Chip for pneumoconiosis detection electronic nose and detection system

Abstract

The invention discloses a chip for a pneumoconiosis detection electronic nose and a detection system, and the chip comprises a gas parameter database which is used for storing gas component parameter data and a gas component proportion; the smell detection subsystem is used for inputting exhaled gas to be detected and converting the exhaled gas into gas parameter values; the data analysis system is used for analyzing according to the stored data and the gas parameter values, and judging whether the input exhaled gas suffers from pneumoconiosis or not and the lung condition; the result evaluation subsystem is used for evaluating the pneumoconiosis degree according to the lung condition; and the display subsystem is used for displaying the gas parameter value, the lung condition and the pneumoconiosis degree evaluation result. According to the pneumoconiosis detection system and method, the gas components of the gas exhaled by different organisms are stored by setting the database system, the lung state corresponding to the exhaled gas is obtained in a weight distribution and calculation mode, the pneumoconiosis degree is obtained through a score calculation method when it is judged that the pneumoconiosis occurs, and rapid detection of the pneumoconiosis is achieved.

Description

Technical Field

[0001] The invention belongs to the technical field of pneumoconiosis detection, and in particular relates to a chip and a detection system for an electronic nose for pneumoconiosis detection. Background Art

[0002] Pneumoconiosis is a systemic disease characterized by diffuse fibrosis (scarring) of lung tissue caused by long-term inhalation of industrial dust (dust) and its retention in the lungs. Pneumoconiosis is a preventable but incurable disease. The current medical level can only alleviate the pain of pneumoconiosis patients, but cannot cure the disease. Therefore, early and rapid identification of pneumoconiosis symptoms is crucial to physical health.

[0003] Existing methods of detecting pneumoconiosis often rely on doctors to make manual diagnoses through the patient's X-ray images. This method not only has the defects of cumbersome procedures and inability to make rapid diagnosis, but also the imaging effect of X-ray films is easily affected by the external environment, thereby affecting the diagnosis results. Summary of the invention

[0004] The purpose of the present invention is to provide a chip and a detection system for an electronic nose for pneumoconiosis detection, so as to solve the problems existing in the above-mentioned prior art.

[0005] On the one hand, to achieve the above-mentioned purpose, the present invention provides a chip for electronic nose for pneumoconiosis detection, including a gas parameter database, a gas detection subsystem, a data analysis subsystem, a result evaluation subsystem, and a display subsystem;

[0006] Wherein, the gas parameter database and the gas detection subsystem are respectively connected to the data analysis subsystem; the data analysis subsystem, the result evaluation subsystem and the display subsystem are connected in sequence;

[0007] The gas parameter database is used to store gas composition parameter data and gas composition ratio;

[0008] The gas detection subsystem is used to input the exhaled gas to be detected, convert the exhaled gas into an output signal, and convert the output signal into a gas parameter value;

[0009] The data analysis system is used to analyze the stored data in the gas parameter database and the gas parameter value to obtain the lung condition;

[0010] The result evaluation subsystem evaluates the degree of pneumoconiosis according to the lung condition;

[0011] The display subsystem is used to display the gas parameter values, lung conditions and the pneumoconiosis degree evaluation results of each detection process.

[0012] Optionally, the gas parameter database includes exhaled gas component parameters of gases with odors of several animals and human bodies and the proportion of each gas component, and also includes standard component values ​​of exhaled gas of each animal and human body suffering from pneumoconiosis and the proportion of each gas component.

[0013] Optionally, the gas detection subsystem includes a plurality of electronic nose devices, and the electronic nose devices include a sampling module, a sensor module, a control drive circuit, a single-chip control chip, an interface circuit and a data processing circuit;

[0014] The exhaled gas enters the sensor module through the sampling module, the exhaled gas is detected by the sensor module, an output signal is obtained and transmitted to the signal processing circuit through the single-chip control chip, the signal processing circuit includes a processing chip, the signal feature of the output signal is extracted by the processing chip, and a signal recognition algorithm is used to build and train the model, and the output signal is converted into a corresponding gas parameter value in combination with the parameter data in the gas parameter database.

[0015] Optionally, the data analysis subsystem performs statistical calculations on the gas parameter values ​​output by the gas detection subsystem, and performs parameter comparison with the gas parameter values ​​based on the gas composition parameters in the gas parameter database and the proportion of each gas component. When each gas component value in the gas parameter value reaches the standard composition value of pneumoconiosis gas, a lung injury score is obtained based on the gas parameter value and the proportion of each gas, combined with the gas component proportion in the gas parameter database. A weight is allocated based on the lung injury score, a pneumoconiosis degree score is calculated based on the weight allocation result, and the lung condition is obtained based on the pneumoconiosis degree score.

[0016] Optionally, the result evaluation subsystem constructs a fuzzy evaluation library to evaluate the degree of pneumoconiosis, the fuzzy evaluation library includes the degree of pneumoconiosis and lung condition, the lung condition is converted into the degree of pneumoconiosis, the degree of pneumoconiosis is converted into a fuzzy language value, the fuzzy language value includes TE, E, M and B, the degree of pneumoconiosis is converted into the fuzzy language value and input into the fuzzy evaluation library, a fuzzy judgment is made on the lung condition, and a lung condition evaluation result is obtained.

[0017] Optionally, the display subsystem integrates and displays the gas parameter values, whether pneumoconiosis is present, lung condition and lung status evaluation results obtained during each detection process, and displays the comparison data between the data analysis subsystem and the gas parameter database during each detection process in the form of a bar graph.

[0018] On the other hand, to achieve the above-mentioned purpose, the present invention provides a pneumoconiosis detection system, including a transistor structure, a gas sensor array and a signal analysis module;

[0019] wherein the gas sensor array is connected to the signal analysis module via the transistor structure;

[0020] The gas sensor array includes a plurality of gas sensors made of carbon nanotubes;

[0021] The signal analysis module is used to convert the output signal of the gas sensor into a gas parameter value by using a signal recognition algorithm.

[0022] Optionally, the transistor includes a substrate, a gate insulating layer, and a channel active layer, an active electrode and a drain electrode are arranged on the channel active layer, and the channel active layer is a quantum dot film formed by depositing quantum dot material; and a gate electrode is arranged on the substrate.

[0023] Optionally, the signal recognition algorithm adopted by the signal analysis module includes cluster analysis method, principal component analysis method, probabilistic neural network algorithm, reverse artificial neural network algorithm, Bayesian algorithm and matrix decomposition method.

[0024] The technical effects of the present invention are:

[0025] The present invention stores the gas components of exhaled gases of different organisms by setting up a database system, and converts the exhaled gases to be detected into parameter values ​​by using a recognition algorithm, and compares them with the database data, and obtains the lung state corresponding to the exhaled gases by means of weight distribution and calculation. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0027] Figure 1 Schematic diagram of the structure of a pneumoconiosis detection system in an embodiment of the present invention. DETAILED DESCRIPTION

[0028] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0029] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0030] Embodiment 1

[0031] like Figure 1 As shown, this embodiment provides a pneumoconiosis detection system, including a gas parameter database, a gas detection subsystem, a data analysis subsystem, a result evaluation subsystem, and a display subsystem;

[0032] Among them, the gas parameter database and the gas detection subsystem are connected to the data analysis subsystem respectively; the data analysis subsystem, the result evaluation subsystem and the display subsystem are connected in sequence;

[0033] The functional structure of each subsystem includes: the gas parameter database is used to store gas component parameter data and gas component ratio; the gas detection subsystem is used to input the exhaled gas to be detected, and convert the exhaled gas into an output signal, and convert the output signal into a gas parameter value; the data analysis system is used to analyze the stored data in the gas parameter database and the gas parameter value to determine whether the input exhaled gas suffers from pneumoconiosis and the lung condition; the result evaluation subsystem evaluates the degree of pneumoconiosis according to the lung condition; the display subsystem is used to display the gas parameter value, lung condition and pneumoconiosis degree evaluation results of each detection process. Specifically:

[0034] The gas parameter database includes exhaled gas component parameters of several animals and human odor gases and the proportion of each gas component, as well as the standard component values ​​of exhaled gas of each animal and human suffering from pneumoconiosis and the proportion of each gas component.

[0035] The gas detection subsystem includes several electronic nose devices, which include a sampling module, a sensor module, a control drive circuit, a single-chip control chip, an interface circuit and a data processing circuit;

[0036] The exhaled gas enters the sensor module through the sampling module, and the exhaled gas is detected by the sensor module, and the output signal is obtained and transmitted to the signal processing circuit through the single-chip control chip. The signal processing circuit includes a processing chip, and the signal feature of the output signal is extracted by the processing chip, and the model is constructed and trained using a signal recognition algorithm. Combined with the parameter data in the gas parameter database, the output signal is converted into a corresponding gas parameter value.

[0037] The data analysis subsystem performs data analysis based on gas parameter values ​​and database storage data, including:

[0038] The gas output by the gas detection subsystem is obtained and statistically calculated, and a parameter comparison is performed with the gas parameter value according to the gas component parameters in the gas parameter database and the proportion of each gas component. When each gas component value in the gas parameter value reaches the standard component value of pneumoconiosis gas, it is determined that the exhaled gas corresponding to the gas parameter value suffers from pneumoconiosis;

[0039] When it is determined that a person suffers from pneumoconiosis, a lung injury score is obtained based on the gas parameter values ​​of the pneumoconiosis and the proportion of each gas, combined with the gas component proportions in the gas parameter database. A weight is allocated based on the lung injury score, a pneumoconiosis degree score is calculated based on the weight allocation result, and the lung condition is obtained based on the pneumoconiosis degree score.

[0040] The process of the result evaluation subsystem to evaluate the degree of pneumoconiosis according to the lung condition includes:

[0041] A fuzzy evaluation library is constructed, and the degree of pneumoconiosis is evaluated through the fuzzy evaluation library. The fuzzy evaluation library includes the severity of pneumoconiosis and the lung condition. The lung condition is converted into the severity of pneumoconiosis, and the severity of pneumoconiosis is converted into a fuzzy language value. The fuzzy language value includes TE, E, M and B. The severity of pneumoconiosis is converted into the fuzzy language value and input into the fuzzy evaluation library, and a fuzzy judgment is made on the lung condition to obtain a lung condition evaluation result.

[0042] The process of the result evaluation subsystem to evaluate the degree of pneumoconiosis based on the lung condition includes the following steps:

[0043] First, a fuzzy evaluation library needs to be constructed. Evaluation indicators are defined to determine the various indicators used to evaluate the degree of pneumoconiosis, such as lung imaging features (nodule density, size, and distribution) and lung function test results. Then, membership functions are designed for each indicator, which are used to convert specific lung condition data into fuzzy sets. For example, nodule density can be represented by three fuzzy sets of "low", "medium", and "high", each of which is defined by a membership function.

[0044] Next is the fuzzification step, which converts the specific lung condition data into a fuzzy set. First, the patient's lung condition data is obtained through medical examinations, such as CT scan results, lung function test data, etc. Then, a predefined membership function is applied to convert the obtained lung condition data into a fuzzy set. Each data point will have a membership degree, indicating the degree to which it belongs to a fuzzy set.

[0045] When constructing a fuzzy evaluation rule base, it is necessary to determine the evaluation criteria for the degree of pneumoconiosis based on the experience of medical experts and existing research, and define the level of pneumoconiosis (such as TE: very serious, E: serious, M: moderate, B: mild). Next, a fuzzy rule base is established to convert lung conditions into the degree of pneumoconiosis. For example, if the nodule density is high and the nodule size is large, the pneumoconiosis degree is very serious (TE); if the nodule density is medium and the nodule size is medium, the pneumoconiosis degree is moderate (M).

[0046] Then, fuzzy reasoning is performed. The fuzzy set obtained by fuzzification processing is input into the fuzzy evaluation library, and the input fuzzy set is reasoned according to the fuzzy evaluation rule library to obtain the fuzzy output (i.e. the fuzzy language value of the degree of pneumoconiosis).

[0047] Finally, defuzzification is performed. The fuzzy language values ​​of the severity of pneumoconiosis obtained by fuzzy reasoning (such as TE, E, M, B) are converted into specific evaluation results. The fuzzy output is converted into specific numerical evaluation results through defuzzification methods (such as the centroid method, the maximum membership method, etc.).

[0048] As a preferred embodiment of the present application, the display subsystem integrates and displays the gas parameter values, whether pneumoconiosis is present, lung condition, and lung status evaluation results obtained during each detection process, and displays the comparison data between the data analysis subsystem and the gas parameter database during each detection process in the form of a bar graph.

[0049] This embodiment also provides a pneumoconiosis detection electronic nose chip, which specifically includes a transistor structure, a gas sensor array and a signal analysis module; wherein the gas sensor array and the signal analysis module are connected through the transistor structure;

[0050] The gas sensor array includes a number of gas sensors made of carbon nanotubes;

[0051] The signal analysis module is used to convert the output signal of the gas sensor into a gas parameter value by using a signal recognition algorithm.

[0052] As a preferred embodiment of the present application, the transistor includes a substrate, a gate insulating layer, and a channel active layer, wherein an active electrode and a drain electrode are arranged on the channel active layer, and the channel active layer is a quantum dot film formed by depositing quantum dot materials; and a gate electrode is arranged on the substrate.

[0053] As a preferred implementation of the present application, the signal recognition algorithms used by the signal analysis module include cluster analysis, principal component analysis, probabilistic neural network algorithm, reverse artificial neural network algorithm, Bayesian algorithm and matrix decomposition method.

[0054] Those skilled in the art will appreciate that embodiments of the present invention may be provided as systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0055] The present invention is described with reference to the flowcharts and / or block diagrams of computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as the combination of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0056] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0057] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0058] The above is only a preferred specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A pneumoconiosis detection system, characterized in that: Including gas parameter database, gas detection subsystem, data analysis subsystem, result evaluation subsystem, and display subsystem; Wherein, the gas parameter database and the gas detection subsystem are respectively connected to the data analysis subsystem; the data analysis subsystem, the result evaluation subsystem and the display subsystem are connected in sequence; The gas parameter database is used to store gas composition parameter data and gas composition ratio; The gas detection subsystem is used to input the exhaled gas to be detected, convert the exhaled gas into an output signal, and convert the output signal into a gas parameter value; The data analysis system is used to analyze the stored data in the gas parameter database and the gas parameter value to obtain the lung condition; The result evaluation subsystem evaluates the degree of pneumoconiosis according to the lung condition; The display subsystem is used to display the gas parameter values, lung conditions and the pneumoconiosis degree evaluation results of each detection process.

2. The pneumoconiosis detection system according to claim 1, characterized in that: The gas parameter database includes exhaled gas component parameters and the proportion of each gas component of gases with several kinds of animal and human odors, and also includes the standard component values ​​and the proportion of each gas component of the exhaled gas of each animal and human suffering from pneumoconiosis.

3. The pneumoconiosis detection system according to claim 1, characterized in that: The gas detection subsystem includes a plurality of electronic nose devices, and the electronic nose devices include a sampling module, a sensor module, a control drive circuit, a single-chip control chip, an interface circuit and a data processing circuit; The exhaled gas enters the sensor module through the sampling module, the exhaled gas is detected by the sensor module, an output signal is obtained and transmitted to the signal processing circuit through the single-chip control chip, the signal processing circuit includes a processing chip, the signal feature of the output signal is extracted by the processing chip, and a signal recognition algorithm is used to build and train the model, and the output signal is converted into a corresponding gas parameter value in combination with the parameter data in the gas parameter database.

4. The pneumoconiosis detection system according to claim 1, characterized in that: The data analysis subsystem performs statistical calculations on the gas parameter values ​​output by the gas detection subsystem, and performs parameter comparison with the gas parameter values ​​according to the gas component parameters in the gas parameter database and the proportion of each gas component. When each gas component value in the gas parameter value reaches the standard component value of pneumoconiosis gas, a lung injury score is obtained by comparing the gas parameter value and the proportion of each gas in combination with the gas component proportion in the gas parameter database, a weight is allocated according to the lung injury score, a pneumoconiosis degree score is calculated according to the weight allocation result, and the lung condition is obtained according to the pneumoconiosis degree score.

5. The pneumoconiosis detection system according to claim 1, characterized in that: The result evaluation subsystem constructs a fuzzy evaluation library to evaluate the degree of pneumoconiosis, which includes the degree of pneumoconiosis and lung conditions. The lung conditions are converted into the degree of pneumoconiosis, and the degree of pneumoconiosis is converted into a fuzzy language value. The fuzzy language value includes TE, E, M and B. The degree of pneumoconiosis is converted into the fuzzy language value and input into the fuzzy evaluation library, and a fuzzy judgment is made on the lung status to obtain a lung status evaluation result.

6. The pneumoconiosis detection system according to claim 1, characterized in that: The display subsystem integrates and displays the gas parameter values, lung conditions and lung status evaluation results obtained in each detection process, and displays the comparison data between the data analysis subsystem and the gas parameter database in the form of a bar graph in each detection process.

7. A chip for electronic nose for pneumoconiosis detection, characterized in that: It includes a transistor structure, a gas sensor array, and a signal analysis module; wherein the gas sensor array is connected to the signal analysis module via the transistor structure; The gas sensor array includes a plurality of gas sensors made of carbon nanotubes; The signal analysis module is used to convert the output signal of the gas sensor into a gas parameter value by using a signal recognition algorithm.

8. The electronic nose chip for pneumoconiosis detection according to claim 7, characterized in that: The transistor structure comprises a substrate, a gate insulating layer, and a channel active layer. An active electrode and a drain electrode are arranged on the channel active layer. The channel active layer is a quantum dot film formed by depositing quantum dot materials. A gate electrode is arranged on the substrate.

9. The electronic nose chip for pneumoconiosis detection according to claim 7, characterized in that: The signal recognition algorithms adopted by the signal analysis module include cluster analysis method, principal component analysis method, probabilistic neural network algorithm, reverse artificial neural network algorithm, Bayesian algorithm and matrix decomposition method.

Images