitude time sequence, a normalized amplitude time sequence. The characterization method also comprises a classification step, which, from a normalized amplitude time sequence, delivers a classification of the sequence. In the learning mode, this classification is adjusted, as explained below. This classification is in the form of at least one probability of the normalized time sequence belonging to a given class of movements. The network used is an “Echo State Network” (REE) type network, comprising a reduced number of neurons.According to the present invention, the combination of the normalization step, which leads to a significant simplification (similar to a destructive compression) of the input signals, associated with the implementation of the echo state network makes it possible to meet the requirements of reducing resource consumption while guaranteeing a result (i.e. confidence in the classification) superior to those obtained by the technique of the prior art, in particular thanks to the simplicity of the learning step.

[0038] In use mode, the characterization method comprises the step of normalizing the received signal data (these data being obviously different from the data that were used for the parameterization of the echo state network). The normalized data are then provided to the echo state network which performs the classification of the normalized data.

[0039] The classification step delivers, from one or more input time sequences, a classification of the sequence(s). This classification is presented in the form of at least one probability of belonging of the normalized time sequence to a given class of events corresponding to movements.

[0040] In the implemented configuration, for the intended application, the sequence is classified among an established list of movements (lying down, falling, walking, running, sitting down, standing up). Certain classes can be associated with the triggering of security alerts (such as for example "falling") to a monitoring program, also installed on one of the "WLAN" devices of the home or accommodation.

[0041] Thus, the proposed technique has many advantages: - It is non-invasive and non-intrusive; - It does not require wearing a particular object or sensor; - It is not very sensitive to obstacles and is not limited to a direct line of sight, as with a camera; - It is not very sensitive to variations in light and works day and night; - When executed locally, for example on home Wi-Fi equipment (e.g. a Box), it does not reveal the identity of the actors and respects privacy (GDPR); - It has a low installation cost and has a lower environmental impact because it uses existing WLAN devices and does not require additional hardware; and - It has low energy consumption in operation due to the absence of running a large network, the absence of transmitting large volumes of data over a communication network and the (destructive) compression carried out on the input signal, which is then greatly simplified.

[0042] In relation to [Fig.2], we present the different learning steps for the configuration of the echo state network (REE). As part of the presentation of these steps, a particular example of a signal is illustrated. The raw signal (Sig_B) represented here comes from the reception on 3 antennas (in light gray, dark gray, and black) of a WLAN device and corresponds to a disturbance induced by a person walking collected on each of the antennas. The raw signal is therefore partitioned into 3 signals: the Sig_B signal 1 (in light gray) corresponds to the reception of the disturbance on the first antenna, the Sig_B2 signal (in dark gray) corresponds to the reception of the disturbance on the second antenna, the signal_B3 corresponds to the reception of the disturbance on the third antenna.At the end of the normalization step, (P_l), each resulting signal (Sig_Tl, Sig_T2, Sig_T3) is normalized over K intervals, which results in the production of K samples (el, e2, e3, ..., eK) per signal (so here Kx3) to be injected into the echo state network (REE) with N nodes (N = 7 in the figure, to simplify the illustration) during the processing step (P_2). In a realistic configuration, for an example of this type, N is between 25 and 250 and the number of sequences to be processed is obviously much larger. At the end of this processing step, we therefore have K samples (per signal). For greater readability, only Sig_Tl is shown.

[0043] Thus, at the end of the processing step (P2) of the first sample (el), we have a first state (#1). Then at the end of the second sample (e2), we have a second state (#2), and so on until the injection of the last sample (eK) which delivers the last state (#K). As illustrated schematically, each sample produces a reservoir state (column vector of size N x 1 containing the states of the N nodes of the network), and the K states are collected at the end of the processing (we then have K states for each portion of the signal in light gray, dark gray, and original black).

[0044] In learning mode, the echo state network is then optimized (P_4) so ​​that it can provide a probability of the signal portion belonging to a given class. According to the invention, this optimization is performed on the output layer of the network only, and not on its internal connections. This optimization is performed by performing a linear regression on all the output weights, so that the final (supervised) classification is obtained based on the different states of the reservoir. The echo state network has a temporal memory of the samples supplied to it so that learning is performed by memorizing the class of the different samples successively transmitted to it until a classification is obtained based on the succession of samples injected.

[0045] In order to obtain better classification results (e.g. for training and learning the echo state network), one can (optionally) proceed to the concatenation (P_3) of different states of the reservoir in order to increase its memory capacity and classification of events. The number and indices of the states [#1,... ,#K] chosen for the concatenation are determined according to the conditions (e.g. depending on the signature of the signal and the capacity of the echo state network to classify the samples alone, as explained later). In the example of [Eig.2], the combinations of 1, 2 and 3 states are illustrated. In such a situation, the optimization of the output weights is performed on the concatenation of the states and not on a single state.This way of proceeding makes it possible, as will be developed later, to avoid a phenomenon of forgetting which can be generated depending on the initial configurations chosen for the echo state network.

[0046] Thus, the inventors used WLAN signals to detect a change in the situation in a particular environment. The room in which the tests were conducted included a WLAN signal transmitter and suitable receivers. When these devices exchange packets, the electromagnetic waves are reflected and the bounces of these electromagnetic waves are multiple in the room. The receiver therefore does not receive just one wave but a combination of signals reflected in the room in multiple ways. If an object moves in the room, the final combination of these bounces changes and this change can be detected. In the implemented configuration, the transmitting equipment was equipped with three antennas and transmitted at a frequency of 2.4 GHz, each antenna having 30 channels. Thus, up to 90 time traces (raw signals) were collected for training the system.The number of channels specified here is specific to recordings made in this confi-. guration. In real conditions, this number may vary depending on the band chosen and the equipment available. 1. Description of an embodiment

[0047] This example presents an embodiment that the inventors have implemented for the implementation of the characterization method, in learning mode, as previously explained. The method implements the following steps: - a normalization step (P_l) of the input data including: - a step of receiving, from a signal data reception module, time sequences comprising data representative of the state of the channel (CSI), comprising a variation in the amplitude of the signal over time; - a data compression step, including, for each time sequence: • A sub-step of reducing the size of the time sequence: the sequence is re-encoded with single precision (32 bits), delivering a re-encoded time sequence; • A sub-step of filtering the re-encoded time sequence by a low-pass linear filter, for example of the “Butterworth” type of order 4, with an upper limit cut-off frequency of 24Hz: this smoothing makes it possible to eliminate electromagnetic noise; In practice, the cut-off frequency is more frequently between 10 and 15Hz. • A sub-step of resizing the filtered time sequence to obtain a series of zero average with values ​​included in the interval [-1, +1]: this operation makes it possible to average the signals and to relativize the amplitudes in order to obtain equal data from each channel, for all the sequences; the channels are considered as equivalent for the processing carried out; • A padding sub-step: each sequence is either cut or lengthened to have a homogeneous data size (for example 10 thousand or 20 thousand samples per sequence). • An averaging sub-step (downsampling): each sequence is downsampled to a pre-number determined number of samples (e.g. 10 to 100 samples depending on the averaging parameter) by averaging over a number of intervals corresponding to the number of samples. More specifically, for the intended application, the number of samples is between 5 and 100, more specifically between 10 and 25. - A processing step (P_2) comprising the supervised learning (i.e. optimization) (P_4) of the sequences within the echo state network, comprising a predetermined (and reduced) number of nodes. More specifically, for the intended application, the number of nodes is between 25 and 250 nodes, depending on the fineness of the movements to be recognized. A number of nodes equal to 50 is sufficient, in practice, to classify the signals according to the six classes mentioned previously (“lie down”, “fall”, “walk”, “run”, “sit”, “stand up”). This is a compromise between the fineness of recognition of the event and the resulting computational load.

[0048] The inventors determined that gesture recognition must exploit the natural dynamics of a dynamic system trained for computation and that an echo-state network is suited to this problem. Thus, the combination of judicious normalization of input signals and an echo-state network capturing and memorizing the dynamics of the signals provides a combination that can solve the problems posed by prior techniques.

[0049] Echo state networks are very different from most physical systems. First, they operate in discrete time. Furthermore, they are usually fully connected, which is not possible for most physical systems. However, using such a network alone is not in itself a recipe for success, as it only works well if there is a good match between the system dynamics and what is expected for a given task. Thus, the data normalization step, in the intended application, has the function of simplifying the capture of signal dynamics by eliminating non-representative disturbances. The number of samples retained after normalization varies depending on the fineness of motion recognition performed, as does the number of nodes in the echo state network.

[0050] An echo-state network used herein is schematically illustrated in [Fig.3]. It is a network of nodes in which the input signal is connected to a fixed (i.e., non-trainable) and random dynamic system, called the reservoir, thus creating a higher-dimensional representation (embedding).

[0051] To be more precise, the node network is shallow and consists of three layers: - An input layer (Lin); - A hidden internal layer (Tk), called the reservoir; - And an output layer (LO).

[0052] At initialization, the input nodes are connected to the reservoir and connection weights W are randomly generated. inp between the inlet layer and the reservoir.

[0053] The peculiarity of this network lies in the characteristic that the nodes of the reservoir are sparsely connected and the connections are assigned only once and are completely random. The weights W int of the tank are not trained and therefore not optimized.

[0054] To train the linear readout of the echo-state network, we calculate the output weights W out by solving a system of linear equations Y = W out X, where the state matrix X and the target matrix Y are constructed using, respectively, x(n) and the vector of target outputs y(n) as columns for each time (i.e. sample) t n .(n is between 1 and K):

[0055] Random weights: W inp , W int ;

[0056] Optimizable weights (and optimized during training): W out ;

[0057] Evolution equation:

[0059] Output layer delivering the reservoir states (column vector of size N x 1 containing the states of the N nodes of the network):

[0061] Connection weights W out between the reservoir and the output layer are optimized, during learning (at step P_4), based on a linear relationship (for example by calculating a linear regression). There are as many output weights as there are neurons (the diagram in [Eig.3] is thus simplified for greater readability).

[0062] Network optimization involves solving a linear optimization problem using efficient and robust algorithms such as linear regression algorithms. The calculations are simple and fast, without recurring iterations, and allow for finding an optimal value for the output weights given the desired classification.

[0063] The advantage of implementing an echo-state network is that the sparse random connections in the reservoir allow previous states to "echo" even after they have passed, so that when the network receives a new input (a signal sample from normalization) similar to something it has trained on, the dynamics in the reservoir follow the appropriate activation trajectory for the input and in this way can provide an output that matches what it has trained on, and when well trained, it can generalize from the signals it has already encountered, following activation trajectories that would make sense given the input signal driving the reservoir.

[0064] In the context of the invention and the standardization carried out on the input signal (which basically has too much information), the advantage is that the network does not require training on all the nodes to obtain good performance and is not very energy and computing power intensive.

[0065] More particularly, according to the present, the normalization of the amplitudes of the signals delivers a predetermined number K of samples (for example between 10 and 25).

[0066] Each sample (of the predetermined number K of samples) is injected into the network of nodes.

[0067] Then, for each of these samples, we capture the state of the system x ; at the output of the network (hidden internal layer). We therefore obtain K states of the system, or K SOI (“State Of Interest”) represented by the column matrices at the output of the reservoir.

[0068] The result y(n) is the class obtained by linear combination of a state x ; with the weights w out at the output layer according to the previous equation. The output weights are optimized by linear regression to assign the correct class to the input signal.

[0069] Before optimization, it is possible to perform a concatenation step (P_3) of the outputs of the echo state network: cleverly, the SOIs can be concatenated to improve the system memory. For example, one could concatenate the states x K and x K to reinforce the presence of the first captures in the “memory” of the reservoir (these first captures would possibly be “attenuated” at the time of the K èmecapture). Thus, by concatenating two output states, in the case where the node network comprises for example 50 nodes, we obtain a final state vector (column) (i.e. resulting from the concatenation) of 100x1 elements at the output layer (instead of 50x1 in the case of a single SOI) and we optimize 100 output weights instead of 50 during the linear regression.

[0070] To determine the optimal number of SOIs to combine, as well as the specific SOIs to use, an iterative determination process can optionally be implemented during training. In this process of determining the number of concatenations, the number of SOIs is first set to 1, and K simulations are performed.

[0071] In each independent simulation, the reservoir is initialized from the beginning, and the entire database of preprocessed input signal recordings is passed through it.

[0072] In the first simulation, we retain the first SOI Xj at the output layer (i.e. the state of the system after processing the first sample), we optimize the 50 reading weights (by linear regression) and we note the performance (classification accuracy) of the network.

[0073] In the second simulation, we use the SOI x2, train the output layer and note the performance. And so on up to K simulations, where we use x K for training. At the end of these K simulations, we retain the best performance and conclude that with a single SOI, the optimal choice is x ; which gives an accuracy of X%.

[0074] Then, we set the number of SOIs to two (concatenation of two SOIs), and we perform K*((Kl) / 2) simulations. In the first simulation, we combine the states x, and x2 in a 100x1 vector (still for a network of 50 nodes), we optimize 100 reading weights, and we note the performance. In the second simulation, we combine the states Xj and x3, and so on until the last simulation, where we combine the states x Ki and x K We retain the best performance of the K*((Kl) / 2) simulations and conclude on the best combination of 2 SOIs and the precision obtained.

[0075] This is done for three SOIs, then four SOIs, and so on. In practice, the inventors have determined that the performance level reaches a plateau, at which point adding more SOIs does not improve the final result. In the inventors' experience, concatenating NbConcat = 5 SOIs is sufficient to achieve optimal performance.

[0076] Concatenation increases the computational complexity of the training process, since the number of read weights increases linearly with concatenation: e.g., combining 2 reservoir states implies training 12N read weights instead of 6N (for the 6 binary output nodes and the N reservoir nodes). More specifically, the number of output nodes corresponds to the number of actions to be distinguished (in this case, 6: "lie down", "fall", "walk", "run", "sit", "stand up"). In this example, rather than determining one output node for X actions to be distinguished (and thus, training the system to produce the responses from 1 to X corresponding to each class), we define X binary output nodes, and train each of the nodes independently to produce 1 if the input matches its class, and 0 otherwise.In practice, output nodes produce real numbers between 0 and 1: each node gives a probability that the input matches its class, and the binary output node that produces the highest value is selected to assign the input's class. 1. Other features and benefits

[0077] In relation to [Fig. 3], a simplified architecture of an electronic processing device (TC) capable of carrying out all or part of the processing operations as presented previously is presented. An electronic processing device comprises a first electronic module comprising a memory 31, a processing unit 32 equipped for example with a microprocessor, and controlled by a computer program 33. The electronic processing device optionally comprises, for func- security features, such as anonymization of signal data or states from these signals, a second electronic module comprising a secure memory 34, which can be merged with the memory 31 (as indicated by dotted lines, in this case the memory 31 is a secure memory), a secure processing unit 35 equipped for example with a secure microprocessor and physical protection measures (physical protection around the chip, by lattice, vias, etc. and protection on the data transmission interfaces), and controlled by a computer program 36 specifically dedicated to this secure processing unit 35, this computer program 36 implementing all or part of the characterization method as previously described. The group composed of the secure processing unit 35, the secure memory 34 and the dedicated computer program 36 constitutes the secure module (PS) of the electronic processing device.In at least one embodiment, the present technique is implemented in the form of a set of programs installed in part or in full on this secure portion of the electronic processing device. In at least one other embodiment, the present technique is implemented in the form of a dedicated component (CpX) capable of processing data from the processing units and installed in part or in full on the secure portion of the electronic processing device. Furthermore, the device also comprises communication means (CIE) presented for example in the form of network components (Wlan, Wi-Fi, 3G / 4G / 5G, wired) which allow the device to receive data (I) from entities connected to one or more communication networks and to transmit processed data (T) to such entities.

[0078] Such a device comprises, depending on the embodiments, the means previously described: - means of obtaining data representative of a signal; and in particular: - means for obtaining signal amplitude variation data as previously described; - means of standardizing the data representative of this signal; - means of processing standardized data; and - means for optimizing the output weights of an echo state network, these means being implemented when learning the membership classes of the signals supplied to the system; - means of transmission of the class retained for the data representative of the input signal.

[0079] As explained previously, these means are implemented through modules and / or components, for example secure ones. They thus make it possible to ensure the safety of the treatments carried out.

Claims

Claims

1. Method for characterizing an event occurring within a space comprising WLAN signal reception equipment, method implemented by an electronic processing device, method characterized in that it comprises: - a step of normalization (P_l) of the input data aiming at reducing the resolution of a plurality of WLAN signal sequences received by said reception equipment, delivering a plurality of compressed sequences; and - a step of processing (P_2) the plurality of compressed sequences by an echo state network comprising a predetermined number N of nodes, delivering a probability of belonging of each compressed sequence to a class among a predetermined set of event classes.

2. Characterization method according to claim 1, characterized in that the step of normalization (P_l) of the input data aiming at reducing the resolution of the plurality of sequences of WLAN signals received, comprises: - a step of obtaining the plurality of signal sequences, each signal sequence comprising a one-dimensional signal amplitude variation over time; - a step of compressing each signal sequence of the plurality of signal sequences, in which a sub-sampling of each signal sequence is carried out, so that the number of samples of each resulting compressed sequence is equal to a predetermined number K.

3. Characterization method according to claim 2, characterized in that the step of compressing each signal sequence of the plurality of signal sequences comprises, for a current signal sequence: - a step of re-encoding the current sequence with reduced precision, delivering a re-encoded sequence; - a step of filtering the re-encoded sequence by a low-pass linear filter, with an upper limit cut-off frequency of 24Hz, delivering a filtered time sequence; - a step of resizing the filtered time sequence to obtain a series of zero mean with values ​​included in the interval [-1, +1]; - a step of padding the resized sequence to produce a sequence of a predetermined length; - a sub-sampling step to the predetermined number K of samples by averaging the values ​​of said padded sequence over a number of intervals corresponding to the number K of samples.

4. Method for characterizing an event according to claim 1, characterized in that the step of processing (P_2) the plurality of sequences compressed by an echo state network comprises a step of optimizing a predetermined number X of output weights of a predetermined number N of nodes of the echo state network so that each input signal sequence can be assigned to a predetermined event class among the predetermined set of event classes.

5. Method for characterizing an event according to claim 4 characterized in that the step of optimizing the predetermined number X of weights of outputs of the echo state network comprises a step of calculating a linear regression.

6. Characterization method according to claim 5, characterized in that the step of calculating a linear regression comprises: - a step of concatenating a predetermined number of states of the echo state network which are selected from among the K states of the echo state network, delivering a concatenated state; - a step of calculating a linear regression to adjust the output weights of the echo state network according to the concatenated state.

7. Method according to claim 1, characterized in that the number N of nodes of the echo state network is between 25 and 250.

8. Method according to claim 2, characterized in that the number of samples K of each sequence is between 10 and 25.

9. Electronic device for characterizing an event occurring at within a space comprising WLAN signal reception equipment, device characterized in that it comprises: - means for reducing the resolution of a plurality of WLAN signal sequences received by said receiving equipment, delivering compressed sequences; and - means for processing the compressed sequences by an echo state network comprising a predetermined number N of nodes, delivering a probability of belonging of each compressed sequence to a class among a predetermined set of event classes.

10. Computer program product downloadable from a communications network and / or stored on a computer-readable medium and / or executable by a microprocessor, characterized in that it comprises program code instructions for executing a method according to any one of claims 1 to 8 when executed by a computer.

Images