Rapid diagnosis method for field symptoms of sesame wilt
Spectral features are extracted through hyperspectral imaging technology and algorithms, and a diagnostic model for sesame blight is established, which solves the subjectivity and time-consuming problems of existing diagnostic methods, and achieves rapid and accurate diagnosis of sesame blight, and supports real-time detection in the field.
Patent Information
- Application Number
- CN202411598441.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-11
- Publication Date
- 2025-03-11
AI Technical Summary
The existing diagnosis methods for sesame blight are subjectively affected by subjective observation, cumbersome and time-consuming, and cannot be detected in real time in the field, making it difficult to meet the needs of fast and accurate diagnosis.
Hyperspectral imaging technology is used to capture the spectral data of sesame plants within a specific spectral range, combine algorithms to extract key spectral characteristics, establish diagnostic models, and achieve rapid, accurate and non-destructive diagnosis of sesame blight.
It improves diagnostic efficiency, ensures the objectivity and accuracy of diagnostic results, can be directly applied in the field, and supports early detection and timely prevention and treatment.
Smart Images
Figure CN119595561A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of agricultural disease diagnosis, in particular to a method for rapid field symptom diagnosis of sesame wilt. Background Art
[0002] As an important oil and edible crop, sesame occupies an important position in global agricultural production. However, sesame is often threatened by a variety of diseases during its growth, among which wilt is particularly serious. Fusarium wilt is caused by the sesame-specific pathogen Fusarium oxysporum, which infects the roots and stems of sesame, destroys the plant's vascular system, and causes plant growth stagnation, ultimately affecting sesame yield and quality. Accurate and timely diagnosis of sesame wilt is crucial for formulating effective prevention and control strategies and ensuring agricultural production.
[0003] Among traditional diagnostic methods, the identification of sesame wilt disease mainly relies on manual observation of plant symptoms, collection of samples for pathogen detection and laboratory analysis. Although these methods can diagnose the disease to a certain extent, they have many shortcomings. First, manual observation of symptoms is easily affected by subjective judgment, leading to misdiagnosis or missed diagnosis. Second, the pathogen detection and laboratory analysis process is cumbersome and time-consuming, and it is difficult to meet the needs of large-scale and rapid diagnosis. Finally, these methods usually need to be carried out under laboratory conditions and cannot be directly tested in real time in the field, which limits their application in actual production.
[0004] In view of the above situation, it is necessary to optimize the existing rapid diagnosis method of sesame wilt field symptoms, and realize rapid and accurate diagnosis of sesame wilt by capturing the characteristic changes of sesame plants within a specific spectral range. Therefore, it is of great significance to develop a rapid diagnosis method of sesame wilt field symptoms that can comprehensively realize the above characteristics. Summary of the invention
[0005] The purpose of the present invention is to make up for the deficiencies of the prior art and provide a method for rapid diagnosis of field symptoms of sesame wilt disease. The method can utilize the advantages of hyperspectral imaging technology in spectral data acquisition and analysis, capture the characteristic changes of sesame plants within a specific spectral range, and combine with an algorithm to achieve rapid, accurate, and non-destructive diagnosis of sesame wilt disease, thereby not only improving the diagnostic efficiency, but also ensuring the objectivity and accuracy of the diagnostic results. At the same time, the non-destructive detection method enables the method to be directly applied in the field, providing strong technical support for the early detection and timely prevention and control of sesame wilt disease.
[0006] In order to solve the above technical problems, the present invention provides the following technical solution: a method for rapid diagnosis of field symptoms of sesame wilt, the method comprising the following specific steps:
[0007] S100, equipment preparation: prepare a hyperspectral imaging device that can cover the visible light to near infrared spectrum;
[0008] S200, field data collection: In the sesame field, sesame plants of different health conditions are selected as samples, and each sesame plant is scanned using a hyperspectral imaging device to obtain its reflection or transmission spectrum data within a specific spectral range;
[0009] S300, spectral feature extraction: preprocessing the collected spectral data, including denoising, smoothing and normalization, to extract key spectral features related to sesame wilt disease;
[0010] S400, model building and training: Based on the extracted spectral features, the algorithm is used to build a diagnostic model for sesame wilt disease, and the spectral data of known healthy and wilt samples are used to train and verify the model;
[0011] S500, rapid diagnosis: The trained model is deployed to the field diagnosis system, and the sesame plants to be diagnosed are scanned by hyperspectral imaging to obtain their spectral data, and analysis is performed based on the data.
[0012] Furthermore, the step S200 includes:
[0013] S201, in the sesame field, healthy plants, plants suspected of having wilt disease, and plants known to have wilt disease were preliminarily selected as samples based on the external symptoms of the plants;
[0014] S202, before data collection, control the consistency of the field environment, including light intensity, temperature and humidity, to reduce the impact of environmental factors on spectral data;
[0015] S203, using a hyperspectral imaging device to scan each sesame plant.
[0016] Furthermore, the specific steps of scanning each sesame plant using a hyperspectral imaging device in step S203 are as follows:
[0017] (1) Aim the hyperspectral imaging device at the sesame plant to be scanned, and adjust the distance and angle between the lens and the plant to cover the entire plant or key parts;
[0018] (2) Start the scanning program. The device will automatically scan the plants according to the preset parameters and modes. During the scanning process, keep the device stable.
[0019] (3) The device will automatically record the spectral data acquired during the scanning process and store it in the internal memory or external storage device.
[0020] Furthermore, the step S300 includes:
[0021] S301, importing the collected spectral data into data processing software, and performing preprocessing operations including denoising, smoothing and normalization;
[0022] S302, based on the study of spectral characteristics of sesame wilt, key wavelengths or bands related to the disease are selected as features, including reflectance changes at specific wavelengths, specific shapes and slopes of spectral curves;
[0023] S303, extracting key features from the preprocessed spectral data using an algorithm.
[0024] Furthermore, the step S303 uses an algorithm to extract key features from the preprocessed spectral data. Specifically, the preprocessed data is standardized to obtain a standardized data matrix Z, and the covariance matrix C of the standardized data matrix Z is calculated, and the calculation formula is: Where n is the number of samples, Z T is the transposed matrix of Z, C is the covariance matrix, and by performing eigenvalue decomposition on the covariance matrix C, we get the eigenvalues λ1≥λ2≥…≥λ p and the corresponding eigenvectors q1,q2,…,q p , select the first k eigenvectors as principal components according to the size of the eigenvalue, project the original data Z onto the k principal component, and obtain the reduced-dimensional data matrix T, whose calculation formula is: T = ZQ k , Q k It is a matrix composed of the first k eigenvectors. The column vectors of the matrix T represent the scores of each sample on the selected k principal components, which serve as the key features extracted from the preprocessed data.
[0025] Furthermore, the step S400 includes:
[0026] S401, dividing the feature data set into a training set and a test set, the training set is used for model establishment and training, and the test set is used for evaluating the performance of the model;
[0027] S402, selecting an algorithm to build a diagnostic model based on data characteristics and diagnostic requirements;
[0028] S403, training the selected model using the training set data;
[0029] S404, use the test set data to verify the trained model and evaluate its accuracy, stability and generalization ability.
[0030] Furthermore, the step S402 selects an algorithm to construct a diagnosis model according to data characteristics and diagnosis requirements, and the algorithm formula is: Among them, S is the health status index of sesame plants, R irepresents the reflectivity at a specific wavelength i, n is the number of key wavelengths selected, and w i is the weight coefficient of wavelength i, k is the adjustment parameter, thresholds T1 and T2 are set, and T1<T2. When S is less than threshold T1, it can be judged as infected with wilt disease and it is more serious. When S is between thresholds T1 and T2, it is judged as suspected infection. When S is greater than threshold T2, it is judged as a healthy plant.
[0031] Furthermore, the specific steps of step S403 for training the selected model using the training set data are:
[0032] (1) Input the data in the training set into the model and calculate the error between the model's predicted output and the actual output;
[0033] (2) Calculate the gradient based on the error and back-propagate the gradient to each layer of the model to update the model parameters;
[0034] (3) Use an optimization algorithm to update the model parameters based on the gradient to reduce the error;
[0035] (4) Repeat the iteration until the preset number of iterations is reached.
[0036] Furthermore, the step S403 uses an optimization algorithm to update the parameters of the model according to the gradient, and the calculation formula is: Where: θ t+1 is the updated model parameter, θ t is the current model parameter, η is the learning rate, which controls the step size of parameter update, In the current dataset D t The gradient of the loss function L with respect to the model parameter θ, λ is the weight factor, Δθ hist It is the model parameter adjustment amount calculated based on the feedback results. This formula calculates the gradient of the loss function based on the current data and adjusts the model parameters based on the feedback.
[0037] Furthermore, the step S500 includes:
[0038] S501, deploying the trained model to the field diagnosis system, performing hyperspectral imaging scanning on the sesame plants to be diagnosed, and obtaining their spectral data;
[0039] S502, inputting the spectral data obtained by scanning into the diagnostic model, the model will automatically process and analyze the spectral data, extract key features and compare them with the training set data;
[0040] S503, the model outputs a diagnosis conclusion based on the comparison result, including whether the wilt disease is infected and its severity, and the diagnosis result is presented to the user through a display screen, a printed report, and a wireless transmission method.
[0041] Compared with the prior art, the method for rapid diagnosis of field symptoms of sesame wilt has the following beneficial effects:
[0042] 1. The present invention adopts hyperspectral imaging technology to automatically and quickly obtain spectral data of sesame plants within a specific spectral range, and accurately extracts spectral features related to wilt disease through advanced data processing and algorithms, thereby achieving accurate diagnosis of the disease. It not only greatly improves the diagnostic efficiency and reduces manual intervention, but also significantly improves the accuracy of diagnosis, providing a reliable basis for timely prevention and control measures.
[0043] 2. By deploying the trained diagnostic model into the field diagnostic system, the present invention can realize real-time monitoring and rapid diagnosis of sesame plants, and timely detect and control the spread of diseases. This not only helps to reduce the impact of diseases on sesame yields and improve agricultural production efficiency, but also helps to promote the intelligent transformation of agricultural production and promote sustainable agricultural development.
[0044] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0045] 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 prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0046] Figure 1 This is a flowchart of a rapid field symptom diagnosis method for sesame wilt;
[0047] Figure 2 Flowchart for model establishment and training of a rapid field symptom diagnosis method for sesame wilt. DETAILED DESCRIPTION
[0048] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0049] Embodiment 1
[0050] This embodiment describes in detail a specific implementation method of a method for rapid diagnosis of field symptoms of sesame wilt disease. By using a hyperspectral imaging device to collect spectral information of sesame plants and combining an algorithm to analyze the spectral data, a rapid and accurate diagnosis of sesame wilt disease can be achieved.
[0051] For the equipment preparation stage (S100), a hyperspectral imaging device that can cover the visible light to near-infrared spectral range is prepared. The device should have high resolution, high sensitivity and fast scanning capabilities to ensure the quality of the collected spectral data. The hyperspectral imaging device is calibrated before use to ensure the accuracy and repeatability of the spectral data.
[0052] In the field data collection stage (S200), in the sesame field, healthy plants, suspected wilt plants and known wilt plants are preliminarily screened as samples based on the appearance symptoms of the plants (such as leaf color, morphological changes, etc.). The selection of samples should be representative to cover sesame plants with different health conditions and disease levels. Before data collection, the consistency of the field environment, including light intensity, temperature and humidity, is controlled. The impact of environmental factors on spectral data is reduced by building a sunshade and using temperature control equipment. A hyperspectral imaging device is used to scan each sesame plant. The device is aimed at the sesame plant to be scanned, and the distance and angle between the lens and the plant are adjusted to ensure that the entire plant or key parts (such as leaves, stems, etc.) are covered. The scanning program is started, and the device will automatically scan the plant according to the preset parameters and mode, and record the spectral data during the scanning process.
[0053] In the spectral feature extraction stage (S300), the collected spectral data is imported into the data processing software for preprocessing operations such as denoising, smoothing and normalization. The denoising operation can eliminate random noise and outliers in the data, the smoothing operation can reduce data fluctuations and improve the signal-to-noise ratio, and the normalization process can eliminate the differences between different samples caused by factors such as light intensity. According to the spectral feature research of sesame wilt disease, key wavelengths or bands related to the disease are selected as features. These features usually include reflectivity changes at specific wavelengths, specific shapes and slopes of spectral curves, etc. By comparing the spectral data of healthy plants and wilt plants, the characteristic wavelengths or bands closely related to the disease can be determined. The algorithm is used to extract key features from the preprocessed spectral data. The algorithm can reduce the data dimension, extract the characteristic components that have the greatest impact on the diagnosis results, and improve the efficiency and accuracy of model training.
[0054] For the model building and training stage (S400), the extracted feature data set is divided into a training set and a test set. The training set is used for model building and training, and the test set is used to evaluate the performance of the model. The algorithm is selected according to the data characteristics and diagnostic requirements to build a diagnostic model. The selected model is trained using the training set data. The error between the predicted output and the actual output of the model is calculated, and the gradient is calculated based on the error to update the model parameters. This process usually involves multiple iterations until the preset number of iterations is reached or other stopping conditions are met. The trained model is verified using the test set data to evaluate its accuracy, stability and generalization ability. The model performance is quantified by calculating indicators such as the model's accuracy, recall rate, and F1 score.
[0055] In the rapid diagnosis stage (S500), the trained model is deployed to the field diagnosis system, which can be a portable device or integrated on platforms such as drones and ground robots to realize automated and intelligent diagnosis services. The sesame plants to be diagnosed are scanned by hyperspectral imaging to obtain their spectral data. The spectral data obtained by the scan is input into the diagnosis model. The model will automatically process and analyze the spectral data, extract key features and compare them with the training set data. The model outputs a diagnosis conclusion based on the comparison results, including whether the plant is infected with wilt disease and its severity. The diagnosis results can be intuitively displayed to farmers or technicians through a display screen, and can be sent to agricultural management departments or relevant experts through wireless transmission for further analysis and processing. In addition, the diagnosis results can also be combined with other agricultural information (such as weather, soil conditions, etc.) to provide farmers with targeted prevention and control suggestions.
[0056] In summary, this embodiment, by adopting hyperspectral imaging technology, can automatically and quickly obtain spectral data of sesame plants within a specific spectral range, and through advanced data processing and algorithms, accurately extract spectral features related to wilt disease, thereby achieving accurate diagnosis of the disease. It not only greatly improves the diagnostic efficiency and reduces manual intervention, but also significantly improves the accuracy of diagnosis, providing a reliable basis for timely prevention and control measures.
[0057] Embodiment 2
[0058] Based on the first embodiment, this embodiment describes in detail the model establishment and training process of a method for rapid field symptom diagnosis of sesame wilt.
[0059] From the sesame plant spectral data collected by the hyperspectral imaging device, the algorithm is used to extract key features from the preprocessed spectral data. Specifically, the preprocessed data is standardized to obtain the standardized data matrix Z, and the covariance matrix C of the standardized data matrix Z is calculated. The calculation formula is: Where n is the number of samples, Z Tis the transposed matrix of Z, C is the covariance matrix, and by performing eigenvalue decomposition on the covariance matrix C, we get the eigenvalues λ1≥λ2≥…≥λ p and the corresponding eigenvectors q1,q2,…,q p , select the first k eigenvectors as principal components according to the size of the eigenvalue, project the original data Z onto the k principal component, and obtain the reduced-dimensional data matrix T, whose calculation formula is: T = ZQ k , Q k It is a matrix composed of the first k eigenvectors. The column vectors of the matrix T represent the scores of each sample on the selected k principal components, which serve as the key features extracted from the preprocessed data.
[0060] The feature data set is randomly divided into a training set and a test set. The training set is used to establish and train the model, and the test set is used to evaluate the performance of the model. According to the characteristics and data characteristics of sesame wilt disease diagnosis, an algorithm is selected as the diagnostic model. According to the data characteristics and diagnostic requirements, an algorithm is selected to construct a diagnostic model. The algorithm formula is as follows: Among them, S is the health status index of sesame plants, R i represents the reflectivity at a specific wavelength i, n is the number of key wavelengths selected, and w i is the weight coefficient of wavelength i, k is the adjustment parameter, thresholds T1 and T2 are set, and T1<T2. When S is less than threshold T1, it can be judged as infected with wilt disease and it is more serious. When S is between thresholds T1 and T2, it is judged as suspected infection. When S is greater than threshold T2, it is judged as a healthy plant.
[0061] The random forest model is trained using the training set data. During the training process, the data in the training set is input into the model, the error between the predicted output and the actual output of the model is calculated, the gradient is calculated based on the error, and the gradient is back-propagated to each layer of the model to update the parameters of the model. The optimization algorithm is used to update the parameters of the model based on the gradient to reduce the error. The calculation formula is: Where: θ t+1 is the updated model parameter, θ t is the current model parameter, η is the learning rate, which controls the step size of parameter update, In the current dataset D t The gradient of the loss function L with respect to the model parameter θ, λ is the weight factor, Δθ hist It is the amount of model parameter adjustment calculated based on the feedback results. The formula calculates the gradient of the loss function based on the current data, and adjusts the model parameters based on the feedback, repeating the iteration until the preset number of iterations is reached.
[0062] In summary, this embodiment extracts key features from hyperspectral imaging data, constructs a data set containing the characteristics of healthy plants and wilt plants, and divides it into a training set and a test set. Subsequently, an algorithm is selected to build a model and train it, thereby achieving real-time monitoring and rapid diagnosis of sesame plants.
[0063] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.
Claims
1. A method for rapid diagnosis of field symptoms of sesame wilt, characterized in that: The method comprises the following specific steps: S100, equipment preparation: preparing a hyperspectral imaging device, and the device can cover the visible light to near infrared spectrum range; S200, field data collection: In the sesame field, sesame plants of different health conditions are selected as samples, and each sesame plant is scanned using a hyperspectral imaging device to obtain its reflection or transmission spectrum data within a specific spectral range; S300, spectral feature extraction: preprocessing the collected spectral data, including denoising, smoothing and normalization, to extract key spectral features related to sesame wilt disease; S400, model building and training: Based on the extracted spectral features, the algorithm is used to build a diagnostic model for sesame wilt disease, and the spectral data of known healthy and wilt samples are used to train and verify the model; S500, rapid diagnosis: The trained model is deployed to the field diagnosis system, and the sesame plants to be diagnosed are scanned by hyperspectral imaging to obtain their spectral data, and analysis is performed based on the data.
2. A method for rapid diagnosis of field symptoms of sesame wilt according to claim 1, characterized in that: The step S200 includes: S201, in the sesame field, healthy plants, plants suspected of having wilt disease, and plants known to have wilt disease were preliminarily selected as samples based on the external symptoms of the plants; S202, before data collection, control the consistency of the field environment, including light intensity, temperature and humidity, to reduce the impact of environmental factors on spectral data; S203, using a hyperspectral imaging device to scan each sesame plant.
3. A method for rapid diagnosis of field symptoms of sesame wilt according to claim 2, characterized in that: The specific steps of step S203 of using a hyperspectral imaging device to scan each sesame plant are: (1) Aim the hyperspectral imaging device at the sesame plant to be scanned, and adjust the distance and angle between the lens and the plant to cover the entire plant or key parts; (2) Start the scanning program. The device will automatically scan the plants according to the preset parameters and modes. During the scanning process, keep the device stable. (3) The device will automatically record the spectral data acquired during the scanning process and store it in the internal memory or external storage device.
4. The method for rapid diagnosis of field symptoms of sesame wilt according to claim 1, characterized in that: The step S300 includes: S301, importing the collected spectral data into data processing software, and performing preprocessing operations including denoising, smoothing and normalization; S302, based on the study of spectral characteristics of sesame wilt, key wavelengths or bands related to the disease are selected as features, including reflectance changes at specific wavelengths, specific shapes and slopes of spectral curves; S303, extracting key features from the preprocessed spectral data using an algorithm.
5. A method for rapid diagnosis of field symptoms of sesame wilt according to claim 4, characterized in that: The step S303 uses an algorithm to extract key features from the preprocessed spectral data. Specifically, the preprocessed data is standardized to obtain a standardized data matrix Z, and the covariance matrix C of the standardized data matrix Z is calculated. The calculation formula is: Where n is the number of samples, Z T is the transposed matrix of Z, C is the covariance matrix, and by performing eigenvalue decomposition on the covariance matrix C, we get the eigenvalues λ1≥λ2≥…≥λ p and the corresponding eigenvectors q1,q2,…,q p , select the first k eigenvectors as principal components according to the size of the eigenvalue, project the original data Z onto the k principal component, and obtain the reduced-dimensional data matrix T, whose calculation formula is: T = ZQ k , Q k It is a matrix composed of the first k eigenvectors. The column vectors of the matrix T represent the scores of each sample on the selected k principal components, which serve as the key features extracted from the preprocessed data.
6. The method for rapid diagnosis of field symptoms of sesame wilt according to claim 1, characterized in that: The step S400 includes: S401, dividing the feature data set into a training set and a test set, the training set is used for model establishment and training, and the test set is used for evaluating the performance of the model; S402, selecting an algorithm to build a diagnostic model based on data characteristics and diagnostic requirements; S403, training the selected model using the training set data; S404, use the test set data to verify the trained model and evaluate its accuracy, stability and generalization ability.
7. A method for rapid diagnosis of field symptoms of sesame wilt according to claim 6, characterized in that ,The step S402 selects an algorithm to construct a diagnostic model according to data characteristics and diagnostic requirements, and the algorithm formula is: Among them, S is the health status index of sesame plants, R i represents the reflectivity at a specific wavelength i, n is the number of key wavelengths selected, and w i is the weight coefficient of wavelength i, k is the adjustment parameter, thresholds T1 and T2 are set, and T1<T2. When S is less than threshold T1, it can be judged as infected with wilt disease and it is more serious. When S is between thresholds T1 and T2, it is judged as suspected infection. When S is greater than threshold T2, it is judged as a healthy plant.
8. The method for rapid diagnosis of field symptoms of sesame wilt according to claim 6, characterized in that The specific steps of step S403 for training the selected model using the training set data are: (1) Input the data in the training set into the model and calculate the error between the model's predicted output and the actual output; (2) Calculate the gradient based on the error and back-propagate the gradient to each layer of the model to update the model parameters; (3) Use an optimization algorithm to update the model parameters based on the gradient to reduce the error; (4) Repeat the iteration until the preset number of iterations is reached.
9. A method for rapid diagnosis of field symptoms of sesame wilt according to claim 8, characterized in that ,The step S403 uses an optimization algorithm to update the parameters of the model according to the gradient, and its calculation formula is: Where: θ t+1 is the updated model parameter, θ t is the current model parameter, η is the learning rate, which controls the step size of parameter update, In the current dataset D t The gradient of the loss function L with respect to the model parameter θ, λ is the weight factor, Δθ hist It is the model parameter adjustment amount calculated based on the feedback results. This formula calculates the gradient of the loss function based on the current data and adjusts the model parameters based on the feedback.
10. The method for rapid diagnosis of field symptoms of sesame wilt according to claim 1, characterized in that , the step S500 includes: S501, deploying the trained model to the field diagnosis system, performing hyperspectral imaging scanning on the sesame plants to be diagnosed, and obtaining their spectral data; S502, inputting the spectral data obtained by scanning into the diagnostic model, the model will automatically process and analyze the spectral data, extract key features and compare them with the training set data; S503, the model outputs a diagnosis conclusion based on the comparison result, including whether the wilt disease is infected and its severity, and the diagnosis result is presented to the user through a display screen, a printed report, and a wireless transmission method.