CN109669403A - It is a kind of that danger agricultural input product intelligent monitor system is related to based on DBN-SOFTMAX - Google Patents
It is a kind of that danger agricultural input product intelligent monitor system is related to based on DBN-SOFTMAX Download PDFInfo
- Publication number
- CN109669403A CN109669403A CN201811217079.8A CN201811217079A CN109669403A CN 109669403 A CN109669403 A CN 109669403A CN 201811217079 A CN201811217079 A CN 201811217079A CN 109669403 A CN109669403 A CN 109669403A
- Authority
- CN
- China
- Prior art keywords
- softmax
- module
- dbn
- sensor
- lora
- 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.)
- Granted
Links
- QVFWZNCVPCJQOP-UHFFFAOYSA-N chloralodol Chemical compound CC(O)(C)CC(C)OC(O)C(Cl)(Cl)Cl QVFWZNCVPCJQOP-UHFFFAOYSA-N 0.000 claims abstract description 53
- 238000004891 communication Methods 0.000 claims description 27
- 238000012544 monitoring process Methods 0.000 abstract description 5
- 230000006870 function Effects 0.000 description 18
- 238000012549 training Methods 0.000 description 10
- 239000010410 layer Substances 0.000 description 7
- 238000000034 method Methods 0.000 description 5
- 238000000605 extraction Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 239000002689 soil Substances 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 239000003337 fertilizer Substances 0.000 description 2
- 239000000575 pesticide Substances 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 239000011229 interlayer Substances 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41875—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by quality surveillance of production
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32368—Quality control
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of to relate to danger agricultural input product intelligent monitor system based on DBN-SOFTMAX, including monitoring center and LORA gateway, Cloud Server is equipped with inside the monitoring center, smart machine module, DBN-SOFTMAX network and database, and the inside of DBN-SOFTMAX network is equipped with input prediction module and SOFTMAX classifier, LORA gateway side is connected with several LoRa nodes, the LORA gateway other side is connect by data reception service end with Cloud Server and database, the Cloud Server side is connect with input prediction module, input prediction module side is connect with smart machine module side, the database is connect with SOFTMAX classifier.The present invention can agricultural input product real-time monitoring to planting base.
Description
Technical field
It is specifically a kind of that danger is related to based on DBN-SOFTMAX the present invention relates to a kind of agricultural input product intelligent monitor system
Agricultural input product intelligent monitor system belongs to agricultural input product monitoring applied technical field.
Background technique
Agricultural product quality safety traceability system is to solve food-safety problem important means, and pesticide, chemical fertilizer etc. relate to danger agricultural
Input information is one of most concerned problem of consumer in information of tracing to the source;Agricultural is thrown currently, having many scholars both at home and abroad
Enter product Fast Detection Technique to be studied.
At present to agricultural input product monitoring mostly be postpartum period residue detection, can't real-time online to pesticide,
The inputs such as chemical fertilizer are detected;Traceability system can be by inquiring the countryside tax system of information tracing agricultural product production process of tracing to the source
Product service condition, but since information of tracing to the source is mainly manual entry, it not can guarantee the timely, accurate of information of tracing to the source.Therefore, for
The above problem propose it is a kind of based on DBN-SOFTMAX relate to danger agricultural input product intelligent monitor system.
Summary of the invention
The object of the invention is that solve the above-mentioned problems and provide it is a kind of based on DBN-SOFTMAX relating to danger agricultural
Input intelligent monitor system.
The present invention is achieved through the following technical solutions above-mentioned purpose, a kind of to relate to danger agricultural throwing based on DBN-SOFTMAX
Enter product intelligent monitor system, including monitoring center and LORA gateway, Cloud Server is equipped with inside the monitoring center, intelligence is set
Standby module, DBN-SOFTMAX network and database, and the inside of DBN-SOFTMAX network be equipped with input prediction module and
SOFTMAX, the prediction module include DBN and SOFTMAX, are classified after the probability value that the DBN is calculated by SOFTMAX,
LORA gateway side is connected with several LoRa nodes, and the LORA gateway other side passes through data reception service end and cloud
Server is connected with database, and the Cloud Server side is connect with input prediction module, the input prediction module one
Side is connect with smart machine module side, and the database is connect with SOFTMAX classifier;
The LoRa intra-node is chimeric to be equipped with sensor module, RS serial communication modular, processor module and LoRa
Wireless communication module, the sensor module side are connect by RS serial communication modular with processor module, the processor
Module side is connect with LoRa wireless communication module.
Preferably, it is connected between the LoRa node and LORA gateway by LoRa wireless communication module.
Preferably, the chimeric pH value sensor, EC sensor, temperature sensor, wet of being equipped with inside the sensor module
Spend sensor and single-chip microcontroller, the pH value sensor, EC sensor, temperature sensor, humidity sensor with single-chip microcontroller side
Connection.
Preferably, the SOFTMAX classifier is connected to input prediction module.
Preferably, it is connected between the sensor module and RS serial communication modular by single-chip microcontroller.
Preferably, the inside of the LoRa wireless communication module is equipped with antenna.
Preferably, the processor module is a kind of central processor core.
Preferably, the smart machine module is made of personal smart machine, such as: tablet computer, desktop computer etc..
The beneficial effects of the present invention are: structure of the invention design is rationally, realizes and danger agricultural input product is related to planting base
Real time on-line monitoring, when planting base apply input when, the kind of input can be predicted, thus with traceability system
Input kind, the administration time of base management person's typing are compared, once enterprise does not have timely, accurate or even wrong record
Enter information of tracing to the source, system can in real time, accurately capture relevant information, it is pre- to carry out safety from trend supervision department and manufacturing enterprise
It is alert, it is ensured that information of tracing to the source it is true, accurate;To establish consumer to the degree of belief for information of tracing to the source, accelerate building for traceability system
If.
Detailed description of the invention
Fig. 1 is overall structure of the present invention;
Fig. 2 is LoRa node structure schematic diagram of the present invention;
Fig. 3 is monitoring center working principle diagram of the present invention;
Fig. 4 is input prediction module of the present invention and SOFTMAX classifier working principle diagram.
Fig. 5 is softmax sorter model of the present invention;
In figure: 1, LoRa node, 101, sensor module, 101A, pH value sensor, 101B, EC sensor, 101C, temperature
Degree sensor, 101D, humidity sensor, 101E, single-chip microcontroller, 102, RS485 serial communication modular, 103, processor module,
104, LoRa wireless communication module, 104A, antenna, 2, LORA gateway, 3, data reception service end, 4, monitoring center, 5, cloud clothes
Business device, 6, DBN-SOFTMAX network, 7, database, 8, input prediction module, 9, SOFTMAX, 10, smart machine module.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Please refer to shown in Fig. 1-4, it is a kind of based on DBN-SOFTMAX relate to danger agricultural input product intelligent monitor system, including
Monitoring center 4 and LORA gateway 2, LORA gateway 2 are used to receive the wireless signal of the transmission of LoRa node 1, the monitoring center
4 inside are equipped with Cloud Server 5, smart machine module 10, DBN-SOFTMAX network 6 and database 7, and database 7 is used for LoRa
The record of 1 acquisition parameter of node, and the inside of DBN-SOFTMAX network 6 is equipped with input prediction module 8 and SOFTMAX classifies
Device 9,2 side of LORA gateway are connected with several LoRa nodes 1, and 2 other side of LORA gateway is taken by data receiver
Business end 3 is connect with Cloud Server 5 and database 7, and 5 side of Cloud Server is connect with input prediction module 8, the investment
8 side of product prediction module is connect with 10 side of smart machine module, and the database 7 is connect with SOFTMAX classifier 9,
SOFTMAX classifier 9 carries out the supervision that DBN-SOFTMAX network 6 is predicted;
It is fitted into inside the LoRa node 1 and sensor module 101, RS485 serial communication modular 102, processor is installed
Module 103 and LoRa wireless communication module 104,101 side of sensor module by RS485 serial communication modular 102 with
Processor module 103 connects, and 103 side of processor module is connect with LoRa wireless communication module 104, can be to the ginseng of soil
Number is acquired in real time.
It is connected between the LoRa node 1 and LORA gateway 2 by LoRa wireless communication module 104, LoRa wireless communication
The parameter that module 104 acquires LoRa node 1, with wireless signal transfer to LORA gateway 2;Inside the sensor module 101
It is chimeric that pH value sensor 101A, EC sensor 101B, temperature sensor 101C, humidity sensor 101D and single-chip microcontroller are installed
101E, pH value sensor 101A, EC sensor 101B, temperature sensor 101C, humidity sensor 101D are and single-chip microcontroller
The connection of the side 101E, can PH, EC to soil, temperature and humidity carry out the acquisitions of data;The SOFTMAX classifier 9 connects
It is connected to input prediction module 8, SOFTMAX classifier 9 is trained after DBN feature extraction, then carries out input prediction
The update and supervision of 8 data of module;Pass through single-chip microcontroller between the sensor module 101 and RS485 serial communication modular 102
101E connection, the parameter that single-chip microcontroller 101E can acquire sensor module 101 are handled;The LoRa wireless communication module
104 inside is equipped with antenna 104A, convenient for being wirelessly transferred between LoRa wireless communication module 104 and LORA gateway 2;Institute
State processor module 103 be a kind of central processor core, can to transmit into data handle;The smart machine module
10 are made of personal smart machine, such as: tablet computer, desktop computer etc., smart machine module 10 can carry out depositing for data
Storage, while the data of the data and prediction that are manually stored in are compared.
External connection power supply and control switch, LoRa node 1 are uniform when in use for the electric elements occurred in the application
Setting in crop planting base, in planting base apply input when, sensor module 101 at interval of 15 seconds carry out
Acquisition is primary, by pH value sensor 101A, EC sensor 101B, temperature sensor 101C in sensor module 101 and wet
The soil parameters that sensor 101D monitoring acquisition is applied before and after input is spent to go here and there after handling by single-chip microcontroller 101E by RS485
Port communications module 102 is transferred to processor module 103, is then arrived by LoRa wireless communication module 104 with wireless signal transmission
LORA gateway 2, the signal that LORA gateway 2 receives are transmitted in Cloud Server 5 and database 7 by data reception service end 3,
It is stored in database 7, Cloud Server 5 carries out rough set Data Reduction to data, and the data after reduction are imported into throwing
Enter and carry out classification prediction in product prediction module 8, predict the kind of input, then by the information predicted and application when
Between be transferred in smart machine module 10, the record for the information that trace to the source, staff is applied by the record of smart machine module 10
With situation, typing is traced to the source in information, and the information of staff's record is compared with the information predicted, once without it is timely,
Accurate or even wrong typing is traced to the source information, system can in real time, accurately capture relevant information, from trend supervision department and production
Enterprise carry out safe early warning, it is ensured that information of tracing to the source it is true, accurate;
Time every other week is recorded in the data in database 7 by the way that after DBN feature extraction, investment SOFTMAX divides
In class device 9, it is trained study, carries out the update of data in input prediction module 8, realizes supervision.
Feature extracting method based on DBN
Limited Boltzmann machine (RBM)
θ={ W_ij, a_i, b_j }, wherein W_ij indicates that the connection weight between visible element i and hidden unit j, m, n divide
Not Wei RBM hidden unit number and visible element number, wherein visible element and hidden unit are two-valued variable, i.e.,J, v_i ∈
{ 0,1 }, h_j ∈ { 0,1 }, a_i are the biasing of visible element i, and b_j is the biasing of visible element j, and T is sample size;H is hidden
Layer unit, v are visible layer unit.
RBM is a kind of undirected graph model, and the given training data of the value fitting by solving parameter θ completes feature extraction,
The task of RBM is optimal parameter θ to be found out, to complete feature extraction by the training data of fitting input.Parameter θ can be
Study maximizes log-likelihood function and obtains on training set, and formula is as follows
Wherein:
Solve optimized parameter θ*Key be obtain log (V(t)| θ) about Wij,ai,bjEtc. parameters partial derivative.Assuming that θ '
For some parameter value of θ, then gradient of the log-likelihood function about θ ' are as follows:
Due to sample size T it is known that then log-likelihood function is about connection weight wij, visible layer unit biasing aiWith it is hidden
The biasing b of layer unitjPartial derivative can by P (h | V(t), θ) and P (v, h | θ) it is calculated;P (h | V (t) θ) it is training sample V(t)Hidden layer probability distribution;P (v, h | θ) is the joint probability function for given state (v, h), expression formula are as follows:
Wherein E (v, h | θ) is the energy function of RBM, and Z (θ) is normalization factor.
CD algorithm
According to Long and Servedio (2010) [16] conclusion: normalization factor Z (θ) is difficult to resolve, therefore, joint
Probability function P (v, h | θ) it is also difficult to calculate.In order to solve this problem, it is calculated herein using based on the Fast Learning to sdpecific dispersion
Method (Contrastive Divergence, CD) training data, the specific steps are as follows:
According to Long and Servedio (2010) [16] conclusion: normalization factor Z (θ) is difficult to resolve, therefore, joint
Probability function P (v, h | θ) it is also difficult to calculate.In order to solve this problem, it is calculated herein using based on the Fast Learning to sdpecific dispersion
Method (Contrastive Divergence, CD) training data, the specific steps are as follows:
1, by formulaIt can obtain, and P (v, h | θ) distribution of joint probability limit
2, connectionless in layer since RBM network structure is that interlayer has a connection, and symmetrical configuration, it can obtain:
When the state of visible element is fixed, j-th of hidden unit activation probability is
P(hj=1 | v, θ)=σ (bj+∑iviWij) (4-1)
When the state of hidden unit is fixed, i-th of hidden unit activation probability is
P(vi=1 | h, θ)=σ (ai+∑jhjWij) (4-2)
3, two state of value that all Hidden units are calculated by formula (4-1), after the state of all Hidden units determines, root
I-th of visible element v is determined according to formula (4-2)iThe probability that value is 1, and then generate a reconstruct of visible layer
(reconstruction), the parameter more new formula in data training process is as follows:
ΔWij=∈ (< vihj>data-<vihj>recon)
Δai=∈ (< vi>data-<vi>recon)
Δbj=∈ (< hj>data-<hj>recon)
Wherein ∈ is learning rate,<>reconThe distribution defined for model after expression reconstruct.
Softmax classifier
In network before, finally obtained is x(i)Characteristic value, so, entire mistake different with supervised learning
Journey is there is no classifying, it is desirable that inputting a unmarked data and exporting its classification, institute in the prediction of input kind
Also to need to increase a softmax classifier, come to unsupervised learning to characteristic value classify.Softmax classifier
It is usually used in more classification problems, for tape label training set { (x(1),y(1)),(x(2),y(2)),…,(x(m),y(m)), wherein y(j)
∈ 1,2 ..., and k } represent training sample x(i)Belong to kth class, x is inputted for given test(i), it is calculated by disaggregated model
It is belonging respectively to the probability of each classification.So the vector for needing to export k dimension comes for the sample set with k type
Indicate probability vector, wherein j-th element represents the probability for belonging to j-th of classification and the value of all elements in probability vector
Summation is 1.Specifically, our hypothesis function hθ(x) form is as follows:
Wherein θ1,θ2,θ3,…,θkIt is the parameter of network model, usesIt indicates,This is main
It is to limit every probability value to be between 0 to 1, and the sum of every probability value is made to be 1.As shown in Figure 5;
According to Fig.5,;In formula (4-3), sample x(i)The output of categorized device belong to jth class probability be (1 { true }=
1,1 { false }=0):
The then corresponding likelihood function of all training samples are as follows:
Optimized parameter of parameter θ when making the likelihood function maximum as softmax classifier is taken, softmax is returned at this time
Return the cost function of model are as follows:
Cost function is minimized by gradient descent method, gradient function is as follows:
Softmax classifier has a uncommon feature: it has the parameter set of one " redundancy ".For the ease of illustrating this
One feature, it is assumed that we are from parameter vector θjIn subtracted vector μ, at this moment, each θjAll become θj- μ (j=1,2 ...,
k).It is assumed that function becomes following formula:
It can be seen that parameter θ in formula (4-9)j- μ and θjFunction can be made to obtain the same result, that is to say, that but θj
When for optimized parameter, θj- μ can also play same effect, and here it is there are the parameters of redundancy in softmax classifier
Disadvantage.Because the loss function of softmax classifier is not stringent non-convex, although there are minimum point, minimum
Be not on a point, but one " flat " spatially, i.e., this spatially all the points can make function obtain it is minimum
Value.For the convex function for making cost function become stringent, need to be added weight attenuation term, specific as follows:
It is obvious to a person skilled in the art that invention is not limited to the details of the above exemplary embodiments, Er Qie
In the case where without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Benefit requires rather than above description limits, it is intended that by fall in claim with all in the meaning and scope of important document
Variation is included within the present invention.Any reference signs in the claims should not be construed as limiting the involved claims.
In addition, it should be understood that although this specification is described in terms of embodiments, but not each embodiment is only wrapped
Containing an independent technical solution, this description of the specification is merely for the sake of clarity, and those skilled in the art should
It considers the specification as a whole, the technical solutions in the various embodiments may also be suitably combined, forms those skilled in the art
The other embodiments being understood that.
Claims (7)
1. a kind of relate to danger agricultural input product intelligent monitor system based on DBN-SOFTMAX, it is characterised in that: including monitoring center
(4) and LORA gateway (2), the monitoring center (4) are internal equipped with Cloud Server (5), smart machine module (10), DBN-
SOFTMAX network (6) and database (7), and the inside of DBN-SOFTMAX network (6) is equipped with input prediction module (8), institute
Stating prediction module (8) includes DBN and SOFTMAX, is classified after the probability value that the DBN is calculated by SOFTMAX, the LORA
Gateway (2) side is connected with several LoRa nodes (1), and LORA gateway (2) other side passes through data reception service end (3)
It is connect with Cloud Server (5) and database (7), Cloud Server (5) side is connect with input prediction module (8), described
Input prediction module (8) side is connect with smart machine module (10) side, the database (7) and SOFTMAX classifier
(9) it connects;
It is chimeric inside the LoRa node (1) that sensor module (101), RS485 serial communication modular (102), processing are installed
Device module (103) and LoRa wireless communication module (104), sensor module (101) side pass through RS485 serial communication mould
Block (102) is connect with processor module (103), and processor module (103) side and LoRa wireless communication module (104) are even
It connects.
2. it is according to claim 1 it is a kind of danger agricultural input product intelligent monitor system is related to based on DBN-SOFTMAX, it is special
Sign is: being connect between the LoRa node (1) and LORA gateway (2) by LoRa wireless communication module (104).
3. it is according to claim 1 it is a kind of danger agricultural input product intelligent monitor system is related to based on DBN-SOFTMAX, it is special
Sign is: chimeric inside the sensor module (101) to be equipped with pH value sensor (101A), EC sensor (101B), temperature
Sensor (101C), humidity sensor (101D) and single-chip microcontroller (101E), the pH value sensor (101A), EC sensor
(101B), temperature sensor (101C), humidity sensor (101D) are connect with the side single-chip microcontroller (101E).
4. it is according to claim 1 it is a kind of danger agricultural input product intelligent monitor system is related to based on DBN-SOFTMAX, it is special
Sign is: the SOFTMAX classifier (9) is connected to input prediction module (8).
5. it is according to claim 1 it is a kind of danger agricultural input product intelligent monitor system is related to based on DBN-SOFTMAX, it is special
Sign is: being connect between the sensor module (101) and RS485 serial communication modular (102) by single-chip microcontroller (101E).
6. it is according to claim 1 it is a kind of danger agricultural input product intelligent monitor system is related to based on DBN-SOFTMAX, it is special
Sign is: the inside of the LoRa wireless communication module (104) is equipped with antenna (104A).
7. it is according to claim 1 it is a kind of danger agricultural input product intelligent monitor system is related to based on DBN-SOFTMAX, it is special
Sign is: the processor module (103) is a kind of central processor core.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811217079.8A CN109669403B (en) | 2018-10-18 | 2018-10-18 | Dangerous agricultural input material intelligent monitoring system based on DBN-SOFTMAX |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811217079.8A CN109669403B (en) | 2018-10-18 | 2018-10-18 | Dangerous agricultural input material intelligent monitoring system based on DBN-SOFTMAX |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109669403A true CN109669403A (en) | 2019-04-23 |
CN109669403B CN109669403B (en) | 2020-05-19 |
Family
ID=66141671
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811217079.8A Active CN109669403B (en) | 2018-10-18 | 2018-10-18 | Dangerous agricultural input material intelligent monitoring system based on DBN-SOFTMAX |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109669403B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110234090A (en) * | 2019-07-23 | 2019-09-13 | 克拉玛依油城数据有限公司 | A kind of data management cloud platform based on LoRa |
CN111107530A (en) * | 2019-12-06 | 2020-05-05 | 深圳大学 | Agricultural disease and pest control system based on LoRa technology |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102193524A (en) * | 2010-03-02 | 2011-09-21 | 上海城市食品配送有限公司 | Safety guarantee control system for quality of vegetables in standard farm garden |
CN103310383A (en) * | 2013-06-25 | 2013-09-18 | 莘县农业局 | Whole-process monitoring and tracing system and method for quality safety of agricultural products |
CN203241793U (en) * | 2013-04-18 | 2013-10-16 | 何惠彬 | Agriculture production monitoring and management system based on internet of things |
CN106651391A (en) * | 2016-11-30 | 2017-05-10 | 深圳凯达通光电科技有限公司 | Agricultural product safety tracing system based on Internet of Things and cloud computing |
CN107491900A (en) * | 2017-09-13 | 2017-12-19 | 浙江农林大学 | A kind of agriculture Internet of Things Technical innova- tion system and its implementation |
CN108489927A (en) * | 2018-01-24 | 2018-09-04 | 仲恺农业工程学院 | Fish place of production source tracing method, electronic equipment, storage medium and device |
-
2018
- 2018-10-18 CN CN201811217079.8A patent/CN109669403B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102193524A (en) * | 2010-03-02 | 2011-09-21 | 上海城市食品配送有限公司 | Safety guarantee control system for quality of vegetables in standard farm garden |
CN203241793U (en) * | 2013-04-18 | 2013-10-16 | 何惠彬 | Agriculture production monitoring and management system based on internet of things |
CN103310383A (en) * | 2013-06-25 | 2013-09-18 | 莘县农业局 | Whole-process monitoring and tracing system and method for quality safety of agricultural products |
CN106651391A (en) * | 2016-11-30 | 2017-05-10 | 深圳凯达通光电科技有限公司 | Agricultural product safety tracing system based on Internet of Things and cloud computing |
CN107491900A (en) * | 2017-09-13 | 2017-12-19 | 浙江农林大学 | A kind of agriculture Internet of Things Technical innova- tion system and its implementation |
CN108489927A (en) * | 2018-01-24 | 2018-09-04 | 仲恺农业工程学院 | Fish place of production source tracing method, electronic equipment, storage medium and device |
Non-Patent Citations (2)
Title |
---|
刘现等: "人工智能在农业生产中的应用进展", 《福建农业学报》 * |
高瑞军等: "图像处理技术及其在食品安全溯源衡器中的应用研究", 《万方数据知识服务平台》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110234090A (en) * | 2019-07-23 | 2019-09-13 | 克拉玛依油城数据有限公司 | A kind of data management cloud platform based on LoRa |
CN111107530A (en) * | 2019-12-06 | 2020-05-05 | 深圳大学 | Agricultural disease and pest control system based on LoRa technology |
Also Published As
Publication number | Publication date |
---|---|
CN109669403B (en) | 2020-05-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Alazab et al. | A multidirectional LSTM model for predicting the stability of a smart grid | |
CN110414305A (en) | Artificial intelligence convolutional neural networks face identification system | |
CN110110707A (en) | Artificial intelligence CNN, LSTM neural network dynamic identifying system | |
CN109490814A (en) | Metering automation terminal fault diagnostic method based on deep learning and Support Vector data description | |
CN109816119A (en) | A kind of wireless sensor abnormal deviation data examination method based on unsupervised learning | |
CN110108914A (en) | One kind is opposed electricity-stealing intelligent decision making method, system, equipment and medium | |
CN111368926B (en) | Image screening method, device and computer readable storage medium | |
CN110309884A (en) | Electricity consumption data anomalous identification system based on ubiquitous electric power Internet of Things net system | |
CN109670584A (en) | A kind of fault diagnosis method and system based on big data | |
CN109669403A (en) | It is a kind of that danger agricultural input product intelligent monitor system is related to based on DBN-SOFTMAX | |
CN113807954A (en) | Wind control platform for live stock mortgage and risk control management method | |
CN116865994A (en) | Network data security prediction method based on big data | |
CN111143835A (en) | Non-invasive protection method for business logic of electric power metering system based on machine learning | |
Wang et al. | Research of the early warning analysis of crop diseases and insect pests | |
Alifah et al. | Smart monitoring of rice logistic employing internet of things network | |
Liu et al. | A system architecture for intelligent agriculture based on edge computing | |
CN204480252U (en) | A kind of drowned pattern intelligent inference system | |
CN113571159A (en) | Autism spectrum disorder child rehabilitation nursing system based on artificial intelligence | |
TWI524724B (en) | Telecommunication network alarm correlation analysis method | |
Yang et al. | The Development of an Intelligent Monitoring System for Agricultural Inputs Basing on DBN‐SOFTMAX | |
Gupta et al. | Ground water quality monitoring using wireless sensors and machine learning | |
CN206162667U (en) | Agricultural product integrated management system | |
CN111857015A (en) | Power transmission and transformation cloud intelligent controller | |
Yang et al. | Monitoring Technology of Abnormal Displacement of BeiDou Power Line Based on Artificial Neural Network | |
CN117110700B (en) | Method and system for detecting pulse power of radio frequency power supply |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |