Cross-domain WiFi personnel identity recognition method based on multi-branch domain alignment model

Abstract

The method is suitable for the technical field of personnel identity recognition. The invention discloses a cross-domain WiFi personnel identity recognition method based on a multi-branch domain alignment model, and the method comprises the steps: building a multi-branch domain alignment DDA model, carrying out the monitoring of the loss of the multi-branch domain alignment model through a loss function, enabling a domain specific classifier to accurately recognize different gait features, and carrying out the recognition of the multi-branch domain alignment DDA model. According to the method, the whole source domain is segmented into two or more groups, each group of source domain is aligned with the target domain, and the distance between the source domain and the target domain of each branch and the distance among the multiple branches are shortened through a series of loss functions, so that simultaneous migration adaptation of the multiple interference domains is realized. According to the invention, negative effects caused by multiple environmental factors which are superposed at the same time can be eliminated at the same time, the accuracy of WiFi human body identity recognition and the reliability of the system are improved, and the difficulty of migration to adapt to multiple interference domains is reduced.

Description

Technical Field

[0001] The present invention relates to network personnel identification, and in particular to a cross-domain WiFi personnel identification method based on a multi-branch domain alignment model. Background Art

[0002] When WiFi devices transmit radio frequency signals in the form of WiFi spectrum during communication, these signals will be reflected and diffracted by the human body in the area, and the fluctuations of the signals can be used to identify various human movements, such as hands, body or breathing. In real life scenarios, this recognition method can be applied to multiple fields, such as security monitoring systems, elderly motor function status monitoring, and smart home devices. Since each person's walking posture (referred to as "gait") is theoretically uniquely bound to biometrics. Some existing technologies attempt to use the channel state information (CSI, Channel State Information) corresponding to the human gait collected by WiFi devices to perform human identification (HI, Human Identification), which is suitable for personalized deployment in various sampling locations such as smart homes and offices. However, the real multi-path environment contains multiple interference factors, also known as domains. For example, the direction of the walking trajectory, the walking speed, the location of the WiFi device, etc. will cause the human gait signal to change, resulting in a decrease in the accuracy of human identity recognition. Existing technologies attempt to use transfer learning to eliminate the negative impact of a single interference domain, but cannot remove multiple types of interference domains at the same time. Summary of the invention

[0003] The main technical problem solved by the present invention is to provide a cross-domain WiFi personnel identification method based on a multi-branch domain alignment model. The cross-domain WiFi personnel identification method based on a multi-branch domain alignment model can avoid the reduction in human identity recognition accuracy caused by only eliminating a single interference domain, eliminate the negative impact of multiple interference domains, and improve the accuracy of human identity recognition.

[0004] In order to solve the above problems, the present invention provides a cross-domain WiFi personnel identity recognition method based on a multi-branch domain alignment model. The cross-domain WiFi personnel identity recognition method based on a multi-branch domain alignment model recognizes the identity of a person by analyzing the gait characteristics of the person, including: A series of loss functions are used to supervise the multi-branch domain alignment model series loss to align the distribution between the source domain and the target domain, so as to enable the domain-specific classifier to accurately identify different gait features. The domain adaptation loss function in the series of loss functions shortens the distance between the source domain and the target domain of each branch and the distance between multiple branches, so as to enable simultaneous migration and adaptation of multiple interference domains. The multi-branch domain alignment DDA model includes dividing the overall source domain into at least two groups, aligning each group of source domains with the target domain respectively, and the network model includes a shared feature extractor. and a feature extractor for the source domain for each group , learn the gait features in each group respectively, and align the embedding features of the target domain obtained by passing the features of the target domain through the network models corresponding to the sub-domains of the two source domains with the embedding features of the two sub-source domains.

[0005] In one embodiment, an MMD domain adaptation loss function is used to minimize the distance between two sets of source domains and target domains. The MMD domain adaptation loss function , in, and Represents two sets of data distribution and expectations, represents the reproducing kernel Hilbert space, which is equipped with a characteristic kernel function , used to measure the distance between sample pairs, function and Represents the feature map that transforms the original sample into the reproducing kernel Hilbert space, the kernel function is defined as the feature representation corresponding to the source samples and correspond to the feature representation of the target sample respectively The inner product between and Represent the WiFi data samples of the source domain and the target domain respectively.

[0006] In one embodiment, the series of loss functions includes domain adaptation loss , convergence loss and cross entropy loss .

[0007] In one embodiment, the domain adaptation loss : , Among them, and Represent the WiFi data samples of the source domain and the target domain respectively, represents the number of network branches, A simplified estimate of The MMD loss applied in the two branch networks of the DDA model helps to align the distribution between the source and target domains in each branch respectively. and Indicates that the source domain or target domain sample is extracted by the common feature extractor E, Represents the source domain grouping feature extractor The extracted features, represents the source domain, Indicates the target area, The range is from 1 to .

[0008] In one embodiment, the number of the network branches is 2, 3 or 4.

[0009] In one embodiment, the cross entropy loss function shown in the DDA model is For supervised classification learning, the cross entropy loss function : , in, Indicates the number of gait labels, represents the true category label of the sample, It refers to the SoftMax function operation. Represents a branch A classifier is used to convert the network output into a probability value The range is 1 to , The denotation parameter is the expectation of the source domain samples.

[0010] In one embodiment, the DDA model uses unlabeled samples from the target domain to bring multiple branches closer together, by converging the loss Help the model achieve a specific domain alignment of the two branches, the convergence loss : .

[0011] In one embodiment, the domain alignment loss function : ,

[0012] in, and Respectively and The importance weight of .

[0013] In one embodiment, in the early stage of training, the two weights are dynamically adjusted using a progressive strategy according to the formula , gradually changes from 0 to 1 as the training iteration proceeds, where It changes linearly during the training process. The value was empirically taken as 10 and remained constant throughout the experiment. Meaning is based on the exponent e .

[0014] The present invention discloses a cross-domain WiFi personnel identification method based on a multi-branch domain alignment model. The cross-domain WiFi personnel identification method adopts a multi-branch domain alignment (DDA, Divided Domain Adaptation) model and a series of loss functions to divide the overall source domain into two or more groups, and align each source domain with a target domain respectively. The series of series of loss functions shortens the distance between the source domain and the target domain of each branch and the distance between multiple branches, thereby realizing simultaneous migration adaptation of multiple interference domains. The method can simultaneously eliminate the negative effects brought about by multiple environmental factors that appear simultaneously, improve the accuracy of WiFi human identity identification and the reliability of the system, and reduce the difficulty of migration adaptation to multiple interference domains. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the description only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 It is a schematic diagram of the multi-branch domain alignment model of the present invention.

[0017] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0018] The claims of the present invention are further described in detail below in conjunction with specific embodiments and drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments proposed by ordinary technicians in this field before making creative work also fall within the scope of protection of the present invention.

[0019] It should be understood that, in the description of the embodiments of the present invention, all directional indication terms, such as "up", "down", "left", "right", "front", "back", etc., indicate the orientation or position relationship based on the orientation, position relationship shown in the drawings or the orientation or position relationship in which the invented product is usually placed when in use, which is only for the convenience of simplifying the description of the present invention, and does not expressly or imply that the device, element or component referred to must have a specific orientation and a specific orientation structure, and should not be understood as a limitation on the present invention. It is only used to explain the relative position relationship, movement, etc. between the components shown in the drawings. When the specific posture changes, the directional indication may also change accordingly.

[0020] In addition, ordinal numbers such as "first" and "second" in the present invention are only used for the purpose of distinction, and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. The features defined as "first" and "second" can expressly or implicitly indicate at least one of the technical features. In order to facilitate the description, the present invention may have quantifiers such as "one", "two", "multiple", "at least one" or "several" to define the technical (structural) features, where "multiple" means at least two, that is, two or more; "at least one" and "several" mean one or one and the corresponding technical features; quantifiers and other definitions are only for illustrating the specific embodiment or the best implementation method, and should be included as long as they are not contrary to the overall concept of the invention and the purpose of the invention, unless it is clearly stated that the quantifiers must be used to define them in order to be implemented or to achieve the purpose of the invention.

[0021] In the present invention, unless otherwise clearly stipulated and limited, the terms such as "installation", "setting", "connection", "fixation" and "screw-on" should be understood in a broad sense. For example, the positional relationship between components can be relatively fixed, or the components can be physically fixedly connected; they can be detachably connected or integrated; they can be mechanically connected or electrically connected; they can be directly connected or indirectly connected through an intermediate medium or component; they can be internally connected between two elements or interact with each other. Unless otherwise clearly defined in the specification, other interpretations may not achieve the corresponding functions or effects. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0022] The controller and control circuit involved in the present invention are conventional control technologies or units of those skilled in the art. For example, the control circuit of the controller can be realized by ordinary technicians in the field using existing technologies, such as simple programming. If the software or program involved in the control result is not described in detail, it belongs to the use of existing technologies or conventional technologies of ordinary technicians in the field. The power supply also uses the existing technologies in the field, and the main technical point of the present invention is to improve the mechanical device, so the present invention will not describe the specific circuit control relationship and circuit connection in detail.

[0023] The disclosure of the present invention provides many different embodiments or examples to realize different structures of the present invention. In order to simplify the disclosure of the present invention, the components and settings of specific examples are described in the present invention. Of course, they are only examples, and the purpose is not to limit the present invention. In addition, the present invention can repeat reference numbers and / or reference letters in different examples, and this repetition is for the purpose of simplicity and clarity, which itself does not indicate the relationship between the various embodiments and / or settings discussed. In addition, the present invention provides various specific examples of processes and materials, but those of ordinary skill in the art can be aware of the application of other processes and / or the use of other materials.

[0024] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0025] like Figure 1 As shown, the present invention provides an embodiment of a cross-domain WiFi personnel identity recognition method based on a multi-branch domain alignment model.

[0026] WiFi CSI (Channel State Information) human gait data can be divided into source domain data and target domain data. The source domain contains multiple interference domains, such as walking trajectory direction, walking speed, and WiFi device location; each interference domain contains multiple subdomains. The target domain contains multiple interference domains and a small number of subdomains. First, an unsupervised generative adversarial network model is used to learn the migration correspondence between the source domain and the target domain, and a feature extractor for WiFi CSI data is obtained. , the generative adversarial network model enables the feature extractor It has preliminary domain adaptation capabilities, but the generated adversarial network model is not sufficient to alleviate the negative impact of the coexistence of multiple heterogeneous domains, including source domains or target domains. As the backbone network, the multi-branch domain alignment (DDA, Divided Domain Adaptation) model is used to segment the source domain data and convert the source domain data into multiple subsets, namely sub-source domains. For example, it can be converted into two subsets and other more subdivided subdomains, and the two subdomains can be combined to form the entire source domain. For example, five different source domain receiver layout positions are arranged, and the data corresponding to the five different source domain receivers are divided into two clusters of data, one of which includes two subsets and the other includes three subsets.

[0027] The source domain CSI (Channel State Information) data is split into sub-source domains, namely source domain 1 and source domain 2, and the target domain CSI data is converted to target domain 1. Subsequently, the multi-branch domain alignment model, namely DDA (Divided Domain Adaptation, multi-branch domain alignment model) uses a pre-designed network model with the same structure and , network model and Feature extractor for a source domain branch Perform feature extraction, extract data features of specific branches, learn gait features in each sub-source domain respectively, and use the network model and The gait features in source domain 1 and source domain 2 are learned respectively, and the features of the target domain are respectively passed through the sub-domains of the two source domains, that is, the embedded features obtained by the network model corresponding to the sub-source domains are aligned and learned with the embedded features of the two sub-source domains. In this embodiment, different arrows represent the data processing process of different domains. In order to achieve domain adaptation, the MMD (Maximum Mean Discrepancy) domain adaptation loss is introduced to minimize the distance between the two sets of source domains and the target domain. The MMD domain adaptation loss is also referred to as MMD loss. The MMD domain adaptation loss function can be formally expressed as shown in formula (1): (1), in, and Respectively represent the distribution and expectations, represents the reproducing kernel Hilbert space, a mathematical basis for analyzing and manipulating data, which is equipped with a characteristic kernel function , used to measure the distance between sample pairs, function and Represents the feature map that transforms the original sample into the reproducing kernel Hilbert space. This function is defined as the feature representation corresponding to the source samples and correspond to the feature representation of the target sample respectively The inner product between and Represent the WiFi data samples of the source domain and the target domain respectively.

[0028] Specifically, the MMD loss applied in the two branch networks of the DDA model can be formally expressed as follows: (2), In formula (2), Indicates the number of network branches (the actual value is 2, 3 or 4), A simplified estimate of The MMD loss applied in the two branch networks of the DDA model helps to align the distribution between the source and target domains in each branch respectively. and Indicates that the source domain or target domain sample is extracted by the common feature extractor E, Represents the source domain grouping feature extractor The extracted features, s represents the source domain, Indicates the target area, ranges from 1 to N.

[0029] In order to make full use of the known label characteristics of source domain data, the DDA model uses the cross entropy loss function shown in formula (3) for supervised classification learning. Specifically, the cross entropy loss is formalized as follows: (3), In the formula, K represents the number of gait labels, that is, the category of gait features. represents the true category label of the sample, It refers to the SoftMax function operation. Represents a branch The classifier is used to convert the network output into a probability value. K represents the number of gait labels. The range is from 1 to K, The denotation parameter is the expectation of the source domain samples.

[0030] Since the two domain-specific classifiers, source and target, are trained on different sets of source domains, they may disagree on the prediction of target domain samples. The consistency between classifiers helps to eliminate the domain differences between branches and further improves the domain adaptation performance. To achieve this goal, a convergence loss is designed. To help the model achieve domain alignment of two specific branches. Specifically, the domain alignment model designed in this patent will calculate the absolute value between the probability outputs of two specific classifiers, using The loss is used to calculate the distance between different branches and the output results of the target domain data prediction, so as to shorten the distance between multiple branches and eliminate the differences between them. From the perspective of the overall network training logic, the DDA model uses unlabeled samples in the target domain to shorten the distance between multiple branches as a supervised convergence loss, and its definition is formally expressed as shown in (4).

[0031] (4).

[0032] The DDA model uses a series of loss functions to supervise the loss, including the domain adaptation loss function , convergence loss function and cross entropy loss , to align the distribution between the source and target domains, such as Figure 1 As shown, and the domain-specific classifier is prompted to accurately identify different gait features. The domain-specific classifier is referred to as the domain classifier or classifier for short, such as Figure 1 Classifier 1 and Classifier 2. Overall, domain alignment loss It can be summarized as formula (5): (5), in, and Respectively and The importance weight of .

[0033] In the early stages of training, these two weights are dynamically adjusted using a progressive strategy, according to the formula , that is, gradually changes from 0 to 1 as the training iteration proceeds, where It changes linearly during the training process. The value was empirically taken as 10 and remained constant throughout the experiment. Meaning is based on the exponent e After training, during testing on target domain data samples, the model uses the average prediction results of two or more classifiers, shown as the box "Average (Test)" in the figure, to predict data samples in the target domain.

[0034] The present invention provides a cross-domain WiFi personnel identification method based on a multi-branch domain alignment model, including establishing a multi-branch domain alignment model, i.e., a DDA model, and using a loss function to supervise the DDA model, so that a domain-specific classifier can accurately identify different gait features, divide the overall source domain into two or more groups, and align each source domain with the target domain respectively, and shorten the distance between the source domain and the target domain of each branch and the distance between multiple branches through a series of loss functions, so as to achieve simultaneous migration and adaptation of multiple interference domains. It can simultaneously eliminate the negative effects brought about by multiple environmental factors that appear simultaneously, improve the accuracy of WiFi human identity identification and the reliability of the system, and reduce the difficulty of migration and adaptation of multiple interference domains.

[0035] The multi-branch domain alignment model divides the overall source domain into two or more groups, and aligns each group of source domains with the target domain respectively, shortens the distance between the source domain and the target domain of each branch through a series of loss functions, and shortens the distance between multiple branches at the same time, thereby achieving simultaneous migration and adaptation of multiple interference domains.

[0036] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents, and these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A cross-domain WiFi personnel identification method based on a multi-branch domain alignment model, which recognizes the identity of a person through his or her gait characteristics, is characterized by: include, A series of loss functions are used to align the distribution between the source domain and the target domain in the multi-branch domain alignment DDA model, so as to encourage domain-specific classifiers to accurately identify different gait features. The domain adaptation loss function in the series of loss functions shortens the distance between the source domain and the target domain of each branch and the distance between multiple branches, so as to enable simultaneous migration and adaptation of multiple interference domains. The multi-branch domain alignment DDA model includes dividing the overall source domain into at least two groups, aligning each group of source domains with the target domain respectively, and the network model includes a common feature extractor and a feature extractor for the source domain of each group, learning the gait features in each group respectively, and aligning the embedded features of the target domain features obtained by passing the network models corresponding to the sub-domains of the two source domains with the embedded features of the two sub-source domains respectively.

2. According to claim 1, the cross-domain WiFi personnel identification method based on the multi-branch domain alignment model is characterized in that: The MMD domain adaptation loss function is used to minimize the distance between the two sets of source domains and the target domain. , in, and Represents two sets of data distribution and expectations, represents the reproducing kernel Hilbert space, which is equipped with a characteristic kernel function , used to measure the distance between sample pairs, function and Represents the feature map that transforms the original sample into the reproducing kernel Hilbert space, the kernel function is defined as the feature representation corresponding to the source samples and correspond to the feature representation of the target sample respectively The inner product between and Represent the WiFi data samples of the source domain and the target domain respectively.

3. The cross-domain WiFi personnel identification method based on the multi-branch domain alignment model according to claim 1 or 2 is characterized in that: The series of loss functions include domain adaptation loss , convergence loss and cross entropy loss .

4. According to claim 3, the cross-domain WiFi personnel identification method based on the multi-branch domain alignment model is characterized in that: The domain adaptation loss , ， Among them, and Represent the WiFi data samples of the source domain and the target domain respectively, represents the number of network branches, A simplified estimate of The MMD loss applied in the two branch networks of the DDA model helps to align the distribution between the source and target domains in each branch respectively. and Indicates that the source domain or target domain sample is extracted by a common feature extractor , Represents the source domain grouping feature extractor The extracted features, represents the source domain, Indicates the target area, The range is from 1 to .

5. According to claim 4, the cross-domain WiFi personnel identification method based on the multi-branch domain alignment model is characterized in that: The number of the network branches is 2, 3 or 4.

6. The cross-domain WiFi personnel identification method based on the multi-branch domain alignment model according to claim 4 is characterized in that: Cross entropy loss function shown for the DDA model For supervised classification learning, the cross entropy loss function : ， in, Indicates the number of gait labels, represents the true category label of the sample, It refers to the SoftMax function operation. Represents a branch A classifier is used to convert the network output into a probability value The range is 1 to , The denotation parameter is the expectation of the source domain samples.

7. The cross-domain WiFi personnel identification method based on the multi-branch domain alignment model according to claim 6 is characterized in that: The DDA model uses unlabeled samples from the target domain to narrow the distance between multiple branches and converges through the loss Help the model achieve a specific domain alignment of the two branches, the convergence loss : 。 8. The cross-domain WiFi personnel identification method based on the multi-branch domain alignment model according to claim 3 or 7 is characterized in that: Domain Alignment Loss Function : ， in, and Respectively and The importance weight of .

9. The cross-domain WiFi personnel identification method based on the multi-branch domain alignment model according to claim 8 is characterized in that: In the early stages of training, the two weights are dynamically adjusted using a progressive strategy, according to the formula , gradually changes from 0 to 1 as the training iteration proceeds, where It changes linearly during the training process. The value was empirically taken as 10 and remained constant throughout the experiment. Meaning is based on the exponent e .

Images