Object classification method and device based on Raman surface enhanced spectroscopy, and medium
By using the combination of Raman surface enhancement spectrum and support vector machine model in object classification, the problem of inaccurate object category detection in the prior art is solved, and the accuracy and reliability of classification are improved.
Patent Information
- Application Number
- CN202310756841.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-06-25
- Publication Date
- 2024-12-27
AI Technical Summary
In the prior art, object category detection methods have problems with inaccurate detection, especially when unsupervised principal component analysis or linear discriminant analysis is used.
The object classification method based on Raman surface enhancement spectrum is used to measure Raman surface enhancement spectrum by obtaining the mixture of the serum of the measured object and the colloidal gold nanoparticles, and the sample data is processed using a pre-trained support vector machine model. to improve the accuracy of classification.
Through the coordinated operation of surface-enhanced Raman spectroscopy and the support vector machine model, the changes in multi-dimensional parameters in the serum are coordinated, the accidentality of analysis and judgment is reduced, the accuracy of classification of the measured objects is improved, and information loss is avoided.
Smart Images
Figure CN119198667A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the technical field of Raman spectroscopy, and in particular to an object classification method, device and medium based on Raman surface enhanced spectroscopy. Background Art
[0002] The category of an object can help study the nature of the object. In the related art, the category of the object can be preliminarily detected by using unsupervised principal component analysis or linear discriminant analysis. However, this detection method has the problem of inaccurate detection. Summary of the invention
[0003] The purpose of the present disclosure is to provide an object classification method, device and medium based on Raman surface enhanced spectroscopy to improve the accuracy of classifying the measured objects.
[0004] In order to achieve the above-mentioned object, a first aspect of an embodiment of the present disclosure provides an object classification method based on Raman surface enhanced spectroscopy, the method comprising:
[0005] Acquiring sample data of the subject to be tested, wherein the sample data of the subject to be tested is a Raman surface enhanced spectrum obtained by performing Raman surface enhanced spectroscopy measurement on a mixture of serum of the subject to be tested and colloidal gold nanoparticles;
[0006] The sample data of the object to be measured is processed by a pre-trained support vector machine model to obtain the category corresponding to the object to be measured.
[0007] Optionally, the method further comprises:
[0008] Acquire a plurality of training sample data, wherein each of the training sample data includes sample data of a sample object and a category corresponding to the sample object;
[0009] Based on the multiple training sample data, an initial support vector machine model is trained to obtain the pre-trained support vector machine model.
[0010] Optionally, the colloidal gold nanoparticles are prepared by the following steps:
[0011] Adding 2 volumes of sodium citrate (1% w / v) aqueous solution and 2 volumes of citric acid (0.05% w / v) solution to 50 volumes of boiling HAuCl4·3H2O (0.01% w / v) solution to obtain a first mixed solution;
[0012] The first mixed solution was boiled for 5 minutes and then cooled to room temperature as a seed solution;
[0013] Dilute 3 mL of the seed solution to 20 mL with deionized water;
[0014] The diluted seed solution was grown by using 10 mL of a first solution containing HAuCl4·3H20 (0.04% w / v) and 10 mL of a second solution containing ascorbic acid (0.05% w / v) and sodium citrate (0.025% w / v) to obtain the colloidal gold nanoparticles.
[0015] Optionally, the step of growing the seed solution with 10 mL of a first solution containing HAuCl4·3H20 (0.04% w / v) and 10 mL of a second solution containing ascorbic acid (0.05% w / v) and sodium citrate (0.025% w / v) to obtain the colloidal gold nanoparticles comprises:
[0016] dripping the first solution and the second solution into the diluted seed solution by siphoning to obtain a second mixed solution;
[0017] draining the second mixed solution for 40 minutes, boiling the drained second solution for 5 minutes and then cooling it to obtain a growth solution after the first growth;
[0018] Obtain 4.5 mL of the growth solution after the first growth and dilute it to 20 mL with water;
[0019] dripping the first solution and the second solution into the diluted growth solution in a siphoning manner to obtain a third mixed solution;
[0020] The third mixed solution was drained for 40 minutes, and the drained third solution was boiled for 5 minutes and then cooled to obtain the colloidal gold nanoparticles.
[0021] Optionally, the sample data of the object to be measured is prepared by the following steps:
[0022] Wash 2 mL of the colloidal gold nanoparticles with deionized water, and concentrate the washed colloidal gold nanoparticles to 10 μL;
[0023] The concentrated colloidal gold nanoparticles were centrifuged at 4500 rpm for 5 min;
[0024] Mixing 20 μL of serum with the centrifuged colloidal gold nanoparticles to obtain a fourth mixed solution;
[0025] Dropping the fourth mixed solution on a quartz substrate, and drying in a vacuum chamber for 30 minutes to obtain the mixture;
[0026] The mixture is subjected to Raman surface enhanced spectroscopy measurement to obtain sample data of the measured object.
[0027] Optionally, the colloidal gold nanoparticles have a diameter of 70 to 75 nm.
[0028] Optionally, the sample data includes a Raman surface enhanced spectrum of at least one of tyrosine, phenylalanine, glutamine-leucine, hypoxanthine, thymine, cholesterol, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol and triglycerides.
[0029] A second aspect of the embodiments of the present disclosure provides an object classification device based on Raman surface enhanced spectroscopy, the device comprising:
[0030] An acquisition module is configured to acquire sample data of the object under test, wherein the sample data of the object under test is a Raman surface enhanced spectrum obtained by performing Raman surface enhanced spectrum measurement on a mixture of serum of the object under test and colloidal gold nanoparticles;
[0031] The processing module is configured to process the sample data of the object under test through a pre-trained support vector machine model to obtain the category corresponding to the object under test.
[0032] A third aspect of the embodiments of the present disclosure provides an object classification device based on Raman surface enhanced spectroscopy, the device comprising:
[0033] A sample data acquisition device, used to acquire sample data of a test object, wherein the sample data of the test object is a Raman surface enhanced spectrum obtained by performing Raman surface enhanced spectrum measurement on a mixture of serum of the test object and colloidal gold nanoparticles;
[0034] A memory for storing program instructions executable by the processor;
[0035] A processor, configured to call a pre-trained support vector machine model stored in a memory to process the sample data of the object under test, so as to obtain a category corresponding to the object under test;
[0036] Category output device, used for outputting the category corresponding to the measured object.
[0037] A fourth aspect of the embodiments of the present disclosure provides a non-transitory computer-readable storage medium having program instructions stored thereon, which implements the following steps when the program instructions are executed by a processor:
[0038] Acquiring sample data of the subject to be tested, wherein the sample data of the subject to be tested is a Raman surface enhanced spectrum obtained by performing Raman surface enhanced spectroscopy measurement on a mixture of serum of the subject to be tested and colloidal gold nanoparticles;
[0039] Calling a pre-trained support vector machine model stored in a memory to process the sample data of the object under test to obtain a category corresponding to the object under test;
[0040] Output the category corresponding to the object under test.
[0041] By adopting the above technical solution, at least the following beneficial technical effects can be achieved:
[0042] After obtaining the sample data of the object to be tested, the sample data of the object to be tested can be processed by the pre-trained support vector machine model to obtain the category corresponding to the object to be tested. Since the sample data of the object to be tested is the Raman surface enhanced spectrum obtained by Raman surface enhanced spectroscopy measurement of the mixture of the serum of the object to be tested and the colloidal gold nanoparticles, considering that the serum corresponds to the spectral data corresponding to multiple components, the Raman surface enhanced spectral data corresponding to the serum is processed by the support vector machine model without causing information loss, so that the coordinated operation of the surface enhanced Raman spectroscopy and the support vector machine model can coordinate the changes in the multi-dimensional parameters in the serum, reduce the randomness of the analysis and judgment, and improve the accuracy of the classification of the object to be tested.
[0043] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings:
[0045] Figure 1 The figure is a flow chart of an object classification method based on Raman surface enhanced spectroscopy according to an exemplary embodiment of the present disclosure.
[0046] Figure 2 The figure is a block diagram of an object classification device based on Raman surface enhanced spectroscopy according to an exemplary embodiment of the present disclosure.
[0047] Figure 3 The figure is a block diagram of an object classification device based on Raman surface enhanced spectroscopy according to an exemplary embodiment of the present disclosure.
[0048] Figure 4 It is a block diagram of an electronic device according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION
[0049] The specific implementation of the present disclosure is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.
[0050] It should be noted that all actions of acquiring signals, information or data in the present disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the device is located and with the authorization given by the owner of the corresponding device.
[0051] Raman spectroscopy refers to the spectrum formed by the Raman scattering effect (the phenomenon that the frequency of light waves changes after being scattered) after the incident light is reflected by the sample to be tested. Raman spectroscopy can be used to analyze the vibration and rotation energy levels of the molecules in the sample to be tested. The Raman spectra of different molecules are different, so different molecules can be identified through Raman spectroscopy, which has a wide range of applications in the field of chemical analysis.
[0052] Raman surface enhancement refers to the use of Raman spectroscopy to measure samples adsorbed on the rough surface of colloidal metal particles such as silver, gold or copper, which have low or no signal under traditional Raman spectroscopy. The Raman surface enhancement effect can achieve qualitative and quantitative testing of more molecules.
[0053] Figure 1 The present invention is a flowchart of an object classification method based on Raman surface enhanced spectroscopy according to an exemplary embodiment of the present invention. The object classification method based on Raman surface enhanced spectroscopy is applied to electronic devices, such as mobile phones, tablets, computers, etc.
[0054] like Figure 1 As shown, the object classification method based on Raman surface enhanced spectroscopy may include the following steps:
[0055] S110, obtaining sample data of the object to be measured.
[0056] The sample data of the object to be tested is a Raman surface enhanced spectrum obtained by performing Raman surface enhanced spectroscopy measurement on a mixture of the serum of the object to be tested and colloidal gold nanoparticles.
[0057] S120, processing the sample data of the object to be tested by using a pre-trained support vector machine model to obtain a category corresponding to the object to be tested.
[0058] In the embodiment of the present disclosure, the category of the detected object may include a first category and a second category.
[0059] In some embodiments, the first category may indicate that the subject is abnormal, and the second category may indicate that the subject is normal.
[0060] In some embodiments, after obtaining the category of the object being measured, medical personnel can further analyze and determine whether the object being measured has a certain property based on the category.
[0061] In some embodiments, the sample data includes a Raman surface enhanced spectrum of at least one of tyrosine, phenylalanine, glutamine-leucine, hypoxanthine, thymine, cholesterol, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, and triglycerides.
[0062] In this way, after obtaining the sample data of the object to be tested, the sample data of the object to be tested can be processed by the pre-trained support vector machine model to obtain the category corresponding to the object to be tested. Since the sample data of the object to be tested is the Raman surface enhanced spectrum obtained by Raman surface enhanced spectroscopy measurement of the mixture of the serum of the object to be tested and the colloidal gold nanoparticles, considering that the serum corresponds to the spectrum data corresponding to multiple components, the Raman surface enhanced spectrum data corresponding to the serum is processed by the support vector machine model without causing information loss, so that the coordinated operation of the surface enhanced Raman spectroscopy and the support vector machine model can coordinate the changes in the multi-dimensional parameters in the serum, reduce the randomness of the analysis and judgment, and improve the accuracy of the classification of the object to be tested.
[0063] In addition, the object classification method based on Raman surface enhanced spectroscopy of the embodiment of the present disclosure also provides the preparation steps of colloidal gold nanoparticles. That is, in some embodiments, the colloidal gold nanoparticles in the embodiment of the present disclosure are prepared by the following steps:
[0064] Two volumes of sodium citrate (1% w / v) aqueous solution and two volumes of citric acid (0.05% w / v) solution were added to 50 volumes of boiling HAuCl4·3H2O (0.01% w / v) solution to obtain a first mixed solution; the first mixed solution was boiled for 5 minutes and then cooled to room temperature as a seed solution; 3 mL of the seed solution was diluted to 20 mL with deionized water; the diluted seed solution was grown by 10 mL of the first solution containing HAuCl4·3H20 (0.04% w / v) and 10 mL of the second solution containing ascorbic acid (0.05% w / v) and sodium citrate (0.025% w / v) to obtain colloidal gold nanoparticles.
[0065] Here, w / v represents mass concentration.
[0066] In some embodiments, a volume may be 1 mL. In this case, 2 mL of sodium citrate (1% w / v) aqueous solution and 2 mL of citric acid (0.05% w / v) solution may be added to 50 mL of boiling HAuCl4·3H2O (0.01% w / v) solution to obtain a first mixed solution.
[0067] In some embodiments, growing the seed solution with 10 mL of a first solution containing HAuCl4·3H20 (0.04% w / v) and 10 mL of a second solution containing ascorbic acid (0.05% w / v) and sodium citrate (0.025% w / v) to obtain colloidal gold nanoparticles may include the following steps:
[0068] The first solution and the second solution are dropped into the diluted seed solution by siphoning to obtain a second mixed solution; the second mixed solution is drained for 40 minutes, and the drained second solution is boiled for 5 minutes and then cooled to obtain a growth solution after the first growth; 4.5 mL of the growth solution after the first growth is obtained and diluted to 20 mL with water; the first solution and the second solution are dropped into the diluted growth solution by siphoning to obtain a third mixed solution; the third mixed solution is drained for 40 minutes, and the drained third solution is boiled for 5 minutes and then cooled to obtain colloidal gold nanoparticles.
[0069] In some embodiments, when the first solution and the second solution are dripped into the diluted seed solution by siphoning, the first solution and the second solution can be dripped into the diluted seed solution in sequence in a tandem manner, so that the mixing of the second mixed solution can be increased.
[0070] That is, in some embodiments of the present disclosure, 2 mL of sodium citrate (1% w / v) aqueous solution and 2 mL of citric acid (0.05% w / v) solution can be added to 50 mL of boiling HAuCl4·3H2O (0.01% w / v) solution to obtain a first mixed solution, and the first mixed solution is boiled for 5 minutes and then cooled to room temperature as a seed solution for subsequent two rounds of growth of gold seeds.
[0071] In the first round of growth, 3 mL of seed solution was diluted to 20 mL with deionized water, and the first solution and the second solution were dripped into the diluted seed solution in sequence in a siphon manner in a tandem manner to obtain a second mixed solution. Then, the second mixed solution was drained for 40 minutes, and the drained second solution was boiled for 5 minutes and then cooled. Thus, the first round of growth was completed, and the growth solution after the first growth was obtained.
[0072] Next, 4.5 mL of the growth solution after the first growth was obtained and diluted to 20 mL with water, and then the first solution and the second solution were dripped into the diluted growth solution in sequence in a siphon manner in a tandem manner to obtain a third mixed solution. Then, the third mixed solution was drained for 40 minutes, and the drained third solution was boiled for 5 minutes and then cooled, thereby completing the second round of growth to obtain colloidal gold nanoparticles.
[0073] In some embodiments, after the second round of growth, the diameter of the colloidal gold nanoparticles obtained is 70-75 nm.
[0074] In addition, the disclosed embodiments also provide a process of mixing the serum of the subject and the colloidal gold nanoparticles to obtain a mixture, that is, in some embodiments, the sample data of the subject in the disclosed embodiments is prepared by the following steps:
[0075] 2 mL of colloidal gold nanoparticles were washed with deionized water, and the washed colloidal gold nanoparticles were concentrated to 10 μL; the concentrated colloidal gold nanoparticles were centrifuged at a centrifugal force of 4500 rpm for 5 minutes; 20 μL of serum was mixed with the centrifuged colloidal gold nanoparticles to obtain a fourth mixed solution; the fourth mixed solution was dropped on a quartz substrate and dried in a vacuum chamber for 30 minutes to obtain a mixture; the mixture was measured by Raman surface enhanced spectroscopy to obtain sample data of the object under test.
[0076] In the disclosed embodiment, 2 mL of colloidal gold nanoparticles can be washed with deionized water and concentrated to 10 μL. Then, a centrifuge can be used to centrifuge the concentrated colloidal gold nanoparticles at a centrifugal force of 4500 rpm for 5 minutes. Then, 20 μL of serum can be mixed with the centrifuged colloidal gold nanoparticles to obtain a fourth mixed solution. The fourth mixed solution is then dropped onto a quartz substrate and dried in a vacuum chamber for 30 minutes to obtain a mixture.
[0077] After the above operation, a local area of the mixture forms an uneven pattern of coffee ring-shaped AuNP aggregation. In some embodiments, Raman surface enhanced spectroscopy measurement can be performed at the edge of the coffee ring for 10 seconds to obtain Raman surface enhanced spectrum, i.e., sample data of the object being measured. By performing Raman surface enhanced spectroscopy measurement at the edge of the coffee ring, the reliability of the sample data can be improved.
[0078] In addition, the embodiment of the present disclosure also provides a training process of a pre-trained support vector machine, that is, in some embodiments, the object classification method based on Raman surface enhanced spectroscopy of the embodiment of the present disclosure may also include the following steps:
[0079] A plurality of training sample data are obtained, wherein one training sample data includes sample data of a sample object and a category corresponding to the sample object; an initial support vector machine model is trained based on the plurality of training sample data to obtain a pre-trained support vector machine model.
[0080] In the disclosed embodiment, supervised learning may be used to train the initial support vector machine model.
[0081] In the disclosed embodiment, the category corresponding to the sample object is obtained as a label, and then combined with the sample data of the sample object as a training sample data. By training the initial support vector machine model with multiple training sample data of different sample objects, a pre-trained support vector machine model can be obtained.
[0082] In the embodiment of the present disclosure, the sample data of the sample object may be a Raman surface enhanced spectrum obtained by performing Raman surface enhanced spectroscopy measurement on a mixture of the serum of the sample object and the colloidal gold nanoparticles prepared by the method of the above embodiment.
[0083] In some implementations, the support vector machine may use an RBF (Radial Basis Function) kernel, which may also be called a Gaussian kernel. The kernel parameter is set to 9, the cost is 10, and the training process of the support vector machine model is verified by venetian blind cross validation.
[0084] Figure 2 FIG. 1 is a block diagram of an object classification device based on Raman surface enhanced spectroscopy according to an exemplary embodiment of the present disclosure. Figure 2 As shown, the object classification device 200 based on Raman surface enhanced spectroscopy includes:
[0085] The first acquisition module 210 is configured to acquire sample data of the subject, wherein the sample data of the subject is a Raman surface enhanced spectrum obtained by performing Raman surface enhanced spectrum measurement on a mixture of serum of the subject and colloidal gold nanoparticles;
[0086] The processing module 220 is configured to process the sample data of the object under test through a pre-trained support vector machine model to obtain a category corresponding to the object under test.
[0087] In some embodiments, the apparatus 200 further comprises:
[0088] A second acquisition module is configured to acquire a plurality of training sample data, wherein each of the training sample data includes sample data of a sample object and a category corresponding to the sample object;
[0089] The training module is configured to train the initial support vector machine model based on the multiple training sample data to obtain the pre-trained support vector machine model.
[0090] In some embodiments, the colloidal gold nanoparticles are prepared by the following steps:
[0091] Adding 2 volumes of sodium citrate (1% w / v) aqueous solution and 2 volumes of citric acid (0.05% w / v) solution to 50 volumes of boiling HAuCl4·3H2O (0.01% w / v) solution to obtain a first mixed solution;
[0092] The first mixed solution was boiled for 5 minutes and then cooled to room temperature as a seed solution;
[0093] Dilute 3 mL of the seed solution to 20 mL with deionized water;
[0094] The diluted seed solution was grown by using 10 mL of a first solution containing HAuCl4·3H20 (0.04% w / v) and 10 mL of a second solution containing ascorbic acid (0.05% w / v) and sodium citrate (0.025% w / v) to obtain the colloidal gold nanoparticles.
[0095] In some embodiments, the colloidal gold nanoparticles are grown by growing the seed solution with 10 mL of a first solution containing HAuCl4·3H20 (0.04% w / v) and 10 mL of a second solution containing ascorbic acid (0.05% w / v) and sodium citrate (0.025% w / v), comprising:
[0096] dripping the first solution and the second solution into the diluted seed solution by siphoning to obtain a second mixed solution;
[0097] draining the second mixed solution for 40 minutes, boiling the drained second solution for 5 minutes and then cooling it to obtain a growth solution after the first growth;
[0098] Obtain 4.5 mL of the growth solution after the first growth and dilute it to 20 mL with water;
[0099] dripping the first solution and the second solution into the diluted growth solution in a siphoning manner to obtain a third mixed solution;
[0100] The third mixed solution was drained for 40 minutes, and the drained third solution was boiled for 5 minutes and then cooled to obtain the colloidal gold nanoparticles.
[0101] In some embodiments, the sample data of the subject is prepared by the following steps:
[0102] Wash 2 mL of the colloidal gold nanoparticles with deionized water, and concentrate the washed colloidal gold nanoparticles to 10 μL;
[0103] The concentrated colloidal gold nanoparticles were centrifuged at 4500 rpm for 5 min;
[0104] Mixing 20 μL of serum with the centrifuged colloidal gold nanoparticles to obtain a fourth mixed solution;
[0105] Dropping the fourth mixed solution on a quartz substrate, and drying in a vacuum chamber for 30 minutes to obtain the mixture;
[0106] The mixture is subjected to Raman surface enhanced spectroscopy measurement to obtain sample data of the measured object.
[0107] In some embodiments, the colloidal gold nanoparticles have a diameter of 70 to 75 nm.
[0108] In some embodiments, the sample data includes a Raman surface enhanced spectrum of at least one of tyrosine, phenylalanine, glutamine-leucine, hypoxanthine, thymine, cholesterol, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, and triglycerides.
[0109] Figure 3 FIG. 1 is a block diagram of an object classification device based on Raman surface enhanced spectroscopy according to an exemplary embodiment of the present disclosure. Figure 3 As shown, the object classification device 300 based on Raman surface enhanced spectroscopy includes a sample data acquisition device 310, a memory 320, a processor 330 and a category output device 340. Among them:
[0110] The sample data acquisition device 310 is used to acquire sample data of the object to be tested, wherein the sample data of the object to be tested is a Raman surface enhanced spectrum obtained by performing Raman surface enhanced spectrum measurement on a mixture of serum of the object to be tested and colloidal gold nanoparticles;
[0111] Memory 320, for storing program instructions executable by the processor;
[0112] The processor 330 is used to call the pre-trained support vector machine model stored in the memory to process the sample data of the object to be tested, so as to obtain the category corresponding to the object to be tested;
[0113] The category output device 340 is used to output the category corresponding to the detected object.
[0114] In some embodiments, the processor 330 is also used to obtain multiple training sample data, each of which includes sample data of a sample object and a category corresponding to the sample object; based on the multiple training sample data, the initial support vector machine model is trained to obtain the pre-trained support vector machine model.
[0115] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the following steps are implemented: obtaining sample data of the object to be tested, wherein the sample data of the object to be tested is a Raman surface enhanced spectrum obtained by performing Raman surface enhanced spectroscopy measurement on a mixture of serum of the object to be tested and colloidal gold nanoparticles; calling a pre-trained support vector machine model stored in a memory to process the sample data of the object to be tested to obtain a category corresponding to the object to be tested; and outputting the category corresponding to the object to be tested.
[0116] In addition, in some embodiments, when the program instructions are executed by the processor, the following steps can also be implemented: obtaining multiple training sample data, each of the training sample data includes sample data of a sample object and a category corresponding to the sample object; based on the multiple training sample data, training an initial support vector machine model to obtain the pre-trained support vector machine model.
[0117] Figure 4 FIG. 4 is a block diagram of an electronic device 400 according to an exemplary embodiment of the present disclosure. Figure 4 As shown, the electronic device 400 may include: a processor 401 and a memory 402. The electronic device 400 may also include one or more of a multimedia component 403, an input / output (I / O) interface 404, and a communication component 405.
[0118] The processor 401 is used to control the overall operation of the electronic device 400 to complete all or part of the steps in the above-mentioned Raman spectrum test method for mobile terminals. The memory 402 is used to store various types of data to support the operation of the electronic device 400, and these data may include instructions for any application or method for operating on the electronic device 400, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 402 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, disk or optical disk. The multimedia component 403 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone, which is used to receive external audio signals. The received audio signal may be further stored in the memory 402 or sent through the communication component 405. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 404 provides an interface between the processor 401 and other interface modules, and the above-mentioned other interface modules may be keyboards, mice, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 405 is used for wired or wireless communication between the electronic device 400 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or a combination of one or more of them, is not limited here. Therefore, the corresponding communication component 405 may include: Wi-Fi module, Bluetooth module, NFC module, etc.
[0119] In an exemplary embodiment, the electronic device 400 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned Raman spectroscopy test method applied to mobile terminals.
[0120] In another exemplary embodiment, a computer program product is provided. The computer program product includes a computer program executable by a programmable device. The computer program has a code portion for executing any of the above-mentioned object classification methods based on Raman surface enhanced spectroscopy when executed by the programmable device.
[0121] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.
[0122] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.
[0123] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.
Claims
1. An object classification method based on Raman surface enhanced spectroscopy, characterized in that: The method comprises: Acquiring sample data of the subject to be tested, wherein the sample data of the subject to be tested is a Raman surface enhanced spectrum obtained by performing Raman surface enhanced spectroscopy measurement on a mixture of serum of the subject to be tested and colloidal gold nanoparticles; The sample data of the object to be measured is processed by a pre-trained support vector machine model to obtain the category corresponding to the object to be measured.
2. The method according to claim 1, characterized in that The method further comprises: Acquire a plurality of training sample data, wherein each of the training sample data includes sample data of a sample object and a category corresponding to the sample object; Based on the multiple training sample data, an initial support vector machine model is trained to obtain the pre-trained support vector machine model.
3. The method according to claim 1, characterized in that The colloidal gold nanoparticles are prepared by the following steps: Adding 2 volumes of sodium citrate (1% w / v) aqueous solution and 2 volumes of citric acid (0.05% w / v) solution to 50 volumes of boiling HAuCl4·3H2O (0.01% w / v) solution to obtain a first mixed solution; The first mixed solution was boiled for 5 minutes and then cooled to room temperature as a seed solution; Dilute 3 mL of the seed solution to 20 mL with deionized water; The diluted seed solution was grown by using 10 mL of a first solution containing HAuCl4·3H20 (0.04% w / v) and 10 mL of a second solution containing ascorbic acid (0.05% w / v) and sodium citrate (0.025% w / v) to obtain the colloidal gold nanoparticles.
4. The method according to claim 3, characterized in that The method comprises: growing the seed solution with 10 mL of a first solution containing HAuCl4·3H20 (0.04% w / v) and 10 mL of a second solution containing ascorbic acid (0.05% w / v) and sodium citrate (0.025% w / v) to obtain the colloidal gold nanoparticles, comprising: dripping the first solution and the second solution into the diluted seed solution by siphoning to obtain a second mixed solution; draining the second mixed solution for 40 minutes, boiling the drained second solution for 5 minutes and then cooling it to obtain a growth solution after the first growth; Obtain 4.5 mL of the growth solution after the first growth and dilute it to 20 mL with water; dripping the first solution and the second solution into the diluted growth solution in a siphoning manner to obtain a third mixed solution; The third mixed solution was drained for 40 minutes, and the drained third solution was boiled for 5 minutes and then cooled to obtain the colloidal gold nanoparticles.
5. The method according to claim 1, characterized in that The sample data of the measured object is prepared by the following steps: Wash 2 mL of the colloidal gold nanoparticles with deionized water, and concentrate the washed colloidal gold nanoparticles to 10 μL; The concentrated colloidal gold nanoparticles were centrifuged at 4500 rpm for 5 min; Mixing 20 μL of serum with the centrifuged colloidal gold nanoparticles to obtain a fourth mixed solution; Dropping the fourth mixed solution on a quartz substrate, and drying in a vacuum chamber for 30 minutes to obtain the mixture; The mixture is subjected to Raman surface enhanced spectroscopy measurement to obtain sample data of the measured object.
6. The method according to any one of claims 1 to 5, characterized in that: The diameter of the colloidal gold nanoparticles is 70-75 nm.
7. The method according to any one of claims 1 to 5, characterized in that: The sample data includes a Raman surface enhanced spectrum of at least one of tyrosine, phenylalanine, glutamine-leucine, hypoxanthine, thymine, cholesterol, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol and triglycerides.
8. An object classification device based on Raman surface enhanced spectroscopy, characterized in that: The device comprises: An acquisition module is configured to acquire sample data of the object under test, wherein the sample data of the object under test is a Raman surface enhanced spectrum obtained by performing Raman surface enhanced spectrum measurement on a mixture of serum of the object under test and colloidal gold nanoparticles; The processing module is configured to process the sample data of the object under test through a pre-trained support vector machine model to obtain a category corresponding to the object under test.
9. An object classification device based on Raman surface enhanced spectroscopy, characterized in that: The device comprises: A sample data acquisition device, used to acquire sample data of a test object, wherein the sample data of the test object is a Raman surface enhanced spectrum obtained by performing Raman surface enhanced spectrum measurement on a mixture of serum of the test object and colloidal gold nanoparticles; A memory for storing program instructions executable by the processor; A processor, configured to call a pre-trained support vector machine model stored in a memory to process the sample data of the object under test, and obtain a category corresponding to the object under test; Category output device, used for outputting the category corresponding to the measured object.
10. A storage medium having program instructions stored thereon, characterized in that: When the program instructions are executed by the processor, the following steps are implemented: Acquiring sample data of the subject to be tested, wherein the sample data of the subject to be tested is a Raman surface enhanced spectrum obtained by performing Raman surface enhanced spectroscopy measurement on a mixture of serum of the subject to be tested and colloidal gold nanoparticles; Calling a pre-trained support vector machine model stored in a memory to process the sample data of the object under test to obtain a category corresponding to the object under test; Output the category corresponding to the object under test.