CN113610077A - System method and equipment for monitoring and analyzing dissolution behavior by using artificial intelligence image recognition technology - Google Patents
System method and equipment for monitoring and analyzing dissolution behavior by using artificial intelligence image recognition technology Download PDFInfo
- Publication number
- CN113610077A CN113610077A CN202110842211.XA CN202110842211A CN113610077A CN 113610077 A CN113610077 A CN 113610077A CN 202110842211 A CN202110842211 A CN 202110842211A CN 113610077 A CN113610077 A CN 113610077A
- Authority
- CN
- China
- Prior art keywords
- camera
- image recognition
- dissolution
- monitoring
- artificial intelligence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Algebra (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a system method and equipment for monitoring and analyzing dissolution behavior by using an artificial intelligence image recognition technology. The invention monitors the dissolution behavior at a single angle or multiple angles by adopting an artificial intelligent image recognition method, analyzes the data of the volume, the shape and the like of the preparation in the dissolution process, gives a change curve and gives a change time point according to the change, and the dissolution behavior such as the corrosion phenomenon, the disintegration start, the disintegration end and the like, research and development personnel only need to analyze the experimental process according to the information given by the system, and can also play back the video according to the time point given by the system.
Description
Technical Field
The invention relates to the technical field of dissolution behaviors, in particular to a system method and equipment for monitoring and analyzing dissolution behaviors by using an artificial intelligence image recognition technology.
Background
With the development of the pharmaceutical industry, drug quality control has become a crucial issue. Therefore, in the process of developing solid preparations, the in vitro dissolution behavior is regulated by various drug administration departments as an important part of the study on the quality of the medicines. Dissolution profiles become an important investigational standard for drug quality consistency. However, in the development process, the capture of dissolution behavior is very difficult because, in general, formulation researchers and experimenters for dissolution testing belong to two departments, and dissolution testing is a lengthy and tedious process, often exceeding 8 hours. Therefore, in many cases, the pharmaceutical preparation developer can analyze the experimental process only by the final data, and cannot know the dissolution phenomenon.
The existing dissolution experiment recording mode is simple video recording, and research personnel need to perform experiment analysis in a mode of watching videos, so that time and labor are wasted. Furthermore, some samples that are not light stable cannot be observed.
Disclosure of Invention
The technical problem to be solved by the invention is to overcome the defects of the prior art and provide a system method and equipment for monitoring and analyzing the dissolution behavior by using an artificial intelligent image recognition technology, so that the dissolution behavior can be monitored at a single angle or multiple angles.
In order to solve the above technical problem, the present invention provides a first technical solution as follows:
the invention relates to a device for monitoring and analyzing dissolution behavior by utilizing an artificial intelligence image recognition technology, which comprises a computer of an operation system, a camera, a light source, a dissolution instrument, a data transmission module and an image recognition system, wherein the computer of the operation system is developed based on python and matlab, the light source is a visible light source and an infrared light source, the light source can be controlled by a self-contained photosensitive switch, the camera can be jointly collected by a single or a plurality of cameras, the camera is suitable for visible light and invisible light, the dissolution instrument is suitable for dissolution instruments of all brands and models and can be provided with stirring paddles according to the number of dissolution cups, and the data transmission module comprises wireless or wired data transmission.
As a preferred technical solution of the present invention, the cameras may be collected by a single camera or a plurality of cameras in a combined manner, when a single camera is used for collection, the system is set to perform plane analysis to analyze the projection area of the sample, and when a plurality of cameras are used for collection, the system is set to perform 3D analysis to perform volume change recording on the sample.
In a preferred embodiment of the present invention, the camera may perform multi-thread recording analysis by using a plurality of cameras through a plurality of dissolution cups.
The invention provides a second technical scheme as follows:
the invention also provides a method for monitoring and analyzing the dissolution behavior by using the artificial intelligence image recognition technology, which comprises the following specific steps:
a: waking up the camera to acquire images frame by frame;
b: carrying out preprocessing operations such as size adjustment, noise reduction, binarization and the like on the image;
c: carrying out image segmentation processing on the image, and calculating area or volume data of the target medicine;
d: drawing a curve graph according to the area or volume data of image segmentation;
e: according to the volume change trend or the nodes, curve analysis is carried out, the time and the result of the experimental phenomenon are given, and the node data can be directly input into an algorithm to be set or set in a machine learning mode.
Compared with the prior art, the invention has the following beneficial effects:
1: the invention monitors the dissolution behavior at a single angle or multiple angles by adopting an artificial intelligent image recognition method, analyzes the data of the volume, the shape and the like of the preparation in the dissolution process, gives a change curve and gives a change time point according to the change, and the dissolution behavior such as the dissolution phenomenon, the disintegration beginning, the disintegration ending and the like, research personnel only need to analyze the experimental process according to the information given by the system, and can also play back the video according to the time point given by the system.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention.
Wherein like reference numerals refer to like parts throughout.
In addition, if a detailed description of the known art is not necessary to show the features of the present invention, it is omitted. It should be noted that the terms "front," "back," "left," "right," "upper" and "lower" used in the following description refer to directions in the drawings, and the terms "inner" and "outer" refer to directions toward and away from, respectively, the geometric center of a particular component.
In the drawings:
FIG. 1 is an overall schematic view of the present invention;
FIG. 2 is a schematic diagram of an image recognition system;
fig. 3 is a graph of tablet volume as a function of time.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
Example 1
As shown in fig. 1-3, the present invention provides an apparatus for monitoring and analyzing a dissolution behavior by using an artificial intelligence image recognition technology, which comprises a computer of an operating system, a camera and a light source, a dissolution instrument, a data transmission module and an image recognition system, and is characterized in that the computer of the operating system is developed based on python, matlab, the light source is a visible light source and an infrared light source, the light source can be controlled by a photosensitive switch, the camera can be collected by a single or multiple cameras in a combined manner, the camera is suitable for visible light and invisible light, the dissolution instrument is suitable for dissolution instruments of all brands and models, stirring paddles are arranged in the dissolution cup according to the number of the dissolution cups, and the data transmission module comprises wireless or wired data transmission.
Further, the camera can be jointly gathered by single or a plurality of cameras, and when single camera was gathered, the system set for plane analysis, throws the area to the sample and carries out the analysis, and when a plurality of cameras were gathered, the system set up to 3D analysis, carries out volume change record to the sample.
The camera can perform multi-thread recording analysis by adopting a plurality of cameras through a plurality of dissolving-out cups.
The invention provides a method for monitoring and analyzing dissolution behavior by using an artificial intelligence image recognition technology, which comprises the following specific steps:
a: waking up the camera to acquire images frame by frame;
b: carrying out preprocessing operations such as size adjustment, noise reduction, binarization and the like on the image;
c: carrying out image segmentation processing on the image, and calculating area or volume data of the target medicine;
d: drawing a curve graph according to the area or volume data of image segmentation;
e: according to the volume change trend or the nodes, curve analysis is carried out, the time and the result of the experimental phenomenon are given, and the node data can be directly input into an algorithm to be set or set in a machine learning mode.
Specifically, in the using process, after a sample to be measured is put into the dissolution instrument, the camera transmits an image of the sample to a computer and is analyzed by an image recognition system, a photosensitive switch on a main board of the camera performs switching control on a visible light source or an infrared light source according to the ambient illumination intensity, the camera transmits the image to the computer after collecting the image, the image recognition system analyzes the shape, the volume or the area of the image to give a volume or area change curve, and the time for starting and ending the phenomena of disintegration, dissolution and the like is given according to the change analysis.
In the present patent, when the image segmentation is performed, the following segmentation methods, a threshold-based segmentation method, a region-based image segmentation method, a region growing algorithm, an edge detection-based segmentation method, a wavelet analysis and wavelet transformation-based image segmentation method, a fourier transform-based algorithm, a genetic algorithm-based image segmentation method, a genetic algorithm-based segmentation method, an active contour model-based segmentation method, a neural network-based segmentation method, a BP neural network, an RBF neural network, an SOM neural network, a Kohonen neural network, an LVQ neural network, an Elman neural network, a PSO neural network, a Hopfield neural network, a GRNN neural network, etc., and a Dense layer, which may be used in the neural network construction process, may be used, an AveragePolling layer, a MaxPolling layer, a volume layer, a BatchNormalization layer, a GlobalAveragePooling layer, a GlobalMaxBooling layer, an LSTM layer and an RNN layer are segmented based on deep learning, and a CRF/MRF method is used in the method, wherein a Markov random field and a conditional random field can be used; in fig. 3, the horizontal axis represents experiment time, and the vertical axis represents the pixel area of an image.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art will understand that various changes, modifications and substitutions can be made without departing from the spirit and scope of the invention as defined by the appended claims. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (4)
1. The utility model provides an utilize artificial intelligence image recognition technology to carry out monitoring analysis equipment to dissolving out action, includes running system's computer, camera and light source, dissolves out appearance, data transmission module and image recognition system, its characterized in that, running system's computer is based on python, matlab development, the light source is visible light source and infrared light source to the light source can be by the photosensitive switch control of taking oneself, the camera can be gathered by single or a plurality of camera combinations, the camera is applicable to visible light and invisible light, dissolve out the appearance and be applicable to the dissolution appearance of all brands and models, and can be according to dissolving out the quantity of cup, be provided with the stirring rake in dissolving out the cup, data transmission module includes wireless or wired data transmission.
2. The apparatus for monitoring and analyzing dissolution behavior by artificial intelligence image recognition technology as claimed in claim 1, wherein the camera can be collected by a single or multiple cameras, when the single camera is used for collection, the system is set to plane analysis to analyze the sample projection area, when the multiple cameras are used for collection, the system is set to 3D analysis to record the volume change of the sample.
3. The apparatus for monitoring and analyzing dissolution behavior by artificial intelligence image recognition technology as claimed in claim 1, wherein the camera can perform multi-thread record analysis by multiple dissolution cups and multiple cameras.
4. A method for monitoring and analyzing dissolution behavior by using an artificial intelligence image recognition technology is characterized by comprising the following specific steps:
a: waking up the camera to acquire images frame by frame;
b: carrying out preprocessing operations such as size adjustment, noise reduction, binarization and the like on the image;
c: carrying out image segmentation processing on the image, and calculating area or volume data of the target medicine;
d: drawing a curve graph according to the area or volume data of image segmentation;
e: according to the volume change trend or the nodes, curve analysis is carried out, the time and the result of the experimental phenomenon are given, and the node data can be directly input into an algorithm to be set or set in a machine learning mode.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110842211.XA CN113610077A (en) | 2021-07-26 | 2021-07-26 | System method and equipment for monitoring and analyzing dissolution behavior by using artificial intelligence image recognition technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110842211.XA CN113610077A (en) | 2021-07-26 | 2021-07-26 | System method and equipment for monitoring and analyzing dissolution behavior by using artificial intelligence image recognition technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113610077A true CN113610077A (en) | 2021-11-05 |
Family
ID=78338298
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110842211.XA Pending CN113610077A (en) | 2021-07-26 | 2021-07-26 | System method and equipment for monitoring and analyzing dissolution behavior by using artificial intelligence image recognition technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113610077A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114429798A (en) * | 2021-12-31 | 2022-05-03 | 王昊昱 | System and method for artificially and intelligently screening error data |
| CN114512200A (en) * | 2021-12-31 | 2022-05-17 | 王昊昱 | System and method for artificially and intelligently predicting dissolution curve of preparation and screening error data |
| CN115641008A (en) * | 2022-10-31 | 2023-01-24 | 山东科技大学 | Automatic carbonate rock corrosion rate monitoring system based on artificial intelligence |
-
2021
- 2021-07-26 CN CN202110842211.XA patent/CN113610077A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114429798A (en) * | 2021-12-31 | 2022-05-03 | 王昊昱 | System and method for artificially and intelligently screening error data |
| CN114512200A (en) * | 2021-12-31 | 2022-05-17 | 王昊昱 | System and method for artificially and intelligently predicting dissolution curve of preparation and screening error data |
| CN115641008A (en) * | 2022-10-31 | 2023-01-24 | 山东科技大学 | Automatic carbonate rock corrosion rate monitoring system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11330804B2 (en) | Long-term and continuous animal behavioral monitoring | |
| CN113610077A (en) | System method and equipment for monitoring and analyzing dissolution behavior by using artificial intelligence image recognition technology | |
| Zhao et al. | A wheat spike detection method in UAV images based on improved YOLOv5 | |
| Zhang et al. | Automatic individual pig detection and tracking in pig farms | |
| Kim et al. | A video-based fire detection using deep learning models | |
| TWI777092B (en) | Image processing method, electronic device, and storage medium | |
| Xiang et al. | Vehicle counting based on vehicle detection and tracking from aerial videos | |
| Biswas et al. | An automatic car counting system using OverFeat framework | |
| Benito-Picazo et al. | Deep learning-based video surveillance system managed by low cost hardware and panoramic cameras | |
| Wu et al. | Automated 3D trajectory measuring of large numbers of moving particles | |
| Chiu et al. | A background subtraction algorithm in complex environments based on category entropy analysis | |
| Zhang et al. | Unsupervised few shot key frame extraction for cow teat videos | |
| Myat Noe et al. | Comparing state-of-the-art deep learning algorithms for the automated detection and tracking of black cattle | |
| Teixidó et al. | An embedded real-time red peach detection system based on an OV7670 camera, ARM cortex-M4 processor and 3D look-up tables | |
| Grover et al. | O fly, where art thou? | |
| Sundby et al. | Geometric change detection in digital twins | |
| Du et al. | Organoids revealed: morphological analysis of the profound next generation in-vitro model with artificial intelligence | |
| Cherubini et al. | A review of the technology, training, and assessment methods for the first real-time AI-enhanced medical device for endoscopy | |
| Song et al. | A multimodal discrimination method for the response to name behavior of autistic children based on human pose tracking and head pose estimation | |
| Chen et al. | A review of posture detection methods for pigs using deep learning | |
| Zou et al. | Movement tube detection network integrating 3d cnn and object detection framework to detect fall | |
| Qin et al. | Research on wear detection of end milling cutter edge based on image stitching | |
| Ge et al. | Intelligent foreign particle inspection machine for injection liquid examination based on modified pulse-coupled neural networks | |
| Diab et al. | Brain Strategy Algorithm for Multiple Object Tracking Based on Merging Semantic Attributes and Appearance Features | |
| He et al. | Automatic ROI setting method based on LSC for a traffic congestion area |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |