CN107468210A - A kind of Artificial Olfactory detection method based on terminal detection+internet+big data cloud computing platform - Google Patents
A kind of Artificial Olfactory detection method based on terminal detection+internet+big data cloud computing platform Download PDFInfo
- Publication number
- CN107468210A CN107468210A CN201710513289.0A CN201710513289A CN107468210A CN 107468210 A CN107468210 A CN 107468210A CN 201710513289 A CN201710513289 A CN 201710513289A CN 107468210 A CN107468210 A CN 107468210A
- Authority
- CN
- China
- Prior art keywords
- data
- detection
- internet
- artificial olfactory
- cloud computing
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/40—Detecting, measuring or recording for evaluating the nervous system
- A61B5/4005—Detecting, measuring or recording for evaluating the nervous system for evaluating the sensory system
- A61B5/4011—Evaluating olfaction, i.e. sense of smell
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
Abstract
The invention discloses a kind of Artificial Olfactory detection method based on terminal detection+internet+big data cloud computing platform, data collecting system is realized using the three-tier architecture based on browser/Web server/database server, unified Artificial Olfactory endpoint detection methods are pressed in each alliance laboratory, and detection data are reported by four standard operations.The data obtained is uploaded to cloud server in real time, returned again to result to detection terminal after processing.Using ASP.NET technologies, detecting result initial data is obtained, food cpd and food classification information are supplemented；Then, the processing such as the description of sense of taste information, olfactory information description and Global Information classification are carried out, result is formed and records and be stored in detecting result database.Detection method not only ensure that the bionical accuracy of smell；Can also unified operation and data processing, reduce the detection application threshold of user, promote the scale application of detector.
Description
Technical field
The present invention relates to a kind of Artificial Olfactory detection method, refers in particular to one kind and is based on terminal detection+internet+big data cloud meter
Calculate the Artificial Olfactory detection method of platform.
Background technology
Smell is the sensation for being most difficult to simulate, be most difficult to quantization in human sensory, although Nobel's physiology in 2004 or medical science
Encourage winner's Richard Axel Heibergs (RichardAxel) and beautiful jade reach Barks (Linda B.Buck) early in the nineties in last century just
The general principle of human olfactory system is illustrated, but in terms of detecting instrument, current various bionic olfactory instruments not yet obtain prominent
Broken property progress.
The sense organ of the mankind is set up on the basis of smelling many times, trial, is dispersed in each laboratory at present
Electronic nose or electronic tongues data message are limited, can not really establish contacting between transducing signal and human sensory.Each grind
Study carefully all disunities such as the electronic nose of team, electronic tongues construction, detection method, data processing mode, mutual data can not
Compare property.Single experimental data is limited, and the number in each laboratory is seldom integrated using big data, the means of cloud computing
According to, cause existing Artificial Olfactory data can not with existing human sensory evaluate data carry out it is corresponding.
The content of the invention
The present invention is a kind of Artificial Olfactory detection method for being based on " terminal detection+internet+big data cloud computing platform ".
This method mainly includes three parts：1. alliance's laboratory Artificial Olfactory terminal detection based on internet；2. establish Artificial Olfactory
Large database concept；3. intelligent analysis system, rear two parts form data processing centre, are carried to gather and analyzing smell and Taste Signals
For support platform.
Alliance's laboratory Artificial Olfactory terminal detection based on internet refers to each alliance laboratory, using unification
Artificial Olfactory endpoint detection system, system are made up of hardware and software two parts, and hardware components are mainly by collection gaseous sample
Acquisition module, the sensing chip test module of photovoltaic reaction sensor, the signal measurement of conversion signal and control module, increase gas
The power plant module of pressure, the carrier gas module for preserving inert gas, and display composition；Software systems are by data collecting system, spy
Reference extraction system and PRS composition, it is responsible for carrying out feature extraction to the signal collected.
The Artificial Olfactory endpoint detection system presses four standard operations：Authority data interface, specification sampling, sample preparation, detection
Method, cannonical format data upload, cannonical format Statistical Analysis Report, fully ensure the uniformity of data, integrality, accurate
Property, safety and reliability.
The equal configuration high-speed data transmission module of described Artificial Olfactory endpoint detection system, the data obtained is uploaded in real time
Cloud server, the testing result after analysis is fed back into detection terminal again after processing.
The data processing centre, is the data processing centre based on high in the clouds, including Database, detection initial data
Pretreatment and high in the clouds data processing.
The Database：Smell description and threshold data storehouse and complicated general food including single common compounds
Compositional data storehouse and olfactometry database.Using the data fusion and processing mould of data acquisition-information supplement-information processing
Type, realize and quick online acquisition, fusion are carried out to olfactometry result data and is described with reference to the smell of general food compound
Be associated with threshold data storehouse, realize accurate description and sort out, and realize the dynamic addition of olfactometry result database with
Real-time update.
The detection initial data pretreatment, first by ASP.NET technologies, obtains detecting result initial data, to food
Product compound and food classification information are supplemented；Then, the processing such as olfactory information description and Global Information classification is carried out, is formed
As a result record and be stored in general food olfactometry database.
The high in the clouds data processing：Establish a kind of mass small documents processing model (Cloud based on cloud computing environment
Computing-Massive Small Files Process Model, C-MSFPM), to the data and basic database surveyed
In preliminary classification carried out with nearby principle and weights similarity, further pass through nearest neighbor algorithm (KNN algorithms) and SVMs
Algorithm (SVM algorithm) is classified, and is reached precise quantification and described to survey the target of the smell of food and compound.
Beneficial effects of the present invention：
The database built provides science data to be engaged in food smell and sense of taste researcher.Next terminal detection+mutually
Networking+high in the clouds detection pattern can not only study smell under big data background, ensure the bionical accuracy of smell；It can also unify
Operation and data processing, the detection application threshold of user is reduced, promote the scale application of detector.
Brief description of the drawings
Fig. 1 present invention artificial scent data collection, analysis and the schematic diagram of database.
Fig. 2 multilevel policy decision pattern nerve network analysis systems.
Embodiment
The present invention propose it is a kind of based on " the Artificial Olfactory detection method of detection+internet+big data cloud computing platform,
The Artificial Olfactory data acquisition of structure, analysis hierarchical logic signal as shown in figure 1, the data acquisition use based on browser/
The three-tier architecture of Web server/database server, each alliance laboratory use unified Artificial Olfactory endpoint detection system,
By four standard operations：Authority data interface, specification sampling, sample preparation, detection method, cannonical format data upload, cannonical format system
Count analysis report.Detection data are reported, fully the uniformity of guarantee data, integrality, accuracy, safety and reliability.Through
High speed data transfer module in Artificial Olfactory endpoint detection system, the data obtained is uploaded to cloud server in real time, handled
Result is returned again to detection terminal afterwards.Using ASP.NET technologies, obtain detecting result initial data, to food cpd and
Food classification information is supplemented；Then, the processing such as the description of sense of taste information, olfactory information description and Global Information classification are carried out,
Result is formed to record and be stored in detecting result database.
3 basic database structures：The mankind are not inherent for the discriminating power of smell, but pass through the day after tomorrow repeatedly
Study, accumulation are formed.In order to improve the accuracy in detection of bionic olfactory and sense of taste instrument, it is necessary to there is sufficiently large knowledge base to provide
With reference to and support.Therefore, structure is based on more than 10 alliance laboratories by the present invention, passes through alliance laboratory while standard operation
Build 3 smell relevant rudimentary databases, including the smell description of common compounds and threshold data storehouse, the composition of general food
Database and Artificial Olfactory Test database.The data proposed from single food common compounds system to complicated food system obtain
Take-data fusion of information supplement-information processing and processing model, realize smell and sense of taste testing result data are carried out it is fast
Fast online acquisition, fusion and closed with reference to general food compound smell description and threshold data storehouse and sense of taste database
Connection, realize accurate description and sort out, and realize dynamic addition and the real-time update of smell sense of taste testing result database.
Beyond the clouds, in order to effectively utilize distributed algorithm in cloud computing theoretical, by bayesian theory and neural network algorithm
Smell and sense of taste detection data are organically blended.By different physical significances, different dimensions, the bionic olfactory of magnitude and sense of taste sensing
Information projects to higher dimensional space；Then, data rotation and compression are carried out in higher dimensional space, then is closed with basic database result
The analysis of connection property, takes out virtual smell and sense of taste variable, these dummy variables both filled with corresponding human sensory's information respectively
Split-phase is closed, and the information embodied again between different sensors is intersected.Finally, a kind of mass small documents based on cloud computing environment are established
Model (Cloud computing-Massive Small Files Process Model, C-MSFPM) is handled, to what is surveyed
Data pass through multilevel policy decision as shown in Figure 2 with carrying out preliminary classification in basic database with nearby principle and weights similarity
Pattern neutral net means build intellectualized detection method, return again to result to detection terminal after processing.
Those listed above is a series of to be described in detail only for feasibility embodiment of the invention specifically
Bright, they simultaneously are not used to limit the scope of the invention, all equivalent implementations made without departing from skill spirit of the present invention
Or change should be included in the scope of the protection.
Claims (9)
- A kind of 1. Artificial Olfactory detection method based on terminal detection+internet+big data cloud computing platform, it is characterised in that Including：Alliance's laboratory Artificial Olfactory terminal based on internet detects, establishes Artificial Olfactory large database concept in cloud server end And intelligent data analysis；Alliance's laboratory Artificial Olfactory terminal detection based on internet：Manually smelt using unified in some alliance laboratories Endpoint detection system is felt, by four standard operations；Artificial Olfactory large database concept is established at cloud server end：Using the data fusion of data acquisition-information supplement-information processing With handling model, realize and quick online acquisition, fusion are carried out to olfactometry result data and with reference to general food compound Smell description and threshold data storehouse are associated, and are realized accurate description and are sorted out, and realize the dynamic of olfactometry result database State is added and real-time update；Cloud server end data intellectual analysis：Including raw sensor data pretreatment and high in the clouds data processing；Alliance's laboratory Artificial Olfactory terminal configuration high-speed data transmission module based on internet, during by testing number factually Cloud server is uploaded to, returns again to result to detection terminal after cloud server processing.
- A kind of 2. Artificial Olfactory inspection based on terminal detection+internet+big data cloud computing platform according to claim 1 Survey method, it is characterised in that four standard operation includes：Authority data interface, specification sampling, sample preparation, detection method, specification Formatted data uploads, cannonical format Statistical Analysis Report.
- A kind of 3. Artificial Olfactory inspection based on terminal detection+internet+big data cloud computing platform according to claim 1 Survey method, it is characterised in that the Artificial Olfactory large database concept includes：The smell description of single common compounds and threshold data Storehouse, the compositional data storehouse of complicated general food, olfactometry database.
- A kind of 4. Artificial Olfactory inspection based on terminal detection+internet+big data cloud computing platform according to claim 1 Survey method, it is characterised in that the raw sensor data pretreatment：Detecting result initial data is obtained first, to food chemical combination Thing and food classification information are supplemented；Then, olfactory information description and Global Information classification processing are carried out, forms result record And it is stored in general food olfactometry database.
- A kind of 5. Artificial Olfactory inspection based on terminal detection+internet+big data cloud computing platform according to claim 1 Survey method, it is characterised in that the high in the clouds data processing：Mass small documents processing MODEL C of the foundation based on cloud computing environment- MSFPM, to carrying out preliminary classification in the data and basic database surveyed with nearby principle and weights similarity, further divide Class, reach precise quantification and describe to survey the target of the smell of food and compound.
- A kind of 6. Artificial Olfactory inspection based on terminal detection+internet+big data cloud computing platform according to claim 1 Survey method, it is characterised in that the Artificial Olfactory endpoint detection system is made up of hardware and software two parts, and hardware components are main By sample collection module, sensing chip test module, signal measurement and control module, power plant module, carrier gas module, and display Device forms；Software systems are made up of data collecting system, feature signal extraction system and PRS, are responsible for gathering The signal arrived carries out feature extraction.
- A kind of 7. Artificial Olfactory inspection based on terminal detection+internet+big data cloud computing platform according to claim 1 Survey method, it is characterised in that some alliance laboratories are more than 10.
- A kind of 8. Artificial Olfactory inspection based on terminal detection+internet+big data cloud computing platform according to claim 4 Survey method, it is characterised in that the raw sensor data pretreatment is realized by ASP.NET technologies.
- A kind of 9. Artificial Olfactory inspection based on terminal detection+internet+big data cloud computing platform according to claim 5 Survey method, it is characterised in that the classification is realized by improving KNN algorithms and SVM algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710513289.0A CN107468210A (en) | 2017-06-29 | 2017-06-29 | A kind of Artificial Olfactory detection method based on terminal detection+internet+big data cloud computing platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710513289.0A CN107468210A (en) | 2017-06-29 | 2017-06-29 | A kind of Artificial Olfactory detection method based on terminal detection+internet+big data cloud computing platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107468210A true CN107468210A (en) | 2017-12-15 |
Family
ID=60596125
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710513289.0A Pending CN107468210A (en) | 2017-06-29 | 2017-06-29 | A kind of Artificial Olfactory detection method based on terminal detection+internet+big data cloud computing platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107468210A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110057975A (en) * | 2019-04-22 | 2019-07-26 | 广东工业大学 | A kind of olfactory descriptor acquiring method, system and relevant apparatus |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1453584A (en) * | 2003-06-02 | 2003-11-05 | 江苏大学 | Fast non-destructive detection method and device of food smell based on gas sensor array technology |
| WO2017076882A1 (en) * | 2015-11-02 | 2017-05-11 | Alpha M.O.S | Gas sensor controller |
-
2017
- 2017-06-29 CN CN201710513289.0A patent/CN107468210A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1453584A (en) * | 2003-06-02 | 2003-11-05 | 江苏大学 | Fast non-destructive detection method and device of food smell based on gas sensor array technology |
| WO2017076882A1 (en) * | 2015-11-02 | 2017-05-11 | Alpha M.O.S | Gas sensor controller |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110057975A (en) * | 2019-04-22 | 2019-07-26 | 广东工业大学 | A kind of olfactory descriptor acquiring method, system and relevant apparatus |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xie et al. | A deep-learning-based real-time detector for grape leaf diseases using improved convolutional neural networks | |
| Yang et al. | Local-scale partitioning of functional and phylogenetic beta diversity in a tropical tree assemblage | |
| Ayturan et al. | Air pollution modelling with deep learning: a review | |
| Franklin et al. | Big data for forecasting the impacts of global change on plant communities | |
| Gong et al. | Multi-objective parameter optimization of common land model using adaptive surrogate modeling | |
| Xu et al. | Some insights on grassland health assessment based on remote sensing | |
| Asefa et al. | Environmental filtering structures tree functional traits combination and lineages across space in tropical tree assemblages | |
| WO2018192418A1 (en) | Pesticide residue detection data platform based on high resolution mass spectrum, internet and data science, and method for automatically generating detection report | |
| Van Den Bergh et al. | HiTempo: a platform for time-series analysis of remote-sensing satellite data in a high-performance computing environment | |
| Karimi et al. | Generalizability of gene expression programming and random forest methodologies in estimating cropland and grassland leaf area index | |
| Zhu et al. | Mapping rice paddy distribution using remote sensing by coupling deep learning with phenological characteristics | |
| Su et al. | Prediction of future natural suitable areas for rice under representative concentration pathways (RCPs) | |
| Abbasi et al. | Modelling methane and nitrous oxide emissions from rice paddy wetlands in India using artificial neural networks (ANNs) | |
| Zhao et al. | Predictions of the potential geographical distribution and quality of a Gynostemma pentaphyllum base on the fuzzy matter element model in China | |
| Umaña et al. | Relating leaf traits to seedling performance in a tropical forest: building a hierarchical functional framework | |
| Gerges et al. | A novel Bayesian deep learning approach to the downscaling of wind speed with uncertainty quantification | |
| CN107468210A (en) | A kind of Artificial Olfactory detection method based on terminal detection+internet+big data cloud computing platform | |
| Zhang et al. | Climate, life form and family jointly control variation of leaf traits | |
| CN107480630A (en) | A kind of method that Ecological Function zoning is carried out using remote sensing technology | |
| Xiao et al. | A combined raindrop aggregate destruction test-settling tube (RADT-ST) approach to identify the settling velocity of sediment | |
| Viciani et al. | The Quercus petraea-dominated communities in Italy: floristic, coenological and chorological diversity in an European perspective | |
| CN102902739A (en) | Workflow flow construction method for uncertain data sources under cloud computing environment | |
| Gunarathna et al. | A Functional analysis of pedotransfer functions developed for Sri Lankan soils: applicability for process-based crop models | |
| Vehmas et al. | Airborne laser scanning for the site type identification of mature boreal forest stands | |
| Qian et al. | Soil Quality Evaluation Based on a Minimum Data Set (MDS)—A Case Study of Tieling County, Northeast China |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20171215 |
|
| WD01 | Invention patent application deemed withdrawn after publication |