CN109766941B - Farmland data fusion processing method based on multiple sensors - Google Patents
Farmland data fusion processing method based on multiple sensors Download PDFInfo
- Publication number
- CN109766941B CN109766941B CN201910001608.9A CN201910001608A CN109766941B CN 109766941 B CN109766941 B CN 109766941B CN 201910001608 A CN201910001608 A CN 201910001608A CN 109766941 B CN109766941 B CN 109766941B
- Authority
- CN
- China
- Prior art keywords
- value
- sensors
- acquisition terminal
- data
- farmland
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
Abstract
The invention aims to provide a farmland data fusion processing method based on multiple sensors, which is used for comparing actual measurement values X of n acquisition terminal sensors and acquiring a maximum value XmaxAnd minimum value XminAdding and dividing by two to obtain a median value YkRespectively connecting n values acquired by the acquisition terminal sensor with YkComparing to obtain the average value of the actual measurement values of the two sensors, classifying the data after the last classification, determining the next new median value, and comparing YkAnd Yk+1According to YkObtaining variance values of n sensors observing the parameter to be measured
Description
Technical Field
The invention belongs to the technical field of data processing, and relates to a farmland data fusion processing method based on multiple sensors.
Background
The data fusion processing technology is a novel technology combining multiple disciplines, is mainly used for comprehensively and uniformly processing a large amount of data, can process various data, has strong flexibility, and can analyze the data by utilizing multiple discipline methods to generate multiple different results. Because data fusion is an emerging technology, the definition of the data fusion is always quite fuzzy, and the data fusion is preliminarily described as an information processing technology capable of simplifying, calibrating and comprehensively analyzing data obtained according to a certain rule under a specific rule according to the application characteristics, so that the redundancy and the accuracy of the obtained processing result are far superior to those of the initial data. The multi-sensor data fusion is a process of processing information acquired by a sensor by using a data fusion technology as the name suggests, and the multi-sensor data fusion is gradually mature along with the development of scientific technology and the rise of information technology. People summarize the working principle of the multi-sensor data fusion technology as follows: the method comprises the steps of measuring the same measured parameter by using a plurality of sensors at different time, and then comprehensively processing the measured parameter under a certain rule by means of a mathematical model or an algorithm and the like, so that the measured parameter can be more scientifically and visually explained, and the method is convenient for decision analysis to be taken next. The multi-sensor data fusion technology can be vividly compared with the process of sensing external information by human body, the human body can sense the external information by the sensors such as hands, eyes, nose and the like, and then the information is processed uniformly by the brain to obtain an accurate conclusion, and how to apply the multi-sensor data fusion technology to a farmland information monitoring system is introduced below. Because the farmland area is great, need to arrange a plurality of sensor nodes in same farmland and come even collection environmental information, if will gather simultaneously and will produce a large amount of data to many mu farmland. In addition, because the geographical environment of most farmlands is remote and the natural environment is complex, the measurement accuracy of the sensor is easily interfered, and if a large amount of information is transmitted at the same time, the generated energy consumption also has great influence on the acquisition accuracy of the sensor. In order to meet the requirement of a digital farmland information acquisition system on acquisition precision, a data-level fusion mode which is characterized by processing information non-loss and high performance is designed and adopted to fuse the environmental data of the farmland. The specific idea is that after the sensor node collects farmland environment data, the data are transmitted to a nearby LoRa gateway, then the data can be immediately and effectively fused in a microcontroller of the LoRa gateway, and the fused original data are not processed at all, so that the influence caused by interference factors can be effectively eliminated, and a very accurate and effective fusion result is obtained.
Disclosure of Invention
The invention aims to provide a farmland data fusion processing method based on multiple sensors, and the farmland data fusion processing method has the beneficial effect of improving the farmland information fusion precision.
The technical scheme adopted by the invention is carried out according to the following steps:
(1) comparing the actual measured values X of the n acquisition terminal sensors, and acquiring the maximum value XmaxAnd minimum value XminAdding and dividing by two to obtain a median value Yk：
In the above formula, k is the number of times of calculation, and k is a positive integer from 1.
(2) Respectively connecting the n values acquired by the acquisition terminal sensor with YkBy comparison, greater than YkIs classified into HkIs less than YkIs classified into H-k：
In the above formula, k is the number of times of calculation, and k is a positive integer from 1.
(3) And (3) calculating the average value of the actual measurement values of the two acquisition terminal sensors:
in the above formula, k is the number of times of calculation, and k is a positive integer from 1. XiFor collecting the ith measured value, N, of the terminal sensoriThe weight value of each acquisition terminal sensor is 1.
(4) Continuously classifying the data after the last classification, and determining the next new median value:
(5) comparison of YkAnd Yk+1If Y is presentk＝Yk+1Stopping the calculation if Yk≠Yk+1Continuing to step (4) until Yk＝Yk+1Y thus obtainedkThe value of (b) is the actual measurement value of the acquisition terminal sensor which is close to the true value wirelessly.
(6) According to YkObtaining variance values of n sensors observing the parameter to be measured
i＝1，2，3，…n
Total mean square error sigma2Weighting factor Wi。
Detailed Description
The present invention will be described in detail with reference to the following embodiments.
The farmland data fusion processing method based on the multiple sensors adopts a multiple sensor self-adaptive weighting fusion algorithm, and the specific implementation process is as follows:
(1) comparing the actual measured values X of the n acquisition terminal sensors, and acquiring the maximum value XmaxAnd the minimum value xminAdding and dividing by two to obtain a median value Yk：
In the above formula, k is the number of times of calculation, and k is a positive integer from 1.
(2) Respectively connecting the n values acquired by the acquisition terminal sensor with YkBy comparison, greater than YkIs classified into HkIs less than YkIs classified into H-k：
In the above formula, k is the number of times of calculation, and k is a positive integer from 1.
(3) And (3) calculating the average value of the actual measurement values of the two acquisition terminal sensors:
in the above formula, k is the number of times of calculation, and k is a positive integer from 1. XiFor collecting the ith measured value, N, of the terminal sensoriThe weight value of each acquisition terminal sensor is 1.
(4) Continuously classifying the data after the last classification, and determining the next new median value:
(5) comparison of YkAnd Yk+1If Y is presentk＝Yk+1Stopping the calculation if Yk≠Yk+1Then proceed toStep (4) until Yk＝Yk+1Y thus obtainedkThe value of (b) is the actual measurement value of the acquisition terminal sensor which is close to the true value wirelessly.
(6) According to YkObtaining variance values of n sensors observing the parameter to be measured
i＝1，2，3，…n
Total mean square error sigma2Weighting factor Wi。
Data fusion test result analysis
For the feasibility of inspection algorithm, the information monitoring data in the farmland has been carried out the experiment and has been compared, the experiment place is in certain green house in zibo city Boshan district, during the experiment every a section distance in the farmland is on average to dispose a sensor node, evenly disposes 5 sensor nodes in the farmland, every group node all can adopt the air temperature and humidity, soil temperature and humidity and the illumination intensity in collection farmland, from morning 9: 00 starts and data is collected every 30 minutes until 14: 00, 10 times of sampling data are collected. In the process of collecting certain data by each collecting node, when the difference value between the maximum value and the minimum value reaches 10 units, the type of the data of the collecting node of the sensor is interfered by noise, and the collected actual detailed data is shown in table 1.
TABLE 1 sensor data acquisition
The result of the fusion of the actual test value obtained by each sensor for measuring the same kind of parameters and the data shows that the fusion result is good and can meet the requirements, so the improved data fusion algorithm is feasible.
The invention carries out overall analysis aiming at the key technology of farmland information acquisition, provides the use significance of the multi-sensor data fusion processing technology based on the problems of large information amount, complex environment, weak signals and the like in the farmland information acquisition process, and describes three fusion categories in detail. The accuracy of the algorithm is confirmed by averagely deploying 5 sensor nodes in the farmland, the environment information of the farmland is respectively collected, the collected data are subjected to fusion processing and then are compared with the initial value, and the comparison result shows that the improved self-adaptive fusion algorithm can achieve a better fusion effect and meet the requirement of digital farmland information monitoring.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not intended to limit the present invention in any way, and all simple modifications, equivalent variations and modifications made to the above embodiments according to the technical spirit of the present invention are within the scope of the present invention.
Claims (1)
1. A farmland data fusion processing method based on multiple sensors is characterized by comprising the following steps:
(1) comparing the actual measured values X of the n acquisition terminal sensors to obtainMaximum value x collectedmaxAnd the minimum value xminAdding and dividing by two to obtain a median value Yk：
In the above formula, k is the number of times of calculation, and k is a positive integer from 1;
(2) respectively connecting the n values acquired by the acquisition terminal sensor with YkBy comparison, greater than YkIs classified into HkIs less than YkIs classified into H-k：
In the above formula, k is the number of times of calculation, and k is a positive integer from 1;
(3) and (3) calculating the average value of the actual measurement values of the two acquisition terminal sensors:
in the above formula, k is the number of times of calculation, starting from 1, k is a positive integer, and XiFor collecting the ith measured value, N, of the terminal sensoriThe weight value of each acquisition terminal sensor is 1;
(4) continuously classifying the data after the last classification, and determining the next new median value:
(5) comparison of YkAnd Yk+1If Y is presentk＝Yk+1Stopping the calculation if Yk≠Yk+1Continuing to step (4) until Yk＝Yk+1Y thus obtainedkThe value of (A) is the actual measurement value of the acquisition terminal sensor which infinitely approaches the true value;
(6) according to YkObtaining variance values of n sensors observing the parameter to be measured
i＝1，2，3，…n
Total mean square error sigma2Weighting factor Wi。
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910001608.9A CN109766941B (en) | 2019-01-02 | 2019-01-02 | Farmland data fusion processing method based on multiple sensors |
| PCT/CN2019/000263 WO2020140189A1 (en) | 2019-01-02 | 2019-12-30 | Farmland data fusion processing method employing multiple sensors |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910001608.9A CN109766941B (en) | 2019-01-02 | 2019-01-02 | Farmland data fusion processing method based on multiple sensors |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109766941A CN109766941A (en) | 2019-05-17 |
| CN109766941B true CN109766941B (en) | 2021-09-21 |
Family
ID=66453569
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910001608.9A Active CN109766941B (en) | 2019-01-02 | 2019-01-02 | Farmland data fusion processing method based on multiple sensors |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109766941B (en) |
| WO (1) | WO2020140189A1 (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109766941B (en) * | 2019-01-02 | 2021-09-21 | 青岛理工大学 | Farmland data fusion processing method based on multiple sensors |
| CN110298409A (en) * | 2019-07-03 | 2019-10-01 | 广东电网有限责任公司 | Multi-source data fusion method towards electric power wearable device |
| CN111766370A (en) * | 2020-07-08 | 2020-10-13 | 王善举 | Real-time detection system for total nitrogen content of soil |
| CN112268719A (en) * | 2020-09-29 | 2021-01-26 | 河南科技大学 | Remote fault diagnosis method for header of combine harvester |
| CN113873459B (en) * | 2021-07-16 | 2024-03-12 | 合肥工业大学 | Multi-sensor optimized deployment method for soil component collection |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103822662A (en) * | 2014-02-10 | 2014-05-28 | 北京林业大学 | Temperature-humidity illumination intelligent sensor for agriculture and forestry |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6909997B2 (en) * | 2002-03-26 | 2005-06-21 | Lockheed Martin Corporation | Method and system for data fusion using spatial and temporal diversity between sensors |
| CN109766941B (en) * | 2019-01-02 | 2021-09-21 | 青岛理工大学 | Farmland data fusion processing method based on multiple sensors |
-
2019
- 2019-01-02 CN CN201910001608.9A patent/CN109766941B/en active Active
- 2019-12-30 WO PCT/CN2019/000263 patent/WO2020140189A1/en active Application Filing
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103822662A (en) * | 2014-02-10 | 2014-05-28 | 北京林业大学 | Temperature-humidity illumination intelligent sensor for agriculture and forestry |
Non-Patent Citations (3)
| Title |
|---|
| 基于无线传感器网络的农田环境监测系统研究与实现;孙玉文;《中国博士学位论文全文数据库》;20131231;87-91 * |
| 基于自适应加权与LZW的WSNs层次式数据融合算法;张志伟 等;《传感技术学报》;20110831;第24卷(第08期);1193-1196 * |
| 基于自适应加权数据融合算法的数据处理;唐亚鹏;《计算机技术与发展》;20150430;第25卷(第4期);53-55 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109766941A (en) | 2019-05-17 |
| WO2020140189A1 (en) | 2020-07-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109766941B (en) | Farmland data fusion processing method based on multiple sensors | |
| CN106934126B (en) | Mechanical part health index construction method based on recurrent neural network fusion | |
| CN110991786B (en) | 10kV static load model parameter identification method based on similar daily load curve | |
| CN112147573A (en) | Passive positioning method based on amplitude and phase information of CSI (channel State information) | |
| CN110087207B (en) | Method for reconstructing missing data of wireless sensor network | |
| CN109255100B (en) | Urban rainfall inversion method based on microwave attenuation characteristic response fingerprint identification | |
| Sugiarto et al. | Data classification for air quality on wireless sensor network monitoring system using decision tree algorithm | |
| CN108090515B (en) | Data fusion-based environment grade evaluation method | |
| CN109640254B (en) | Weighted centroid positioning algorithm based on improved Gaussian filtering | |
| CN106908668B (en) | Processing method and system for actually measured ground synthetic electric field data | |
| CN107257351A (en) | One kind is based on grey LOF Traffic anomaly detections system and its detection method | |
| CN108648764A (en) | Rainfall measurement system and its measurement method based on the identification of rainwater knock | |
| CN109063885A (en) | A kind of substation's exception metric data prediction technique | |
| CN104586402B (en) | A kind of feature extracting method of physical activity | |
| CN110260774A (en) | A kind of inspection of GNSS deformation information and method for early warning based on Pettitt algorithm | |
| CN116665001A (en) | Intelligent park multisource data dynamic monitoring and real-time analysis system and method | |
| CN111465093A (en) | Fingerprint positioning method and device, electronic equipment and computer storage medium | |
| CN114330486A (en) | Power system bad data identification method based on improved Wasserstein GAN | |
| CN113449254A (en) | Method for analyzing monitoring stability of arbitrary net type deformation and method for determining position of monitoring point | |
| Li et al. | Two indoor location algorithms based on sparse fingerprint library | |
| CN117034189A (en) | Multi-source internet of things data fusion method | |
| CN116739619A (en) | Energy power carbon emission monitoring analysis modeling method and device | |
| CN106618499A (en) | Falling detection equipment, falling detection method and device | |
| CN111444946B (en) | Non-household series investigation method and system based on generalized Dice coefficient and local outlier factor | |
| CN112261718B (en) | Indoor positioning method |
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 |