CN113672608A - Internet of things perception data reduction system and method based on self-adaptive reduction threshold - Google Patents
Internet of things perception data reduction system and method based on self-adaptive reduction threshold Download PDFInfo
- Publication number
- CN113672608A CN113672608A CN202110978851.3A CN202110978851A CN113672608A CN 113672608 A CN113672608 A CN 113672608A CN 202110978851 A CN202110978851 A CN 202110978851A CN 113672608 A CN113672608 A CN 113672608A
- Authority
- CN
- China
- Prior art keywords
- data
- reduction
- threshold value
- adaptive
- internet
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/23—Updating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/31—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y20/00—Information sensed or collected by the things
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a system and a method for reducing perception data of the Internet of things based on a self-adaptive reduction threshold value, wherein the system comprises a data loading module, a self-adaptive data reduction module and a data reconstruction module; the method for reducing data by adopting the system is based on real-time internet of things perception data, the data change trend is modeled by concept drift detection at a sensor end, the reduction threshold value of a Kalman filter is determined by drift detection dynamic self-adaption, data is reduced based on the difference between data estimation and an actual value of the Kalman filter, the reduced data and the modeled data trend are uploaded to an edge end, the data is reconstructed at the edge end according to the reduced data and the data trend, the purposes of reducing data acquisition and transmission on the premise of ensuring data accuracy and data quality are finally achieved, and meanwhile, the energy consumption of sensor nodes and the data storage at the edge end can be remarkably reduced.
Description
Technical Field
The invention relates to the technical field of network data communication, in particular to a system and a method for internet of things perception data reduction based on a self-adaptive reduction threshold.
Background
With the development of the internet of things technology, a large amount of sensing data is collected and transmitted in real time by mobile equipment, sensors and other internet of things equipment. Edge computing emphasizes computation and storage on the edge of the network, and energy of sensors is greatly consumed by sensor equipment close to the edge end to frequently acquire and upload data. Where sensor communication consumes the most energy, transmitting 1 bit of data typically consumes 1000 times more energy than one 32-bit computing device can calculate at a time. The energy of the sensor node under the edge calculation only depends on a battery, and once deployed, the sensor node cannot be charged normally. In the face of constraints such as energy consumption, transmission capacity and storage, how to reduce data communication between the sensor end and the edge end on the premise of ensuring the accuracy of edge calculation data is a key to the data reduction problem under edge calculation.
The data reduction method based on the Kalman filter mainly comprises the step of establishing a prediction model based on a time sequence, so that the sensor numerical value can be predicted within a data reduction error threshold value. The model is simultaneously positioned at the sensor node and the edge end, data does not need to be transmitted when the sensor node judges that the predicted value meets the required precision, and otherwise, sensing data are uploaded to the edge end and the model is updated. When the error threshold is small, a large amount of data is regarded as abnormal data and transmitted to the edge end, at the moment, the data reduction rate is low, and the data reconstruction accuracy rate is high. In the operation of a Kalman filter model, the larger the error threshold value is, the higher the data reduction rate is, the lower the accuracy rate after data reconstruction is, and the Kalman filtering threshold value has a key influence on the data reduction effect. However, in the prior art, the adaptability to the environment of the internet of things with frequently changing data trends and rules is insufficient, and the fixed threshold setting cannot meet the requirements of adapting to different changes of perception data of the internet of things and the balance between high data reduction rate and high data reconstruction accuracy rate. Meanwhile, the traditional kalman filter method cannot dynamically adjust the data reduction rate according to the specific data change rule in the real environment, so that the difference exists between the reconstructed data at the edge end and the actual data, and the data application is influenced.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a system and a method for reducing perception data of the internet of things based on a self-adaptive reduction threshold.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows: a perception data reduction system of the Internet of things based on a self-adaptive reduction threshold value comprises a data loading module, a self-adaptive data reduction module and a data reconstruction module;
the data loading module loads a plurality of different types of sensing data and loads the sensing data into the memory for the self-adaptive data reduction module to process;
the plurality of different types of perception data includes:
(1) static data in txt, csv, and xlsx formats;
(2) static data stored in a database;
(3) streaming dynamic data collected in real time.
The self-adaptive data reduction module receives the perception data information collected by the data loading module, analyzes the drift condition of the perception data, and dynamically generates a Kalman filter threshold value to carry out data reduction;
further, the adaptive data reduction module comprises a concept drift detection unit, a dynamic threshold adjustment unit and an equipment-side data reduction unit;
the concept drift detection unit is used for detecting whether concept drift occurs to the sensing data and providing a drift judgment result to the dynamic threshold adjustment unit;
the dynamic threshold adjusting unit dynamically generates a threshold of the Kalman filter based on a drift result;
and the equipment-side data reduction unit is used for carrying out data reduction based on a dynamically generated Kalman filter threshold value and a data prediction method.
The data reconstruction module comprises an edge end data reconstruction unit, and the edge end data reconstruction unit reconstructs and restores data according to a Kalman filter based on the reduction result of the self-adaptive data reduction module and the drift condition of the perception data.
Furthermore, the data reconstruction module further comprises an offline data reduction effect analysis unit, and the offline data reduction effect analysis unit analyzes the effects of data reduction and reconstruction according to the data reduction rate and the reconstruction accuracy rate.
Furthermore, the data reconstruction module further comprises a sensor end model updating unit, and the data reconstruction module provides updating assistance for the sensor end adaptive data reduction module based on the analyzed reduction effect, and specifically comprises updating of a concept drift detection unit and a dynamic threshold value adjusting unit.
On the other hand, the invention also provides a method for data reduction by adopting the internet of things perception data reduction system based on the self-adaptive reduction threshold, which comprises the following steps:
step 1: uniformly loading static data in a database and file form or dynamically acquired Internet of things perception data into a memory;
step 2: carrying out concept drift detection on the internet of things perception data stored in the memory, and dynamically and adaptively generating a threshold value of a Kalman filter based on a concept drift detection result, wherein the process is as follows:
step 2.1: storing a current error threshold value e _ max, a threshold minimum value min _ error and a threshold maximum value max _ error;
step 2.2: detecting the change of the perception data of the Internet of things in a short time through a concept drift detection algorithm, reducing a current error threshold value when concept drift occurs, and setting a minimum value of the threshold value as a minimum value min { e _ max, min _ error } in a current error threshold value e _ max and a minimum value min _ error of the threshold value, so as to ensure that the data reduction threshold value is greater than the minimum value of the reduction threshold value;
step 2.3: and when the concept drift does not occur, increasing the current error threshold value, and setting the maximum value of the threshold value as the maximum value max { e _ max, max _ error } in the current error threshold value e _ max and the maximum value max _ error, so as to ensure that the data reduction threshold value is smaller than the maximum value of the reduction threshold value.
And step 3: and (3) carrying out data reduction on the Internet of things perception data in the step (1) at the equipment end according to the dynamically generated Kalman filter threshold, wherein the process is as follows:
step 3.1: caching a currently received time-series sensor sensing data set { z ═ z1,z2,…,zt-1}；
Step 3.2: calculating the current data trend according to the latest data and the Internet of things perception data cached in the step 3.1:
wherein zt represents the actual value of the sensor perception data at the time t, dt represents the data trend value at the time t, alpha is the smooth weight of the range [0,1], and the value close to 1 represents the preference for the recent trend;
step 3.3: calculating an estimated value xt through a Kalman filter based on the Kalman filter threshold value e _ max generated in the step 2 in a self-adaptive manner, and if the difference et between the actual value zt of the sensor sensing data at the moment t and the estimated value xt of the Kalman filter is smaller than the current error threshold value e _ max, proving that the current moment data does not need to be uploaded to the cloud end, and reducing through the Kalman filter; otherwise, the current data zt and the data trend dt are sent to the edge terminal.
And 4, step 4: reconstructing original internet of things perception data at the edge end according to the reduced perception data obtained in the step 3, wherein the process is as follows:
step 4.1: if the equipment side uploads the data ztThen receiving the data z uploaded by the device endtAnd updates the current data trend dt，；
Step 4.2: if the data z uploaded by the equipment end in real time is not receivedtThen, based on the current data trend and the Kalman filter, the estimated values re _ data and x are calculated respectivelyt(ii) a When the difference between the two is larger than a Kalman filter threshold value e _ max, storing the perception data re _ data reconstructed by the data trend as current reconstruction data; otherwise, the estimated value x generated by the Kalman filtertAs current reconstruction data;
step 4.3: and when the equipment end stops acquiring data or the static sensing data is processed, skipping to the step 5.
And 5: and (4) comparing the reconstructed sensing data obtained in the step (4) with the original data, and calculating the data reduction rate and the reconstruction accuracy rate.
Adopt the produced beneficial effect of above-mentioned technical scheme to lie in:
1. according to the method, the data rule analysis is carried out on the single-dimensional data value, the data reduction threshold is dynamically adjusted according to the data change rule, the data reduction rate can be improved to the maximum extent when a stable data set is faced, and the high data reconstruction accuracy is kept; when a non-stable data set is faced, in order to ensure high data accuracy, the data reduction rate is automatically reduced, and a high-sensitivity state is kept.
2. The invention reduces data acquisition and transmission on the premise of ensuring data accuracy and data quality, and can obviously reduce energy consumption of sensor nodes and data storage of edge terminals.
Drawings
Fig. 1 is a schematic structural diagram of an internet of things perception data reduction system based on an adaptive reduction threshold provided in an embodiment of the present invention;
FIG. 2 is a flowchart of a method for data reduction using an IOT-aware data reduction system based on adaptive reduction thresholds according to the present invention.
Detailed Description
The following detailed description of embodiments of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
As shown in fig. 1, in this embodiment, the internet of things perception data reduction system based on the adaptive reduction threshold is as follows: the system comprises a data loading module, a self-adaptive data reduction module and a data reconstruction module;
the data loading module loads a plurality of different types of sensing data and loads the sensing data into the memory for the self-adaptive data reduction module to process;
the plurality of different types of perception data includes:
(1) static data in txt, csv, and xlsx formats;
(2) static data stored in a database;
(3) streaming dynamic data collected in real time.
The self-adaptive data reduction module receives the perception data information collected by the data loading module, analyzes the drift condition of the perception data, and dynamically generates a Kalman filter threshold value to carry out data reduction;
further, the adaptive data reduction module comprises a concept drift detection unit, a dynamic threshold adjustment unit and an equipment-side data reduction unit;
the concept drift detection unit is used for detecting whether concept drift occurs to the sensing data and providing a drift judgment result to the dynamic threshold adjustment unit;
the dynamic threshold adjusting unit dynamically generates a threshold of the Kalman filter based on a drift result;
and the equipment-side data reduction unit is used for carrying out data reduction based on a dynamically generated Kalman filter threshold value and a data prediction method.
The data reconstruction module comprises an edge end data reconstruction unit, and the edge end data reconstruction unit reconstructs and restores data according to a Kalman filter based on the reduction result of the self-adaptive data reduction module and the drift condition of the perception data.
Furthermore, the data reconstruction module further comprises an offline data reduction effect analysis unit, and the offline data reduction effect analysis unit analyzes the effects of data reduction and reconstruction according to the data reduction rate and the reconstruction accuracy rate.
Furthermore, the data reconstruction module further comprises a sensor end model updating unit, and the data reconstruction module provides updating assistance for the sensor end adaptive data reduction module based on the analyzed reduction effect, and specifically comprises updating of a concept drift detection unit and a dynamic threshold value adjusting unit.
On the other hand, the invention also provides a method for data reduction by using the internet of things perception data reduction system based on the self-adaptive reduction threshold, the flow of which is shown in fig. 2, and the method comprises the following steps:
step 1: uniformly loading static data in a database and file form or dynamically acquired Internet of things perception data into a memory;
step 2: carrying out concept drift detection on the internet of things perception data stored in the memory, and dynamically and adaptively generating a threshold value of a Kalman filter based on a concept drift detection result, wherein the process is as follows:
step 2.1: storing a current error threshold value e _ max, a threshold minimum value min _ error and a threshold maximum value max _ error;
step 2.2: detecting the change of the perception data of the Internet of things in a short time through a concept drift detection algorithm, reducing a current error threshold value when concept drift occurs, and setting a minimum value of the threshold value as a minimum value min { e _ max, min _ error } in a current error threshold value e _ max and a minimum value min _ error of the threshold value, so as to ensure that the data reduction threshold value is greater than the minimum value of the reduction threshold value;
step 2.3: and when the concept drift does not occur, increasing the current error threshold value, and setting the maximum value of the threshold value as the maximum value max { e _ max, max _ error } in the current error threshold value e _ max and the maximum value max _ error, so as to ensure that the data reduction threshold value is smaller than the maximum value of the reduction threshold value.
And step 3: and (3) carrying out data reduction on the Internet of things perception data in the step (1) at the equipment end according to the dynamically generated Kalman filter threshold, wherein the process is as follows:
step 3.1: caching a currently received time-series sensor sensing data set { z ═ z1,z2,…,zt-1}；
Step 3.2: calculating the current data trend according to the latest data and the Internet of things perception data cached in the step 3.1:
wherein zt represents the actual value of the sensor perception data at the time t, dt represents the data trend value at the time t, alpha is the smooth weight of the range [0,1], and the value close to 1 represents the preference for the recent trend;
step 3.3: calculating an estimated value xt through a Kalman filter based on the Kalman filter threshold value e _ max generated in the step 2 in a self-adaptive manner, and if the difference et between the actual value zt of the sensor sensing data at the moment t and the estimated value xt of the Kalman filter is smaller than the current error threshold value e _ max, proving that the current moment data does not need to be uploaded to the cloud end, and reducing through the Kalman filter; otherwise, the current data zt and the data trend dt are sent to the edge terminal.
And 4, step 4: reconstructing original internet of things perception data at the edge end according to the reduced perception data obtained in the step 3, wherein the process is as follows:
step 4.1: if the equipment side uploads the data ztThen receiving the data z uploaded by the device endtAnd updates the current data trend dt，；
Step 4.2: if the data z uploaded by the equipment end in real time is not receivedtThen, based on the current data trend and the Kalman filter, the estimated values re _ data and x are calculated respectivelyt(ii) a When the difference between the two is larger than a Kalman filter threshold value e _ max, storing the perception data re _ data reconstructed by the data trend as current reconstruction data; otherwise, the estimated value x generated by the Kalman filtertAs current reconstruction data;
step 4.3: and when the equipment end stops acquiring data or the static sensing data is processed, skipping to the step 5.
And 5: and (4) comparing the reconstructed sensing data obtained in the step (4) with the original data, and calculating the data reduction rate and the reconstruction accuracy rate.
Claims (9)
1. The Internet of things perception data reduction system based on the self-adaptive reduction threshold is characterized by comprising a data loading module, a self-adaptive data reduction module and a data reconstruction module;
the data loading module loads a plurality of different types of sensing data and loads the sensing data into the memory for the self-adaptive data reduction module to process;
the self-adaptive data reduction module receives the perception data information collected by the data loading module, analyzes the drift condition of the perception data, and dynamically generates a Kalman filter threshold value to carry out data reduction;
the data reconstruction module comprises an edge end data reconstruction unit, and the edge end data reconstruction unit reconstructs and restores data according to a Kalman filter based on the reduction result of the self-adaptive data reduction module and the drift condition of the perception data.
2. The internet of things aware data reduction system based on an adaptive reduction threshold as claimed in claim 1, wherein: the plurality of different types of perception data includes:
(1) static data in txt, csv, and xlsx formats;
(2) static data stored in a database;
(3) streaming dynamic data collected in real time.
3. The internet of things aware data reduction system based on an adaptive reduction threshold as claimed in claim 1, wherein: the self-adaptive data reduction module comprises a concept drift detection unit, a dynamic threshold value adjusting unit and an equipment-side data reduction unit;
the concept drift detection unit is used for detecting whether concept drift occurs to the sensing data and providing a drift judgment result to the dynamic threshold adjustment unit;
the dynamic threshold adjusting unit dynamically generates a threshold of the Kalman filter based on a drift result;
and the equipment-side data reduction unit is used for carrying out data reduction based on a dynamically generated Kalman filter threshold value and a data prediction method.
4. The internet of things aware data reduction system based on an adaptive reduction threshold as claimed in claim 3, wherein: the data reconstruction module also comprises an off-line data reduction effect analysis unit which analyzes the data reduction and reconstruction effects according to the data reduction rate and the reconstruction accuracy.
5. The internet of things aware data reduction system based on an adaptive reduction threshold as claimed in claim 4, wherein: the data reconstruction module further comprises a sensor end model updating unit, and based on the analyzed reduction effect, the data reconstruction module provides updating assistance for the sensor end self-adaptive data reduction module, and specifically comprises updating of a concept drift detection unit and a dynamic threshold value adjusting unit.
6. The method for data reduction by using the internet of things perception data reduction system based on the adaptive reduction threshold value as claimed in any one of claims 1 to 5, characterized by comprising the following steps:
step 1: uniformly loading static data in a database and file form or dynamically acquired Internet of things perception data into a memory;
step 2: carrying out concept drift detection on the internet of things perception data stored in the memory, and dynamically and adaptively generating a threshold value of a Kalman filter based on a concept drift detection result;
and step 3: carrying out data reduction on the Internet of things perception data in the step 1 at the equipment end according to the dynamically generated Kalman filter threshold;
and 4, step 4: reconstructing original sensing data of the Internet of things at the edge end according to the reduced sensing data obtained in the step 3;
and 5: and (4) comparing the reconstructed sensing data obtained in the step (4) with the original data, and calculating the data reduction rate and the reconstruction accuracy rate.
7. The method for data reduction using an adaptive reduction threshold based internet of things aware data reduction system according to claim 6, wherein the procedure of step 2 is as follows:
step 2.1: storing a current error threshold value e _ max, a threshold minimum value min _ error and a threshold maximum value max _ error;
step 2.2: detecting the change of the perception data of the Internet of things in a short time through a concept drift detection algorithm, reducing a current error threshold value when concept drift occurs, and setting a minimum value of the threshold value as a minimum value min { e _ max, min _ error } in a current error threshold value e _ max and a minimum value min _ error of the threshold value, so as to ensure that the data reduction threshold value is greater than the minimum value of the reduction threshold value;
step 2.3: and when the concept drift does not occur, increasing the current error threshold value, and setting the maximum value of the threshold value as the maximum value max { e _ max, max _ error } in the current error threshold value e _ max and the maximum value max _ error, so as to ensure that the data reduction threshold value is smaller than the maximum value of the reduction threshold value.
8. The method for data reduction using an adaptive reduction threshold based internet of things aware data reduction system according to claim 6, wherein the procedure of step 3 is as follows:
step 3.1: caching a currently received time-series sensor sensing data set { z ═ z1,z2,…,zt-1}；
Step 3.2: calculating the current data trend according to the latest data and the Internet of things perception data cached in the step 3.1:
wherein zt represents the actual value of the sensor perception data at the time t, dt represents the data trend value at the time t, alpha is the smooth weight of the range [0,1], and the value close to 1 represents the preference for the recent trend;
step 3.3: calculating an estimated value xt through a Kalman filter based on the Kalman filter threshold value e _ max generated in the step 2 in a self-adaptive manner, and if the difference et between the actual value zt of the sensor sensing data at the moment t and the estimated value xt of the Kalman filter is smaller than the current error threshold value e _ max, proving that the current moment data does not need to be uploaded to the cloud end, and reducing through the Kalman filter; otherwise, the current data zt and the data trend dt are sent to the edge terminal.
9. The method for data reduction using an adaptive reduction threshold based internet of things aware data reduction system according to claim 6, wherein the procedure of step 4 is as follows:
step 4.1: if the equipment side uploads the data ztThen receiving the data z uploaded by the device endtAnd updates the current data trend dt，；
Step 4.2: if the data z uploaded by the equipment end in real time is not receivedtThen, based on the current data trend and the Kalman filter, the estimated values re _ data and x are calculated respectivelyt(ii) a When the difference between the two is larger than a Kalman filter threshold value e _ max, storing the perception data re _ data reconstructed by the data trend as current reconstruction data; otherwise, the estimated value x generated by the Kalman filtertAs current reconstruction data;
step 4.3: and when the equipment end stops acquiring data or the static sensing data is processed, skipping to the step 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110978851.3A CN113672608B (en) | 2021-08-25 | 2021-08-25 | Internet of things perception data reduction system and method based on self-adaptive reduction threshold |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110978851.3A CN113672608B (en) | 2021-08-25 | 2021-08-25 | Internet of things perception data reduction system and method based on self-adaptive reduction threshold |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113672608A true CN113672608A (en) | 2021-11-19 |
| CN113672608B CN113672608B (en) | 2023-07-25 |
Family
ID=78545924
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110978851.3A Active CN113672608B (en) | 2021-08-25 | 2021-08-25 | Internet of things perception data reduction system and method based on self-adaptive reduction threshold |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113672608B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117411463A (en) * | 2023-12-15 | 2024-01-16 | 南京群顶科技股份有限公司 | Edge computing gateway data acquisition-oriented adaptive filtering method |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104156564A (en) * | 2014-07-16 | 2014-11-19 | 中国矿业大学 | Downhole equipment detection rule set reduction method based on discrete Calman filter |
| CN105931275A (en) * | 2016-05-23 | 2016-09-07 | 北京暴风魔镜科技有限公司 | Monocular and IMU fused stable motion tracking method and device based on mobile terminal |
| CN107270894A (en) * | 2017-06-02 | 2017-10-20 | 南京理工大学 | GNSS/SINS deep integrated navigation systems based on Dimensionality Reduction |
| KR20180058263A (en) * | 2016-11-23 | 2018-06-01 | 한국철도기술연구원 | Data processing method and apparatus of gateway for railroad iot |
| CN109213755A (en) * | 2018-09-30 | 2019-01-15 | 长安大学 | A kind of traffic flow data cleaning and restorative procedure based on Time-space serial |
| CN109975839A (en) * | 2019-04-10 | 2019-07-05 | 华砺智行(武汉)科技有限公司 | A kind of Federated filter optimization method of vehicle satellite location data |
| CN109993088A (en) * | 2019-03-22 | 2019-07-09 | 江南大学 | A kind of blind calibration method of wireless sensor network data wander |
| US20190225149A1 (en) * | 2018-01-22 | 2019-07-25 | Henan Polytechnic University | Graded early warning system for rollover of heavy-duty truck based on time-varying interactive kalman filtering and early warning method thereof |
| CN110969238A (en) * | 2019-12-31 | 2020-04-07 | 安徽建筑大学 | Method and device for calibrating electricity consumption data |
| CN110991015A (en) * | 2019-11-19 | 2020-04-10 | 三峡大学 | MEMS gyroscope self-adaptive outlier-resistant denoising method integrating Kalman and wavelets |
| CN112801267A (en) * | 2020-12-30 | 2021-05-14 | 西北工业大学 | Multiple fault diagnosis device for aircraft engine with dynamic threshold value |
-
2021
- 2021-08-25 CN CN202110978851.3A patent/CN113672608B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104156564A (en) * | 2014-07-16 | 2014-11-19 | 中国矿业大学 | Downhole equipment detection rule set reduction method based on discrete Calman filter |
| CN105931275A (en) * | 2016-05-23 | 2016-09-07 | 北京暴风魔镜科技有限公司 | Monocular and IMU fused stable motion tracking method and device based on mobile terminal |
| KR20180058263A (en) * | 2016-11-23 | 2018-06-01 | 한국철도기술연구원 | Data processing method and apparatus of gateway for railroad iot |
| CN107270894A (en) * | 2017-06-02 | 2017-10-20 | 南京理工大学 | GNSS/SINS deep integrated navigation systems based on Dimensionality Reduction |
| US20190225149A1 (en) * | 2018-01-22 | 2019-07-25 | Henan Polytechnic University | Graded early warning system for rollover of heavy-duty truck based on time-varying interactive kalman filtering and early warning method thereof |
| CN109213755A (en) * | 2018-09-30 | 2019-01-15 | 长安大学 | A kind of traffic flow data cleaning and restorative procedure based on Time-space serial |
| CN109993088A (en) * | 2019-03-22 | 2019-07-09 | 江南大学 | A kind of blind calibration method of wireless sensor network data wander |
| CN109975839A (en) * | 2019-04-10 | 2019-07-05 | 华砺智行(武汉)科技有限公司 | A kind of Federated filter optimization method of vehicle satellite location data |
| CN110991015A (en) * | 2019-11-19 | 2020-04-10 | 三峡大学 | MEMS gyroscope self-adaptive outlier-resistant denoising method integrating Kalman and wavelets |
| CN110969238A (en) * | 2019-12-31 | 2020-04-07 | 安徽建筑大学 | Method and device for calibrating electricity consumption data |
| CN112801267A (en) * | 2020-12-30 | 2021-05-14 | 西北工业大学 | Multiple fault diagnosis device for aircraft engine with dynamic threshold value |
Non-Patent Citations (4)
| Title |
|---|
| YING-GANG XIE等: "Noise Reduction Based on Kalman Filter of Low Precision Gyrosecope", 《JOURNAL OF COMPUTERS》, vol. 30, no. 5, pages 313 - 327 * |
| 武加文: "无线传感器网络漂移校准与数据重建方法研究", 《中国优秀硕士学位论文全文数据库信息科技辑》, no. 12, pages 136 - 193 * |
| 段强: "基于多传感器的盲区定位与运动轨迹追踪误差消除研究", 《中国优秀硕士学位论文全文数据库信息科技辑》, no. 05, pages 136 - 132 * |
| 邓心等: "基于深度强化学习的智能灯个性化调节方法", 《计算机工程与应用》, vol. 58, no. 06, pages 264 - 270 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117411463A (en) * | 2023-12-15 | 2024-01-16 | 南京群顶科技股份有限公司 | Edge computing gateway data acquisition-oriented adaptive filtering method |
| CN117411463B (en) * | 2023-12-15 | 2024-02-20 | 南京群顶科技股份有限公司 | Edge computing gateway data acquisition-oriented adaptive filtering method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113672608B (en) | 2023-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11449771B2 (en) | Systems and methods for processing vehicle data | |
| WO2021026944A1 (en) | Adaptive transmission method for industrial wireless streaming media employing particle swarm and neural network | |
| CN112214342B (en) | Efficient error data detection method in federal learning scene | |
| CN110602723A (en) | Two-stage bidirectional prediction data acquisition method based on underwater edge equipment | |
| CN110113777B (en) | Data acquisition method | |
| CN113672608A (en) | Internet of things perception data reduction system and method based on self-adaptive reduction threshold | |
| CN112884146B (en) | Method and system for training model based on data quantization and hardware acceleration | |
| KR101189864B1 (en) | A sampling interval adjusting technique using detection error of a sensor | |
| EP4395209A1 (en) | Data transmission control method and apparatus, computer-readable storage medium, computer device, and computer program product | |
| CN111882119A (en) | Battery SOH prediction optimization method based on SA-BP neural network | |
| CN112050742A (en) | Landslide crack displacement self-adaptive monitoring system and method | |
| CN113326132A (en) | Information adjusting method, equipment and storage medium | |
| CN117395699A (en) | Monitoring factor energy-saving communication method and system based on Internet of things | |
| CN112311935B (en) | Abnormity detection method and device and electronic equipment | |
| CN117240757A (en) | Flow-based self-adaptive data acquisition method and system | |
| CN112600869A (en) | Calculation unloading distribution method and device based on TD3 algorithm | |
| Hua et al. | $ H_ {\infty} $ Filtering for Discrete-Time Periodic Markov Jump Systems With Quantized Measurements: A New Packet Loss Compensation Strategy | |
| CN113647909B (en) | Sleep index monitoring method, electronic device, device and readable storage medium | |
| CN116540274A (en) | Self-adaptive integrated navigation method and device, electronic equipment and storage medium | |
| CN114996660B (en) | Carbon capacity prediction method and device, electronic equipment and storage medium | |
| CN113660049B (en) | Design method of event trigger control and wireless communication combined system | |
| CN115719093A (en) | Distributed training method, device, system, storage medium and electronic equipment | |
| CN111108738A (en) | Data processing device, data analysis device, data processing system, and method for processing data | |
| CN114779098A (en) | State evaluation method and system of lithium ion battery | |
| CN114818476A (en) | Federal learning system and method applied to service life prediction of rotating machinery equipment |
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 |