CN110069551A - Medical Devices O&M information excavating analysis system and its application method based on Spark - Google Patents
Medical Devices O&M information excavating analysis system and its application method based on Spark Download PDFInfo
- Publication number
- CN110069551A CN110069551A CN201910336853.5A CN201910336853A CN110069551A CN 110069551 A CN110069551 A CN 110069551A CN 201910336853 A CN201910336853 A CN 201910336853A CN 110069551 A CN110069551 A CN 110069551A
- Authority
- CN
- China
- Prior art keywords
- data
- spark
- medical devices
- module
- cluster
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- 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
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- 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
- G06F16/26—Visual data mining; Browsing structured data
-
- 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
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
-
- 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
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Probability & Statistics with Applications (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Fuzzy Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a kind of Medical Devices O&M information excavating analysis system and its application method based on Spark include the following steps: that the running state information for obtaining medical equipment in hospital is stored in MySQL database；DB type data are drawn into HDFS from MySQL database by Sqoop tool；The data acquisition of text log type is imported in HDFS or MySQL database by Kettle tool；Using Standalone as resource manager, the K-means algorithm construction prediction model in the library Spark MLlib is used；According to the equipment operation information in prediction model and training set, three kinds of state clusterings are calculated；The test set received is predicted, and prediction data is grouped into one of these three clusters, cluster data is analyzed, analysis result is intuitively presented.The present invention realizes the locating and monitoring for Medical Devices, and can be intuitively presented the operating status of equipment, significantly reduces the investment of personnel needed for Medical Equipment Maintenance, reduces a large amount of personnel cost.
Description
Technical field
The present invention relates to technical field of medical equipment, and in particular to a kind of Medical Devices O&M information digging based on Spark
Dig analysis system and its application method.
Background technique
Method used in existing most of management of medical apparatus maintenance is all PDCA, that is, needs Facilities Engineer
Entire quality monitoring process is participated in, this mode is limited by knowledge and the equipment update of maintenance personal, tieed up in corrective maintenance
The stage of repairing does not have perspective prediction.Such as " PDCA method in management of medical apparatus maintenance in " China Health industry " periodical
Application research " the PDCA method that is previously mentioned in a text；" operational system quality control module is based on " Chinese medicine equipment " periodical
The implementation of lower Medical Devices preventive maintenance program " Medical Devices PM plan in a text.These are all to need to put into a large amount of matter
Inspection person could complete, and the input cost of personnel is very big.
Summary of the invention
Goal of the invention: in order to overcome the deficiencies in the prior art, a kind of Medical Devices O&M based on Spark is provided
Information excavating analysis system and its application method can sort out complicated running state information, reach predictive maintenance
Purpose, and the state that equipment is run intuitively is shown, reduces a large amount of personnel investment.
Technical solution: to achieve the above object, the present invention provides a kind of Medical Devices O&M information excavating based on Spark
Analysis system, including data source modules, data acquisition module, storage and processing module, algorithm model module and system application mould
Block, the data source modules include DB type data and text file data, and the data acquisition module includes for acquiring DB type
The DB metadata acquisition tool of data and text file sampling instrument for acquiring text file data, the storage and processing mould
Block includes Data Warehouse Platform and data processing platform (DPP), and the Data Warehouse Platform includes MySQL database, the data processing
Platform includes HDFS distributed storage device and Standalone resource manager, and the DB type data are stored in MySQL database
In, DB type data for being drawn into HDFS by the DB metadata acquisition tool from MySQL database, the text file acquisition
Tool is used to import text file data in HDFS distributed storage device or MySQL database, the algorithm model module
For structure forecast model, the system application module includes visualizing module and early warning system module.
Further, the algorithm model module includes data analysis module, data-mining module and algoritic module.
A kind of application method of the Medical Devices O&M information excavating analysis system based on Spark, includes the following steps:
S1: the running state information for obtaining medical equipment in hospital is stored in MySQL database, and running state information includes DB
(DataBase) type data；
S2: (Sqoop) tool is acquired by DB data and is drawn into DB type data in HDFS from MySQL database；
S3: for text file type data acquisition by text file acquire (Kettle) tool importing HDFS or
In MySQL database；
S4: using Standalone as resource manager, the K-means algorithm construction in the library Spark MLlib is used
Prediction model；
S5: according to the equipment operation information in prediction model and training set, three kinds of state clusterings are calculated；
S6: predicting the test set received, and prediction data is grouped into one of these three clusters, to cluster numbers
According to being analyzed, cluster analysis result is stored in MySQL database, in conjunction with JavaScript technology, using Json as number
According to transport-type, analysis result is intuitively presented.
Further, specific using the K-means algorithm construction prediction model in the library Spark MLlib in the step S4
Include the following steps:
S4-1: Medical Devices O&M big data is read from HDFS, and creates RDD；
S4-2: K initial cluster center is generated at random；
S4-3: each point is calculated to the distance of cluster centre and carries out reduction；
S4-4: data point is assigned to nearest cluster mass center；
S4-5: calculating the average value of sample point in each division, as new cluster centre；
S4-6: repeating step S4-4 and S4-5, until reaching the number of iterations or clustering convergence, finally output cluster is tied
Fruit.
Further, three kinds of state clusterings are respectively dangerous, inferior health and health in the step S5.
Further, data point is assigned to nearest cluster mass center in the step S4-4 specifically: given for one
D dimension strong point, nearest cluster mass center is determined using distance function, it is raw that this cluster mass center is calculated using Euclidean distance function
A possibility that at the data point, wherein obtaining two d dimension strong point x=(x by Euclidean distance formula1, x2..., xd) and y=
(y1, y2..., yd) between Euclidean distance, Euclidean distance formula expression is as follows:
Dist (x, y)=√ (x1-y1)2+(x2-y2)2+...+(xd+yd)2
Further, cluster data is placed on Spark platform in the step S6 and is analyzed.
Further, in the step S6 in such a way that a variety of charts in selection Echart are in Baidu map API combination
Analysis result is presented.
Further, pre- using the prediction model progress abnormal data of the K-means algorithm construction in the library Spark MLlib
It surveys.
Further, clustering convergence in the step S4-6 specifically: the variation for dividing center is less than predefined threshold value.
K-means involved in the present invention is a data mining algorithm, belongs to unsupervised learning, can be according to object
Attribute or characteristic are higher with the object similarity in cluster by N number of clustering objects to K cluster；And the object in different clusters is similar
It spends smaller.Allow data between respective cluster mass center at a distance from quadratic sum it is minimum, thus this achievable grouping.
Its algorithm expression formula are as follows:
Wherein xnIndicate n d dimension data, μiIndicate the average value at cluster center, rnkWhen indicating that data are classified into cluster
It is 1, is otherwise 0.
In the present invention by visualization interface to last analysis as a result, the operating status of namely equipment is presented,
Visualization interface is broadly divided into two parts of equipment essential information and data O&M information.In terms of data visualization, using Java
MySQL database link block is write, in conjunction with JavaScript technology, using Json as data transmission.Visually
As a result it is presented in such a way that still image and dynamic image combine, allows users to go observation data view from different angles
Figure.
Basic information of the equipment essential information part mainly for equipment, health status, distribution situation and whole system
Error log is shown, and real-time update.Data O&M message part is utilized mainly for the data come are analyzed in algorithm
Echart chart shows with being association of activity and inertia.
The utility model has the advantages that compared with prior art, the present invention having following advantage:
1, traditional medical equipment O&M is placed on Spark platform, realize more rapidly, accurate O&M function；It is logical
The early warning mechanism of equipment is crossed, the failure of reduction Medical Devices in use is possible, improves the effective rate of utilization of equipment；
2, the locating and monitoring for Medical Devices is realized, and the operating status of equipment can be intuitively presented,
The investment of personnel needed for Medical Equipment Maintenance is significantly reduced, a large amount of personnel cost is reduced.
Detailed description of the invention
Fig. 1 is the frame diagram of present system structure；
Fig. 2 is the flow chart using the K-means algorithm construction prediction model in the library SparkMLlib；
Fig. 3 is the time state figure of liquid helium pressure in Medical Devices；
Fig. 4 is the dynamic data comparison diagram that chamber temperature and hydraulic pressure are scanned in Medical Devices；
Fig. 5 is equipment health status schematic diagram；
Fig. 6 is equipment state distribution schematic diagram；
Fig. 7 is error log schematic diagram.
Specific embodiment
In the following with reference to the drawings and specific embodiments, the present invention is furture elucidated.
As shown in Figure 1, the present invention provides a kind of Medical Devices O&M information excavating analysis system based on Spark, including
Data source modules, data acquisition module, storage and processing module, algorithm model module and system application module, data source modules
Including DB type data and text file data, data acquisition module include for acquire the DB metadata acquisition tool of DB type data and
For acquiring the text file sampling instrument of text file data, storage and processing module include at Data Warehouse Platform and data
Platform, Data Warehouse Platform include MySQL database, data processing platform (DPP) include HDFS distributed storage device,
Standalone resource manager and unified calculation control interface, unified calculation control interface include memory Computational frame and offline
Computational frame, DB type data are stored in MySQL database, and DB metadata acquisition tool is used for DB type data from MySQL data
Library is drawn into HDFS, text file sampling instrument be used for by text file data import HDFS distributed storage device or
In MySQL database, algorithm model module is used for structure forecast model, and system application module is including visual presentation module and in advance
Alert system module, algorithm model module includes data analysis module, data-mining module and algoritic module.
The present invention is based on above-mentioned analysis systems, provide a kind of Medical Devices O&M information excavating analysis system based on Spark
The application method of system, includes the following steps:
S1: the running state information for obtaining medical equipment in hospital is stored in MySQL database, and running state information includes DB
(DataBase) type data；
S2: (Sqoop) tool is acquired by DB data and is drawn into DB type data in HDFS from MySQL database；
S3: for text file type data acquisition by text file acquire (Kettle) tool importing HDFS or
In MySQL database；
S4: using Standalone as resource manager, the K-means algorithm construction in the library Spark MLlib is used
Prediction model；
S5: according to the equipment operation information in prediction model and training set, three kinds of state clusterings are calculated；
S6: predicting the test set received, and prediction data is grouped into one of these three clusters, to cluster numbers
According to being analyzed, cluster analysis result is stored in MySQL database, in conjunction with JavaScript technology, using Json as number
According to transport-type, analysis result is intuitively presented.
As shown in Fig. 2, specifically being wrapped in step S4 using the K-means algorithm construction prediction model in the library Spark MLlib
Include following steps:
S4-1: Medical Devices O&M big data is read from HDFS, and creates RDD；
S4-2: K initial cluster center is generated at random；
S4-3: each point is calculated to the distance of cluster centre and carries out reduction；
S4-4: data point is assigned to nearest cluster mass center；
S4-5: calculating the average value of sample point in each division, as new cluster centre；
S4-6: repeating step S4-4 and S4-5, until reaching the number of iterations or clustering convergence, finally output cluster is tied
Fruit.
Three kinds of state clusterings are respectively dangerous, inferior health and health in step S5；Cluster data is placed in step S6
It is analyzed on Spark platform；It will in such a way that a variety of charts in selection Echart are in Baidu map API combination in step S6
Analysis result is presented；It is pre- that abnormal data is carried out using the prediction model of the K-means algorithm construction in the library Spark MLlib
It surveys；Clustering convergence in step S4-6 specifically: the variation for dividing center is less than predefined threshold value.
Embodiment 1:
Above system is applied in Anyang the People's Hospital 3.0T HDXT model device in the present embodiment, in 2018-
The data that this section of period operation of 06-27 to 2018-11-16 generates sum up the standard that operating parameter threshold value out is predicted.Type
It is as shown in the table for number 3.0T HDXT equipment operating parameter threshold value:
1 model 3.0T HDXT equipment operating parameter threshold value of table
9 parameters such as liquid helium pressure, scanning chamber temperature, liquid helium level, water temperature, water flow are taken, with the K- based on Spark
Means algorithm carries out cluster calculation, and 3 cluster centres of generation obtain K-means cluster centre, shown in table 2 specific as follows:
According to Tables 1 and 2 comparison it is found that the liquid helium level for being located at the data point of the first and second class is higher, magnet shield layer temperature
It spends lower；The liquid helium pressure of the data point of third class is very low, and scanning chamber temperature is higher, and water temperature is higher, and cold head temperature is higher, thus
This 30,000 data can be simply divided into 3 classes and do preliminary prediction.
Embodiment 2:
Above system is applied in " the second hospital of Wuxi City " in the present embodiment, final analysis result passes through selection
A variety of charts are presented in the mode that Baidu map API is combined in Echart, specific as follows:
It is illustrated in figure 3 the time state figure of liquid helium pressure in the Medical Devices of monitoring, is shown using echart line chart
Show particular state, be normal range value between 1 and 5 dotted line, other are non-normal range value.
It is illustrated in figure 4 the dynamic data comparison diagram that chamber temperature and hydraulic pressure are scanned in the Medical Devices of monitoring.
It is illustrated in figure 5 equipment health status schematic diagram, in device data, is shown and is set using echart pie diagram form
Standby health status, the in a tabular form specific information of presentation device.
It is illustrated in figure 6 the equipment state distribution schematic diagram of the second hospital of Wuxi City, Baidu is utilized in device distribution figure
Map api positions equipment, and dangerous, inferior health and healthy three kinds of states are respectively indicated with 1,2 and 3.
As shown in fig. 7, showing error log using table in error log summarizes, and counts different times and accident occurs
Number of devices.
Claims (9)
1. the Medical Devices O&M information excavating analysis system based on Spark, it is characterised in that: including data source modules, data
Acquisition module, storage and processing module, algorithm model module and system application module, the data source modules include DB type data
With text file data, the data acquisition module includes DB metadata acquisition tool for acquiring DB type data and for acquiring
The text file sampling instrument of text file data, the storage include that Data Warehouse Platform and data processing are flat with processing module
Platform, the Data Warehouse Platform include MySQL database, the data processing platform (DPP) include HDFS distributed storage device and
Standalone resource manager, the DB type data are stored in MySQL database, and the DB metadata acquisition tool is used for will
DB type data are drawn into HDFS from MySQL database, and the text file sampling instrument is for importing text file data
In HDFS distributed storage device or MySQL database, the algorithm model module is used for structure forecast model, and the system is answered
It include visualizing module and early warning system module with module.
2. the Medical Devices O&M information excavating analysis system according to claim 1 based on Spark, it is characterised in that:
Include the following steps: that the algorithm model module includes data analysis module, data-mining module and algoritic module.
3. the application method of the Medical Devices O&M information excavating analysis system according to claim 1 based on Spark,
It is characterized in that: including the following steps:
S1: the running state information for obtaining medical equipment in hospital is stored in MySQL database, and running state information includes DB type number
According to；
S2: DB type data are drawn into HDFS from MySQL database by DB metadata acquisition tool；
S3: the data acquisition of text file type is imported in HDFS or MySQL database by text file sampling instrument；
S4: it using Standalone as resource manager, is predicted using the K-means algorithm construction in the library Spark MLlib
Model；
S5: according to the equipment operation information in prediction model and training set, three kinds of state clusterings are calculated；
S6: predicting the test set received, and by prediction data be grouped into these three cluster one of, to cluster data into
Row analysis, cluster analysis result is stored in MySQL database, in conjunction with JavaScript technology, is passed using Json as data
Defeated type is intuitively presented analysis result.
4. the application method of the Medical Devices O&M information excavating analysis system according to claim 3 based on Spark,
It is characterized in that: being specifically included in the step S4 using the K-means algorithm construction prediction model in the library Spark MLlib as follows
Step:
S4-1: Medical Devices O&M big data is read from HDFS, and creates RDD；
S4-2: K initial cluster center is generated at random；
S4-3: each point is calculated to the distance of cluster centre and carries out reduction；
S4-4: data point is assigned to nearest cluster mass center；
S4-5: calculating the average value of sample point in each division, as new cluster centre；
S4-6: repeating step S4-4 and S4-5, until reaching the number of iterations or clustering convergence, finally exports cluster result.
5. the application method of the Medical Devices O&M information excavating analysis system according to claim 3 based on Spark,
Be characterized in that: three kinds of state clusterings are respectively dangerous, inferior health and health in the step S5.
6. the application method of the Medical Devices O&M information excavating analysis system according to claim 4 based on Spark,
It is characterized in that: data point is assigned to nearest cluster mass center in the step S4-4 specifically: the d dimension data given for one
Point determines nearest cluster mass center using distance function, this cluster mass center is calculated using Euclidean distance function and generates the data
A possibility that point, wherein obtaining two d dimension strong point x=(x by Euclidean distance formula1, x2..., xd) and y=(y1,
y2..., yd) between Euclidean distance, Euclidean distance formula expression is as follows:
Dist (x, y)=√ (x1-y1)2+(x2-y2)2+...+(xd+yd)2。
7. the application method of the Medical Devices O&M information excavating analysis system according to claim 3 based on Spark,
It is characterized in that: cluster data being placed on Spark platform in the step S6 and is analyzed.
8. the application method of the Medical Devices O&M information excavating analysis system according to claim 3 based on Spark,
It is characterized in that: being tied analysis by way of Baidu map API combination a variety of charts in selection Echart in the step S6
Fruit is presented.
9. the application method of the Medical Devices O&M information excavating analysis system according to claim 4 based on Spark,
It is characterized in that: clustering convergence in the step S4-6 specifically: the variation for dividing center is less than predefined threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910336853.5A CN110069551A (en) | 2019-04-25 | 2019-04-25 | Medical Devices O&M information excavating analysis system and its application method based on Spark |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910336853.5A CN110069551A (en) | 2019-04-25 | 2019-04-25 | Medical Devices O&M information excavating analysis system and its application method based on Spark |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110069551A true CN110069551A (en) | 2019-07-30 |
Family
ID=67368745
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910336853.5A Pending CN110069551A (en) | 2019-04-25 | 2019-04-25 | Medical Devices O&M information excavating analysis system and its application method based on Spark |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110069551A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110633271A (en) * | 2019-11-20 | 2019-12-31 | 紫光云(南京)数字技术有限公司 | Data extraction method from Hbase to mysql based on json |
| CN110633082A (en) * | 2019-09-26 | 2019-12-31 | 山东浪潮商用系统有限公司 | Dynamic data display method and system combining echart and html |
| CN110674143A (en) * | 2019-10-18 | 2020-01-10 | 长春理工大学 | No-tillage machine operation information monitoring system and method |
| CN113254541A (en) * | 2021-04-15 | 2021-08-13 | 浙江工业大学 | Theatre operation and maintenance management method based on cluster analysis |
| CN113313272A (en) * | 2021-06-15 | 2021-08-27 | 江苏杰瑞信息科技有限公司 | Intelligent early warning design method for failure of marine auxiliary engine equipment based on artificial intelligence |
| CN113533875A (en) * | 2020-04-22 | 2021-10-22 | 杭州释普科技有限公司 | Method for intelligently judging laboratory equipment running state and calculating equipment utilization rate |
| CN114358212A (en) * | 2022-01-25 | 2022-04-15 | 电子科技大学 | Cancer prearrangement index data analysis system based on K-means |
| CN115587140A (en) * | 2022-12-09 | 2023-01-10 | 四川新迎顺信息技术股份有限公司 | Electronic engineering project data visual management method and device based on big data |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105095653A (en) * | 2015-07-13 | 2015-11-25 | 湖南互动传媒有限公司 | Basic service system for medical large data application |
| CN105138661A (en) * | 2015-09-02 | 2015-12-09 | 西北大学 | Hadoop-based k-means clustering analysis system and method of network security log |
| US20170330132A1 (en) * | 2016-05-13 | 2017-11-16 | International Business Machines Corporation | Method and system to manage supervision activity in utility system to reduce damage |
| CN107463620A (en) * | 2017-07-05 | 2017-12-12 | 洛川闰土农牧科技有限责任公司 | A kind of elevator accident early-warning and predicting system based on data mining |
| CN107563153A (en) * | 2017-08-03 | 2018-01-09 | 华子昂 | A kind of PacBio microarray dataset IT architectures based on Hadoop structures |
| CN108062555A (en) * | 2016-11-08 | 2018-05-22 | 南京理工大学 | Monitoring data early warning system based on Spark streamings cluster |
-
2019
- 2019-04-25 CN CN201910336853.5A patent/CN110069551A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105095653A (en) * | 2015-07-13 | 2015-11-25 | 湖南互动传媒有限公司 | Basic service system for medical large data application |
| CN105138661A (en) * | 2015-09-02 | 2015-12-09 | 西北大学 | Hadoop-based k-means clustering analysis system and method of network security log |
| US20170330132A1 (en) * | 2016-05-13 | 2017-11-16 | International Business Machines Corporation | Method and system to manage supervision activity in utility system to reduce damage |
| CN108062555A (en) * | 2016-11-08 | 2018-05-22 | 南京理工大学 | Monitoring data early warning system based on Spark streamings cluster |
| CN107463620A (en) * | 2017-07-05 | 2017-12-12 | 洛川闰土农牧科技有限责任公司 | A kind of elevator accident early-warning and predicting system based on data mining |
| CN107563153A (en) * | 2017-08-03 | 2018-01-09 | 华子昂 | A kind of PacBio microarray dataset IT architectures based on Hadoop structures |
Non-Patent Citations (6)
| Title |
|---|
| 徐元熙等: "数据挖掘在医院信息系统中的应用研究", 《微计算机信息》 * |
| 徐元熙等: "数据挖掘在医院信息系统中的应用研究", 《微计算机信息》, no. 33, 25 November 2008 (2008-11-25) * |
| 陈润: "面向铁路运维的大数据流式处理技术的研究与应用", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 陈润: "面向铁路运维的大数据流式处理技术的研究与应用", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 1, 15 January 2018 (2018-01-15), pages 2 - 4 * |
| 高峰 等: "医疗设备全生命周期维修管理系统的设计与实现", 《中国医疗设备》 * |
| 高峰 等: "医疗设备全生命周期维修管理系统的设计与实现", 《中国医疗设备》, vol. 31, no. 2, 25 February 2016 (2016-02-25), pages 155 - 156 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110633082A (en) * | 2019-09-26 | 2019-12-31 | 山东浪潮商用系统有限公司 | Dynamic data display method and system combining echart and html |
| CN110674143A (en) * | 2019-10-18 | 2020-01-10 | 长春理工大学 | No-tillage machine operation information monitoring system and method |
| CN110633271A (en) * | 2019-11-20 | 2019-12-31 | 紫光云(南京)数字技术有限公司 | Data extraction method from Hbase to mysql based on json |
| CN113533875A (en) * | 2020-04-22 | 2021-10-22 | 杭州释普科技有限公司 | Method for intelligently judging laboratory equipment running state and calculating equipment utilization rate |
| CN113533875B (en) * | 2020-04-22 | 2024-02-23 | 释普信息科技（上海）有限公司 | Method for intelligently judging running state of laboratory equipment and calculating equipment utilization rate |
| CN113254541A (en) * | 2021-04-15 | 2021-08-13 | 浙江工业大学 | Theatre operation and maintenance management method based on cluster analysis |
| CN113313272A (en) * | 2021-06-15 | 2021-08-27 | 江苏杰瑞信息科技有限公司 | Intelligent early warning design method for failure of marine auxiliary engine equipment based on artificial intelligence |
| CN114358212A (en) * | 2022-01-25 | 2022-04-15 | 电子科技大学 | Cancer prearrangement index data analysis system based on K-means |
| CN114358212B (en) * | 2022-01-25 | 2024-01-30 | 电子科技大学 | Cancer prescriptions index data analysis system based on K-means |
| CN115587140A (en) * | 2022-12-09 | 2023-01-10 | 四川新迎顺信息技术股份有限公司 | Electronic engineering project data visual management method and device based on big data |
| CN115587140B (en) * | 2022-12-09 | 2023-03-28 | 四川新迎顺信息技术股份有限公司 | Electronic engineering project data visual management method and device based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110069551A (en) | Medical Devices O&M information excavating analysis system and its application method based on Spark | |
| CN108388503A (en) | Data-base performance monitoring method, system, equipment and computer readable storage medium | |
| CN104638764A (en) | Intelligent state diagnosis and overhauling system for power distribution network equipment | |
| CN109800995A (en) | A kind of grid equipment fault recognition method and system | |
| CN112529327A (en) | Method for constructing fire risk prediction grade model of buildings in commercial areas | |
| CN109740872A (en) | The diagnostic method and system of a kind of area's operating status | |
| CN107391335A (en) | A kind of method and apparatus for checking cluster health status | |
| An et al. | Condition parameter degradation assessment and prediction for hydropower units using Shepard surface and ITD | |
| CN117196159A (en) | Intelligent water service partition metering system based on Internet big data analysis | |
| CN114662712A (en) | Rotating machine state monitoring method based on Wasserstein depth digital twin model | |
| CN117194919A (en) | Production data analysis system | |
| CN117787711A (en) | Arch bridge construction single-end management system based on big data | |
| CN105930255A (en) | Method and apparatus for predicting health degree of system | |
| CN105938573A (en) | Actuarial early-warning system and method for medical benefits fund | |
| CN110956281A (en) | Power equipment abnormity detection alarm system based on Log analysis | |
| CN108761263A (en) | A kind of fault diagnosis system based on evidence theory | |
| CN106649034A (en) | Visual intelligent operation and maintenance method and platform | |
| CN110837970A (en) | Regional health platform quality control method and system | |
| CN108258802A (en) | The monitoring method and device of the operation conditions of controller switching equipment in a kind of power distribution network | |
| CN107087284A (en) | Quality control method and monitoring system, the server of a kind of network cell | |
| CN113642669B (en) | Feature analysis-based fraud prevention detection method, device, equipment and storage medium | |
| CN111221704B (en) | Method and system for determining running state of office management application system | |
| CN207232961U (en) | A kind of system that can be tested in real time to watermark protocol data | |
| CN112764985A (en) | Intelligent monitoring method for data center system | |
| Wang et al. | Air quality data analysis and forecasting platform based on big data |
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 |