Fall prediction method, system, electronic device and storage medium

Abstract

The embodiment of the present invention discloses a fall prediction method, system, electronic device and storage medium. The fall prediction method includes: extracting gait parameters related to human balance ability from the acquired historical data; processing the gait parameters to obtain corresponding wavelet features; obtaining the regression function relationship between the wavelet features and the fall probability value; and constructing a prediction model based on the regression function relationship. By using the wavelet features as parameters for constructing the prediction model, the wavelet features can more completely preserve the information in the original signal, accurately reflect the waveform characteristics of the information, and at least achieve the advantage of more comprehensive fall prediction indicators.

Description

Technical Field

[0001] The present invention relates to the field of mathematical sciences, and in particular to a fall prediction method, system, electronic device and storage medium. Background Art

[0002] With the development of an aging society, the application of fall prediction technology in reality is very important. Common fall detection systems include: video-based fall test systems, acoustic-based fall prediction systems, and wearable sensor-based systems. Video-based fall detection systems may involve privacy violations and require pre-installation of test sites at the event location, which lacks practicality. Acoustic-based systems are easily disturbed by noise. Both detection systems have obvious limitations on the venues they can be used in. The wearable sensor-based fall prediction system is not limited to specific event venues, is more practical, and meets the requirements of a real-time fall detection system.

[0003] For the fall detection system based on wearable sensors, according to the main principles, the main technologies are: threshold and machine learning technology. Threshold-based technology usually uses thresholds for single or multiple features. The choice of threshold depends mainly on experience and analysis of the collected signals. Machine learning technology can also effectively distinguish between falls and daily activities. There are usually six technologies: k-nearest neighbor classifier, least squares method, support vector machine, Bayesian decision, dynamic time warping and artificial neural network.

[0004] The current technical solutions have the following defects: 1) The indicators for predicting falls are relatively simple. The classic extracted features are scalar features, such as peak value, amplitude, etc. However, these features cannot fully characterize the information contained in the original signal. Researchers and research institutions in the existing technology have mostly used basic statistical indicators of the signal, which are relatively simple. Statistical indicators can represent the state of human movement to a certain extent, but cannot reflect information such as the change trend of the signal. Information such as the change trend is a very critical indicator with value for judging falls; 2) The threshold selection method is simple. The determination of the threshold in the threshold technology plays a decisive role in the experimental results. Most of the current technologies use empirical judgments without clear theoretical support, resulting in the non-universality of the system design; 3) The prediction results are single. Currently, there are only two prediction results: fall and no fall, and it is impossible to make a richer prediction effect based on the current state. Summary of the invention

[0005] In view of this, the embodiments of the present invention provide a fall prediction method, system, electronic device and storage medium, which at least partially solve the problem that the fall prediction indicator in the prior art is relatively single.

[0006] In a first aspect, an embodiment of the present invention provides a fall prediction method, comprising:

[0007] Extracting gait parameters related to human balance ability from the acquired historical data;

[0008] Processing the gait parameters to obtain corresponding wavelet features;

[0009] Obtain the regression function relationship between wavelet features and fall probability values;

[0010] A prediction model is constructed based on the regression function relationship.

[0011] Optionally, after the step of obtaining the regression function relationship between the wavelet feature and the fall probability value, the following steps are included:

[0012] Performing a sparse representation on the regression function relationship;

[0013] A prediction model is constructed based on the sparse representation.

[0014] Optionally, the sparsely representing the regression function relationship includes:

[0015] A sparse representation of the regression function relationship is obtained based on the LASSO algorithm.

[0016] Optionally, the output of the prediction model is a real number in the interval [0,1].

[0017] Optionally, extracting gait parameters related to human balance ability from the acquired historical data includes:

[0018] The information to be measured is obtained from the historical data, and the information within the peak setting range of the information to be measured is intercepted.

[0019] Optionally, the processing of the gait parameters to obtain corresponding wavelet features includes:

[0020] Performing discrete wavelet transform on the gait parameters to obtain corresponding wavelet coefficient vectors;

[0021] The wavelet coefficient vector is screened by threshold value to obtain the corresponding wavelet features.

[0022] Optionally, the step of obtaining a regression function relationship between the wavelet feature and the fall probability value includes:

[0023] The regression function relationship between wavelet features and fall probability values ​​was obtained through logistic regression.

[0024] In a second aspect, an embodiment of the present invention further provides a fall prediction system, including:

[0025] Extraction module: used to extract gait parameters related to human balance ability from the acquired historical data;

[0026] Wavelet processing module: used for processing the gait parameters to obtain corresponding wavelet features;

[0027] Function module: used to obtain the regression function relationship between wavelet features and fall probability values;

[0028] Model building module: a module for building a prediction model based on the regression function relationship.

[0029] In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:

[0030] at least one processor; and,

[0031] a memory communicatively connected to the at least one processor; wherein,

[0032] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the fall prediction method described in any one of the first aspects.

[0033] In a fourth aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to execute the fall prediction method described in any one of the first aspects of the claims.

[0034] The fall prediction method provided by the present invention uses wavelet features as parameters for constructing a prediction model. The wavelet features can more completely preserve the information in the original signal and accurately reflect the waveform characteristics of the information, thereby achieving the advantage of more comprehensive fall prediction indicators.

[0035] In addition, by screening the wavelet coefficient vector, the factors that have little impact on the risk of falling can be effectively removed to achieve the effect of noise reduction.

[0036] The output value is a real number in the interval [0,1], which probabilizes the risk of falling to obtain richer prediction effects.

[0037] The LASSO algorithm is introduced to improve the accuracy and stability of prediction.

[0038] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above or other purposes, features and advantages of the present invention more obvious and easy to understand, the following lists the preferred embodiments and describes them in detail with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 A flow chart of a fall prediction method provided by an embodiment of the present invention;

[0041] Figure 2 A schematic diagram of the acceleration of a tester for a total of 10 seconds with the fall probability mutation point as the center provided by an embodiment of the present invention;

[0042] Figure 3 This is a comparison diagram of the wavelet coefficient reconstruction signal and the original signal (x-axis signal) after screening in an embodiment of the present invention (taking 10 seconds as an example);

[0043] Figure 4 This is a comparison diagram of the wavelet coefficient reconstruction signal and the original signal (y-axis signal) after screening in an embodiment of the present invention (taking 10 seconds as an example);

[0044] Figure 5 This is a comparison diagram of the wavelet coefficient reconstruction signal and the original signal (z-axis signal) after screening in an embodiment of the present invention (taking 10 seconds as an example);

[0045] Figure 6 A principle block diagram of a fall prediction method provided by an embodiment of the present invention;

[0046] Figure 7 A functional block diagram of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0048] It should be clear that the following embodiments of the present invention are described by specific specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in the field without making creative work belong to the scope of protection of the present invention.

[0049] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present invention, it should be understood by those skilled in the art that an aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects described herein can be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein can be used to implement this device and / or practice this method.

[0050] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention. The drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0051] Additionally, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, it will be understood by those skilled in the art that the aspects described may be practiced without these specific details.

[0052] Without any interference, the movement of the human body is a continuous behavior, that is, the corresponding motion parameter change trajectory is a continuous curve. Therefore, once the smoothness of the motion parameter curve suddenly changes at a certain point, it means that the behavior has changed. Based on the above ideas, this embodiment chooses to use function data to establish a model and analyze the fall risk from the perspective of function smoothness.

[0053] like Figure 1 As shown, a fall prediction method includes:

[0054] Step S101: extracting gait parameters related to human balance ability from the acquired historical data;

[0055] The historical data in this embodiment is collected based on the wearable device of the human body, that is, the gait parameters of the human body in motion are collected through the wearable device of the human body.

[0056] Step S102: Processing the gait parameters to obtain corresponding wavelet features;

[0057] That is, the gait parameters are subjected to discrete wavelet transform to obtain the corresponding wavelet coefficient vector; then the wavelet features in the information are extracted through threshold screening.

[0058] Step S103: obtaining a regression function relationship between wavelet features and fall probability values;

[0059] Step S104: constructing a prediction model based on the regression function relationship.

[0060] That is, by analyzing the gait parameters within the set range when falling in the historical data, a prediction model is constructed. When the prediction model receives new information collected by the wearable device of the human body, the prediction model performs discrete wavelet transform and threshold screening on the newly received information to obtain the corresponding wavelet features, thereby obtaining the corresponding output result based on the obtained wavelet features and the regression function relationship between the wavelet features pre-stored in the prediction model and the probability of falling. The output result is the probability of falling risk, that is, the probability of falling risk corresponding to the current human gait data, and the result can be a real number in the interval [0,1] such as 0.1 or 0.8. The larger the number, the greater the possibility of falling. In other embodiments, the result can also be processed in reverse, and the smaller the number, the greater the possibility of falling.

[0061] Optionally, after the step of obtaining the regression function relationship between the wavelet feature and the fall probability value, the following steps are included:

[0062] Performing a sparse representation on the regression function relationship;

[0063] A prediction model is constructed based on the sparse representation.

[0064] Optionally, the sparsely representing the regression function relationship includes:

[0065] A sparse representation of the regression function relationship is obtained based on the LASSO algorithm.

[0066] The LASSO algorithm was introduced to obtain the sparse representation of the regression function relationship, and a functional logistic regression model was constructed with wavelet features as input and fall probability value as output.

[0067] Optionally, the output of the prediction model is a real number in the interval [0,1].

[0068] Optionally, extracting gait parameters related to human balance ability from the acquired historical data includes:

[0069] The information to be measured is obtained from the historical data, and the information within the peak setting range of the information to be measured is intercepted.

[0070] The information to be measured is the waveform information monitored by the wearable human sensor including human falls, and the range can be set according to the needs. For example, in this embodiment, the acceleration of 10 seconds around the center of the fall probability mutation point is collected. Figure 2 shown.

[0071] Optionally, the processing of the gait parameters to obtain corresponding wavelet features includes:

[0072] Performing discrete wavelet transform on the gait parameters to obtain corresponding wavelet coefficient vectors;

[0073] The wavelet coefficient vector is screened by threshold value to obtain the corresponding wavelet features.

[0074] The comparison between the reconstructed signal of the screened wavelet coefficients and the original signal is as follows: Figures 3 to 5 shown.

[0075] Optionally, the step of obtaining a regression function relationship between the wavelet feature and the fall probability value includes:

[0076] The regression function relationship between wavelet features and fall probability values ​​was obtained through logistic regression.

[0077] When constructing the model, this embodiment extracts key features from the trajectory of motion parameters to reveal the deep relationship between gait data and fall risk. The original signal is represented by a linear combination of wavelet basis functions using discrete wavelet transform to obtain the corresponding wavelet coefficient vector. The wavelet coefficients are screened to obtain some wavelet coefficients as the wavelet features of the signal. Through screening, factors that have little impact on the risk of falling can be effectively removed to achieve the effect of noise reduction. In addition, by comparing the signal reconstructed by the wavelet feature with the original signal, it is found that the wavelet feature can more completely preserve the information in the original signal and accurately reflect the waveform characteristics of the information.

[0078] In order to quantify the probability of elderly people falling, a functional logistic regression model is constructed with wavelet features as input and the probability of falling as output. The output value is a real number in the interval [0,1], which has a probabilistic meaning. Compared with the traditional "falling\not falling" prediction results, this model probabilizes the risk of falling to obtain richer prediction results. In order to further improve the accuracy and stability of the algorithm, the LASSO algorithm is introduced to penalize factors with small regression coefficients and obtain a sparse function representation. As a result, the accuracy and stability of the algorithm are improved.

[0079] like Figure 6 As shown, a fall prediction system comprises:

[0080] Extraction module: used to extract gait parameters related to human balance ability from the acquired historical data;

[0081] Wavelet processing module: used for processing the gait parameters to obtain corresponding wavelet features;

[0082] Function module: used to obtain the regression function relationship between wavelet features and fall probability values;

[0083] Model building module: a module for building a prediction model based on the regression function relationship.

[0084] Optionally, a sparse representation module is further included, which is used to perform sparse representation on the regression function relationship;

[0085] A prediction model is constructed based on the sparse representation.

[0086] Optionally, the sparsely representing the regression function relationship includes:

[0087] A sparse representation of the regression function relationship is obtained based on the LASSO algorithm.

[0088] Optionally, the output of the prediction model is a real number in the interval [0,1].

[0089] Optionally, extracting gait parameters related to human balance ability from the acquired historical data includes:

[0090] The information to be measured is obtained from the historical data, and the information within the peak setting range of the information to be measured is intercepted.

[0091] Optionally, the processing of the gait parameters to obtain corresponding wavelet features includes:

[0092] Performing discrete wavelet transform on the gait parameters to obtain corresponding wavelet coefficient vectors;

[0093] The wavelet coefficient vector is screened by threshold value to obtain the corresponding wavelet features.

[0094] Optionally, the step of obtaining a regression function relationship between the wavelet feature and the fall probability value includes:

[0095] The regression function relationship between wavelet features and fall probability values ​​was obtained through logistic regression.

[0096] An electronic device according to an embodiment of the present invention includes a memory and a processor.

[0097] The memory is used to store non-temporary computer-readable instructions. Specifically, the memory may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may, for example, include random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may, for example, include read-only memory (ROM), hard disk, flash memory, etc.

[0098] The processor may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions. In one embodiment of the present invention, the processor is used to run the computer-readable instructions stored in the memory, so that the electronic device performs all or part of the steps of the fall prediction method of each embodiment of the present invention.

[0099] Those skilled in the art should be able to understand that in order to solve the technical problem of how to obtain a good user experience, the present embodiment may also include well-known structures such as a communication bus and an interface, and these well-known structures should also be included in the protection scope of the present invention.

[0100] For detailed description of this embodiment, reference may be made to the corresponding descriptions in the aforementioned embodiments, which will not be repeated here.

[0101] The computer-readable storage medium according to the embodiment of the present invention stores non-transitory computer-readable instructions, and when the non-transitory computer-readable instructions are executed by a processor, all or part of the steps of the fall prediction method of each embodiment of the present invention are executed.

[0102] The above-mentioned computer-readable storage media include, but are not limited to: optical storage media (e.g., CD-ROM and DVD), magneto-optical storage media (e.g., MO), magnetic storage media (e.g., magnetic tape or mobile hard disk), media with built-in rewritable non-volatile memory (e.g., memory card) and media with built-in ROM (e.g., ROM box).

[0103] For detailed description of this embodiment, reference may be made to the corresponding descriptions in the aforementioned embodiments, which will not be repeated here.

[0104] Figure 7 2 is a schematic diagram illustrating the hardware structure of a terminal device according to an embodiment of the present invention. Figure 7 As shown, the terminal may use an embodiment of a fall prediction method.

[0105] The terminal device can be implemented in various forms. The terminal device in the present invention may include but is not limited to mobile terminal devices such as mobile phones, smart phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), navigation devices, vehicle-mounted terminal devices, vehicle-mounted display terminals, vehicle-mounted electronic rearview mirrors, etc., as well as fixed terminal devices such as digital TVs, desktop computers, etc.

[0106] As an equivalent alternative implementation, the terminal may also include other components. Figure 7As shown, the terminal may include a power supply unit, a wireless communication unit, an A / V (audio / video) input unit, a user input unit, a sensing unit, an interface unit, a controller, an output unit, a storage unit, and the like. Figure 7 A terminal is shown having various components, but it is understood that implementing all of the components shown is not a requirement, and more or fewer components may alternatively be implemented.

[0107] Among them, the wireless communication unit allows radio communication between the terminal and the wireless communication system or network. The A / V input unit is used to receive audio or video signals. The user input unit can generate key input data according to the command input by the user to control various operations of the terminal device. The sensing unit detects the current state of the terminal, the position of the terminal, the presence or absence of the user's touch input to the terminal, the orientation of the terminal, the acceleration or deceleration movement and direction of the terminal, etc., and generates commands or signals for controlling the operation of the terminal. The interface unit is used as an interface through which at least one external device can be connected to the terminal. The output unit is configured to provide output signals in a visual, audio and / or tactile manner. The storage unit can store software programs for processing and control operations performed by the controller, etc., or can temporarily store data that has been output or is to be output. The storage unit may include at least one type of storage medium. Moreover, the terminal can cooperate with a network storage device that performs the storage function of the storage unit through a network connection. The controller generally controls the overall operation of the terminal device. In addition, the controller may include a multimedia module for reproducing or playing back multimedia data. The controller may perform a pattern recognition process to recognize handwriting input or picture drawing input performed on the touch screen as a character or image. The power supply unit receives external power or internal power and provides appropriate power required to operate various elements and components under the control of the controller.

[0108] Various embodiments of the fall prediction method proposed in the present invention can be implemented using a computer-readable medium such as computer software, hardware, or any combination thereof. For hardware implementation, various embodiments of the fall prediction method proposed in the present invention can be implemented by using at least one of an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a processor, a controller, a microcontroller, a microprocessor, and an electronic unit designed to perform the functions described herein. In some cases, various embodiments of the fall prediction method proposed in the present invention can be implemented in a controller. For software implementation, various embodiments of the fall prediction method proposed in the present invention can be implemented with a separate software module that allows the execution of at least one function or operation. The software code can be implemented by a software application (or program) written in any appropriate programming language, and the software code can be stored in the storage unit 89 and executed by the controller 87.

[0109] For detailed description of this embodiment, reference may be made to the corresponding descriptions in the aforementioned embodiments, which will not be repeated here.

[0110] The basic principle of the present invention is described above in conjunction with specific embodiments. However, it should be pointed out that the advantages, strengths, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. must be possessed by each embodiment of the present invention. In addition, the specific details of the above invention are only for the purpose of illustration and facilitation of understanding, rather than limitation, and the above details do not limit the present invention to being implemented by adopting the above specific details.

[0111] In the present invention, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. The block diagrams of the devices, devices, equipment, and systems involved in the present invention are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, devices, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them.

[0112] Additionally, as used herein, "or" used in a list of items beginning with "at least one" indicates a separate list, so that, for example, a list of "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not mean that the example described is preferred or better than other examples.

[0113] It should also be noted that in the system and method of the present invention, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present invention.

[0114] Various changes, substitutions, and modifications of the techniques described herein may be made without departing from the teachings defined by the appended claims. Furthermore, the scope of the claims of the present invention is not limited to the specific aspects of the processes, machines, manufactures, compositions of events, means, methods, and actions described above. Currently existing or later to be developed processes, machines, manufactures, compositions of events, means, methods, or actions that perform substantially the same functions or achieve substantially the same results as the corresponding aspects described herein may be utilized. Thus, the appended claims include such processes, machines, manufactures, compositions of events, means, methods, or actions within their scope.

[0115] The above description of the invented aspects is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present invention. Therefore, the present invention is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features of the present invention.

[0116] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present invention to the form invented herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A fall prediction method, characterized in that: include: Acquire the information to be measured from the acquired historical data, intercept the information within the peak setting range in the information to be measured, and extract gait parameters related to the balance ability of the human body; Performing discrete wavelet transform on the gait parameters to obtain corresponding wavelet coefficient vectors, and filtering the wavelet coefficient vectors by threshold values ​​to obtain corresponding wavelet features; The regression function relationship between the wavelet feature and the fall probability value is obtained through logistic regression, and the sparse representation of the regression function relationship is obtained based on the LASSO algorithm; A prediction model is constructed based on the sparse representation of the regression function relationship.

2. The fall prediction method according to claim 1, characterized in that: The output of the prediction model is a real number in the interval [0,1].

3. A fall prediction system, characterized in that: include: Extraction module: used to obtain the information to be measured from the acquired historical data, intercept the information within the peak setting range of the information to be measured, and extract gait parameters related to the balance ability of the human body; Wavelet processing module: used for performing discrete wavelet transform on the gait parameters to obtain corresponding wavelet coefficient vectors, and filtering the wavelet coefficient vectors by threshold value to obtain corresponding wavelet features; Function module: used to obtain the regression function relationship between wavelet features and fall probability values ​​through logistic regression, and obtain the sparse representation of the regression function relationship based on the LASSO algorithm; Model building module: used to build a prediction model based on the sparse representation of the regression function relationship.

4. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the fall prediction method according to claim 1 or 2.

5. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium stores computer instructions, which are used to enable a computer to execute the fall prediction method according to claim 1 or 2.

Images