Ai-based high-precision bacteria analysis device

Abstract

An AI-based high-precision bacteria analysis device of the present invention comprises: a sampling module for capturing airborne bacteria onto a culture medium by using a built-in impactor; a culture-photographing module for accommodating the culture medium, culturing the bacteria according to a predetermined temperature and time, and generating image data by photographing the cultured bacteria; a transfer module for transferring the culture medium between the sampling module and the culture-photographing module; and an analysis module for analyzing the image data through an AI model to measure the airborne bacteria.

Description

AI-based high-precision bacteria analysis device

[0001] The present invention relates to an AI-based high-precision bacterial analysis device, and more specifically, to an AI-based high-precision bacterial analysis device capable of reducing culture time and detecting minute bacteria using an AI model.

[0002] As the global pharmaceutical and food markets expand, the number of sterile facilities for pharmaceutical and food production is increasing. These facilities are required by regulations to measure bacterial counts several times a day.

[0003] As sterile facilities increase, the demand for bacterial measurement is increasing. However, most measurement personnel are still performing manual measurements through sampling, culturing, and analysis processes.

[0004] When measuring personnel manually measure bacteria, errors are likely to occur due to inconsistencies in the skill level of the measuring personnel and measurement standards.

[0005] To overcome the problems of manual methods, automatic bacteria measuring devices have been developed and distributed, but the measurement range remains at 2,000 to 20,000 CFU.

[0006] However, in sterile facilities or hospitals, bacteria in the range of 1 to 800 CFU must be measured, so there is a need to improve the measurement sensitivity and accuracy of existing automatic bacteria measuring devices.

[0007] In order to solve the above-described problem, the present invention aims to provide an AI-based high-precision bacteria analysis device capable of automatically measuring microscopic bacteria in the range of 1 to 800 CFU.

[0008] The AI-based high-precision bacteria analysis device of the present invention may include a sampling module that captures airborne bacteria in a culture medium using a built-in impactor; a culture-photographing module that receives the culture medium, cultures it at a preset temperature and time, and photographs the cultured bacteria to generate image data; a transport module that transports the culture medium between the sampling module and the culture-photographing module; and an analysis module that analyzes the image data using an AI model to measure the airborne bacteria.

[0009] The above-mentioned culture-photography module may include a sensor unit that measures the internal temperature and humidity of the culture medium; a light source unit that supplies heat capable of maintaining the internal temperature and provides lighting for photography; and a photography unit that photographs the cultured bacteria at regular time intervals to generate a plurality of image data.

[0010] The above analysis module may include a reading unit that analyzes the image data using a reading model and measures a colony of the cultured bacteria; and a prediction unit that receives a measurement result of the colony from the reading unit and predicts the growth of the colony using a prediction model based on the measurement result.

[0011] The above-mentioned reading unit can list the image data in time series order, perform image segmentation on the cluster included in the image data using the reading model, and output a segmentation map reflecting the characteristics of the cluster.

[0012] The above reading unit can compare the segmentation maps according to the time series order to derive a boundary change rate vector of the colony.

[0013] The above-mentioned reading unit can input the boundary change velocity vector into the reading model, and detect the colony whose boundary change velocity is less than a preset boundary change velocity standard as a first colony, and detect the colony whose boundary change velocity is greater than or equal to the standard as a second colony.

[0014] The above prediction unit can input the boundary change velocity vector of the first colony into the above prediction model and predict the size growth rate of the first colony after a certain period of time.

[0015] The above prediction unit can compare the size growth rate with a preset reference growth rate to calculate a probability that the size growth rate exceeds the preset reference growth rate, and detect the first colony whose probability is greater than the preset reference probability as a third colony.

[0016] The above analysis module can measure the second colony and the third colony and output the number of colonies per unit area (CFU / m3).

[0017] The sampling module may include an air inlet pipe connected to the impactor; a micro-flow sensor installed in the air inlet pipe to measure the amount of air being introduced; and a micro-flow control valve that receives measurement data from the micro-flow sensor and adjusts the amount of air.

[0018] According to the present invention as described above, the following effects are achieved.

[0019] The present invention can reduce errors and provide accurate bacteria measurements by capturing, culturing, and measuring bacteria in the air according to a standard method.

[0020] The present invention can secure reproducibility and accuracy of measurement by performing a measurement process using a robot structure.

[0021] The present invention can eliminate deviations due to subjectivity or skill of measurement personnel by reading bacteria using an AI model.

[0022] The present invention can shorten analysis time and secure measurement accuracy by predicting the growth of microscopic bacteria using an AI model.

[0023] In addition, other features and advantages of the present invention may be newly discovered through the embodiments of the present invention.

[0024] FIG. 1 is a drawing showing the appearance of an AI-based high-precision bacteria analysis device according to an embodiment of the present invention.

[0025] FIG. 2 is a diagram schematically illustrating the configuration of an AI-based high-precision bacteria analysis device according to an embodiment of the present invention.

[0026] FIG. 3 is a diagram showing the configuration of a sampling module according to an embodiment of the present invention.

[0027] Figure 4 is a drawing showing the configuration of a culture-photography module according to an embodiment of the present invention.

[0028] Figure 5 is a diagram showing the configuration of an analysis module according to an embodiment of the present invention.

[0029] FIG. 6 is a drawing to help understand the process of a reading unit reading a bacterial colony according to an embodiment of the present invention.

[0030] FIG. 7 is a diagram to help understand the process of predicting bacterial colonies by a prediction unit according to an embodiment of the present invention.

[0031] Figure 8 is a flowchart illustrating a process of measuring bacteria by an AI-based high-precision bacteria analysis device according to an embodiment of the present invention.

[0032] When assigning reference numbers to components in each drawing in this specification, it should be noted that, as much as possible, identical components are given the same numbers even if they are shown in different drawings. In this specification, the singular also includes the plural unless specifically stated otherwise. As used herein, the terms "comprises" and / or "comprising" do not exclude the presence or addition of one or more other components in addition to the components mentioned.

[0033] The above-described purposes, other purposes, features, and advantages of the present invention will be readily understood through the following preferred embodiments, illustrated in the accompanying drawings. However, the present invention is not limited to the embodiments described herein and may be embodied in other forms. Rather, the embodiments presented herein are provided to ensure that the disclosure is thorough and complete, and to ensure that the spirit of the present invention is fully conveyed to those skilled in the art.

[0034]

[0035] Hereinafter, preferred embodiments of the present invention designed to solve the above problems will be described in detail with reference to the attached drawings. The AI-based high-precision bacterial analysis device (1000) according to an embodiment of the present invention will be referred to as a high-precision bacterial analysis device (1000) hereinafter.

[0036] FIG. 1 is a drawing showing the appearance of an AI-based high-precision bacteria analysis device according to an embodiment of the present invention.

[0037] The high-precision bacteria analysis device (1000) according to the embodiment of the present invention illustrated in FIG. 1 can perform a sampling-cultivation-analysis process to measure bacteria in the air. The high-precision bacteria analysis device (1000) can be installed in sterile facilities such as clean rooms, pharmaceutical processing lines, hospitals, and daycare centers, or facilities requiring management of bacterial concentration. The high-precision bacteria analysis device (1000) can be installed alone, or multiple devices can be installed at regular intervals for efficient measurement.

[0038] FIG. 2 is a diagram schematically illustrating the configuration of an AI-based high-precision bacteria analysis device according to an embodiment of the present invention.

[0039] Referring to FIG. 2, a high-precision bacterial analysis device (1000) according to an embodiment of the present invention may include a sampling module (1100), a transport module (1200), a culture-photographing module (1300), and an analysis module (1400).

[0040] FIG. 3 is a diagram showing the configuration of a sampling module according to an embodiment of the present invention.

[0041] Referring to FIGS. 2 and 3, a sampling module (1100) according to an embodiment of the present invention may include an air inlet pipe (1110), a micro-flow sensor (1120), a micro-flow control valve (1130), and an impactor (1140).

[0042] The sampling module (1100) can capture airborne bacteria in a culture medium using a built-in impactor (1140). The impactor (1140) is a device that captures airborne particles and can capture particles such as fine dust, viruses, and bacteria floating in the air.

[0043] Tryptic soy agar (TSA) culture media can be prepared in a semi-solid form by adding agar to a liquid medium (nutrient solution) in a petri dish. Note that solid culture media allow cells to grow in immobile, discrete, visible clumps called colonies.

[0044] The impactor (1140) may be connected to an air inlet pipe (1110) through which indoor air is introduced. The air inlet pipe (1110) may be equipped with a micro-flow sensor (1120) capable of measuring the amount of air introduced.

[0045] The micro-flow sensor (1120) can transmit data measuring the air volume to the micro-flow controller (1130). The micro-flow controller (1130) receives the data measuring the air volume and controls the valve to finely adjust the amount of air flowing in through the air inlet pipe (1110).

[0046] The sampling module (1100) can precisely measure bacteria by finely controlling the amount of air flowing in and capturing only trace amounts of bacteria.

[0047] The culture-photography module (1300) according to an embodiment of the present invention can accommodate a culture medium, culture it at a preset temperature and time, and photograph the cultured bacteria to generate image data. For example, the culture-photography module (1300) can culture the culture medium in a sealed state at a temperature of 34 to 36°C for 12 to 48 hours, thereby allowing the bacteria to grow to a size that can be analyzed or observed.

[0048] Although not shown, the culture-photography module (1300) may further be equipped with a cooling device and a ventilation device to maintain a constant temperature.

[0049] Figure 4 is a drawing showing the configuration of a culture-photography module according to an embodiment of the present invention.

[0050] Referring to FIG. 4, the culture-photography module (1300) may include a sensor unit (1310), a light source unit (1320), and a photography unit (1330).

[0051] The sensor unit (1310) can measure the internal temperature and humidity of the culture medium. The sensor unit (1310) may include a thermometer and a hygrometer for measuring temperature and humidity. In addition to temperature and humidity, the sensor unit (1310) may include other measuring devices necessary for culturing bacteria and collect data.

[0052] The light source unit (1320) can supply heat to maintain the internal temperature of the culture medium and provide lighting for photography when taking pictures.

[0053] The photographing unit (1330) can capture images of cultured bacteria at regular intervals to generate multiple image data. The time interval for capturing the bacteria can be appropriately selected. As described below, since the rate of change in the boundary formed by bacterial colonies must be measured, a shorter time interval allows for more accurate predictions. However, a large amount of image data can slow down processing speed and consume significant computing resources. Therefore, a time interval that allows for efficient measurement must be selected.

[0054] The transport module (1200) according to an embodiment of the present invention can transport a culture medium between the sampling module (1100) and the culture-photography module (1300).

[0055] Although not shown, the transport module (1200) may include a rotary robot structure and a flipper robot structure. The rotary robot structure can transport or flip the culture medium around a rotation axis. The flipper robot structure can pick up or rotate the culture medium.

[0056] The transport module (1200) can precisely control the process of transporting culture medium, thereby preventing errors or contamination that may occur during the transport process.

[0057] Figure 5 is a diagram showing the configuration of an analysis module according to an embodiment of the present invention.

[0058] Referring to FIG. 5, an analysis module (1400) according to an embodiment of the present invention may include a reading unit (1410) and a prediction unit (1420). The analysis module (1400) may measure airborne bacteria by analyzing image data of cultured bacteria using an AI model.

[0059] The reading unit (1410) can analyze image data using a reading model and measure colonies of cultured bacteria.

[0060] The reading model according to an embodiment of the present invention may be a hybrid model combining a U-NET model and an LSTM model. However, this is not limited to this model, and other appropriate AI models may be selected. For example, the U-NET++ model, which is an improvement over the U-NET model, may be used.

[0061] The U-NET model is an image segmentation neural network used in image analysis. The U-NET model performs accurate segmentation by combining features extracted from images of various resolutions.

[0062] The LSTM model is a type of recurrent neural network (RNN) and is an AI model used to process time series data.

[0063] FIG. 6 is a drawing to help understand the process of a reading unit reading a bacterial colony according to an embodiment of the present invention.

[0064] Referring to Fig. 6, it can be seen that when the U-NET model receives an original image as input, it outputs a segment map including the features of the image through a shrinkage path and an expansion path.

[0065] The shrinkage path is similar to the structure of a convolutional neural network (CNN). It extracts high-level abstract features from the input original image. Each stage of the shrinkage path consists of two 3x3 convolution operations and a ReLU activation function. After the convolution operations, a 2x2 max pooling operation is performed to reduce the spatial resolution. As the shrinkage path progresses, the number of channels doubles, allowing for the learning of more feature maps.

[0066] For example, if the input image is 572x572 in size, it is gradually reduced to 284x284, 142x142, 71x71, etc. through max pooling.

[0067] The dilation path gradually restores the feature map obtained from the shrinkage path to its original resolution. The dilation path restores positional information to perform fine-grained segmentation. Each step of the dilation path consists of an upsampling operation and a convolution operation. The dilation path doubles the spatial resolution of the feature map through the upsampling operation.

[0068] After each upsampling step, feature maps of corresponding sizes are concatenated and combined in the shrinking path. The dilation path processes the combined feature maps with two 3x3 convolutions and the ReLU activation function.

[0069] The extended path repeats the upsampling and combining process to restore the original input image to the same resolution.

[0070] The U-NET model connects the shrinkage and expansion paths using a structure called skip connections. These skip connections directly integrate high-resolution information from the shrinkage path into the upsampling process of the expansion path. Skip connections restore lost details and yield more accurate segmentation results.

[0071] Below, the process of reading a bacterial colony using a reading model including a U-NET model by a reading unit (1410) is described in detail.

[0072] The reading unit (1410) can list image data generated by the shooting unit (1330) by shooting at regular time intervals in chronological order.

[0073] The reading unit (1410) segments each image data listed in time series order using a reading model including a U-NET model. The reading unit (1410) can output a segmentation map reflecting the characteristics of the bacterial colony.

[0074] The process of the reading unit (1410) dividing the image data can be performed along the contraction path and expansion path described above.

[0075] The characteristics of bacterial colonies reflected in the segmentation map output by the reading unit (1410) may include colony boundaries and colony sizes. In addition to colony boundaries and colony sizes, other characteristics may be included. For example, the segmentation map may include colony shape, the shapes of individual bacteria forming the colony, and colony color.

[0076] The reading unit (1410) can compare segmentation maps divided according to time series order to calculate a velocity vector of cluster boundary changes. The boundary change velocity can be calculated in pixel units or length units. For example, the boundary change velocity can be 2.5 pixels / min or 5.5 um / min.

[0077] According to another embodiment of the present invention, the reading unit (1410) may compare segmentation maps divided according to time-series order to calculate a velocity vector indicating the change in the area of ​​a colony. The velocity of area change may be calculated in units of pixels or area. For example, it may be 6.25 pixels / min or 30.25 um / min.

[0078] According to an embodiment of the present invention, the reading unit (1410) can classify clusters by inputting a boundary change velocity vector into a reading model. At this time, an LSTM model included in the reading model can be utilized.

[0079] The reading unit (1410) can detect a colony as a first colony if the boundary change rate of the bacterial colony is less than a preset boundary change rate standard. The first colony may be a colony of bacteria with a very fast boundary change rate. For example, the first colony may be a colony of microscopic bacteria with a very small number of captured bacterial cells.

[0080] The reading unit (1410) can detect a colony as a second colony if the boundary change rate of the bacterial colony is greater than a preset boundary change rate standard. For example, the second colony may be a bacterial colony that can be easily observed due to a sufficient number of captured bacterial cells.

[0081] The boundary change rate criterion can be used to determine whether a microscopic bacterial colony is present. The boundary change rate criterion can be appropriately selected based on factors such as the location where the high-precision bacterial analysis device (1000) is installed and the inspection speed.

[0082] The prediction unit (1420) according to an embodiment of the present invention receives the measurement results of the colony from the reading unit (1410) and can predict the growth of the colony using a prediction model based on the measurement results.

[0083] The prediction model according to an embodiment of the present invention may be an LSTM model, but is not limited thereto and may be appropriately selected.

[0084] The prediction unit (1420) inputs the boundary change velocity vector of the first colony from the reading unit (1410) into the prediction model and can predict the size growth rate of the first colony after a certain period of time.

[0085] For example, the size growth rate of the first colony could be the rate of increase in the area of ​​the bacterial colony. Alternatively, the size growth rate of the first colony could refer to the rate of increase in the diameter of the bacterial colony. Depending on the type of bacteria, it may be more efficient to predict the size growth rate based on area, or it may be more efficient to predict the size growth rate based on diameter. Therefore, the growth rate criterion can be appropriately selected.

[0086] The growth rate of a bacterial colony can be an indicator of how much the colony has grown over a given period of time. Calculating the growth rate of a bacterial colony can be used to determine the size of a bacterial colony over time.

[0087] The prediction unit (1420) can compare the size growth rate with a preset reference growth rate and calculate the probability that the size growth rate will exceed the reference growth rate.

[0088] If the growth rate of the first colony exceeds the reference growth rate, the first colony can be predicted to grow to a detectable size after a certain period of time. The reference growth rate can be appropriately selected depending on the type of bacteria, the environment in which the high-precision bacterial analysis device is installed, the season, etc.

[0089] Since the growth rate of a bacterial colony may not remain constant due to various causes, the prediction unit (1420) can calculate the probability that the growth rate of the size of a bacterial colony exceeds a reference growth rate.

[0090] If the probability that the first colony's growth rate will exceed the reference growth rate is greater than the reference probability, the first colony can be predicted to survive for a certain period of time. The reference probability can be appropriately selected based on factors such as the type of bacteria, the environment in which the high-precision bacterial analysis device is installed, and the season. For example, the reference probability could be 95%.

[0091] The prediction unit (1420) can detect the first colony, which has a probability of a size growth rate exceeding a reference growth rate greater than a reference probability, as the third colony.

[0092] FIG. 7 is a diagram to help understand the process of predicting bacterial colonies by a prediction unit according to an embodiment of the present invention.

[0093] Referring to FIG. 7, the analysis module (1400) according to an embodiment of the present invention can measure the second colony and the third colony and output the number of colonies per unit area (CFU / m3).

[0094] As shown in (A) of Fig. 7, in the past, to measure bacteria, bacteria were cultured for 48 hours and colonies were detected.

[0095] As illustrated in (B) of FIG. 7, according to an embodiment of the present invention, bacteria can be cultured for 24 hours to measure bacteria. For example, when the culture time reaches 24 hours, the reading unit (1410) can use the reading model to detect a colony whose boundary change rate exceeds a standard as a second colony. In other words, when the culture time reaches 24 hours, a colony of bacteria that has grown sufficiently and is detectable can be detected. For example, the second colony may have 8 CFU.

[0096] For example, the prediction unit (1420) can use a prediction model to predict the growth rate of the first colony at 24 hours into the culture, calculate the probability that the growth rate will exceed the reference growth rate, and detect the third colony. In other words, it can predict whether a bacterial colony will grow and be detectable at 48 hours into the culture. The third colony may be a colony among the first colonies that can grow to a detectable size at 48 hours. For example, the third colony may be predicted to have 4 CFU.

[0097] The analysis module (1400) can detect the number of bacteria in the air as 12 CFU by adding 8 CFU, which is the number of the second colony, and 4 CFU, which is the number of the third colony.

[0098] According to an embodiment of the present invention, a high-precision bacterial analysis device can culture and detect bacteria in a relatively short period of time, unlike conventional methods.

[0099] Additionally, microscopic bacteria that require relatively long culture periods to be detected can be detected by predicting their growth based on AI models.

[0100] Figure 8 is a flowchart illustrating a process of measuring bacteria by an AI-based high-precision bacteria analysis device according to an embodiment of the present invention.

[0101] Referring to FIG. 8, the process of measuring bacteria by the high-precision bacteria analysis device (1000) of the present invention is described.

[0102] A high-precision bacteria analysis device (1000) according to an embodiment of the present invention can capture airborne bacteria in a culture medium (S10).

[0103] A high-precision bacteria analysis device (1000) can accommodate a culture medium and culture bacteria according to a preset temperature and time (S20).

[0104] A high-precision bacteria analysis device (1000) can generate image data by photographing bacteria in a culture medium during the time that bacteria are cultured (S30).

[0105] A high-precision bacteria analysis device (1000) can list image data included in the generated image data in time series order and perform image segmentation on colonies of bacteria included in the image data using a reading model (S40).

[0106] A high-precision bacterial analysis device (1000) can output a segmentation map containing characteristics of a bacterial colony (S50).

[0107] A high-precision bacterial analysis device (1000) can compare segmentation maps in time series order to produce a boundary change velocity vector of a bacterial colony (S60).

[0108] A high-precision bacterial analysis device (1000) can input a boundary change velocity vector into a reading model, detect a bacterial colony whose boundary change velocity is less than a preset boundary change velocity standard as a first colony, and detect a bacterial colony whose boundary change velocity is greater than the standard as a second colony (S70).

[0109] A high-precision bacteria analysis device (1000) inputs the boundary change velocity vector of the first colony into a prediction model and can predict the size growth rate of the first colony after a certain period of time (S80).

[0110] A high-precision bacteria analysis device (1000) can compare a size growth rate with a preset reference growth rate to calculate a probability that the size growth rate exceeds the reference growth rate, and detect a first colony whose probability is greater than the preset reference probability as a third colony (S90).

[0111] A high-precision bacteria analysis device (1000) can measure the second colony and the third colony and output the number of colonies per unit area (CFU / m3) (S100).

[0112] Although the embodiments described above have been described by way of limited examples and drawings, those skilled in the art will appreciate that various modifications and variations can be made based on the above description. For example, appropriate results can still be achieved even if the described techniques are performed in a different order than described, and / or the components of the described structures, devices, etc. are combined or combined in a different manner than described, or are replaced or substituted with other components or equivalents.

[0113] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims set forth below.

[0114] An AI-based high-precision bacteria analysis device according to an embodiment of the present invention includes a sampling module that captures airborne bacteria in a culture medium using a built-in impactor; a culture-photographing module that receives the culture medium, cultures it at a preset temperature and time, and photographs the cultured bacteria to generate image data; a transport module that transports the culture medium between the sampling module and the culture-photographing module; and an analysis module that analyzes the image data using an AI model to measure the airborne bacteria, thereby predicting the growth of microscopic bacteria, thereby shortening the analysis time and ensuring the accuracy of the measurement.

Claims

1. A sampling module that captures airborne bacteria into a culture medium using a built-in impactor; A culture-photographing module that receives the culture medium, cultures the cultured bacteria at a preset temperature and time, and photographs the cultured bacteria to generate image data; A transport module for transporting the culture medium between the sampling module and the culture-photography module; and An AI-based high-precision bacteria analysis device comprising an analysis module that measures bacteria in the air by analyzing the image data using an AI model.

2. In paragraph 1, The above culture-photography module A sensor unit for measuring the internal temperature and humidity of the culture medium; A light source unit that supplies heat to maintain the internal temperature and provides lighting for shooting; and An AI-based high-precision bacteria analysis device comprising a photographing unit that photographs the cultured bacteria at regular time intervals to generate multiple image data.

3. In paragraph 1, The above analysis module A reading unit that analyzes the image data using a reading model and measures colonies of the cultured bacteria; and An AI-based high-precision bacteria analysis device, comprising a prediction unit that receives the measurement results of the colony from the reading unit and predicts the growth of the colony using a prediction model based on the measurement results.

4. In paragraph 3, An AI-based high-precision bacteria analysis device, wherein the reading unit lists the image data in chronological order, performs image segmentation on the colony included in the image data using the reading model, and outputs a segmentation map reflecting the characteristics of the colony.

5. In paragraph 4, An AI-based high-precision bacteria analysis device, wherein the above-mentioned reading unit compares the segmentation maps in time series order to derive a boundary change rate vector of the colony.

6. In paragraph 5, An AI-based high-precision bacteria analysis device, wherein the reading unit inputs the boundary change velocity vector into the reading model, detects a colony whose boundary change velocity is less than a preset boundary change velocity standard as a first colony, and detects a colony whose boundary change velocity is greater than or equal to the standard as a second colony.

7. In paragraph 3, An AI-based high-precision bacteria analysis device, wherein the above prediction unit inputs the boundary change velocity vector of the first colony into the prediction model and predicts the size growth rate of the first colony after a certain period of time.

8. In paragraph 7, An AI-based high-precision bacteria analysis device, wherein the prediction unit compares the size growth rate with a preset reference growth rate to calculate a probability that the size growth rate exceeds the preset reference growth rate, and detects the first colony, whose probability is greater than the preset reference probability, as a third colony.

9. In paragraph 3, The above analysis module is an AI-based high-precision bacteria analysis device that measures the second colony and the third colony and outputs the number of colonies per unit area (CFU / m3).

10. In paragraph 1, The above sampling module An air inlet pipe connected to the above impactor; A micro-flow sensor installed in the air inlet pipe to measure the amount of air being introduced; and An AI-based high-precision bacteria analysis device including a micro-flow controller that receives measurement data from the micro-flow sensor and adjusts the air volume.

Images