Method, device and electronic device for detecting content of biologically active molecules
By detecting vibrating sound on piezoelectric sensors and using neural network models, the problem of low efficiency in disease diagnosis and health assessment in the prior art is solved, and the rapid and accurate detection of biologically active molecules is achieved, and the diagnosis and screening efficiency is improved.
Patent Information
- Application Number
- CN202111590339.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-12-23
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2041-12-23
AI Technical Summary
In the prior art, disease diagnosis, drug screening and health assessment are relatively inefficient, and systematic nucleic acid and protein detection methods are lacking.
Using a sounding device equipped with a piezoelectric sensor, vibrating sound is generated by controlling the piezoelectric sensor to vibrate at the target frequency, and input it into a pre-configured neural network model. Combining the training sample sound and labeling results, the neural network model iteratively updates it to Determine the mass of biologically active molecules.
It realizes rapid detection of the content of biologically active molecules, reduces the detection time of nucleic acid or protein, and improves the efficiency of disease diagnosis, drug screening and health assessment.
Smart Images

Figure CN114333906B_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of detection technology, and in particular to a method and device for detecting the content of bioactive molecules and a method for detecting the content of bioactive molecules in an electronic device. Background Art
[0002] At present, in disease diagnosis, drug screening and health assessment, the detection of nucleic acids and proteins can be used to complete disease diagnosis, drug screening and health assessment. However, in the prior art, there is no systematic description of how to check nucleic acids and proteins, resulting in low efficiency in disease diagnosis, drug screening and health assessment. Summary of the invention
[0003] The present disclosure provides a method, device and electronic device for detecting the content of bioactive molecules, which solves the problem of low efficiency in disease diagnosis, drug screening and health assessment in the prior art.
[0004] In order to solve the above technical problems, the embodiments of the present disclosure adopt the following technical solutions:
[0005] In a first aspect, the present invention provides a method for detecting the content of bioactive molecules, comprising: collecting vibration sounds to be analyzed; the vibration sounds are generated by a sound-generating device equipped with a piezoelectric sensor, and when bioactive molecules are attached to the surface of the piezoelectric sensor, controlling the piezoelectric sensor to vibrate at a target frequency; the vibration sounds are input into a pre-configured neural network model to determine the mass of the bioactive molecules corresponding to the vibration sounds.
[0006] In an practicable manner, before obtaining the vibration sound to be analyzed, the present disclosure provides a method for detecting the content of bioactive molecules, further comprising: obtaining a training sample sound and a labeling result of the training sample sound; wherein the training sample sound includes a sound generated by a piezoelectric sensor with bioactive molecules of different masses attached to the surface vibrating at a preset frequency; inputting the training sample sound into a neural network model; and determining, based on a target loss function, whether a predicted comparison result of the training sample sound output by the neural network model matches the labeling result;
[0007] When the predicted comparison result does not match the annotation result, the network parameters of the neural network model are iteratively updated repeatedly until the model converges to obtain a neural network model.
[0008] In one practicable manner, the piezoelectric material of the piezoelectric sensor is a polarized piezoelectric material having a piezoelectric effect.
[0009] In one practicable manner, the piezoelectric material includes any one of a piezoelectric film, a ceramic, and a single crystal.
[0010] In a second aspect, the present disclosure provides a detection device for bioactive molecules, comprising: a collection unit for collecting vibration sounds to be analyzed; the vibration sounds are produced by a sound-generating device equipped with a piezoelectric sensor, when bioactive molecules are attached to the surface of the piezoelectric sensor, controlling the piezoelectric sensor to vibrate at a target frequency; and a processing unit for inputting the vibration sounds collected by the collection unit into a preconfigured neural network model to determine the mass of the bioactive molecules corresponding to the vibration sounds.
[0011] In one practicable manner, the detection device also includes an acquisition unit; the acquisition unit is used to acquire training sample sounds and labeling results for the training sample sounds; wherein the training sample sounds include sounds generated by a piezoelectric sensor having bioactive molecules of different masses attached to its surface vibrating at a preset frequency; the processing unit is also used to input the training sample sounds acquired by the acquisition unit into a neural network model; the processing unit is also used to determine, based on a target loss function, whether a predicted comparison result of the training sample sounds output by the neural network model matches the labeling result; the processing unit is also used to iteratively update network parameters of the neural network model repeatedly and cyclically when the predicted comparison result does not match the labeling result until the model converges to obtain a neural network model.
[0012] In one practicable manner, the piezoelectric material of the piezoelectric sensor is a polarized piezoelectric material having a piezoelectric effect.
[0013] In one practicable manner, the piezoelectric material includes any one of a piezoelectric film, a ceramic, and a single crystal.
[0014] In a third aspect, the present disclosure provides a detection system for bioactive molecules, including a sound-generating device equipped with a piezoelectric sensor and an electronic device, wherein the sound-generating device is used to control the piezoelectric sensor to vibrate at a target frequency to generate a vibration sound to be analyzed when the bioactive molecules are attached to the surface of the piezoelectric sensor, and the electronic device is used to collect the vibration sound to be analyzed emitted by the sound-generating device, and the electronic device is used to execute any one of the methods for detecting the content of bioactive molecules provided in the first aspect.
[0015] In a fourth aspect, the present disclosure provides a computer storage medium comprising instructions, which, when executed on a computer, enables the computer to execute any one of the methods for detecting the content of bioactive molecules provided in the first aspect.
[0016] In a fifth aspect, the present disclosure provides an electronic device, comprising: a communication interface, a processor, a memory, and a bus; the memory is used to store computer execution instructions, the processor and the memory are connected through the bus, and when the electronic device is running, the processor executes the computer execution instructions stored in the memory, so that the electronic device executes any one of the methods for detecting the content of bioactive molecules provided in the first aspect.
[0017] Compared with the prior art, the technical solution provided by the embodiments of the present disclosure has the following advantages:
[0018] The detection method of the content of bioactive molecules provided by the embodiment of the present disclosure can analyze the collected vibration sound to be analyzed through a pre-configured neural network model, so that the mass of the bioactive molecule corresponding to the vibration sound can be determined. In this way, when the sound-generating device equipped with a piezoelectric sensor is collected, and the bioactive molecules to be analyzed of different masses are attached to the surface of the piezoelectric sensor, when the vibration sound generated by controlling the piezoelectric sensor to vibrate at a target frequency can be input into the pre-configured neural network model to determine the mass of the bioactive molecule corresponding to the vibration sound. In this way, the bioactive molecules to be detected can be detected quickly. For example, when the bioactive molecule is a nucleic acid or a protein, the detection method of the content of bioactive molecules provided by the embodiment of the present disclosure can be used to determine the specific type of the nucleic acid or protein, thereby reducing the detection time of the nucleic acid or protein, thereby improving the efficiency of disease diagnosis, drug screening and health assessment, and solving the problem of low efficiency of disease diagnosis, drug screening and health assessment in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.
[0020] 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, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0021] Figure 1 A schematic diagram of a scenario for applying the method for detecting the content of bioactive molecules provided in an embodiment of the present disclosure;
[0022] Figure 2 One of the flow diagrams of the method for detecting the content of bioactive molecules provided in the embodiments of the present disclosure;
[0023] Figure 3 The second schematic diagram of the process of the method for detecting the content of bioactive molecules provided in the embodiment of the present disclosure;
[0024] Figure 4 A schematic diagram of a first interface of a method for detecting the content of bioactive molecules provided in an embodiment of the present disclosure;
[0025] Figure 5One of the schematic diagrams of the confusion matrix of the method for detecting the content of bioactive molecules provided in the embodiments of the present disclosure;
[0026] Figure 6 A second schematic diagram of a confusion matrix for the method for detecting the content of bioactive molecules provided in an embodiment of the present disclosure;
[0027] Figure 7 One of the structural schematic diagrams of an electronic device provided by an embodiment of the present disclosure;
[0028] Figure 8 One of the structural schematic diagrams of an electronic device provided by an embodiment of the present disclosure;
[0029] Fig. 9 A schematic diagram of the structure of a computer program product for a method for detecting the content of bioactive molecules provided in an embodiment of the present disclosure. DETAILED DESCRIPTION
[0030] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.
[0031] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.
[0032] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
[0033] Figure 1The scene schematic diagram provided for the embodiment of the present disclosure includes a sound-generating device 1 and an electronic device 2 equipped with a piezoelectric sensor. The sound-generating device 1 is used to control the piezoelectric sensor to vibrate at a target frequency to generate a vibration sound to be analyzed. The electronic device 2 is used to collect the vibration sound to be analyzed emitted by the sound-generating device 1, and input the vibration sound into a pre-configured neural network model to determine the detection result. In one case, the surface of the piezoelectric sensor is not attached with bioactive molecules to be analyzed. At this time, the sound-generating device 1 generates a vibration sound to be analyzed (such as referred to as vibration sound 1) when controlling the piezoelectric sensor to vibrate at the target frequency. After collecting the vibration sound 1 emitted by the sound-generating device 1, the electronic device 2 inputs the vibration sound 1 into a pre-configured neural network model. At this time, the inspection result output by the neural network model is that the mass of the bioactive molecules attached to the surface of the piezoelectric sensor is 0 (it can also be called: no bioactive molecules are attached to the surface of the piezoelectric sensor). In another case, the surface of the piezoelectric sensor is attached with bioactive molecules of different masses to be analyzed. At this time, the sound-generating device 1 generates a vibration sound to be analyzed (such as referred to as vibration sound 2) when controlling the piezoelectric sensor to vibrate at the target frequency. After collecting the vibration sound 2 emitted by the sound-generating device 1, the electronic device 2 inputs the vibration sound 2 into a pre-configured neural network model. At this time, the inspection result output by the neural network model is that bioactive molecules are attached to the surface of the piezoelectric sensor, and the mass of the bioactive molecules is N. Wherein, N is greater than 0.
[0034] Among them, the piezoelectric sensor is made of piezoelectric material, and its surface can be combined with bioactive molecules. In this way, the piezoelectric sensor is deformed (usually this phenomenon is called the inverse piezoelectric effect) and vibrates under the action of an external electric field. In this way, when bioactive molecules are attached to the surface of the piezoelectric sensor, a mass load is generated on the surface of the piezoelectric sensor, so that when the piezoelectric sensor vibrates, its original vibration state is changed, so that the biological signal can be converted into a vibration signal.
[0035] Specifically, the upper surface and the lower surface of the piezoelectric material face the region coated with the conductive film, and the conductive film region includes the working electrode of the piezoelectric material and the electrode conduction region connected to the electrode in the working area of the piezoelectric material.
[0036] The above examples are described by assuming that the sound-generating device 1 is separately disposed outside the electronic device 2. In some other examples, the sound-generating device 1 may also be disposed on the electronic device 2. In this way, the user can more conveniently perform the detection of the content of bioactive molecules.
[0037] The electronic device 2 is used to collect the vibration sound to be analyzed emitted by the sound-generating device 1. Optionally, the electronic device 2 can be various handheld devices, wearable devices, and computers with communication functions, and the embodiments of the present disclosure do not impose any restrictions on this. For example, the handheld device can be a smart phone. The wearable device can be a smart bracelet. The computer can be a personal digital assistant (PDA), a tablet computer, and a laptop computer.
[0038] The following takes the case where the sound-generating device 1 is separately arranged outside the electronic device 2 and the electronic device 2 is the executing subject of the embodiment of the present disclosure as an example to exemplarily illustrate the method for detecting the content of bioactive molecules provided by the embodiment of the present disclosure.
[0039] Figure 2 is a flow chart of a method for detecting the content of a bioactive molecule according to an exemplary embodiment. Figure 2 As shown, the method for detecting the content of bioactive molecules is applied to the electronic device 2, and the method includes the following S11 and S12.
[0040] S11, the electronic device 2 collects the vibration sound to be analyzed. The vibration sound is generated by controlling the piezoelectric sensor to vibrate at a target frequency when a bioactive molecule is attached to the surface of the piezoelectric sensor.
[0041] In some examples, a sound sensor (such as a microphone) is provided in the electronic device 2 to collect the vibration sound to be analyzed emitted by the sound-generating device 1. For example, a sound-sensitive condenser electret microphone is built into the microphone. When the electronic device 2 collects the vibration sound to be analyzed emitted by the sound-generating device 1, the vibration sound will cause the electret film in the condenser electret microphone on the electronic device 2 to vibrate, resulting in a change in capacitance, and generating a small voltage corresponding to the change. This voltage is then converted into a voltage of 0-5V, so that the electronic device 2 can collect the vibration sound to be analyzed emitted by the sound-generating device 11.
[0042] In some examples, the target frequency may be any frequency that can be collected by the microphone. For example, the target frequency is any frequency in the audible sound frequency, and the target frequency f∈[20Hz, 20000Hz]. For another example, when the target frequency is equal to the natural frequency of the piezoelectric material of the piezoelectric sensor, the target frequency f may be called the resonant frequency, thereby ensuring the accuracy of the vibration sound to be analyzed.
[0043] In some examples, bioactive molecules can be attached to the surface of the piezoelectric sensor by physical or chemical means. After the bioactive molecules are attached to the surface of the piezoelectric sensor, a mass load is generated on the surface of the piezoelectric sensor. If the sound-generating device 1 controls the piezoelectric sensor to vibrate at a resonant frequency, the vibration state of the piezoelectric sensor will be different from when the bioactive molecules are not attached. At this time, the sound to be analyzed collected by the electronic device 2 includes the changes in the vibration sound caused by the attachment of the bioactive molecules to the surface of the piezoelectric sensor. Since the vibration sounds generated when piezoelectric sensors with different mass loads vibrate are different, the mass of the bioactive molecules can be identified by the vibration sound.
[0044] S12, the electronic device 2 inputs the vibration sound into a pre-configured neural network model to determine the mass of the bioactive molecules corresponding to the vibration sound.
[0045] In the method for detecting the content of bioactive molecules provided in the embodiment of the present disclosure, the electronic device 2 can analyze the collected vibration sound to be analyzed through a pre-configured neural network model, so as to determine the mass of the bioactive molecule corresponding to the vibration sound. In this way, when the electronic device 2 collects the vibration sound emitted by the sound-generating device 1 equipped with a piezoelectric sensor, the vibration sound can be input into the pre-configured neural network model to determine the mass of the bioactive molecule corresponding to the vibration sound. In this way, the content of the bioactive molecule to be detected can be quickly detected. For example, when the bioactive molecule is a nucleic acid or a protein, the method for detecting the content of the bioactive molecule provided in the embodiment of the present disclosure can be used to determine the mass of the nucleic acid or the protein, thereby reducing the detection time of the nucleic acid or the protein. In this way, the efficiency of disease diagnosis, drug screening and health assessment can be improved, and the problem of low efficiency of disease diagnosis, drug screening and health assessment in the prior art is solved.
[0046] In one practicable manner, combining Figure 2 ,like Figure 3 As shown, the method for detecting the content of bioactive molecules to be separated provided by the embodiment of the present disclosure also includes: S13-S16.
[0047] S13, the electronic device 2 obtains training sample sounds and labeling results of the training sample sounds, wherein the training sample sounds include sounds generated by a piezoelectric sensor with bioactive molecules of different masses attached to its surface vibrating at a preset frequency.
[0048] In some examples, in order to ensure the integrity of the training sample sound, it is necessary to collect the vibration sound when no bioactive molecules are attached to the surface of the piezoelectric sensor (such as called vibration sound 3), and mark the vibration sound 3 (such as marking each vibration sound 3 as produced when no bioactive molecules are attached to the surface of the piezoelectric sensor). At the same time, it is also necessary to collect the vibration sound when bioactive molecules are attached to the surface of the piezoelectric sensor (such as called vibration sound 4), and mark the vibration sound 4 (such as marking the mass of the bioactive molecule corresponding to each vibration sound 4).
[0049] Exemplarily, the process of collecting the vibration sound 3 by the electronic device 2 is as follows:
[0050] 1. The frequency of the electrical signal input from the sound-generating device 1 to the piezoelectric sensor is fixed at any frequency (e.g., 10 kHz) in the audible sound wave range (20 Hz-20 kHz), so that the piezoelectric sensor vibrates at a frequency of 10 kHz under the influence of the electrical signal input from the sound-generating device 1. The electronic device 2 collects the vibration sound 3 when no bioactive molecules are attached to the surface of the piezoelectric sensor (e.g., the so-called no-load condition) .
[0051] Specifically, to ensure that the obtained neural network model can accurately identify whether there are bioactive molecules attached to the surface of the current piezoelectric sensor, the electronic device 2 can traverse each frequency in the range of 20Hz-20kHz, thereby obtaining all the vibration sounds 3 of the piezoelectric sensor under no-load conditions.
[0052] 2. Label the sound features (such as loudness, frequency, volume, pitch and timbre, etc.) corresponding to the vibration sound 3 to obtain the vibration sound 3 in the training sample sound and the labeling result of the vibration sound 3.
[0053] Exemplarily, the process of collecting the vibration sound 4 by the electronic device 2 is as follows:
[0054] 1. After attaching different masses (e.g., 1 μg-8 μg) of bioactive molecules to the surface of the piezoelectric sensor, the frequency of the electrical signal input from the sound-generating device 1 to the piezoelectric sensor is fixed at any frequency (e.g., 10 kHz) in the audible sound wave range (20 Hz-20 kHz), so that the pressure transmitter vibrates at a frequency of 10 kHz under the influence of the electrical signal input from the sound-generating device 1. The electronic device 2 collects the vibration sound 4 of the piezoelectric sensor under the condition of bioactive molecules attached to the surface (e.g., non-no-load condition) .
[0055] Specifically, in order to ensure that the obtained neural network model can accurately identify the mass of the bioactive molecules attached to the surface of the current piezoelectric sensor, the electronic device 2 can traverse each target frequency in the range of 20Hz-20kHz, thereby obtaining all vibration sounds 4 when the piezoelectric sensor is under non-no-load conditions and has bioactive molecules of different masses attached to the surface and vibrates at different target frequencies.
[0056] 2. Label the sound features corresponding to the vibration sound 4 (such as loudness, frequency, volume, pitch and timbre, etc.) and the mass of the bioactive molecules attached to the surface of the piezoelectric sensor to obtain the vibration sound 4 in the training sample sound and the labeling result of the vibration sound 4.
[0057] In this way, the electronic device 2 obtains the training sample sound and the labeling result of the training sample sound.
[0058] S14. The electronic device 2 inputs the training sample sound into the neural network model.
[0059] In some examples, the electronic device 2 inputs the training sample sound into the neural network model and displays the following Figure 4 The first interface 400 is shown. The first interface 400 includes a first window 401, a second window 402, a third window 403, a status indicator 404, an algorithm selection button 405, an online data selection button 406, an offline data selection button 407, a sensor load type selection button 408, and a sensor accuracy prompt window 409. The first window 401 is used to display the time domain signal of the training sample sound, the second window 402 is used to display the frequency domain signal of the training sample sound, the third window 403 is used to display the image information of the surface of the piezoelectric sensor, the status indicator 404 is used to indicate whether the current electronic device is running, the algorithm selection button 405 is used to select the required neural network model, the online data selection button 406 is used to indicate that the data of the training sample sound currently used comes from online, the offline data selection button 407 is used to indicate that the data of the training sample sound currently used comes from local, the sensor load type selection button 408 is used to select the sensor type currently used, and the sensor accuracy prompt window 409 is used to give the current detection result.
[0060] S15. The electronic device 2 determines whether the predicted comparison result of the training sample sound output by the neural network model matches the labeled result based on the target loss function.
[0061] S16. When the predicted comparison result does not match the marked result, the electronic device 2 iteratively updates the network parameters of the neural network model repeatedly and cyclically until the model converges to obtain a neural network model.
[0062] In some examples, in order to confirm the detection results of the neural network model, it is necessary to determine whether the predicted comparison results of the training sample sounds match the labeled results. For example, when the vibration sound 3 of the piezoelectric sensor under no-load conditions is input into the neural network model, if the predicted comparison result of the neural network model is that there are no bioactive molecules attached to the surface of the piezoelectric sensor, it means that the predicted comparison result matches the labeled result. If the predicted comparison result of the neural network model is that there are bioactive molecules attached to the surface of the piezoelectric sensor, it means that the predicted comparison result does not match the labeled result. Alternatively, when the vibration sound 4 of the piezoelectric sensor under non-no-load conditions is input into the neural network model, if the predicted comparison result of the neural network model is that there are bioactive molecules attached to the surface of the piezoelectric sensor, it means that the predicted comparison result matches the labeled result. If the predicted comparison result of the neural network model is that there are no bioactive molecules attached to the surface of the piezoelectric sensor, it means that the predicted comparison result does not match the labeled result.
[0063] For example, taking the vibration sound to be analyzed generated by the piezoelectric sensor of the sound-generating device 1 under no-load conditions as an example, the vibration sound to be analyzed is input into the neural network model, and the detection results output by the neural network model are summarized to form a Figure 5 The confusion matrix is shown.
[0064] The sum of each row represents the number of real samples of vibration sound to be analyzed of this category. For example, taking the first row as an example, the number of real samples of vibration sound to be analyzed is 355+5=360.
[0065] like Figure 5 As shown in the figure, the first row shows that 355 vibration sounds to be analyzed (hereinafter referred to as vibration sound 5) generated by the piezoelectric sensors of the sound-generating device vibrating under no-load conditions are correctly predicted as no bioactive molecules attached to the surface of the piezoelectric sensors, and 5 vibration sounds are incorrectly predicted as bioactive molecules attached to the surface of the piezoelectric sensors. It can be seen that the neural network model has an accurate recognition rate of vibration sound 5. The false recognition rate is 1-98.6%=1.4%.
[0066] The second row shows that there is a vibration sound to be analyzed (hereinafter referred to as vibration sound 6) generated by the piezoelectric sensor of the sound-generating device under no-load conditions, which is incorrectly predicted as no bioactive molecules attached to the surface of the piezoelectric sensor, and 359 vibration sounds 6 are correctly predicted as bioactive molecules attached to the surface of the piezoelectric sensor. It can be seen that the neural network model has an accurate recognition rate of vibration sound 6. The false recognition rate is 1-99.7%=0.3%.
[0067] In some other examples, since the training sample sounds contain the corresponding training sample sounds when the bioactive molecules of different masses are attached to the surface of the piezoelectric sensor. Therefore, the neural network model can also determine the mass of the bioactive molecules attached to the surface of the pressure sensor. For example, when the vibration sound of the piezoelectric sensor under non-no-load conditions is input into the neural network model, if the predicted comparison result of the neural network model is that the surface of the piezoelectric sensor is attached with bioactive molecules, and the predicted value of the bioactive molecules is the same as the annotation result, it means that the predicted comparison result matches the annotation result. If the predicted comparison result of the neural network model is that the surface of the piezoelectric sensor is attached with bioactive molecules, and the predicted value of the bioactive molecules is different from the annotation result, it means that the predicted comparison result does not match the annotation result.
[0068] For example, taking the case where eight biologically active molecules of different masses (e.g., mass 1, mass 2, mass 3, mass 4, mass 5, mass 6, mass 7, and mass 8) are attached to the surface of the piezoelectric sensor of the sound-generating device 1, after the sound-generating device 1 controls the piezoelectric sensor to vibrate and generate the vibration sound to be analyzed, the electronic device 2 collects the vibration sound to be analyzed emitted by the sound-generating device 1, and inputs the vibration sound to be analyzed into the neural network model, and summarizes the detection results output by the neural network model to form a graph such as Figure 6 The confusion matrix is shown.
[0069] like Figure 6 As shown in the figure, the first row shows that after 120 bioactive molecules with a mass of 1 are attached to the surface of the piezoelectric sensor, the vibration sound to be analyzed generated by the generator 1 when controlling the piezoelectric sensor to vibrate is correctly predicted as the mass of the bioactive molecules attached to the surface of the piezoelectric sensor being mass 1. It can be seen that the neural network model has an accurate recognition rate of 1 for the bioactive molecules attached to the surface of the piezoelectric sensor being mass 1. The false recognition rate is 1-100%=0%.
[0070] The second row shows that after 110 bioactive molecules with a mass of 2 are attached to the surface of the piezoelectric sensor, the vibration sound to be analyzed generated by the generator 1 when controlling the piezoelectric sensor to vibrate is correctly predicted as the mass of the bioactive molecules attached to the surface of the piezoelectric sensor being 2. After 9 bioactive molecules with a mass of 2 are attached to the surface of the piezoelectric sensor, the vibration sound to be analyzed generated by the generator 1 when controlling the piezoelectric sensor to vibrate is incorrectly predicted as the mass of the bioactive molecules attached to the surface of the piezoelectric sensor being 1. After 1 bioactive molecule with a mass of 2 is attached to the surface of the piezoelectric sensor, the vibration sound to be analyzed generated by the generator 1 when controlling the piezoelectric sensor to vibrate is incorrectly predicted as the mass of the bioactive molecules attached to the surface of the piezoelectric sensor being 6. It can be seen that the neural network model has an accurate recognition rate of the bioactive molecules attached to the surface of the piezoelectric sensor being 2. The error recognition rate is 1-91.7%=8.3%.
[0071] The third row shows that after 119 bioactive molecules with a mass of 3 are attached to the surface of the piezoelectric sensor, the vibration sound to be analyzed generated by the generator 1 when controlling the piezoelectric sensor to vibrate is correctly predicted to be the mass of the bioactive molecules attached to the surface of the piezoelectric sensor being 3. After 1 bioactive molecule with a mass of 3 is attached to the surface of the piezoelectric sensor, the vibration sound to be analyzed generated by the generator 1 when controlling the piezoelectric sensor to vibrate is incorrectly predicted to be the mass of the bioactive molecules attached to the surface of the piezoelectric sensor being 6. It can be seen that the neural network model has an accurate recognition rate of 3 for the bioactive molecules attached to the surface of the piezoelectric sensor. The error recognition rate is 1-99.2%=0.8%.
[0072] The fourth row shows that after 119 bioactive molecules with a mass of 4 are attached to the surface of the piezoelectric sensor, the vibration sound to be analyzed generated by the generator 1 when controlling the piezoelectric sensor to vibrate is correctly predicted to be the mass of the bioactive molecules attached to the surface of the piezoelectric sensor being 4. After 1 bioactive molecule with a mass of 4 is attached to the surface of the piezoelectric sensor, the vibration sound to be analyzed generated by the generator 1 when controlling the piezoelectric sensor to vibrate is incorrectly predicted to be the mass of the bioactive molecules attached to the surface of the piezoelectric sensor being 6. It can be seen that the neural network model has an accurate recognition rate of 4 for the bioactive molecules attached to the surface of the piezoelectric sensor. The error recognition rate is 1-99.2%=0.8%.
[0073] The fifth row shows that after 115 bioactive molecules with a mass of 5 are attached to the surface of the piezoelectric sensor, the vibration sound to be analyzed generated by the generator 1 when controlling the piezoelectric sensor to vibrate is correctly predicted to be the mass of the bioactive molecules attached to the surface of the piezoelectric sensor being 5. After 1 bioactive molecule with a mass of 5 is attached to the surface of the piezoelectric sensor, the vibration sound to be analyzed generated by the generator 1 when controlling the piezoelectric sensor to vibrate is incorrectly predicted to be the mass of the bioactive molecules attached to the surface of the piezoelectric sensor being 6. After 4 bioactive molecules with a mass of 5 are attached to the surface of the piezoelectric sensor, the vibration sound to be analyzed generated by the generator 1 when controlling the piezoelectric sensor to vibrate is incorrectly predicted to be the mass of the bioactive molecules attached to the surface of the piezoelectric sensor being 8. It can be seen that the accuracy rate of the neural network model for the bioactive molecules attached to the surface of the piezoelectric sensor being 5 is The error recognition rate is 1-95.8%=4.2%.
[0074] The sixth row shows that after 119 bioactive molecules with a mass of 6 are attached to the surface of the piezoelectric sensor, the vibration sound to be analyzed generated by the generator 1 when controlling the piezoelectric sensor to vibrate is correctly predicted to be the mass of the bioactive molecules attached to the surface of the piezoelectric sensor being 6. After 1 bioactive molecule with a mass of 6 is attached to the surface of the piezoelectric sensor, the vibration sound to be analyzed generated by the generator 1 when controlling the piezoelectric sensor to vibrate is incorrectly predicted to be the mass of the bioactive molecules attached to the surface of the piezoelectric sensor being 5. It can be seen that the neural network model has an accurate recognition rate of 6 for the bioactive molecules attached to the surface of the piezoelectric sensor. The error recognition rate is 1-99.2%=0.8%.
[0075] The seventh row shows that after 114 bioactive molecules with a mass of 7 are attached to the surface of the piezoelectric sensor, the vibration sound to be analyzed generated by the generator 1 when controlling the piezoelectric sensor to vibrate is correctly predicted to be the mass of the bioactive molecules attached to the surface of the piezoelectric sensor being 7. After 2 bioactive molecules with a mass of 7 are attached to the surface of the piezoelectric sensor, the vibration sound to be analyzed generated by the generator 1 when controlling the piezoelectric sensor to vibrate is incorrectly predicted to be the mass of the bioactive molecules attached to the surface of the piezoelectric sensor being 5. After 1 bioactive molecule with a mass of 7 is attached to the surface of the piezoelectric sensor, the vibration sound to be analyzed generated by the generator 1 when controlling the piezoelectric sensor to vibrate is incorrectly predicted to be the mass of the bioactive molecules attached to the surface of the piezoelectric sensor being 6. After 3 bioactive molecules with a mass of 7 are attached to the surface of the piezoelectric sensor, the vibration sound to be analyzed generated by the generator 1 when controlling the piezoelectric sensor to vibrate is incorrectly predicted to be the mass of the bioactive molecules attached to the surface of the piezoelectric sensor being 8. It can be seen that the accuracy of the neural network model for the bioactive molecules attached to the surface of the piezoelectric sensor with a mass of 7 is The error recognition rate is 1-95.0%=5%.
[0076] The eighth row shows that after 111 bioactive molecules with a mass of 8 are attached to the surface of the piezoelectric sensor, the vibration sound to be analyzed generated by the generator 1 when controlling the piezoelectric sensor to vibrate is correctly predicted to be the mass of the bioactive molecules attached to the surface of the piezoelectric sensor being 8. After 7 bioactive molecules with a mass of 8 are attached to the surface of the piezoelectric sensor, the vibration sound to be analyzed generated by the generator 1 when controlling the piezoelectric sensor to vibrate is incorrectly predicted to be the mass of the bioactive molecules attached to the surface of the piezoelectric sensor being 5. After 1 bioactive molecule with a mass of 8 is attached to the surface of the piezoelectric sensor, the vibration sound to be analyzed generated by the generator 1 when controlling the piezoelectric sensor to vibrate is incorrectly predicted to be the mass of the bioactive molecules attached to the surface of the piezoelectric sensor being 6. After 1 bioactive molecule with a mass of 8 is attached to the surface of the piezoelectric sensor, the vibration sound to be analyzed generated by the generator 1 when controlling the piezoelectric sensor to vibrate is incorrectly predicted to be the mass of the bioactive molecules attached to the surface of the piezoelectric sensor being 7. It can be seen that the accuracy recognition rate of the neural network model for the bioactive molecules attached to the surface of the piezoelectric sensor being 8 is The error recognition rate is 1-92.5%=7.5%.
[0077] In one practicable manner, the piezoelectric material of the piezoelectric sensor is a polarized piezoelectric material having a piezoelectric effect.
[0078] In some examples, the principles for selecting piezoelectric materials are:
[0079] 1.Can produce sound under certain conditions.
[0080] 2. Bioactive molecules can be successfully adsorbed on the surface of the piezoelectric material.
[0081] 3. The attachment of bioactive molecules can affect the vibration sound emitted by the piezoelectric sensor when it vibrates.
[0082] In one practicable manner, the piezoelectric material includes any one of a piezoelectric film, a ceramic, and a single crystal. It should be noted that the piezoelectric material is any one of a piezoelectric film, a ceramic, and a single crystal as an example for explanation here, and other piezoelectric materials that can realize the corresponding functions of any one of the piezoelectric films, ceramics, and single crystals can also be applied to the present disclosure, and the present disclosure does not limit it.
[0083] In some examples, the piezoelectric film may be a polyvinylidene fluoride (PVDF) piezoelectric film. Alternatively, the piezoelectric film may be a potassium sodium niobate (KNN) piezoelectric film.
[0084] The above mainly introduces the solution provided by the embodiment of the present disclosure from the perspective of the method. In order to achieve the above functions, it includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present disclosure.
[0085] The disclosed embodiment can divide the electronic device into functional modules according to the above method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the disclosed embodiment is schematic and is only a logical function division. There may be other division methods in actual implementation.
[0086] like Figure 7 As shown, an embodiment of the present disclosure provides a schematic diagram of the structure of an electronic device 10. The electronic device 10 includes a collection unit 101, a processing unit 102 and an acquisition unit 103.
[0087] The collection unit 101 is used to collect the vibration sound to be analyzed. The vibration sound is generated by controlling the piezoelectric sensor to vibrate at a target frequency when a bioactive molecule is attached to the surface of the piezoelectric sensor. The processing unit 102 is used to input the vibration sound collected by the collection unit 101 into a pre-configured neural network model to determine the mass of the bioactive molecule corresponding to the vibration sound.
[0088] In one practicable manner, the detection device further includes an acquisition unit 103; the acquisition unit 103 is used to acquire training sample sounds and labeling results for the training sample sounds. The training sample sounds include sounds generated by a piezoelectric sensor having bioactive molecules of different masses attached to its surface vibrating at a preset frequency. The processing unit 102 is also used to input the training sample sounds acquired by the acquisition unit 101 into the neural network model. The processing unit 102 is also used to determine, based on the target loss function, whether the predicted comparison results for the training sample sounds output by the neural network model match the labeling results. The processing unit 102 is also used to iteratively update the network parameters of the neural network model repeatedly and cyclically when the predicted comparison results do not match the labeling results, until the model converges, to obtain a neural network model.
[0089] In one practicable manner, the piezoelectric material of the piezoelectric sensor is a polarized piezoelectric material having a piezoelectric effect.
[0090] In one practicable manner, the piezoelectric material includes at least one of a piezoelectric film and a ceramic.
[0091] Among them, all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module, and its role will not be repeated here.
[0092] Of course, the electronic device 10 provided in the embodiment of the present disclosure includes but is not limited to the above modules, for example, the electronic device 10 may also include a storage unit 104. The storage unit 104 may be used to store the program code of the writing electronic device 10, and may also be used to store the data generated by the writing electronic device 10 during operation, such as the data in the writing request, etc.
[0093] Figure 8 A schematic diagram of the structure of an electronic device 10 provided in an embodiment of the present disclosure is shown in FIG. Figure 8 As shown, the electronic device 10 may include: at least one processor 51 , a memory 52 , a communication interface 53 and a communication bus 54 .
[0094] Combine the following Figure 8 The components of the electronic device 10 are described in detail:
[0095] The processor 51 is the control center of the electronic device 10, and may be a processor or a general term for multiple processing elements. For example, the processor 51 is a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present disclosure, such as one or more DSPs, or one or more field programmable gate arrays (FPGAs).
[0096] In a specific implementation, as an embodiment, the processor 51 may include one or more CPUs, such as Figure 8 Also, as an embodiment, the electronic device 10 may include multiple processors, such as Figure 8 51 and 55 are shown in FIG. Each of these processors may be a single-core processor (Single-CPU) or a multi-core processor (Multi-CPU). The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).
[0097] The memory 52 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 52 may exist independently and be connected to the processor 51 via a communication bus 54. The memory 52 may also be integrated with the processor 51.
[0098] In a specific implementation, the memory 52 is used to store the data in the present disclosure and execute the software program in the present disclosure. The processor 51 can execute various functions of the air conditioner by running or executing the software program stored in the memory 52 and calling the data stored in the memory 52.
[0099] The communication interface 53 uses any transceiver-like device to communicate with other devices or communication networks, such as Radio Access Network (RAN), Wireless Local Area Networks (WLAN), terminals, the cloud, etc. The communication interface 53 may include a collection unit and an acquisition unit to implement the receiving function.
[0100] The communication bus 54 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0101] As an example, combining Figure 7 The function implemented by the collection unit 101 in the electronic device 10 is similar to Figure 8 The function of the communication interface 53 in the embodiment is the same as that of the processing unit 102. Figure 8 The function of the processor 51 in the embodiment is the same as that of the acquisition unit 103. Figure 8 The function of the communication interface 53 in the embodiment is the same as that of the storage unit 104. Figure 8 The function of the memory 52 in is the same.
[0102] Another embodiment of the present disclosure further provides a computer-readable storage medium, in which instructions are stored. When the instructions are executed on a computer, the computer executes the method shown in the above method embodiment.
[0103] In some embodiments, the disclosed methods may be implemented as computer program instructions encoded in a machine-readable format on a computer-readable storage medium or on other non-transitory media or articles of manufacture.
[0104] Fig. 9A conceptual partial view of a computer program product provided by an embodiment of the present disclosure is schematically shown, wherein the computer program product includes a computer program for executing a computer process on a computing device.
[0105] In one embodiment, the computer program product is provided using a signal bearing medium 410. The signal bearing medium 410 may include one or more program instructions, which when executed by one or more processors may provide the above-mentioned Figure 2 Thus, for example, reference to Figure 2 In the embodiment shown in , one or more features of S11 and S12 may be undertaken by one or more instructions associated with the signal bearing medium 410. In addition, Fig. 9 The program instructions in also describe example instructions.
[0106] In some examples, signal bearing medium 410 may include computer readable medium 411, such as, but not limited to, a hard drive, a compact disk (CD), a digital video disk (DVD), a digital tape, a memory, a read-only memory (ROM), or a random access memory (RAM), and the like.
[0107] In some implementations, signal bearing medium 410 may include computer recordable medium 412 such as, but not limited to, memory, read / write (R / W) CD, R / W DVD, and the like.
[0108] In some implementations, signal bearing medium 410 may include communication medium 413 such as, but not limited to, digital and / or analog communication media (eg, fiber optic cables, waveguides, wired communication links, wireless communication links, etc.).
[0109] The signal bearing medium 410 may be communicated by a wireless form of communication medium 413 (eg, a wireless communication medium conforming to the IEEE 802.41 standard or other transmission protocol). The one or more program instructions may be, for example, computer executable instructions or logic implemented instructions.
[0110] In some examples, such as for Figure 2 The described writing data device may be configured to provide various operations, functions, or actions in response to one or more program instructions via computer-readable medium 411 , computer-recordable medium 412 , and / or communication medium 413 .
[0111] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.
[0112] In the several embodiments provided in the present disclosure, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0113] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.
[0114] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0115] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present disclosure is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks or optical disks.
[0116] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. Detection method of bioactive molecule content, It is characterized in that include: Collecting vibration sounds to be analyzed; the vibration sounds are generated by controlling a sound-generating device equipped with a piezoelectric sensor to vibrate at a target frequency when bioactive molecules are attached to the surface of the piezoelectric sensor; The vibration sound is input into a pre-configured neural network model to determine the mass of the bioactive molecule corresponding to the vibration sound.
2. The method for detecting the content of bioactive molecules according to claim 1, It is characterized in that Before collecting the vibration sound to be analyzed, the method further includes: Acquiring training sample sounds and labeling results of the training sample sounds; wherein the training sample sounds include sounds generated by a piezoelectric sensor having bioactive molecules of different masses attached to its surface vibrating at a preset frequency; Inputting the training sample sound into a neural network model; Based on the target loss function, determining whether the predicted comparison result of the training sample sound output by the neural network model matches the annotation result; When the predicted comparison result does not match the annotation result, the network parameters of the neural network model are iteratively updated repeatedly and cyclically until the model converges to obtain the neural network model.
3. The method for detecting the content of bioactive molecules according to claim 1 or 2, It is characterized in that The piezoelectric material of the piezoelectric sensor is a polarized piezoelectric material having a piezoelectric effect.
4. The method for detecting the content of bioactive molecules according to claim 3, It is characterized in that The piezoelectric material includes any one of a piezoelectric film, a ceramic, and a single crystal.
5. Detection device for bioactive molecules, It is characterized in that include: A collection unit, used for collecting vibration sounds to be analyzed; the vibration sounds are generated by controlling a sound-generating device equipped with a piezoelectric sensor to vibrate at a target frequency when bioactive molecules are attached to the surface of the piezoelectric sensor; The processing unit is used to input the vibration sound collected by the collection unit into a pre-configured neural network model to determine the mass of the bioactive molecules corresponding to the vibration sound.
6. The bioactive molecule detection device according to claim 5, It is characterized in that The detection device also includes an acquisition unit; The acquisition unit is used to acquire training sample sounds and labeling results of the training sample sounds; wherein the training sample sounds include sounds generated by a piezoelectric sensor having bioactive molecules of different masses attached to its surface vibrating at a preset frequency; The processing unit is further used to input the training sample sound acquired by the acquisition unit into the neural network model; The processing unit is further used to determine whether the predicted comparison result of the training sample sound output by the neural network model matches the annotation result based on the target loss function; The processing unit is also used to iteratively update the network parameters of the neural network model repeatedly and cyclically when the predicted comparison result does not match the annotation result, so as to obtain the neural network model.
7. A detection system for bioactive molecules, It is characterized in that It comprises a sound-generating device and an electronic device equipped with a piezoelectric sensor, wherein the sound-generating device is used to control the piezoelectric sensor to vibrate at a target frequency to generate a vibration sound to be analyzed when bioactive molecules are attached to the surface of the piezoelectric sensor, and the electronic device is used to collect the vibration sound to be analyzed emitted by the sound-generating device and execute the method for detecting the content of bioactive molecules as described in any one of claims 1 to 4.
8. A computer storage medium comprising instructions, which, when executed on a computer, enables the computer to execute the method for detecting the content of a bioactive molecule according to any one of claims 1 to 4.
9. An electronic device, include: Communication interface, processor, memory, bus; The memory is used to store computer-executable instructions. The processor is connected to the memory through a bus. When the electronic device is running, the processor executes the computer-executable instructions stored in the memory so that the electronic device performs the method for detecting the content of bioactive molecules as described in any one of claims 1 to 4 above.
Citation Information
Patent Citations
Method for monitoring a livestock facility and / or livestock animals in a livestock facility using improved sound processing techniques
CN113056785A
Method and device for detecting content of bioactive molecules and electronic equipment
CN114501263A
Wearable socio-biosensor device
US20160302733A1
Acoustic and vibration information accumulation mechanism, acoustic and vibration sensing system, and computer program
US20160367213A1
Sensor for detecting proteins and process for its production
WO1997043631A1
