KR20170098027A - System and method for analyzing bio-signal using data analysis module - Google Patents

System and method for analyzing bio-signal using data analysis module Download PDF

Info

Publication number
KR20170098027A
KR20170098027A KR1020160019891A KR20160019891A KR20170098027A KR 20170098027 A KR20170098027 A KR 20170098027A KR 1020160019891 A KR1020160019891 A KR 1020160019891A KR 20160019891 A KR20160019891 A KR 20160019891A KR 20170098027 A KR20170098027 A KR 20170098027A
Authority
KR
South Korea
Prior art keywords
data
module
signal
analysis
analysis module
Prior art date
Application number
KR1020160019891A
Other languages
Korean (ko)
Other versions
KR101827088B1 (en
Inventor
김희철
주문일
Original Assignee
인제대학교 산학협력단
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 인제대학교 산학협력단 filed Critical 인제대학교 산학협력단
Priority to KR1020160019891A priority Critical patent/KR101827088B1/en
Publication of KR20170098027A publication Critical patent/KR20170098027A/en
Application granted granted Critical
Publication of KR101827088B1 publication Critical patent/KR101827088B1/en

Links

Images

Classifications

    • G06F19/32—
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/024—Detecting, measuring or recording pulse rate or heart rate
    • A61B5/0402—
    • A61B5/0452—
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/08—Detecting, measuring or recording devices for evaluating the respiratory organs
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
    • G06F17/30194—
    • G06F17/30318—
    • G06F17/30339—
    • G06F17/30592—

Abstract

The present invention relates to a biological signal analysis system and method based on an analysis module, and more particularly, to a biological signal analysis system and method based on an analysis module that receives raw data of biological signals measured by a biological signal measurement device through a web service, A transmitting / receiving unit for identifying a data storage according to the location of the data storage and designating a location of the data storage; A module management engine unit for defining an analysis module in accordance with the predefined module information and searching an analysis module according to module information to be searched out among the defined analysis modules; Storing the defined analysis module in a module repository, storing raw data of the received bio-signal in a data repository, processing the stored raw data by applying the retrieved analysis module to generate processed data, A Hadoop distributed file system (HDFS) that stores data in a data warehouse; And a service providing unit for providing the processed data through a web service of the transceiver unit as a result of analyzing the biological signal.

Description

TECHNICAL FIELD [0001] The present invention relates to a bio-signal analysis system and method based on an analysis module,

The present invention relates to a bio-signal analysis system and method based on an analysis module, and more particularly, to a bio-signal analysis system based on an analysis module, and more particularly, to a data analysis module (e.g., an implemented data analysis algorithm) for collecting various data on a Hadoop platform, And more particularly, to a bio-signal analysis system and method based on an analysis module capable of analyzing data by performing management (e.g., module insertion, module deletion, module modification).

Recently, rapid spread of smart infrastructure, especially big data management and analysis technology, has been rapidly growing with the enhancement of social awareness. Also, with the spread of various wearable devices and smartphone devices, it has become possible to collect various information from individuals, companies and groups. Big data technologies are evolving due to the rapid generation of data, and various big data analysis tools have been developed for analyzing big data, and development is underway.

Big data is large-scale data that is generated in a digital environment, has a large size, has a short generation period, and includes not only numeric data but also text and image data. Big data has various forms such as a linear structure that continuously flows into various types of data, data having a single characteristic value, text-based data, and the like. There is a need to classify and analyze these types of data into meaningful data.

Big data-based big data analysis can be done using tools like statistical-based analysis tool R program and SQL-like Hive's HiveQL. As such, current analytical tools are used to provide services through statistical-based analysis. Big data-based analytics are analyzed using data measured from a variety of objects, data collected from the Web, and data collected from individuals and companies. Because these signals are meaningless data in their own right, they can be stored in the same repository as the big data platform (Hadoop, No-SQL, HBASE, etc.) And statistical analysis using data analysis tools.

However, big data analysis tools alone can not analyze large amounts of data as meaningful data. Therefore, in order to perform various analyzes, it is necessary to retrieve the data from the repository storing the data and the data from the repository, and to store the processed data in the big data analysis tool through the appropriate data analysis module (implemented algorithm).

In addition, to analyze big data, you need to use a platform that integrates storage for data collection and storage and data curation (or data refinement) to analyze the data.

Korean Patent Laid-Open Publication No. 10-2015-0144562 (published Dec. 28, 2015)

For example, signals such as electrocardiograms, respiration, and the like are atypical data having no meaning by raw data alone. A technique for extracting or converting such irregular data into meaningful data (for example, heartbeat variation, pulse rate, etc.) processed, that is, a data processing and analysis module (implemented algorithm) is required. In order to improve the efficiency of big data analysis, a platform is needed which can easily create, delete, and change these analysis modules. When such a platform exists, it is possible to provide a variety of services to users and developers easily and quickly.

To this end, embodiments of the present disclosure may facilitate the management (e.g., module insertion, module deletion, module deletion) of data analysis modules (e.g., implemented data analysis algorithms) that collect various data on the Hadoop platform and process and analyze the data And analyzing the data by analyzing the data of the biological signal.

In addition, the embodiments of the present invention can receive various bio-data bio-signals (e.g., electrocardiogram, respiration, acceleration, SpO2, etc.) and also receive analysis modules capable of analyzing these bio- And to provide a bio-signal analysis system and method based on an analysis module that can be stored in a repository.

In addition, the embodiments of the present invention use raw data of a bio-signal as input values of analysis modules to obtain a result of extracting meaningful data, and analyze processing data of a bio-signal using a combination of analysis modules A biological signal analysis system and method based on an analysis module.

According to the first aspect of the present invention, the raw data of the bio-signal measured by the bio-signal measuring device is received through the web service, the data storage according to the type of the bio-signal is identified, Receiving unit; A module management engine unit for defining an analysis module in accordance with the predefined module information and searching an analysis module according to module information to be searched out among the defined analysis modules; Storing the defined analysis module in a module repository, storing raw data of the received bio-signal in a data repository, processing the stored raw data by applying the retrieved analysis module to generate processed data, A Hadoop distributed file system (HDFS) that stores data in a data warehouse; And a service providing unit for providing the processed data through the web service of the transceiver unit as a result of analysis of the biosignal signal.

The transceiver may receive the SOAP message including the raw data of the bio-signal from the bio-signal measuring device, parse the received SOAP message using the parsing library, and extract the raw data from the parsed data .

The transceiver can receive raw data of any one of an electrocardiogram signal, an acceleration signal, a breathing signal, and a blood coral saturation signal, which are atypical data based on big data.

The module management engine unit includes module description information of the analysis module, an input value for defining an input form of data for executing the analysis module, an output value for showing an output form of the analysis module, and a development language An analysis module may be defined using the module information including the information, and the defined analysis module may be stored in the module repository of the Hadoop distributed file system.

The Hadoop distributed file system may create a data store in the Hadoop repository according to the type of the raw data and store the raw data in the generated data repository.

The Hadoop distributed file system includes: a module storage unit for storing the defined analysis module in a module storage; A raw data storage unit for storing the raw data of the received bio-signal in a data storage; A module interlocking engine unit for processing raw data of the stored bio-signals to generate processed data by applying the searched analysis module; And a data warehouse for storing the generated processing data.

The module interlocking engine unit fetches the raw data stored in the raw data or the processed data stored in the data warehouse in advance according to the input value in the module information of the searched analysis module, Processing data can be generated.

The module interlocking engine unit sequentially applies a plurality of analysis modules to generate a plurality of pieces of machining data, loads the previously machined N-1th machining data in accordance with the module information of the Nth order analysis module, The data can be converted to the input value of the Nth order analysis module and applied to the Nth order analysis module to generate the new processed Nth order processed data as the output value.

According to a second aspect of the present invention, there is provided a bio-signal measuring apparatus for receiving bio-signal raw data measured by a bio-signal measuring device through a web service, determining a data store according to a type of a bio- ; Defining an analysis module according to the predefined module information, and storing the defined analysis module in a module repository; Searching an analysis module according to module information to be searched among the defined analysis modules; Processing the stored raw data by applying the searched analysis module to generate processed data and storing the generated processed data in a data warehouse; And providing the generated processed data as a result of analyzing a living body signal through a web service.

Wherein the step of designating the location of the data repository comprises: receiving a SOAP message including raw data of a bio-signal from the bio-signal measurement device; parsing the received SOAP message using a parsing library; Raw data can be extracted.

The step of designating the location of the data repository may receive raw data of a bio-signal of any one of an ECG signal, an acceleration signal, a respiration signal, and a blood coral saturation signal, which are atypical data based on a big data.

The step of storing in the module repository comprises: defining information of an analysis module; input value defining a data input form for executing the analysis module; output value for showing an output form of the analysis module; An analysis module may be defined using the module information including the developed language information, and the defined analysis module may be stored in the module repository of the Hadoop distributed file system.

The storing in the data warehouse may generate a data store in the Hadoop repository according to the type of the raw data and store the raw data in the generated data repository.

The step of storing in the data warehouse retrieves raw data stored in the raw data or processed data previously stored and stored in the data warehouse according to an input value in module information of the retrieved analysis module, Processing data can be generated by processing according to the language information.

Wherein the step of storing in the data warehouse further comprises the step of sequentially applying a plurality of analysis modules to generate a plurality of processed data, wherein the step of generating the plurality of processed data includes: Is converted into an output value by applying the N-th order processing data to the N-th order analysis module by converting the N-th order processing data according to the input value of the N-th order analysis module, can do.

To this end, embodiments of the present disclosure may facilitate the management (e.g., module insertion, module deletion, module deletion) of data analysis modules (e.g., implemented data analysis algorithms) that collect various data on the Hadoop platform and process and analyze the data The data can be analyzed.

In addition, the embodiments of the present invention can receive various bio-data bio-signals (e.g., electrocardiogram, respiration, acceleration, SpO2, etc.) and also receive analysis modules capable of analyzing these bio- It can be stored in the repository.

In addition, the embodiments of the present invention use raw data of a bio-signal as input values of analysis modules to obtain a result of extracting meaningful data, and analyze processing data of a bio-signal using a combination of analysis modules have.

1 is a block diagram of a bio-signal analysis system based on an analysis module according to an embodiment of the present invention.
FIG. 2 is an explanatory diagram of a raw data storing process in the bio-signal analysis system of FIG. 1 according to the embodiment of the present invention.
3 is an exemplary view of a SOAP message of a web service applied to an embodiment of the present invention.
FIG. 4 is an explanatory diagram illustrating a storing process of the analysis module and module description information in the bio-signal analysis system of FIG. 1 according to the embodiment of the present invention.
5 is an exemplary diagram of development language information in which a language in which the analysis module according to the present embodiment is programmed is defined.
6 is an illustration of processed data stored in a repository of each of the data warehouses according to an embodiment of the present disclosure;
FIG. 7 is an explanatory diagram of a process data generation process performed by the module interlocking engine unit in the bio-signal analysis system of FIG. 1 according to the embodiment of the present invention.
8 is an explanatory diagram illustrating a process of generating processed data by applying a plurality of analysis modules according to an embodiment of the present invention.
FIG. 9 is a flowchart of a bio-signal analysis method based on an analysis module according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. Will be described in detail with reference to the portions necessary for understanding the operation and operation according to the present specification. In describing the embodiments of the present invention, description of technical contents which are well known in the technical field to which the present invention belongs and which are not directly related to the present specification will be omitted. This is for the sake of clarity without omitting the unnecessary explanation and without giving the gist of the present invention.

In describing the components of the present specification, the same reference numerals may be given to components having the same name, and the same reference numerals may be given to different drawings. However, even in such a case, it does not mean that the corresponding component has different functions according to the embodiment, or does not mean that it has the same function in different embodiments, and the function of each component is different from that of the corresponding embodiment Based on the description of each component in FIG.

1 is a block diagram of a bio-signal analysis system based on an analysis module according to an embodiment of the present invention.

1, an analysis module-based bio-signal analysis system 100 according to an embodiment of the present invention includes a transceiver unit 110, a module management engine unit 120, a Hadoop distributed file system (HDFS) a file system 131 and a service provider 140. Here, the Hadoop distributed file system 131 is included in Hadoop 130.

First, a bio-signal analysis system 100 based on an analysis module according to an embodiment of the present invention will be briefly described below.

First, the bio-signal analysis system 100 provides a service for transmitting, receiving, and storing data measured in various objects, data collected on the web, and data collected by an individual and a company via a network.

Second, the bio-signal analysis system 100 can perform insertion, deletion, and correction functions of various analysis modules.

Third, the bio-signal analysis system 100 can perform a module search function for using the analysis module after storing the analysis module in the module storage via the network.

Fourth, the bio-signal analysis system 100 can provide a big data analysis function by applying an analysis module.

For example, the electrocardiogram signal and the acceleration signal in the embodiment of the present invention are defined as raw data, and the data extracted by applying the analysis module to the raw data is defined as processed data. Analysis module is applied to convert raw data to processed data.

The bio-signal analysis system 100 facilitates insertion, deletion, and modification of the analysis module to process the raw data, thereby providing various services and data analysis quickly and easily.

In order to enable such a technique, first, the bio-signal analysis system 100 specifies an accurate analysis module for giving an insertion, deletion, and change function of an analysis module developed in various languages and tools, do.

Second, the bio-signal analysis system 100 includes a module interlocking engine unit 134 for analyzing the analysis module and applying the corresponding analysis module. Here, the module interworking engine 134 is composed of an engine that executes an analysis module in a web service according to different development languages and derives a result value. In addition, the module interworking engine 134 stores the resultant value obtained by using the Hadoop data warehouse 135 to store the derived result.

Hereinafter, the specific configuration and operation of each component of the bio-signal analysis system 100 based on the analysis module according to the embodiment of the present invention shown in FIG. 1 will be described.

The transceiver 110 receives the raw data of the bio-signal measured by the bio-signal measuring device 101 through the web service. The transmission / reception unit 110 determines the data storage according to the type of the biological signal and designates the location of the data storage. The transceiver 110 transmits / receives data to / from the bio-signal measuring device 101 or the user terminal 102 through the web service of the web server.

Here, a web service is a technology for sharing distributed contents in an abstract service form and sharing them in a standardized form. This Web service technology is intended to interoperate between applications built on heterogeneous platforms and freely use a service object or an API (Application Protocol Interface) at a remote location by transmitting and receiving a mutually understandable format message in SOAP (Simple Object Access Protocol) It is possible to accommodate the request of the user terminal 102 to be desired. These Web services are transmitted over HTTP (Hypertext transfer protocol) as a protocol that can access distributed objects without depending on specific distribution or platform. HTTP is a protocol for exchanging information on the World Wide Web.

The bio-signal analysis system 100 based on the analysis module according to the embodiment of the present invention may employ an acceleration analysis module applying an acceleration signal to analyze user's motion and an electrocardiogram analysis module analyzing an electrocardiogram signal.

A separate medical sensor is required to obtain a biological signal (e.g., electrocardiogram, SpO2, respiration, etc.). However, in the bio-signal analysis system 100 according to the embodiment of the present invention, the raw data of the electrocardiogram signal measured by the bio-signal measuring device 101 and the acceleration data stored in the user terminal 102, such as a smart phone, To obtain the raw data of the acceleration signal.

The bio-signal analysis system 100 stores the measured or obtained raw data in respective folders of the Hadoop distributed file system 131 according to the type of data using the web service. In order to store various kinds of data, it is necessary to have a repository for storing the data. The bio-signal analysis system 100 can search and extract data from the Hadoop 130 at any time by checking the structure of the stored data.

For example, the raw data of the big data is transmitted to the web server via the network together with the type of data, the measurement date and time, via the SOAP message. Then, the transceiver 110 parses the necessary information using a parsing library that analyzes the SOAP message in order to check the information about the raw data. The transceiver 110 extracts the raw data from the parsed data and stores the raw data in the Hadoop 130. The Hadoop 130 may store the raw data by creating a data storage area in the Hadoop repository according to the type of the raw data.

Meanwhile, the module management engine unit 120 defines an analysis module according to the predefined module information. The module management engine unit 120 searches the analysis module according to the module information to be searched among the analysis modules stored in the Hadoop distributed file system 131.

In order to specify such an analysis module, the module management engine unit 120 defines a definition module and an analysis module. The module management engine unit 120 uses description information, input values, output values, and development language information of the analysis module. Here, the input value defines the input form of the data to execute the module. The output value is defined to show the output type of the module. In addition, the analysis module can be programmed in various ways or in various languages. Therefore, the development language in which the analysis module is developed is defined in the development language information.

Also, the module management engine unit 120 searches the analysis module using the search module. The module search is confirmed through the module information of the analysis module stored through the search module. The module management engine unit 120 can search the desired analysis module according to the type of the analysis module and the description of the analysis module based on the module information.

Meanwhile, the Hadoop distributed file system (HDFS) 131 stores the analysis module defined in the module management engine unit 120 in the module store. In addition, the Hadoop distributed file system 131 stores the raw data of the bio-signal received by the transceiver 110 in a data store.

The Hadoop distributed file system 131 according to an embodiment of the present invention includes a module storage unit 132, a raw data storage unit 133, a module interlocking engine unit 134, and a data warehouse 135.

The module storage unit 132 stores the analysis module defined in the module management engine unit 120 in the module storage.

The raw data storage unit 133 stores the raw data of the bio-signal received by the transceiver unit 110 in a data storage. Here, the source data storage unit 133 may generate a data store in the Hadoop repository according to the type of the source data extracted from the SOAP message in the transmitter / receiver 110, and store the source data in the generated data store.

The module interlocking engine unit 134 processes the raw data of the bio-signal stored in the raw data storage unit 133 using the analysis module retrieved from the module management engine unit 120 to generate the processed data.

The module interlocking engine 134 extracts the processed data by applying the raw data to the retrieved analysis module. Here, the analysis module can fetch data from raw data or processed data according to input values. The raw data is retrieved from the data stored in Hadoop 130. However, the processed data is fetched and processed using the data warehouse 135. After confirming the input value to the analysis module, the module interworking engine 134 for applying the module processes the processor according to the developed language. The module interlocking engine unit 134 stores the processed data processed by the data warehouse 135 as the result of the processed analysis module.

Meanwhile, the Hadoop distributed file system 131 processes the pre-stored raw data using the analysis module retrieved by the module management engine unit 120 to generate processed data. Then, the Hadoop distributed file system 131 stores the generated processed data in the data warehouse 135. That is, the data warehouse 135 stores the processing data generated by the analysis module by the module interlocking engine unit 134.

As another example, the module interlocking engine unit 134 applies the machining data as an input value to the analysis module, extracts newly machined machining data, and stores the machining data in the data warehouse 135. The retrieval of the machined data requires analysis of the module information. The module interlocking engine unit 134 checks the storage location of the processed data using the module description and the result value of the module information, and loads the data. The module interworking engine 134 converts the imported data into an input value and applies the converted data to a format suitable for the input value of the analysis module to apply the analysis module and then stores the new processed data in the data warehouse 135 do.

Meanwhile, the service provider 140 provides the processed data generated in the Hadoop distributed file system 131 as a result of analyzing the biological signal through the web service of the transceiver 110.

FIG. 2 is an explanatory diagram of a raw data storing process in the bio-signal analysis system of FIG. 1 according to the embodiment of the present invention.

The transceiver 110 receives the SOAP message 202 including the raw data 201 of the bio-signal from the bio-signal measuring device 101. [ The transmission / reception unit 110 parses the received SOAP message using a parsing library. Then, the transmission / reception unit 110 extracts the raw data 201 from the parsed data. For example, the transceiver 110 can receive raw data 201 of a bio-signal, which is atypical data based on big data, an ECG signal, an acceleration signal, a respiration signal, and a blood coral saturation signal.

That is, the transceiver 110 receives the raw data 201 from the bio-signal measuring device 101 or the user terminal 102 connected via a network, and transmits the raw data 201 of the biomedical signal to the Hadoop 130 Check and store the data store according to the type.

Here, Hadoop 130 is a framework that allows distributed processing of large datasets across computer clusters using a simple programming model. Hadoop 130 can perform distributed storage of large amount of data and parallel processing in a plurality of server clusters. The Hadoop platform implementing the Hadoop 130 includes a Hadoop distributed file system 131 and MapReduce. The Hadoop distributed file system 131 divides and stores files, and operates as a name node and a data node, thereby performing stable and fast storage functions.

In this case, data can be classified into data having simple characteristic values and data having a linear structure continuously flowing depending on the type of collected data. In storing these two types of data, the data having the characteristic values are data types suitable for database storage, but the linear structure data is not suitable for storing in the database.

For example, if you store unprocessed data at about 60 signals per second, 216,000 data will accumulate in one hour of measurement. Since the amount of such data can be classified into big data if viewed from a semantic point of view, the original data of the bio signal is stored in Hadoop 130.

3 is an exemplary view of a SOAP message of a web service applied to an embodiment of the present invention.

The transceiver 110 transmits and receives a message to and from the bio-signal measuring device 101 through a SOAP message as shown in FIG. The transceiver 110 sets a repository in the Hadoop 130 according to the type of raw data of the bio-signal in the SOAP message, and stores the raw data in each repository. For example, such a reservoir or storage space may include an electrocardiogram signal and an acceleration signal.

FIG. 4 is an explanatory diagram illustrating a storing process of the analysis module and module description information in the bio-signal analysis system of FIG. 1 according to the embodiment of the present invention.

First, from the module information 301, the module information 301 includes module description information, input values, output values, and development language information.

The input value means a value in which an input form of data for executing the analysis module is defined. The output value is a value for showing the output form of the analysis module.

Also, the development language information includes information about the development language in which the language in which the analysis module is programmed is defined.

The module management engine unit 120 may include a definition module 121 for defining an analysis module and a search module 122 for searching for an analysis module. The module management engine unit 120 includes module description information of the analysis module, an input value for defining an input form of data for executing the analysis module, an output value for showing an output form of the analysis module, The analysis module may be defined using the module information 301 including the developed language information and the defined analysis module may be stored in the module repository 132 of the Hadoop distributed file system 131. [

On the other hand, the continuous linear structure has no meaning by the raw data itself. Such raw data can be obtained by firstly processing the raw data to obtain effective processed data. In order to process with effective processing data, it is necessary to process data using analysis module. In order to process various raw data, the input value and the output value of the analysis module must be accurately specified through the module information 301 of the accurately specified analysis module.

To this end, the bio-signal analysis system 100 according to the embodiment of the present invention can freely apply modules for analysis of big data by applying analysis modules developed in various languages.

In order to specify such an analysis module, in the embodiment of the present invention, a module management engine unit 120 for defining the module information 301 is defined. The module management engine unit 120 uses the module information 301 including description (definition) information of the module, input value, output value, and development language information. In the input value, the input form of the data necessary for applying the module is defined, and the output form of the output result is defined in the output value.

5 is an exemplary diagram of development language information in which a language in which the analysis module according to the present embodiment is programmed is defined.

The module development method is developed with various languages and tools. Matlab as shown in FIG. 5 is widely used as a commonly used language. It is also being developed in development languages such as C, C ++, Java, and R programming. That is, the development language information defines in which language the analysis module is developed.

6 is an illustration of processed data stored in a repository of each of the data warehouses according to an embodiment of the present disclosure;

For example, the module management engine unit 120 according to the embodiment of the present invention inserts an analysis module that extracts heart rate variability (HRV) from raw data of an electrocardiogram signal. Electrocardiogram (ECG) signals record the electrical activity of the heart and are meaningless signals from the raw data of electrocardiogram signals. Electrocardiogram (ECG) signals are signals that can be used to identify various heart diseases or conditions of a measurer using normal electrical patterns.

The transmission / reception unit 110 receives the HRV extraction module from the analysis module through the SOAP message, and the module management engine unit 120 specifies or defines the HRV extraction module, which is the analysis module, and stores it in Hadoop 130.

After that, the module interlocking engine unit 134 may apply the HRV extraction module stored in the Hadoop 130 to store the processed data in the data warehouse 135 in the respective repositories with respect to the processed data, as shown in FIG.

That is, the transceiver 110 transmits and receives developed analysis modules through a SOAP message. The SOAP message includes the development language information, the type of the biological signal, the input value, the output value, the module information, and the implemented analysis module. The transmission / reception unit 110 analyzes the SOAP message and stores the development language information, the type of the living body signal, the input and result values, and the module description information for the analysis module in the module management engine unit 120 for accurate specification of the analysis module .

Thereafter, the module management engine unit 120 stores the implemented analysis module in the storage area of the module store, that is, Hadoop 130. [

Meanwhile, the data warehouse 135 is a tool for analyzing big data and typically has a hive or a tajo. Big data analysis tools provide data summarization, query and analysis capabilities. Data retrieval and analysis tasks can be performed easily using SQL-like language, SQL-On-Hadoop (SQL-On-Hadoop). In addition, the structure for storing data is expressed in a table form. All data for tables and partitions is stored in the hive meta store.

FIG. 7 is an explanatory diagram of a process data generation process performed by the module interlocking engine unit in the bio-signal analysis system of FIG. 1 according to the embodiment of the present invention.

The module interlocking engine unit 134 fetches the raw data stored in the raw data or the processed data stored in advance in the data warehouse 135 according to the input value in the module information of the analysis module retrieved from the module management engine unit 120 . The module interworking engine 134 processes the data according to the development language information of the module information to generate processing data.

The analysis module retrieved through the module management engine unit 120 is applied in the module interlocking engine unit 134 to extract the processed data and stores the extracted data in the data warehouse 135. [ The analysis module to be applied to the module interlocking engine unit 134 is searched through the search module of the module management engine unit 120. At this time, the retrieved analysis module is called from the module store to the module interlocking engine unit 134. The analysis module confirms the input value specified in the module information, applies data corresponding to the analysis module as an input value, and stores the resultant value in the data warehouse 135.

That is, in order to utilize the modules stored in the module repository, the retrieval module of the module management engine unit 120 searches the desired analysis module through the module information of the analysis module included in the SOAP message of the client. Second, the retrieved analysis module fetches raw data or processed data according to the input value required. The raw data is fetched from the data stored in Hadoop 130 and the processed data is fetched from the data warehouse 135 and applied to the analysis module. After confirming the input value to the analysis module, the module interworking engine 134 for applying the analysis module processes the processor according to the language in which the analysis module is implemented. The resultant value of the processed analysis module is stored in the data warehouse 135 as processed data.

For example, an analysis module for extracting HRV from electrocardiogram data is applied. Check module information and HRV extraction module to extract HRV. An input value of the module information, an output value, and information on the development language, and applies the HRV extraction module searched by the module interworking engine 134. For example, the HRV extraction module developed in Matlab is extracted from the bio-signal analysis system 100 using a library for executing Matlab. And stores the resultant value in the data warehouse 135.

8 is an explanatory diagram illustrating a process of generating processed data by applying a plurality of analysis modules according to an embodiment of the present invention.

The module interlocking engine unit 134 can sequentially generate a plurality of processing data by sequentially applying a plurality of analysis modules. Specifically, the module interlocking engine unit 134 loads the previously machined N-1-th machining data according to the module information of the N-th order analysis module. Then, the module interlocking engine unit 134 converts the loaded N-1 st order machining data into an N-th order analysis module and converts the N-th order machining data into an output value have.

For example, the module interlocking engine unit 134 processes the raw data of the bio-signal stored in the Hadoop distributed file system 131 using the primary analysis module to generate primary processing data. Thereafter, the module interlocking engine unit 134 checks the storage position of the primary processing data according to the module information of the secondary analysis module, and recalls the primary processing data. Subsequently, the module interlocking engine unit 134 may convert the imported primary processing data into an input value of the module information, apply the same to the secondary analysis module, and generate the newly processed secondary processing data as an output value.

In this manner, in order to extract another processed secondary processing data by using the processed primary processing data, all the services are not possible with only one analysis module. Accordingly, the module interlocking engine unit 134 can combine various kinds of analysis modules to extract new processed secondary or Nth order processing data.

That is, the module interlocking engine unit 134 can search a plurality of analysis modules and identify required analysis modules and combine them. For example, the module interlocking engine unit 134 includes an HRV extracting module for extracting the HRV 802 from the electrocardiogram 801 and an SDNN extracting module 803 for extracting SDNN (Standard Deviation of NN Interval) To bring the SDNN value 803 as a result value.

More specifically, the bio-signal analysis system 100 searches the analysis modules through the web service to check the module information of the required analysis module, and then applies the analysis module according to the input value and the result value for module application .

For example, the HRV extraction module for extracting the HRV 802 from the electrocardiogram 801 confirms that the input value is the electrocardiogram 801 and the resultant value is the HRV 802. Thereafter, the SDNN extraction module for extracting the SDNN value 803 from the HRV 802 fetches the HRV value 802 through the web service and applies it to the analysis module if the input value is the HRV 802.

FIG. 9 is a flowchart of a bio-signal analysis method based on an analysis module according to an embodiment of the present invention.

The bio-signal analysis system 100 receives the raw data of the bio-signal measured by the bio-signal measuring device 101 through the web service (S901).

Then, the bio-signal analysis system 100 identifies the data repository according to the type of the bio-signal and designates the location of the data repository (S902).

Then, the bio-signal analysis system 100 defines an analysis module according to the predefined module information, and stores the defined analysis module in the module repository (S903).

Thereafter, the bio-signal analysis system 100 searches the analysis module according to module information to be searched among the defined analysis modules (S904).

Then, the bio-signal analysis system 100 generates raw data by processing the raw data using the retrieved analysis module (S905).

The bio-signal analysis system 100 stores the generated processing data in the data warehouse 135 (S906).

Then, the bio-signal analysis system 100 provides the generated processed data as a result of the bio-signal analysis through the web service (S907).

It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit or essential characteristics thereof. Therefore, the embodiments disclosed in the present invention are intended to illustrate rather than limit the scope of the present invention, and the scope of the technical idea of the present invention is not limited by these embodiments. The scope of protection of the present invention should be construed according to the following claims, and all technical ideas within the scope of equivalents should be construed as falling within the scope of the present invention.

100: Biological signal analysis system
101: Bio-signal measuring device
102: user terminal
110: Transmitting /
120: module management engine section
130: Hadoop
131: Hadoop Distributed File System (HDFS)
132: module storage unit
133: Primitive data storage unit
134: module interlocking engine part
135: Data Warehouse
140: Service Offering
121: Definition module
122: Search module

Claims (15)

A transmitting and receiving unit for receiving raw data of biological signals measured by a bio-signal measuring device through a web service, identifying a data storage according to a type of a bio-signal, and designating a location of the data storage;
A module management engine unit for defining an analysis module in accordance with the predefined module information and searching an analysis module according to module information to be searched out among the defined analysis modules;
Storing the defined analysis module in a module repository, storing raw data of the received bio-signal in a data repository, processing the stored raw data by applying the retrieved analysis module to generate processed data, A Hadoop distributed file system (HDFS) that stores data in a data warehouse; And
A service providing unit for providing the generated processing data through the web service of the transmitter /
A bio-signal analysis system based on an analysis module. The method according to claim 1,
The transmitting /
A bio-signal measuring device for receiving a SOAP message including raw data of a bio-signal, parsing the received SOAP message using a parsing library, and extracting the raw data from the parsed data, Signal analysis system. The method according to claim 1,
The transmitting /
A bio-signal analysis system based on an analysis module that receives raw data of a bio-signal of at least one of an ECG signal, an acceleration signal, a respiration signal, and a blood coral saturation signal, which are atypical data based on Big Data. The method according to claim 1,
The module management engine unit
A module including description information of the module of the analysis module, an input value for defining an input form of data for executing the analysis module, an output value for showing an output form of the analysis module, and development language information in which the analysis module is programmed Wherein the analysis module is defined using the information and the defined analysis module is stored in the module repository of the Hadoop distributed file system. The method according to claim 1,
The Hadoop distributed file system
And generating a data store in the Hadoop repository according to the type of the raw data and storing the raw data in the generated data repository. The method according to claim 1,
The Hadoop distributed file system
A module storage unit for storing the analysis module defined in the module repository;
A raw data storage unit for storing the raw data of the received bio-signal in a data storage;
A module interlocking engine unit for processing raw data of the stored bio-signals to generate processed data by applying the searched analysis module; And
A data warehouse < RTI ID = 0.0 >
A bio-signal analysis system based on an analysis module. The method according to claim 6,
The module interlocking engine unit
The raw data stored in the raw data or the processed data stored in advance in the data warehouse is fetched in accordance with the input value in the module information of the searched analysis module and the processed data is processed according to the development language information of the module information, A bio-signal analysis system based on the generated analysis module. The method according to claim 6,
The module interlocking engine unit
Order machining data is generated by sequentially applying a plurality of analysis modules to each of the plurality of analysis modules, and the previously machined N-first order machining data is loaded in accordance with the module information of the N-order analysis module, The analysis module-based bio-signal analysis system that converts the data according to the input value of the module and applies it to the N-dimensional analysis module to generate the newly processed N-dimensional processed data as the output value. Receiving raw data of a bio-signal measured by a bio-signal measuring device through a web service, determining a data store according to a type of the bio-signal, and designating a location of the data store;
Defining an analysis module according to the predefined module information, and storing the defined analysis module in a module repository;
Searching an analysis module according to module information to be searched among the defined analysis modules;
Processing the stored raw data by applying the searched analysis module to generate processed data and storing the generated processed data in a data warehouse; And
Providing the generated processed data as a result of analyzing the biological signal through a web service
Wherein the bio-signal analyzing module comprises: 10. The method of claim 9,
The step of specifying the location of the data repository
A bio-signal measuring device for receiving a SOAP message including raw data of a bio-signal, parsing the received SOAP message using a parsing library, and extracting the raw data from the parsed data, Signal analysis method. 10. The method of claim 9,
The step of specifying the location of the data repository
A bio-signal analysis method based on an analysis module that receives raw data of a bio-signal of at least one of an ECG signal, an acceleration signal, a breathing signal, and a blood coral saturation signal, which are atypical data based on a big data. 10. The method of claim 9,
The step of storing in the module store
A module including description information of the module of the analysis module, an input value for defining an input form of data for executing the analysis module, an output value for showing an output form of the analysis module, and development language information in which the analysis module is programmed A bio-signal analysis method based on an analysis module that defines an analysis module using information and stores the defined analysis module in a module repository of the Hadoop distributed file system. 10. The method of claim 9,
The step of storing in the data warehouse
Generating a data store in the Hadoop repository according to the type of the raw data, and storing the raw data in the generated data repository. 12. The method of claim 11,
The step of storing in the data warehouse
The raw data stored in the raw data or the processed data stored in advance in the data warehouse is fetched in accordance with the input value in the module information of the searched analysis module and the processed data is processed according to the development language information of the module information, A method for analyzing a bio signal based on an analysis module to be generated. 12. The method of claim 11,
The step of storing in the data warehouse
Further comprising the step of sequentially applying a plurality of analysis modules to generate a plurality of processed data,
Wherein the step of generating the plurality of pieces of processed data includes the steps of retrieving the previously processed N-1th order processed data according to the module information of the Nth order analysis module, converting the N-1th order processed data into an input value of the N- The analysis module based bio signal analysis method is applied to the Nth order analysis module to generate the newly processed Nth order processed data as an output value.
KR1020160019891A 2016-02-19 2016-02-19 System and method for analyzing bio-signal using data analysis module KR101827088B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020160019891A KR101827088B1 (en) 2016-02-19 2016-02-19 System and method for analyzing bio-signal using data analysis module

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020160019891A KR101827088B1 (en) 2016-02-19 2016-02-19 System and method for analyzing bio-signal using data analysis module

Publications (2)

Publication Number Publication Date
KR20170098027A true KR20170098027A (en) 2017-08-29
KR101827088B1 KR101827088B1 (en) 2018-03-22

Family

ID=59760092

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020160019891A KR101827088B1 (en) 2016-02-19 2016-02-19 System and method for analyzing bio-signal using data analysis module

Country Status (1)

Country Link
KR (1) KR101827088B1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20190054741A (en) * 2017-11-14 2019-05-22 주식회사 케이티 Method and Apparatus for Quality Management of Data

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20190054741A (en) * 2017-11-14 2019-05-22 주식회사 케이티 Method and Apparatus for Quality Management of Data

Also Published As

Publication number Publication date
KR101827088B1 (en) 2018-03-22

Similar Documents

Publication Publication Date Title
US7660783B2 (en) System and method of ad-hoc analysis of data
EP2919133A1 (en) Method and system for identifying a sensor to be deployed in a physical environment
Anderson et al. Synthetic data generation for the internet of things
Malik et al. Big-data: transformation from heterogeneous data to semantically-enriched simplified data
US20090112903A1 (en) Ontology data import/export method and apparatus
CN105723366B (en) Method for preparing a system for searching a database and system and method for executing a query to a connected data source
CN104951539A (en) Internet data center harmful information monitoring system
EA201300375A1 (en) THE METHOD OF ORGANIZING A SEARCH DATABASE USING FUZZY CRITERIA
WO2020139079A1 (en) System and method for analyzing heterogeneous data by utilizing data virtualization components
CN109684402A (en) One kind being based on big data platform metadata genetic connection implementation method
KR20160125543A (en) User-oriented healthcare big data service method, computer program and system
TW201415254A (en) Method and system for recommending semantic annotations
US9230210B2 (en) Information processing apparatus and method for obtaining a knowledge item based on relation information and an attribute of the relation
Akhtar et al. The impact of big data in healthcare analytics
Lee et al. A data acquisition architecture for healthcare services in mobile sensor networks
Wu et al. A workflow to convert live atmospheric sensor data into linked data
KR101827088B1 (en) System and method for analyzing bio-signal using data analysis module
KR101684579B1 (en) System and method for generating knowledge
CN103020189B (en) Data processing equipment and data processing method
US8856152B2 (en) Apparatus and method for visualizing data
JP2012059212A (en) Extraction apparatus, extraction method and extraction program
KR20200086586A (en) Knowledge extraction system using frame based on ontology
CN114121217A (en) Operating room scheduling method, device, equipment and storage medium
Malik et al. Ontology and Web Usage Mining towards an Intelligent Web focusing web logs
Erbach Data-centric view in e-Science information systems

Legal Events

Date Code Title Description
A201 Request for examination
E902 Notification of reason for refusal
E701 Decision to grant or registration of patent right
GRNT Written decision to grant