GB2604677A - A method and system for online detection and identification of ichthyotoxic harmful algal bloom algae - Google Patents
A method and system for online detection and identification of ichthyotoxic harmful algal bloom algae Download PDFInfo
- Publication number
- GB2604677A GB2604677A GB2113428.3A GB202113428A GB2604677A GB 2604677 A GB2604677 A GB 2604677A GB 202113428 A GB202113428 A GB 202113428A GB 2604677 A GB2604677 A GB 2604677A
- Authority
- GB
- United Kingdom
- Prior art keywords
- algae
- hab
- ichthyotoxic
- identification
- spectral
- 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
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
A method and system for online detection and identification of ichthyotoxic HAB algae, comprises: acquiring three-dimensional fluorescence spectral data of HAB algae samples comprising ichthyotoxic and non-ichthyotoxic algae; pre-treating the spectral data of the HAB algae samples; extracting spectral features from pre-treated spectral data; establishing a mapping model for identifying the haemolytic activity of ichthyotoxic HAB algae based on the extracted spectral features by using the particle swarm optimisation support vector machine method; determining the identification results based on the extracted spectral features by using the mapping model, to identify ichthyotoxic HAB algae or non-ichthyotoxic HAB algae.
Description
A METHOD AND SYSTEM FOR ONLINE DETECTION AND IDENTIFICATION
OF ICHTHYOTOXIC HARMFUL ALGAL BLOOM ALGAE
FIELD OF THE INVENTION
The present disclosure relates to the field of qualitative detection of ichthyotoxic harmful algal bloom algae, and in particular, to a method and system for online detection and identification of ichthyotoxic harmful algal bloom algae.
BACKGROUND OF THE INVENTION
Harmful algal bloom (HAB), also known as red tide, is a harmful ecological phenomenon, which is a discoloration of water caused by the explosive proliferation or high aggregation of certain phytoplankton, protozoa or bacteria in seawater under specific environmental conditions. In which, ichthyotoxic HAB may produce a variety of toxic substances, which can cause a large number of fish and shellfish deaths in a short time. At present, ichthyotoxic HAB algae has widely spread in China's coastal areas. In 2012 alone, more than RMB 2 billion were lost from the East China Sea due to Karenia mikimotoi, and this has seriously restricted the sustainable and healthy development of China's inshore farming industry. If ichthyotoxic FIAB algae can be identified early and quickly, in situ and online, farmers could be warned in advanced, so that relevant measures can be taken to reduce economic losses of the seawater farming industry caused by ichthyotoxic HAB algae.
At present, detection methods of ichthyotoxic HAB algae species mainly comprise the following three types: the first is morphology-based HAB biodetection technique, the second is molecular technique-based algae identification technique, and the third is antibody-based immunological identification technique, and the fourth is algae fluorescence emission spectroscopy-based detection technique. Identification based on cell morphology cannot determine the toxicity category of algae; the molecular technique can only be used in the laboratory for identification of HAB algae species, and it also cannot be used to perform onsite rapid detection; the immunological identification technique has currently developed a variety of kits or reagent strips for the detection of algae, but these reagents can only be used for the detection of known algae, and samples need to be pre-treated in the laboratory, which is time consuming and not time efficient, and cannot be used for in-situ detection. With the advancement of fluorescence detection techniques in recent years, the three-dimensional fluorescence spectroscopy data technique has developed rapidly in the area of algae identification, and is increasingly mature. At present, a variety of professional equipment have been developed for application in areas such as petroleum, polychlorinated biphenyl, biological hormone and microalgae identification. However, there is currently no method or system for online detection or identification of ichthyotoxic HAB algae.
SUMMARY OF THE INVENTION
The objective of the present disclosure is to provide a method and system for the online detection or identification of ichthyotoxic HAB algae, and that is capable of achieving continuous online detection in situ and improving detection precision.
In order to achieve the aforementioned objective, the present disclosure provides the following solution: A method for online detection and identification of ichthyotoxic HAB algae, comprising: acquiring three-dimensional fluorescence spectral data of HAB algae samples; the HAB algae samples comprise ichthyotoxic HAB algae and non-ichthyotoxic HAB algae; pre-treating the three-dimensional fluorescence spectral data of the HAB algae samples; extracting spectral features from pre-treated three-dimensional fluorescence spectral data; establishing a mapping model for identifying the haemolytic activity of ichthyotoxic HAB algae based on the extracted spectral features by using the particle swarm optimisation support vector machine method; determining the identification results based on the extracted spectral features by using the mapping model; the identification result being ichthyotoxic HAB algae or nonichthyotoxic HAB algae.
Preferably, pre-treating the three-dimensional fluorescence spectral data of the HAB algae samples specifically comprises: converting the three-dimensional fluorescence spectral data into xls files, importing the converted files into MATLAB2018a software and converting them into mat files.
Preferably, extracting spectral features from pre-treated three-dimensional fluorescence spectral data specifically comprises: determining the excitation wavelength based on the pre-treated three-dimensional fluorescence spectral data by using the proof by exhaustion method; determining the emission wavelength based on the contour map and spectral interval of the pre-treated three-dimensional fluorescence spectral data; the spectral interval being 650 nm -750 nm; determining the spectral features based on the head-to-tail linking of the emission wavelengths at different excitation wavelengths Preferably, establishing a mapping model for identifying the haemolytic activity of ichthyotoxic HAB algae based on the extracted spectral features by using the particle swarm optimisation support vector machine method specifically comprises: adjusting the parameters of the particle swarm optimisation support vector machine based on the extracted spectral features; the parameters comprise: acceleration constant, maxi mum number of iterations and number of particle swarms; determining the mapping model based on the particle swarm optimisation support vector machine after parameter adjustment; the mapping model uses the extracted spectral features as input and the identification result as output.
A system for online identification and identification of ichthyotoxic HAB algae, comprising: a three-dimensional fluorescence spectral data acquisition module for acquiring three-dimensional fluorescence spectral data of HAB algae samples; the HAB algae samples comprise ichthyotoxic HAB algae and non-ichthyotoxic HAB algae; a pre-treatment module for pre-treating the three-dimensional fluorescence spectral data of HAB algae samples; a spectral feature extraction module for extracting spectral features from pre-treated three-dimensional fluorescence spectral data; a mapping model establishment module for establishing a mapping model for identifying the haemolytic activity of ichthyotoxic HAB algae based on the extracted spectral features by using the particle swarm optimisation support vector machine method; an identification result determination module for determining identification results based on the extracted spectral features by using the mapping model; the identification result being ichthyotoxic HAB algae or non-ichthyotoxic HAB algae.
Preferably, the pre-treatment module specifically comprises: a pre-treatment unit for converting the three-dimensional fluorescence spectral data into workbook/spreadsheet (e.g. xis) files importing the converted files into a multi-paradigm programming language and numeric computing environment (such as MATLAB2018a software) and converting them into formatted data files (e.g. mat files).
Preferably, the spectral feature extraction module specifically comprises: an excitation wavelength determination unit for determining the excitation wavelength based on the pre-treated three-dimensional fluorescence spectral data by using the proof by exhaustion method; an emission wavelength determination unit for determining the emission wavelength based on the contour map and spectral interval of the pre-treated three-dimensional fluorescence spectral data; the spectral interval being 650 nm -750 nm; a spectral feature determination unit for determining the spectral features based on the head-to-tail linking of the emission wavelengths at different excitation wavelengths.
Preferably, the mapping model establishment module specifically comprises: a parameter adjustment unit for adjusting the parameters of the particle swarm optimisation support vector machine based on the extracted spectral features; the parameters comprise: acceleration constant, maximum number of iterations and number of particle swarms; a mapping model establishment unit for determining the mapping model based on the particle swarm optimisation support vector machine after parameter adjustment; the mapping model uses the extracted spectral features as input and the identification result as output.
According to the specific embodiments provided by the present disclosure, the present disclosure discloses the following technical effects: a method and system for online detection and identification of ichthyotoxic HAB algae provided by the present disclosure that carry out detection based on the three-dimensional fluorescence spectroscopy method, with the advantages of not involving chemical reagents, being pollution-free, having simple operations and rapid identification; the extraction of features through three-dimensional fluorescence spectral data and thereby identification using the mapping model is capable of achieving continuous online measurement in situ; and the establishment of a mapping model for identifying the haemolytic activity of ichthyotoxic HAB algae, that is, the particle swarm optimisation support vector machine classification algorithm, and by using the particle swarm optimisation support vector machine method, the algorithm is applied for the first time to identify ichthyotoxic HAB algae and non-ichthyotoxic HAB algae, which uses relatively little spectral information for establishing an optimal identification model of ichthyotoxic HAB algae and has high detection precision.
BRIEF DESCRIPTION OF THE DRAWINGS
To better describe the technical solution in the embodiments of the present disclosure or prior art, the following drawings, which are needed for the embodiments, will be described briefly below. Obviously, the drawings in the following description are only some embodiments of the present disclosure and those of ordinary skill in the art may still acquire other drawings based on the following drawings without creative effort.
Fig. 1 is a schematic diagram of the process of a method for online detection and identification of ichthyotoxic HAB algae as provided by the present disclosure; Fig. 2 is a three-dimensional fluorescence contour map of six kinds of ichthyotoxic HAB algae; Fig. 3A and 3B show three-dimensional fluorescence contour maps of eight kinds of non-ichthyotoxic HAB algae; Fig. 4 is a structural schematic diagram of a system for online detection and identification of ichthyotoxic HAB algae as provided by the present disclosure.
C\J 15 C\I
DETAILED DESCRIPTION
The technical solution in the embodiments of the present disclosure will be clearly and CO completely described below with reference to the drawings in the embodiments of the present disclosure. Obviously, the embodiments described are only part of the embodiments of the present disclosure, and not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by those of ordinary skill in the art without creative effort fall within the scope of protection of the present disclosure.
The objective of the present disclosure is to provide a method and system for the online detection or identification of ichthyotoxic HAB algae, and that is capable of achieving continuous online detection in situ and improving detection precision.
In order to make the above objectives, features and advantages of the present disclosure clearer and easy to understand, the present disclosure will be further described in details below with reference to the attached drawings and specific embodiments.
Fig. 1 is a schematic diagram of the process of a method for online detection and identification of ichthyotoxic HAB algae as provided by the present disclosure, as shown in Fig. 1, a method for online detection and identification of ichthyotoxic HAB algae provided by the present disclosure, comprising: S101, acquiring three-dimensional fluorescence spectral data of HAB algae samples; the HAB algae samples comprise ichthyotoxic HAB algae and non-ichthyotoxic HAB algae; The ichthyotoxic HAB algae comprise: Heterosigma akashiwo, Chattonella marina, Karl odinium venefi cum, Kareni a mikimotoi, Phaeocystis globosa and Prymnesium parvum; the non-ichthyotoxic HAB algae comprise: Prorocentrum donghaiense, Karenia dunnii, prorocentrum lima, Isoscelina galbana, Isosceles globosa, phaeodactylum tricornutum, Skeletonem a costatum or platymonas subcordiformis.
The specific acquisition process involves: diluting ichthyotoxic HAB algae and non-ichthyotoxic HAB algae samples cultured under different nitrogen to phosphorus ratios and light exposures by 10 times, 100 times and 1,000 times when living algae grows to a logarithmic phase, measuring the concentrations of HAB algae at different concentration gradients by microscope and algae counting plate, and measuring the corresponding three-dimensional fluorescence spectrum by fluorescence spectrophotometer.
The different concentration gradients in the three-dimensional fluorescence spectral C\I data of HAB algae at different concentrations are 104 cellImL, 105 cellImL and 106 celllinL; C\I the different nitrogen to phosphorus ratios are 1:1, 16:1 and 128:1; the different light exposures are 20 /and 2 5-1, 60,Eno/ -2 54 and 100 wird the fluorescence
CD
spectrophotometer is the F4600 spectrophotometer from Hitachi Ltd. CO20 S102, pre-treating the three-dimensional fluorescence spectral data of the HAB algae samples.
S102 specifically comprises: converting the three-dimensional fluorescence spectral data into xis files, importing the converted files into MATLAB2018a software and converting them into mat files.
S103, extracting spectral features from pre-treated three-dimensional fluorescence spectral data.
S103 specifically comprises: determining the excitation wavelength based on the pretreated three-dimensional fluorescence spectral data by using the proof by exhaustion method; determining the emission wavelength based on the contour map and spectral interval of the pre-treated three-dimensional fluorescence spectral data; the spectral interval being 650 nm -750 nm. The contour maps are shown as the three-dimensional fluorescence contour map of six kinds of ichthyotoxic HAB algae in Fig. 2 and the three-dimensional fluorescence contour map of eight kinds of non-ichthyotoxic HAB algae in Figs. 3A and 3B.
determining the spectral features based on the head-to-tail linking of the emission wavelengths at different excitation wavelengths.
S104, establishing a mapping model for identifying the haemolytic activity of ichthyotoxic HAB algae based on the extracted spectral features by using the particle swarm optimisation support vector machine method; S104 specifically comprises: adjusting the parameters of the particle swarm opti m i sati on support vector machine based on the extracted spectral features; the parameters comprise: acceleration constant, maximum number of iterations and number of particle swarms determining the mapping model based on the particle swarm optimisation support vector machine after parameter adjustment; the mapping model uses the extracted spectral features as input and the identification result as output. that is, the mapping relationship between spectral features and algae classification labels is established.
S105, determining the identification results based on the extracted spectral features by using the mapping model; the identification result would be ichthyotoxic HAB algae or non-ichthyotoxic HAB algae.
The specific identification process involves: selecting spectral data at the excitation wavelengths of 480 nm and 510 nm, and emission wavelength between 650 nm and 750 nm, linking the head-to-tail data of each HAB algae sample at two excitation wavelengths to form the number of behavioural samples, and listing it as a new HAB algae spectral data matrix of sample features; randomly selecting 70% of the new HAB algae spectral data matrix as a training set, and generating a training set data set T = {(xt y2), (x2, y2), yA)}; in which, N is the number of samples, x, x Rn is the feature vector of the training example, y, e yc (cl, c2, c3, , c3, ) is the category of the training example, using training set data as input of the particle swarm optimisation support vector machine classification algorithm, labelling ichthyotoxic HAB algae as 1, nonichthyotoxic HAB algae as 2, establish a qualitative analysis model of ichthyotoxic HAB algae and non-ichthyotoxic HAB algae; when the test sample is x, obtaining the three-dimensional fluorescence spectral information of the sample by scanning, including its excitation wavelength, emission wavelength and corresponding fluorescence intensity, substituting spectral data at excitation wavelengths of 480 nm and 510 nm and emission wavelength of 650 -750 nm into the particle swarm optimisation support vector machine of ichthyotoxic HAB algae and non-ichthyotoxic HAB algae as the test set, in which, setting the set acceleration constants Cl and c2, maximum number of iterations m, the number of particle swarms T. as 1.5, 1.7, 20 and 100, respectively, and obtaining the results based on the particle swarm optimisation support vector machine classification algorithm.
Fig. 4 is a structural schematic diagram of a system for online detection and identification of ichthyotoxic HAB algae as provided by the present disclosure, as shown in Fig. 4, a system for online detection and identification of ichthyotoxic HAB algae as provided by the present disclosure, comprising: a three-dimensional fluorescence spectral data acquisition module 401 for acquiring three-dimensional fluorescence spectral data of HAB algae samples; the HAB algae samples comprise ichthyotoxic BAB algae and non-ichthyotoxic HAB algae.
a pre-treatment module 402 for pre-treating the three-dimensional fluorescence spectral data of HAB algae samples.
a spectral feature extraction module 403 for extracting spectral features from pre-treated three-dimensional fluorescence spectral data; a mapping model establishment module 404 for establishing a mapping model for identifying the haemolytic activity of ichthyotoxic HAB algae based on the extracted spectral features by using the particle swarm optimisation support vector machine method.
an identification result determination module 405 for determining identification results based on the extracted spectral features by using the mapping model; the identification result being ichthyotoxic HAB algae or non-ichthyotoxic HAB algae.
The pre-treatment module 402 specifically comprises: a pre-treatment unit for converting the three-dimensional fluorescence spectral data into xls files importing the converted files into MATLAB2018a software and converting them into mat files.
The spectral feature extraction module 403 specifically comprises: an excitation wavelength determination unit for determining the excitation wavelength based on the pre-treated three-dimensional fluorescence spectral data by using the proof by exhaustion method.
an emission wavelength determination unit for determining the emission wavelength based on the contour map and spectral interval of the pre-treated three-dimensional fluorescence spectral data; the spectral interval being 650 nm -750 nm.
a spectral feature determination unit for determining the spectral features based on the head-to-tail linking of the emission wavelengths at different excitation wavelengths.
The mapping model establishment module 404 specifically comprises: a parameter adjustment unit for adjusting the parameters of the particle swarm optimisation support vector machine based on the extracted spectral features, the parameters comprise: acceleration constant, maximum number of iterations and number of particle swarms.
a mapping model establishment unit for determining the mapping model based on the particle swarm optimisation support vector machine after parameter adjustment; the mapping model uses the extracted spectral features as input and the identification result as output.
The embodiments in this Specifications are described in a progressive manner. The highlights of each embodiment are different from those of other embodiments, and same or similar parts between the embodiments may be cross-referenced. For the system disclosed in the embodiments, as it corresponds to the method disclosed in the embodiments, the IS description is relatively simple. Please refer to the description on the method for the relevant parts Specific examples are used to illustrate the principles and embodiments of the present disclosure herein The description of the above embodiments is only used to facilitate understanding in the methods and core ideologies of the present disclosure At the same time, for those of ordinary skill in the art, according to the ideology of the present disclosure, there will be changes in the specific embodiments and scope of application. In conclusion, the content of this Specifications shall not be construed as a restriction of the present disclosure.
Claims (8)
- CLAIMS1. A method for online detection and identification of ichthyotoxic HAB algae, wherein comprising: acquiring three-dimensional fluorescence spectral data of HAB algae samples; the HAB algae samples comprise ichthyotoxic HAB algae and non-ichthyotoxic HAB algae; pre-treating the three-dimensional fluorescence spectral data of the HAB algae samples; extracting spectral features from pre-treated three-dimensional fluorescence spectral data; establishing a mapping model for identifying the haemolytic activity of ichthyotoxic HAB algae based on the extracted spectral features by using the particle swarm optimisation support vector machine method; determining the identification results based on the extracted spectral features by using the mapping model; the identification result being ichthyotoxic HAB algae or non-ichthyotoxic HAB algae.
- 2. The method for online detection and identification of ichthyotoxic HAB algae according to Claim 1, wherein pre-treating the three-dimensional fluorescence spectral data of the HAB algae samples specifically comprises: converting the three-dimensional fluorescence spectral data into spreadsheet files, importing the converted files into numeric computing software and converting them into formatted data files.
- 3 The method for online detection and identification of ichthyotoxic HAB algae according to Claim 1, wherein extracting spectral features from pre-treated three-dimensional fluorescence spectral data specifically comprises: determining the excitation wavelength based on the pre-treated three-dimensional fluorescence spectral data by using the proof by exhaustion method; determining the emission wavelength based on the contour map and spectral interval of the pre-treated three-dimensional fluorescence spectral data, the spectral interval being 650 nm -750 nm; determining the spectral features based on the head-to-tail linking of the emission wavelengths at different excitation wavelengths.
- 4. The method for online detection and identification of ichthyotoxic HAB algae according to Claim 1, wherein establishing a mapping model for identifying the haemolytic activity of ichthyotoxic HAB algae based on the extracted spectral features by using the particle swarm optimisation support vector machine method specifically comprises adjusting the parameters of the particle swarm optimisation support vector machine based on the extracted spectral features; the parameters comprise: acceleration constant, maximum number of iterations and number of particle swarms; determining the mapping model based on the particle swarm optimisation support vector machine after parameter adjustment, the mapping model uses the extracted spectral features as input and the identification result as output
- 5. A system for online detection and identification of ichthyotoxic HAB algae, wherein comprises: a three-dimensional fluorescence spectral data acquisition module for acquiring three-dimensional fluorescence spectral data of HAB algae samples; the HAB algae samples comprise ichthyotoxic HAB algae and non-ichthyotoxic HAB algae; a pre-treatment module for pre-treating the three-dimensional fluorescence spectral data of HAB algae samples; a spectral feature extraction module for extracting spectral features from pre-treated three-dimensional fluorescence spectral data; a mapping model establishment module for establishing a mapping model for identifying the haemolytic activity of ichthyotoxic HAB algae based on the extracted spectral features by using the particle swarm optimisation support vector machine method; an identification result determination module for determining identification results based on the extracted spectral features by using the mapping model; the identification result being ichthyotoxic HAB algae or non-ichthyotoxic HAB algae.
- 6. The system for online detection and identification of ichthyotoxic fl AB algae according to Claim 5, wherein the pre-treatment module specifically comprises: a pre-treatment unit for converting the three-dimensional fluorescence spectral data into spreadsheet files importing the converted files into numeric computing software and converting them into formatted data files.
- 7. The system for online detection and identification of ichthyotoxic HAB algae according to Claim 5, wherein the spectral feature extraction module specifically comprises: an excitation wavelength determination unit for determining the excitation wavelength based on the pre-treated three-dimensional fluorescence spectral data by using the proof by exhaustion method; an emission wavelength determination unit for determining the emission wavelength based on the contour map and spectral interval of the pre-treated three-dimensional fluorescence spectral data; the spectral interval being 650 nm -750 nm; a spectral feature determination unit for determining the spectral features based on the head-to-tail linking of the emission wavelengths at different excitation wavelengths
- 8. The system for online detection and identification of ichthyotoxic HAB algae according to Claim 5, wherein the mapping model establishment module specifically comprises: a parameter adjustment unit for adjusting the parameters of the particle swarm optimisation support vector machine based on the extracted spectral features; the parameters comprise: acceleration constant, maximum number of iterations and number of particle swarms; a mapping model establishment unit for determining the mapping model based on the particle swarm optimisation support vector machine after parameter adjustment, the mapping model uses the extracted spectral features as input and the identification result as output
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 |
|---|---|
| GB2604677A true GB2604677A (en) | 2022-09-14 |
Family
ID=76469324
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| GB2113428.3A Pending GB2604677A (en) | 2021-03-10 | 2021-09-21 | A method and system for online detection and identification of ichthyotoxic harmful algal bloom algae |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113030049A (en) |
| GB (1) | GB2604677A (en) |
Families Citing this family (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 |
| CN113916860B (en) * | 2021-11-02 | 2023-04-25 | 淮阴工学院 | Pesticide residue type identification method based on fluorescence spectrum |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040179196A1 (en) * | 2003-03-14 | 2004-09-16 | Hart Sean J. | Light emitting diode (LED) array for excitation emission matrix (EEM) fluorescence spectroscopy |
| CN102608085A (en) * | 2012-01-09 | 2012-07-25 | 暨南大学 | Method for detecting activity of alga hematoxin and application of method |
| 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 (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7964391B2 (en) * | 2006-10-10 | 2011-06-21 | United States Of America As Represented By The Secretary Of The Navy | Automated, field-portable system for conducting toxicity measurements in water, soils, and sediments |
| 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 |
| CN108732142B (en) * | 2018-02-09 | 2021-03-02 | 秦皇岛红燕光电科技有限公司 | Three-dimensional fluorescence spectrum-based seawater algae red tide and toxicity detection method |
| CN110658162B (en) * | 2018-06-29 | 2022-03-11 | 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 |
-
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 (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040179196A1 (en) * | 2003-03-14 | 2004-09-16 | Hart Sean J. | Light emitting diode (LED) array for excitation emission matrix (EEM) fluorescence spectroscopy |
| CN102608085A (en) * | 2012-01-09 | 2012-07-25 | 暨南大学 | Method for detecting activity of alga hematoxin and application of method |
| 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 (6)
| Title |
|---|
| CHEN XIAONA ET AL: "Discrimination of marine algal taxonomic groups based on fluorescence excitation emission matrix, parallel factor analysis and CHEMTAX", ACTA OCEANOLOGICA SINICA, THE CHINESE SOCIETY OF OCEANOGRAPHY, BEIJING, vol. 33, no. 12, 11 December 2014 (2014-12-11), pages 192 - 205, XP035411204, ISSN: 0253-505X, [retrieved on 20141211], DOI: 10.1007/S13131-014-0576-5 * |
| DATABASE MEDLINE [online] US NATIONAL LIBRARY OF MEDICINE (NLM), BETHESDA, MD, US; February 2013 (2013-02-01), HUAN QING-LIU ET AL: "[Identification of ichthyotoxic microalgae species and its hemolytic activity by three-dimensional fluorescence spectra].", XP002806246, Database accession no. NLM23697120 * |
| DATABASE MEDLINE [online] US NATIONAL LIBRARY OF MEDICINE (NLM), BETHESDA, MD, US; June 2012 (2012-06-01), DUAN YA-LI ET AL: "[Research on using 3-D fluorescence spectroscopy-wavelet transform-PSO for rapid discrimination of compositions of phytoplankton population].", XP002806245, Database accession no. NLM22870640 * |
| GUANG PU XUE YU GUANG PU FEN XI = GUANG PU FEB 2013, vol. 33, no. 2, February 2013 (2013-02-01), pages 399 - 403, ISSN: 1000-0593 * |
| GUANG PU XUE YU GUANG PU FEN XI = GUANG PU JUN 2012, vol. 32, no. 6, June 2012 (2012-06-01), pages 1562 - 1569, ISSN: 1000-0593 * |
| ZHANG Q Q ET AL: "Discrimination of phytoplankton classes using characteristic spectra of 3D fluorescence spectra", SPECTROCHIMICA ACTA PART A: MOLECULAR AND BIOMOLECULAR SPECTROSCOPY, ELSEVIER, AMSTERDAM, NL, vol. 63, no. 2, 1 February 2006 (2006-02-01), pages 361 - 369, XP028036235, ISSN: 1386-1425, [retrieved on 20060201], DOI: 10.1016/J.SAA.2005.05.041 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113030049A (en) | 2021-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| GB2604677A (en) | A method and system for online detection and identification of ichthyotoxic harmful algal bloom algae | |
| Dubelaar et al. | Flow cytometry as a tool for the study of phytoplankton | |
| Peniuk et al. | Identification and quantification of suspended algae and bacteria populations using flow cytometry: applications for algae biofuel and biochemical growth systems | |
| CN107101943B (en) | Device and method for detecting microalgae activity by optical flow control lens-free holographic imaging | |
| CN103454204B (en) | Messaging device, information processing method and program | |
| Houliez et al. | Spectral fluorometric characterization of Haptophyte dynamics using the FluoroProbe: an application in the eastern English Channel for monitoring Phaeocystis globosa | |
| CN102901693A (en) | Information processing apparatus, information processing method, program, and method of correcting intensity of fluorescence spectrum | |
| CN113658640B (en) | Fresh water ecological system health evaluation method | |
| JP2017051162A (en) | Method and device for estimating viable cell count on sample surface, and program incorporated into the device | |
| CN111289489A (en) | Raman spectrum-based microbial unicell growth detection method | |
| CN112414979B (en) | Fluorescence characteristic standard spectrum library for identifying microalgae producing paralytic shellfish poison as well as construction method and application thereof | |
| CN111912824B (en) | Application of three-dimensional fluorescence spectrometry in identification of microalgae producing paralytic shellfish poison | |
| CN108489952B (en) | Method for detecting water soluble organic matter by combining three-dimensional fluorescence spectrum with secondary differential | |
| CN102967557B (en) | Biological aerosol water-content determination based on near infrared spectroscopy and classification method thereof | |
| CN110702664A (en) | Method for rapidly identifying gram-negative and gram-positive bacteria | |
| NL2034211A (en) | Method and system for quantitatively identifying multi-pollution sources of mixed water body | |
| Yu et al. | Characterization of activated sludge in wastewater treatment processes using front-face excitation–emission matrix (FF-EEM) fluorescence spectroscopy | |
| CN104350378B (en) | Method and apparatus for the performance of measure spectrum system | |
| Hu et al. | Research on the discrimination methods of algae based on the fluorescence excitation spectra | |
| CN209525266U (en) | A kind of phase demodulating formula petroleum hydrocarbon class pollutant identification apparatus | |
| Dishon et al. | Image-based analysis and quantification of biofouling in cultures of the red alga Asparagopsis taxiformis | |
| JPS6361144A (en) | Method for measuring bacteria | |
| Hu et al. | Multiple excitation wavelength fluorescence emission spectra technique for discrimination of phytoplankton | |
| CN102495205B (en) | Quantum dot labeled antibody multicomponent non-competitive homogeneous immunoassay method for small-molecule organic matter | |
| CN109238993A (en) | The detection method that Determination of Chlorophyll In Seawater content influences underwater optical transmission characteristics |