CN113030049A - Online detection and identification method and system for toxic red tide algae in fish - Google Patents
Online detection and identification method and system for toxic red tide algae in fish Download PDFInfo
- Publication number
- CN113030049A CN113030049A CN202110259038.0A CN202110259038A CN113030049A CN 113030049 A CN113030049 A CN 113030049A CN 202110259038 A CN202110259038 A CN 202110259038A CN 113030049 A CN113030049 A CN 113030049A
- Authority
- CN
- China
- Prior art keywords
- red tide
- tide algae
- fish
- dimensional fluorescence
- fluorescence spectrum
- 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
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
- G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
- G01N21/64—Fluorescence; Phosphorescence
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
- G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
- G01N21/64—Fluorescence; Phosphorescence
- G01N21/6486—Measuring fluorescence of biological material, e.g. DNA, RNA, cells
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/18—Water
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
- G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
- G01N21/64—Fluorescence; Phosphorescence
- G01N2021/6417—Spectrofluorimetric devices
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
- G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
- G01N21/64—Fluorescence; Phosphorescence
- G01N2021/6417—Spectrofluorimetric devices
- G01N2021/6423—Spectral mapping, video display
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Pathology (AREA)
- Analytical Chemistry (AREA)
- Immunology (AREA)
- Biochemistry (AREA)
- Molecular Biology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Biomedical Technology (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Medicinal Chemistry (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Food Science & Technology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Investigating, Analyzing Materials By Fluorescence Or Luminescence (AREA)
Abstract
The invention relates to an online detection and identification method and system for toxic red tide algae in fish. The method comprises the following steps: three-dimensional fluorescence spectrum data of the red tide algae sample; preprocessing the three-dimensional fluorescence spectrum data of the red tide algae sample; extracting spectral characteristics from the preprocessed three-dimensional fluorescence spectrum data; according to the extracted spectral characteristics, establishing a mapping model for identifying the hemolytic activity of the fish toxic red tide algae by adopting a particle swarm optimization support vector machine method; and determining a recognition result by utilizing the mapping model according to the extracted spectral features. The method and the system for online detection and identification of the toxic red tide algae of the fish can realize uninterrupted in-situ online detection and improve the detection precision.
Description
Technical Field
The invention relates to the field of qualitative detection of fish toxic red tide algae, in particular to an online detection and identification method and system for fish toxic red tide algae.
Background
Red tide (HAB), also known as red tide, is a harmful ecological phenomenon in which some phytoplankton, protozoa or bacteria in seawater proliferate explosively or highly aggregate to cause discoloration of water under specific environmental conditions. Wherein the red tide of fish toxicity (Ichthyotoxic) can generate a plurality of toxic substances, which leads to mass death of fishes and shellfishes in a short time. At present, the toxic red tide algae are widely distributed in coastal areas of China, only 2012, the east China sea severely restricts sustainable health development of offshore aquaculture in China because the Karenia mikimotoi loses more than 20 billion yuan, and if the toxic red tide algae can be identified online in situ at an early stage, early warning can be provided for farmers, so that related measures are taken to reduce economic loss of the toxic red tide algae to the mariculture.
The current detection method for the fish toxic red tide algae mainly comprises the following three types: the method comprises the steps of firstly, a red tide biological detection technology based on morphology, secondly, an alga identification technology based on a molecular technology, thirdly, an immune identification technology based on an antibody and fourthly, a detection technology based on an alga emission fluorescence spectrum. Identification based on cell morphology, the toxic class of algae cannot be determined; the molecular technology can be only used for identifying and identifying red tide algae in a laboratory, and can not be used for on-site rapid detection; a plurality of reagent kits or reagent strips for detecting algae have been developed by the immune recognition technology, but the reagents can only be used for detecting the known algae, and samples need to be pretreated in a laboratory, are long in time consumption, lack of timeliness and cannot be used for in-situ detection. With the progress of fluorescence detection technology in recent years, the three-dimensional fluorescence spectrum data technology is rapidly developed in the aspect of algae identification, and the three-dimensional fluorescence spectrum data technology is mature day by day, so that various professional devices applied to the aspects of petroleum, polychlorinated biphenyl, biological hormone, microalgae identification and the like are developed at present. However, at present, no identification method or system can be used for online detection of toxic red tide algae.
Disclosure of Invention
The invention aims to provide a method and a system for online detection and identification of toxic red tide algae in fish, which can realize uninterrupted in-situ online detection and improve the detection precision.
In order to achieve the purpose, the invention provides the following scheme:
an on-line detection and identification method for toxic red tide algae in fish comprises the following steps:
acquiring three-dimensional fluorescence spectrum data of a red tide algae sample; the red tide algae sample comprises fish toxicity red tide algae and non-fish toxicity red tide algae;
preprocessing the three-dimensional fluorescence spectrum data of the red tide algae sample;
extracting spectral characteristics from the preprocessed three-dimensional fluorescence spectrum data;
according to the extracted spectral characteristics, establishing a mapping model for identifying the hemolytic activity of the fish toxic red tide algae by adopting a particle swarm optimization support vector machine method;
determining a recognition result by utilizing the mapping model according to the extracted spectral features; the identification result is fish toxic red tide algae or non-fish toxic red tide algae.
Optionally, the preprocessing of the three-dimensional fluorescence spectrum data of the red tide algae sample specifically includes:
and converting the three-dimensional fluorescence spectrum data into an xls file, and importing the converted file into MATLAB2018a software to be converted into a mat file.
Optionally, the extracting spectral features from the preprocessed three-dimensional fluorescence spectral data specifically includes:
determining the excitation wavelength by adopting an exhaustion method according to the preprocessed three-dimensional fluorescence spectrum data;
determining an emission wavelength according to the contour map and the spectrum interval of the preprocessed three-dimensional fluorescence spectrum data; the spectral interval is 650nm-750 nm;
and determining the spectral characteristics according to the head-to-tail connection of the emission wavelengths under different excitation wavelengths.
Optionally, the establishing a mapping model of the hemolytic activity identification of the fish toxic red tide algae by using a particle swarm optimization support vector machine method according to the extracted spectral features specifically includes:
adjusting parameters of a particle swarm optimization support vector machine according to the extracted spectral features; the parameters include: accelerating constant, maximum iteration times and particle swarm population number;
determining the mapping model according to the particle swarm optimization support vector machine after the parameters are adjusted; the mapping model takes the extracted spectral features as input and the recognition result as output.
An on-line detection and identification system for toxic red tide algae in fish comprises:
the three-dimensional fluorescence spectrum data acquisition module is used for acquiring three-dimensional fluorescence spectrum data of the red tide algae sample; the red tide algae sample comprises fish toxicity red tide algae and non-fish toxicity red tide algae;
the preprocessing module is used for preprocessing the three-dimensional fluorescence spectrum data of the red tide algae sample;
the spectral feature extraction module is used for extracting spectral features from the preprocessed three-dimensional fluorescence spectral data;
the mapping model establishing module is used for establishing a mapping model for identifying the hemolytic activity of the fish toxic red tide algae by adopting a particle swarm optimization support vector machine method according to the extracted spectral characteristics;
the identification result determining module is used for determining an identification result by utilizing the mapping model according to the extracted spectral characteristics; the identification result is fish toxic red tide algae or non-fish toxic red tide algae.
Optionally, the preprocessing module specifically includes:
and the preprocessing unit is used for converting the three-dimensional fluorescence spectrum data into an xls file and importing the converted file into MATLAB2018a software to be converted into a mat file.
Optionally, the spectral feature extraction module specifically includes:
the excitation wavelength determining unit is used for determining the excitation wavelength according to the preprocessed three-dimensional fluorescence spectrum data by adopting an exhaustion method;
the emission wavelength determining unit is used for determining the emission wavelength according to the contour map and the spectrum interval of the preprocessed three-dimensional fluorescence spectrum data; the spectral interval is 650nm-750 nm;
and the spectral characteristic determining unit is used for determining the spectral characteristics according to the head-to-tail connection of the emission wavelengths under different excitation wavelengths.
Optionally, the mapping model establishing module specifically includes:
the parameter adjusting unit is used for adjusting parameters of the particle swarm optimization support vector machine according to the extracted spectral features; the parameters include: accelerating constant, maximum iteration times and particle swarm population number;
the mapping model establishing unit is used for determining the mapping model according to the particle swarm optimization support vector machine after the parameters are adjusted; the mapping model takes the extracted spectral features as input and the recognition result as output.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the on-line detection and identification method and system for the toxic red tide algae of the fish, provided by the invention, are based on the detection of a three-dimensional fluorescence spectrum method, and have the advantages of no chemical reagent, no pollution, simple operation, quick identification and the like; feature extraction is carried out through three-dimensional fluorescence spectrum data, and then a mapping model is used for identification, so that uninterrupted in-situ online measurement can be realized; and a mapping model for identifying the hemolytic activity of the fish toxic red tide algae is established by a particle swarm optimization support vector machine method, namely, a particle swarm optimization support vector machine classification algorithm is applied to the identification of the fish toxic red tide algae and the non-fish toxic red tide algae for the first time, the optimal identification model of the fish toxic red tide algae is established by using less spectral information, and the detection precision is high.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a schematic flow chart of an on-line detection and identification method for toxic red tide algae in fish provided by the present invention;
FIG. 2 is a three-dimensional fluorescence contour plot of 6 fish toxic red tide algae;
FIG. 3 is a three-dimensional fluorescence contour plot of 8 non-fish toxic red tide algae;
FIG. 4 is a schematic structural diagram of an on-line detection and identification system for toxic red tide algae in fish provided by the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a method and a system for online detection and identification of toxic red tide algae in fish, which can realize uninterrupted in-situ online detection and improve the detection precision.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Fig. 1 is a schematic flow chart of a method for online detection and identification of toxic red tide algae in fish provided by the present invention, and as shown in fig. 1, the method for online detection and identification of toxic red tide algae in fish provided by the present invention comprises:
s101, acquiring three-dimensional fluorescence spectrum data of a red tide algae sample; the red tide algae samples comprise fish toxic red tide algae and non-fish toxic red tide algae. The toxic red tide algae comprises: heterokava kashiwo (Heterosporima akashiwo), Kadunn algae (Chattonella marina), Rhabdoviridium kamurae (Karlodinium veneficum), Karenia mikimotoi (Karenia mikimotoi), Phaeocystis globosa (Phaeocystis globosa) and Verbena parvum (Prymnesium parvum); the non-fish toxic red tide algae comprises: prorocentrum donghaiense (Prorocentrum donghaiense), Karenia dunnii (Karenia dunnii), Prorocentrum limani (Prorocentrum lima), Isochrysis luteo (Isochrysis galbana), Isochrysis sphaericus (Isochrysis globosa), Phaeofusca tricornutum (phaeodactylum tricornutum), Skeletonema costatum (Skeletonema costatum) or Clerodendrum subcordiformis (tympana monbcordiformis).
The specific acquisition process comprises the following steps:
culturing samples of the fish toxic red tide algae and the non-fish toxic red tide algae under different nitrogen-phosphorus ratios and illumination, diluting according to 10 times, 100 times and 1000 times when living algae grow to a logarithmic phase, measuring the concentrations of the red tide algae under different concentration gradients through a microscope and an algae counting plate, and measuring corresponding three-dimensional fluorescence spectrums through a fluorescence photometer.
The concentration gradient of the red tide algae three-dimensional fluorescence spectrum data with different concentrations is 104cell/ml、105cell/ml、106cell/ml; the nitrogen-phosphorus ratios are 1:1, 16:1 and 128: 1; 20 mu mol under different illumination-2s-1、60μmol-2s-1、100μmol-2s-1(ii) a The fluorometer is an F4600 spectrofluorometer from Hitachi, Japan.
S102, preprocessing the three-dimensional fluorescence spectrum data of the red tide algae sample.
S102 specifically comprises the following steps:
and converting the three-dimensional fluorescence spectrum data into an xls file, and importing the converted file into MATLAB2018a software to be converted into a mat file.
And S103, extracting spectral characteristics from the preprocessed three-dimensional fluorescence spectral data.
S103 specifically comprises the following steps:
determining the excitation wavelength by adopting an exhaustion method according to the preprocessed three-dimensional fluorescence spectrum data;
determining an emission wavelength according to the contour map and the spectrum interval of the preprocessed three-dimensional fluorescence spectrum data; the spectral interval is 650nm-750 nm. The contour diagrams are respectively shown as a three-dimensional fluorescence contour diagram of 6 kinds of fish toxic red tide algae in figure 2 and a three-dimensional fluorescence contour diagram of 8 kinds of non-fish toxic red tide algae in figure 3.
And determining the spectral characteristics according to the head-to-tail connection of the emission wavelengths under different excitation wavelengths.
And S104, establishing a mapping model for identifying the hemolytic activity of the fish toxic red tide algae by adopting a particle swarm optimization support vector machine method according to the extracted spectral characteristics.
S104 specifically comprises the following steps:
adjusting parameters of a particle swarm optimization support vector machine according to the extracted spectral features; the parameters include: acceleration constant, maximum iteration number and particle swarm population number.
Determining the mapping model according to the particle swarm optimization support vector machine after the parameters are adjusted; the mapping model takes the extracted spectral features as input and the recognition result as output. Namely, a mapping relation between the spectral characteristics and the algae identification labels is established.
S105, determining a recognition result by utilizing the mapping model according to the extracted spectral features; the identification result is fish toxic red tide algae or non-fish toxic red tide algae.
The specific identification process is as follows:
selecting spectral data with excitation wavelengths of 480nm and 510nm and emission wavelengths of 650-750 nm; connecting the data ends of each red tide algae sample under two excitation wavelengths to form a new red tide algae spectral data matrix with the row number of the samples and the column number of the samples as the characteristics of the samples; randomly selecting 70% of the new red tide algae spectral data matrix as a training set to generate a training set data set T { (x)1,y1),(x2,y2),…,(xN,yN) }; wherein, N is the number of samples,
in order to train the feature vectors of the examples,
taking training set data as input of a particle swarm optimization support vector machine classification algorithm for training the category of the example, marking the fish toxicity red tide algae as 1 and the non-fish toxicity red tide algae as 2, and establishing a qualitative analysis model of the fish toxicity red tide algae and the non-fish toxicity red tide algae; when the detection sample is x, byScanning to obtain three-dimensional fluorescence spectrum information of a sample, wherein the three-dimensional fluorescence spectrum information comprises an excitation wavelength, an emission wavelength and corresponding fluorescence intensity, substituting spectral data with the excitation wavelength of 480nm and 510nm and the emission wavelength of 650-750nm as a test set into a particle swarm optimization support vector machine classification model of red tide algae with fish toxicity and non-red tide algae with fish toxicity, and setting a set acceleration constant c1And c2Maximum iteration number m and particle swarm population number Tmax1.5, 1.7, 20 and 100 respectively, and obtaining results based on a particle swarm optimization support vector machine classification algorithm.
Fig. 4 is a schematic structural diagram of an online detection and identification system for toxic red tide algae in fish provided by the present invention, and as shown in fig. 4, the online detection and identification system for toxic red tide algae in fish provided by the present invention comprises:
a three-dimensional fluorescence spectrum data acquisition module 401, configured to acquire three-dimensional fluorescence spectrum data of a red tide algae sample; the red tide algae samples comprise fish toxic red tide algae and non-fish toxic red tide algae.
A preprocessing module 402, configured to preprocess the three-dimensional fluorescence spectrum data of the red tide algae sample.
And a spectral feature extraction module 403, configured to extract spectral features from the preprocessed three-dimensional fluorescence spectral data.
And the mapping model establishing module 404 is configured to establish a mapping model for identifying hemolytic activity of the fish toxic red tide algae by using a particle swarm optimization support vector machine method according to the extracted spectral features.
A recognition result determining module 405, configured to determine a recognition result according to the extracted spectral features by using the mapping model; the identification result is fish toxic red tide algae or non-fish toxic red tide algae.
The preprocessing module 402 specifically includes:
and the preprocessing unit is used for converting the three-dimensional fluorescence spectrum data into an xls file and importing the converted file into MATLAB2018a software to be converted into a mat file.
The spectral feature extraction module 403 specifically includes:
and the excitation wavelength determining unit is used for determining the excitation wavelength by adopting an exhaustion method according to the preprocessed three-dimensional fluorescence spectrum data.
The emission wavelength determining unit is used for determining the emission wavelength according to the contour map and the spectrum interval of the preprocessed three-dimensional fluorescence spectrum data; the spectral interval is 650nm-750 nm.
And the spectral characteristic determining unit is used for determining the spectral characteristics according to the head-to-tail connection of the emission wavelengths under different excitation wavelengths.
The mapping model building module 404 specifically includes:
the parameter adjusting unit is used for adjusting parameters of the particle swarm optimization support vector machine according to the extracted spectral features; the parameters include: acceleration constant, maximum iteration number and particle swarm population number.
The mapping model establishing unit is used for determining the mapping model according to the particle swarm optimization support vector machine after the parameters are adjusted; the mapping model takes the extracted spectral features as input and the recognition result as output.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (8)
1. An online detection and identification method for toxic red tide algae in fish is characterized by comprising the following steps:
acquiring three-dimensional fluorescence spectrum data of a red tide algae sample; the red tide algae sample comprises fish toxicity red tide algae and non-fish toxicity red tide algae;
preprocessing the three-dimensional fluorescence spectrum data of the red tide algae sample;
extracting spectral characteristics from the preprocessed three-dimensional fluorescence spectrum data;
according to the extracted spectral characteristics, establishing a mapping model for identifying the hemolytic activity of the fish toxic red tide algae by adopting a particle swarm optimization support vector machine method;
determining a recognition result by utilizing the mapping model according to the extracted spectral features; the identification result is fish toxic red tide algae or non-fish toxic red tide algae.
2. The method as claimed in claim 1, wherein the preprocessing of the three-dimensional fluorescence spectrum data of the red tide algae sample comprises:
and converting the three-dimensional fluorescence spectrum data into an xls file, and importing the converted file into MATLAB2018a software to be converted into a mat file.
3. The method as claimed in claim 1, wherein the extracting the spectral feature of the preprocessed three-dimensional fluorescence spectrum data comprises:
determining the excitation wavelength by adopting an exhaustion method according to the preprocessed three-dimensional fluorescence spectrum data;
determining an emission wavelength according to the contour map and the spectrum interval of the preprocessed three-dimensional fluorescence spectrum data; the spectral interval is 650nm-750 nm;
and determining the spectral characteristics according to the head-to-tail connection of the emission wavelengths under different excitation wavelengths.
4. The method as claimed in claim 1, wherein the establishing of the mapping model for identifying the hemolytic activity of the toxic red tide algae by using a particle swarm optimization support vector machine method according to the extracted spectral features specifically comprises:
adjusting parameters of a particle swarm optimization support vector machine according to the extracted spectral features; the parameters include: accelerating constant, maximum iteration times and particle swarm population number;
determining the mapping model according to the particle swarm optimization support vector machine after the parameters are adjusted; the mapping model takes the extracted spectral features as input and the recognition result as output.
5. The utility model provides a fish toxicity red tide algae on-line measuring identification system which characterized in that includes:
the three-dimensional fluorescence spectrum data acquisition module is used for acquiring three-dimensional fluorescence spectrum data of the red tide algae sample; the red tide algae sample comprises fish toxicity red tide algae and non-fish toxicity red tide algae;
the preprocessing module is used for preprocessing the three-dimensional fluorescence spectrum data of the red tide algae sample;
the spectral feature extraction module is used for extracting spectral features from the preprocessed three-dimensional fluorescence spectral data;
the mapping model establishing module is used for establishing a mapping model for identifying the hemolytic activity of the fish toxic red tide algae by adopting a particle swarm optimization support vector machine method according to the extracted spectral characteristics;
the identification result determining module is used for determining an identification result by utilizing the mapping model according to the extracted spectral characteristics; the identification result is fish toxic red tide algae or non-fish toxic red tide algae.
6. The system of claim 5, wherein the preprocessing module specifically comprises:
and the preprocessing unit is used for converting the three-dimensional fluorescence spectrum data into an xls file and importing the converted file into MATLAB2018a software to be converted into a mat file.
7. The system of claim 5, wherein the spectral feature extraction module specifically comprises:
the excitation wavelength determining unit is used for determining the excitation wavelength according to the preprocessed three-dimensional fluorescence spectrum data by adopting an exhaustion method;
the emission wavelength determining unit is used for determining the emission wavelength according to the contour map and the spectrum interval of the preprocessed three-dimensional fluorescence spectrum data; the spectral interval is 650nm-750 nm;
and the spectral characteristic determining unit is used for determining the spectral characteristics according to the head-to-tail connection of the emission wavelengths under different excitation wavelengths.
8. The system of claim 5, wherein the mapping model building module specifically comprises:
the parameter adjusting unit is used for adjusting parameters of the particle swarm optimization support vector machine according to the extracted spectral features; the parameters include: accelerating constant, maximum iteration times and particle swarm population number;
the mapping model establishing unit is used for determining the mapping model according to the particle swarm optimization support vector machine after the parameters are adjusted; the mapping model takes the extracted spectral features as input and the recognition result as output.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110259038.0A CN113030049A (en) | 2021-03-10 | 2021-03-10 | Online detection and identification method and system for toxic red tide algae in fish |
| GB2113428.3A GB2604677A (en) | 2021-03-10 | 2021-09-21 | A method and system for online detection and identification of ichthyotoxic harmful algal bloom algae |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110259038.0A CN113030049A (en) | 2021-03-10 | 2021-03-10 | Online detection and identification method and system for toxic red tide algae in fish |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113030049A true CN113030049A (en) | 2021-06-25 |
Family
ID=76469324
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110259038.0A Pending CN113030049A (en) | 2021-03-10 | 2021-03-10 | Online detection and identification method and system for toxic red tide algae in fish |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113030049A (en) |
| GB (1) | GB2604677A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113705608A (en) * | 2021-07-23 | 2021-11-26 | 暨南大学 | Method for identifying bigeye-producing shellfish toxin algae by using machine learning and/or artificial neural network model and application thereof |
| CN113916860A (en) * | 2021-11-02 | 2022-01-11 | 淮阴工学院 | Pesticide residue type identification method based on fluorescence spectrum |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080085506A1 (en) * | 2006-10-10 | 2008-04-10 | Lapota | Automated, field-portable system for conducting toxicity measurements in water, soils, and sediments |
| CN102608085A (en) * | 2012-01-09 | 2012-07-25 | 暨南大学 | Method for detecting activity of alga hematoxin and application of method |
| CN107741410A (en) * | 2017-09-18 | 2018-02-27 | 燕山大学 | A kind of fluorescence spectrum detection method of the benzo class material based on ICSO SVM |
| CN108732142A (en) * | 2018-02-09 | 2018-11-02 | 秦皇岛红燕光电科技有限公司 | Phytoplankton & Suspension red tide based on three-dimensional fluorescence spectrum and detection method of toxicity |
| CN110658162A (en) * | 2018-06-29 | 2020-01-07 | 中国石油化工股份有限公司 | Method for predicting crude oil concentration in rock debris extraction liquid by three-dimensional fluorescence spectrum |
| CN111175260A (en) * | 2020-01-07 | 2020-05-19 | 燕山大学 | Ocean TOC sensor based on ultraviolet three-dimensional fluorescence and using method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6985224B2 (en) * | 2003-03-14 | 2006-01-10 | The United States Of America As Represented By The Secretary Of The Navy | Light emitting diode (LED) array for excitation emission matrix (EEM) fluorescence spectroscopy |
-
2021
- 2021-03-10 CN CN202110259038.0A patent/CN113030049A/en active Pending
- 2021-09-21 GB GB2113428.3A patent/GB2604677A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080085506A1 (en) * | 2006-10-10 | 2008-04-10 | Lapota | Automated, field-portable system for conducting toxicity measurements in water, soils, and sediments |
| CN102608085A (en) * | 2012-01-09 | 2012-07-25 | 暨南大学 | Method for detecting activity of alga hematoxin and application of method |
| CN107741410A (en) * | 2017-09-18 | 2018-02-27 | 燕山大学 | A kind of fluorescence spectrum detection method of the benzo class material based on ICSO SVM |
| CN108732142A (en) * | 2018-02-09 | 2018-11-02 | 秦皇岛红燕光电科技有限公司 | Phytoplankton & Suspension red tide based on three-dimensional fluorescence spectrum and detection method of toxicity |
| CN110658162A (en) * | 2018-06-29 | 2020-01-07 | 中国石油化工股份有限公司 | Method for predicting crude oil concentration in rock debris extraction liquid by three-dimensional fluorescence spectrum |
| CN111175260A (en) * | 2020-01-07 | 2020-05-19 | 燕山大学 | Ocean TOC sensor based on ultraviolet three-dimensional fluorescence and using method |
Non-Patent Citations (2)
| Title |
|---|
| 桓清柳等: "鱼毒性藻类及其溶血活性的三维荧光光谱识别研究", 《光谱学与光谱分析》 * |
| 王书涛等: "基于ICSO-SVM和三维荧光光谱的山梨酸钾浓度检测", 《光谱学与光谱分析》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113705608A (en) * | 2021-07-23 | 2021-11-26 | 暨南大学 | Method for identifying bigeye-producing shellfish toxin algae by using machine learning and/or artificial neural network model and application thereof |
| CN113916860A (en) * | 2021-11-02 | 2022-01-11 | 淮阴工学院 | Pesticide residue type identification method based on fluorescence spectrum |
Also Published As
| Publication number | Publication date |
|---|---|
| GB2604677A (en) | 2022-09-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Boyd et al. | Aerosol iron deposition to the surface ocean—modes of iron supply and biological responses | |
| Babin et al. | Approachesand | |
| Jiang et al. | Effects of seasonal succession and water pollution on the protozoan community structure in an eutrophic lake | |
| CN113030049A (en) | Online detection and identification method and system for toxic red tide algae in fish | |
| Dubelaar et al. | High frequency monitoring reveals phytoplankton dynamics | |
| Thyssen et al. | The emergence of automated high-frequency flow cytometry: revealing temporal and spatial phytoplankton variability | |
| CN103822886A (en) | Analysis detection of biological humic acid and carbon ratio determination method | |
| Ammerman et al. | Continuous underway measurement of microbial ectoenzyme activities in aquatic ecosystems | |
| CN109540859A (en) | The analysis and content prediction method of antibiotic in a kind of water body | |
| Cai et al. | Detection of two Prorocentrum species using sandwich hybridization integrated with nuclease protection assay | |
| CN113658640B (en) | Fresh water ecological system health evaluation method | |
| Wendler et al. | Production of calcareous dinoflagellate cysts in response to monsoon forcing off Somalia: a sediment trap study | |
| Humbert et al. | New tools for the monitoring of cyanobacteria in freshwater ecosystems | |
| Wang et al. | Seasonal variations of phytoplankton phosphorus stress in the Yellow Sea Cold Water Mass | |
| Huo et al. | Multispectral remote sensing inversion for city landscape water eutrophication based on Genetic Algorithm-Support Vector Machine | |
| CN112414979B (en) | Fluorescence characteristic standard spectrum library for identifying microalgae producing paralytic shellfish poison as well as construction method and application thereof | |
| Penna et al. | Potentially harmful microalgal distribution in an area of the NW Adriatic coastline: sampling procedure and correlations with environmental factors | |
| Rekik et al. | Spatial variations of planktonic ciliates, predator-prey interactions and their environmental drivers in the Gulf of Gabes-Boughrara lagoon system | |
| CN111912824A (en) | Application of three-dimensional fluorescence spectrometry in identification of microalgae producing paralytic shellfish poison | |
| CN106018688B (en) | A kind of evaluation method of metal nanoparticle ion and nano effect toxicity contribution rate | |
| CN109781682B (en) | Method for determining soluble organic matters in breeding wastewater duckweed treatment system | |
| CN115219472B (en) | Method and system for quantitatively identifying multiple pollution sources of mixed water body | |
| CN109457017B (en) | Molecular detection method for rapidly quantifying diatom cell density | |
| Liu et al. | Effects of irradiance on pigment signatures of harmful algae during growth process | |
| CN101914615B (en) | Constructing method of standard sample in Alexandrium catenella (A.catenella) fluorescence quantitative polymerase chain reaction |
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 |