Data acquisition system and method for large-scale scoliosis screening

Abstract

The invention discloses a data acquisition system and method for large-scale scoliosis screening, the system comprises a wearable device, a data acquisition device and a data processing device, the data acquisition device comprises a data collection module used for responding to a data collection instruction sent by an external system installed in the data processing device, collecting multi-channel time sequence signal data collected by the wearable device; the communication module is used for transmitting the acquired multi-channel time sequence signal data to the data processing device; a data intelligent processing module in the data processing device is used for processing the multi-channel time sequence signal data to generate a time sequence data broken line graph and generating a scoliosis prediction analysis result by adopting a deep learning method; and the data visualization module is used for visually displaying the time sequence data broken line graph and the scoliosis prediction analysis result at the front end of a webpage. According to the system provided by the invention, the data of the wearable device can be efficiently collected, and the data can be visually displayed.

Description

Technical Field

[0001] The present invention relates to the field of human-computer interaction technology, and in particular to a data acquisition system and method for large-scale screening of scoliosis. Background Art

[0002] In today's technological landscape, embedded wearable devices have become an integral part of people's lives, widely used in health monitoring, fitness tracking, smart wearables, and other applications. These wearable devices typically collect information such as the user's physiological parameters and fitness data, and transmit this data to external systems for analysis and processing via technologies such as Bluetooth. With the development of artificial intelligence and big data technologies, data collection and intelligent processing are becoming increasingly important. Traditional data collection methods can suffer from low data transmission efficiency, low processing efficiency, and unintuitive data visualization.

[0003] Scoliosis is a common condition during adolescent growth and development, and it can be difficult to detect in its early stages. Adolescents are in a critical period of physical growth and development, and if left untreated, it can cause irreversible damage to the spine. Common screening methods involve X-rays or CT scans, which inevitably expose patients to radiation, increase physician workload, and significantly waste medical resources. With the advancement of computer technology, computer-assisted diagnosis (CAD) has become an important tool for assisting physicians in diagnosis. Summary of the Invention

[0004] The purpose of the embodiments of the present invention is to provide a data acquisition system and method for large-scale screening of scoliosis, so as to solve the problems of low efficiency and non-intuitive data visualization in existing data acquisition methods.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] An embodiment of the present invention provides a data acquisition system for large-scale screening of scoliosis, wherein the data acquisition system for large-scale screening of scoliosis includes: a wearable device, a data acquisition device, and a data processing device, wherein the data acquisition device includes:

[0007] a data collection module, configured to collect the multi-channel time series signal data collected by the wearable device in response to a data collection instruction sent by an external system installed in the data processing apparatus;

[0008] a communication module, configured to transmit the collected multi-channel timing signal data to the data processing device;

[0009] The data processing device includes the data intelligent processing module and the data visualization module;

[0010] The data intelligent processing module is used to process the multi-channel time series signal data to generate a time series data broken line graph, and use a deep learning method to generate a scoliosis prediction analysis result;

[0011] The data visualization module is used to visualize the time series data broken line graph and the scoliosis prediction analysis results on the front end of the web page.

[0012] Optionally, the wearable device includes: a flexible strain-stress sensor, an HC-05 Bluetooth module, and an Arduino kit;

[0013] The Arduino kit includes a battery, a breadboard, a resistor, a switch and an Arduino UNO development board. The Arduino UNO development board is connected to the flexible strain-stress sensor and the HC-05 Bluetooth module through an I / O interface.

[0014] Optionally, the communication module is specifically used to initialize the Bluetooth connection, search for the target wearable device according to the name of the wearable device, establish a connection with the HC-05 Bluetooth module of the target wearable device based on the created Bluetooth socket, receive the multi-channel timing signal data collected by the target wearable device through the Bluetooth communication protocol and transmit the multi-channel timing signal data to the data processing device until the Bluetooth connection is interrupted or the Bluetooth connection is manually closed.

[0015] Optionally, the data intelligent processing module is further configured to store the received multi-channel timing signal data in chronological order.

[0016] Optionally, the data collection module is specifically configured to, upon receiving a data collection instruction sent by an external system installed in the data processing device, call the communication module to establish a Bluetooth connection with a target wearable device, and collect the multi-channel time series signal data collected by the wearable device;

[0017] When a data collection stop instruction is received from an external system installed in the data processing device, the multi-channel timing signal data collected by the wearable device is stopped, the Bluetooth connection is disconnected, and the structured table data is saved; wherein, the web page front end of the data processing device is provided with a start receiving and a stop receiving button, and a data collection instruction is generated when the start receiving button is touched, and a data collection stop instruction is generated when the stop receiving button is touched.

[0018] Optionally, the data intelligent processing module is specifically configured to receive the structured table data and store the structured table data in a list; call an underlying drawing engine to generate a time series data line graph based on the data in the list and preset parameters; and analyze the multi-channel time series signal data of different users using a classification model based on a deep learning method on a user-by-user basis to determine the degree of scoliosis of the user;

[0019] The structured table data includes: multi-channel time series signal data collected by target wearable devices worn by multiple users.

[0020] Optionally, the classification model is trained and generated in the following manner:

[0021] Divide the pre-labeled dataset into training and test sets;

[0022] The training set is input into a preset neural network, and the parameters of the preset neural network are iteratively adjusted using a back-propagation algorithm so that the prediction results of the preset neural network are close to the actual labels of the data in the training set.

[0023] An embodiment of the present invention further provides a data collection method for large-scale scoliosis screening, wherein the method comprises:

[0024] The data acquisition device collects the multi-channel time series signal data collected by the wearable device in response to a data collection instruction sent by an external system installed in the data processing device; and transmits the collected multi-channel time series signal data to the data processing device;

[0025] The data processing device processes the multi-channel time series signal data to generate a time series data line graph, and uses a deep learning method to generate a scoliosis prediction analysis result; the time series data line graph and the scoliosis prediction analysis result are visualized on the front end of the web page.

[0026] Optionally, the wearable device includes: a flexible strain-stress sensor, an HC-05 Bluetooth module, and an Arduino kit;

[0027] The Arduino kit includes a battery, a breadboard, a resistor, a switch and an Arduino UNO development board. The Arduino UNO development board is connected to the flexible strain-stress sensor and the HC-05 Bluetooth module through an I / O interface.

[0028] The data acquisition system for large-scale scoliosis screening provided in an embodiment of the present application includes a wearable device, a data acquisition device, and a data processing device. Furthermore, the data acquisition device includes: a data collection module for collecting multi-channel time series signal data collected by the wearable device in response to a data collection instruction sent by an external system installed in the data processing device; a communication module for transmitting the collected multi-channel time series signal data to the data processing device; the data processing device includes a data intelligent processing module and a data visualization module; the data intelligent processing module is used to process the multi-channel time series signal data to generate a time series data line graph, and use a deep learning method to generate scoliosis prediction analysis results; the data visualization module is used to visualize the time series data line graph and the scoliosis prediction analysis results on a web page front end. The data acquisition system for large-scale scoliosis screening can efficiently and accurately collect and process data transmitted by the wearable device through wireless communication such as Bluetooth connection and intelligent processing technology, and at the same time provide an intuitive time series data line graph and scoliosis prediction analysis results on the web page front end of the data processing device to facilitate user understanding and analysis of the data. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 is a structural block diagram of a data acquisition system for large-scale scoliosis screening according to an embodiment of the present application;

[0030] Figure 2 is a hardware structure diagram of a wearable device provided by an embodiment of the present invention;

[0031] Figure 3 It is a flowchart showing the steps of a data collection method for large-scale screening of scoliosis provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0032] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0033] The data collection solution for large-scale scoliosis screening provided by the embodiments of the present application will be described in detail below with reference to the accompanying drawings through specific embodiments and their application scenarios.

[0034] As attached Figure 1 As shown, the data acquisition system for large-scale scoliosis screening of an embodiment of the present application includes: a wearable device 101, a data acquisition device 102 and a data processing device 103, wherein the data acquisition device 102 includes:

[0035] The data collection module 1021 is used to collect the multi-channel timing signal data collected by the wearable device in response to the data collection instruction sent by the external system installed in the data processing device; the communication module 1022 is used to transmit the collected multi-channel timing signal data to the data processing device.

[0036] The data processing device 103 is equipped with an external system, including a data intelligent processing module 1031 and a data visualization module 1032. The external system controls the functional modules within the data processing device. The data intelligent processing module 1031 processes multi-channel time series signal data to generate a time series data line graph and employs deep learning methods to generate scoliosis prediction and analysis results. The data visualization module 1032 visualizes the time series data line graph and scoliosis prediction and analysis results on a webpage for analysis and further diagnosis by doctors.

[0037] It should be noted that the data acquisition device can be set in the wearable device or exist independently of the wearable device.

[0038] Furthermore, the structural block diagram of the wearable device is as follows Figure 2 As shown, wearable devices (i.e. Figure 2 The wearable device includes a flexible strain-stress sensor, an HC-05 Bluetooth module, and an Arduino kit. The Arduino kit includes a battery, a breadboard, a resistor, a switch, and an Arduino UNO development board. The Arduino UNO development board is connected to the flexible strain-stress sensor and the HC-05 Bluetooth module through an I / O interface.

[0039] It should be noted that the wearable device can be a wristband, headband, or other wearable device. A Bluetooth connection is established between the wearable device and the data acquisition device. The data acquisition device then activates or deactivates the collection of multi-channel time-series signal data based on instructions sent by the data acquisition device. The multi-channel time-series signal data can reflect the scoliosis of the user's spine.

[0040] In an optional embodiment, the communication module 1022 is specifically used to initialize the Bluetooth connection, search for the target wearable device according to the name of the wearable device, establish a connection with the HC-05 Bluetooth module of the target wearable device based on the created Bluetooth socket, receive the multi-channel timing signal data collected by the target wearable device through the Bluetooth communication protocol, and transmit the multi-channel timing signal data to the data processing device until the Bluetooth connection is interrupted or the Bluetooth connection is manually closed. It should be noted that if the target wearable device matching the target device name is not found, a prompt message is output to prompt the user that the target wearable device does not exist. The search for the target wearable device is achieved through Bluetooth pairing.

[0041] A Bluetooth socket is a communication endpoint used for data transmission in Bluetooth communications. Its main functions include: Connection establishment: Through a Bluetooth socket, a device can establish a connection with other Bluetooth devices for data transmission between them. Data transmission: Once a connection is established, the Bluetooth socket can be used to transfer data between devices, including text, files, multimedia, and other types of data. Communication control: Bluetooth sockets provide communication control functions, including sending and receiving data and managing connections, thereby achieving reliable Bluetooth communication.

[0042] The data intelligent processing module 1031 is further configured to arrange and store the received multi-channel time series signal data in chronological order for further data analysis.

[0043] In an optional embodiment, the data collection module 1021 is specifically used to call the communication module to establish a Bluetooth connection with the target wearable device when receiving a data collection instruction sent by an external system installed in the data processing device, and collect the multi-channel timing signal data collected by the wearable device; when receiving a data collection stop instruction sent by the external system installed in the data processing device, stop the multi-channel timing signal data collected by the wearable device, disconnect the Bluetooth connection, and save the structured table data.

[0044] Among them, the front end of the data processing device webpage is provided with start receiving and stop receiving buttons. When the start receiving button is touched, a data collection instruction is generated, and when the stop receiving button is touched, a data collection stop instruction is generated.

[0045] In the actual implementation process, a start receiving button and a stop receiving button are set on the front end of the web page. When the start receiving instruction is issued, the external system is controlled to connect to the target Bluetooth device. The external system will establish a Bluetooth connection with the target wearable device through the data acquisition device, continuously receive the data collected by the target wearable device, and write it into the file. When the stop instruction is issued, the external system is controlled to stop receiving the data collected by the target wearable device, control the data acquisition device to disconnect the Bluetooth connection with the target wearable device, save the structured table data, intelligently process the data collected by the target wearable device and display it visually.

[0046] The data collected by the target wearable device can be regarded as sensor data or as multi-channel time series signal data.

[0047] In an optional embodiment, the data intelligent processing module 1031 is specifically configured to receive the structured table data and store the structured table data in a list; call an underlying drawing engine to generate a time series data line graph based on the data in the list and preset parameters; and analyze the multi-channel time series signal data of different users using a classification model based on deep learning methods on a user-by-user basis to determine the user's degree of scoliosis; the user's scoliosis degree can indicate whether the user is a scoliosis patient and, if so, the severity of the scoliosis. The structured table data includes multi-channel time series signal data collected by target wearable devices worn by multiple users.

[0048] In actual implementation, the intelligent data processing module 1031 reads structured table data, stores it in columns, and then calls the underlying drawing engine to generate a corresponding time series data line graph based on the provided data and parameters. The data is converted into a graphic object and associated with a coordinate system, thereby visualizing the data. The drawing process takes into account the specified style, color, line type, and other parameters to ensure that the generated image meets the user's expectations. Deep learning methods are used to classify data from different users, distinguishing between normal individuals and patients with varying degrees of scoliosis severity.

[0049] Furthermore, generating a corresponding time series data line graph based on the provided data and parameters includes: sorting the measured voltage values ​​according to time, reflecting the time series changes of the motion signal in the form of a line graph, and representing the voltage data from different sensors using lines of different colors.

[0050] In an optional implementation, the data visualization module 1032 returns the deep learning results and time series data graphics to the web page front end for rendering and display, allowing doctors to obtain information more quickly and accurately, and determine whether further diagnosis and treatment are needed based on the prediction results given by the neural network.

[0051] In an optional embodiment, the classification model is trained and generated in the following manner:

[0052] Divide the pre-labeled dataset into training and test sets;

[0053] The training set is input into a preset neural network, and the parameters of the preset neural network are iteratively adjusted using a back-propagation algorithm so that the prediction results of the preset neural network are close to the actual labels of the data in the training set.

[0054] In actual implementation, a doctor-labeled dataset is prepared and divided into training and test sets. An appropriate neural network architecture is selected, and the training data is fed into the neural network. Backpropagation is used to continuously adjust network parameters so that the network's predictions approximate the actual labels. The Inception architecture is introduced to the network to improve its ability to extract information at different scales and represent nonlinear features. By continuously optimizing the model and adjusting parameters, a more accurate and efficient classification model is achieved. After new data is input, the trained classification model generates predictive analysis results, determining whether the patient has scoliosis and, if so, the severity of the scoliosis, assisting doctors in making a diagnosis.

[0055] It can be seen that the data acquisition system for large-scale screening of scoliosis provided in the example of this application realizes a system that integrates data acquisition, data intelligent processing and visualization technology. The system flexibly and controllably collects wearable device signals and performs intelligent data processing to help doctors make auxiliary diagnoses.

[0056] The data acquisition system for large-scale scoliosis screening provided in the embodiment of the present application uses the Django framework to achieve an integrated front-end and back-end design, which is easy to deploy. The web page design is simple, beautiful and fully functional, aiming to provide users with an easy-to-use experience. The user interface design of this system is concise and clear, easy to operate and easy to understand, and provides intuitive interface elements and interaction methods to prevent users from getting lost in complex operations. At the same time, this system avoids excessive information and functions interfering with the user's vision and thinking, and does not use overly professional terms and expressions, ensuring that users can easily understand and operate the system. The response speed is fast, allowing users to obtain feedback and results immediately.

[0057] In addition, the system includes a start receiving button (also known as a start detection button) and a stop receiving button (also known as a notification detection button) on the front-end interface of the data processing device, enabling accurate data collection from wearable devices. It also provides the ability to enter a patient (i.e., user) ID (i.e., identification) to facilitate data collection from different individuals. After stopping detection, the sensor data is intelligently processed, presented as an image, and a neural network prediction result is generated.

[0058] The data acquisition system for large-scale scoliosis screening provided in an embodiment of the present application includes a wearable device, a data acquisition device, and a data processing device. Furthermore, the data acquisition device includes: a data collection module for collecting multi-channel time series signal data collected by the wearable device in response to a data collection instruction sent by an external system installed in the data processing device; a communication module for transmitting the collected multi-channel time series signal data to the data processing device; the data processing device includes a data intelligent processing module and a data visualization module; the data intelligent processing module is used to process the multi-channel time series signal data to generate a time series data line chart, and use a deep learning method to generate scoliosis prediction analysis results; the data visualization module is used to visualize the time series data line chart and scoliosis prediction analysis results on a web page front end. The data acquisition system for large-scale scoliosis screening can efficiently and accurately collect and process data transmitted by wearable devices through wireless communication such as Bluetooth connection and intelligent processing technology, and at the same time provide an intuitive time series data line chart and scoliosis prediction analysis results on the web page front end of the data processing device to facilitate user understanding and analysis of the data.

[0059] As attached Figure 3 As shown, the data collection method for large-scale scoliosis screening in an embodiment of the present application includes the following steps:

[0060] Step 301: The data acquisition device collects multi-channel time series signal data collected by the wearable device in response to a data collection instruction sent by an external system installed in the data processing device.

[0061] The data acquisition system for large-scale scoliosis screening is used to implement the data acquisition method for large-scale scoliosis screening described in the embodiments of this application. The data acquisition system for large-scale scoliosis screening can be widely used in the fields of human-computer interaction and data acquisition, providing a convenient and efficient solution for large-scale scoliosis screening. The data acquisition system for large-scale scoliosis screening includes: a wearable device, a data acquisition device, and a data processing device.

[0062] The wearable device includes: a flexible strain-stress sensor, an HC-05 Bluetooth module, and an Arduino kit;

[0063] The Arduino kit includes a battery, a breadboard, a resistor, a switch and an Arduino UNO development board. The Arduino UNO development board is connected to the flexible strain-stress sensor and the HC-05 Bluetooth module through an I / O interface.

[0064] Step 302: Transmit the collected multi-channel timing signal data to a data processing device.

[0065] Step 303: The data processing device processes the multi-channel time series signal data to generate a time series data broken line graph, and uses a deep learning method to generate a scoliosis prediction analysis result.

[0066] Step 304: Visually display the time series data line graph and the scoliosis prediction analysis results on the front end of the web page.

[0067] For the specific description of each step of the data collection method for large-scale screening of scoliosis in the embodiment of the present application, please refer to the description in the corresponding embodiment of the data collection system for large-scale screening of scoliosis, and will not be repeated here.

[0068] In the embodiment of the present application Figure 1 The data processing device in the data acquisition system for large-scale scoliosis screening shown is disposed in an electronic device or server. The electronic device or server in which the device is disposed can be a device having an operating system. The operating system can be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the present embodiment.

[0069] The embodiments of the present application provide Figure 1 The data acquisition system for large-scale scoliosis screening shown can achieve Figure 3 To avoid repetition, the various processes implemented in the method embodiment are not described here.

[0070] Optionally, an embodiment of the present application also provides an electronic device, including a processor, a memory, and a program or instruction stored in the memory and executable on the processor. When the program or instruction is executed by the processor, the various processes executed by the above-mentioned system data processing device are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0071] It should be noted that the electronic device in the embodiment of the present application includes the server described above.

[0072] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer-readable storage medium, such as a computer read-only memory (ROM), random access memory (RAM), a magnetic disk, or an optical disk.

[0073] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or apparatus comprising the element.

[0074] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A data acquisition system for large-scale scoliosis screening, characterized in that: The data acquisition system for large-scale scoliosis screening includes: a wearable device, a data acquisition device and a data processing device, wherein the data acquisition device includes: a data collection module, configured to collect the multi-channel time series signal data collected by the wearable device in response to a data collection instruction sent by an external system installed in the data processing apparatus; a communication module, configured to transmit the collected multi-channel timing signal data to the data processing device; The data processing device includes the data intelligent processing module and the data visualization module; The data intelligent processing module is used to process the multi-channel time series signal data to generate a time series data broken line graph, and use a deep learning method to generate a scoliosis prediction analysis result; The data visualization module is used to visualize the time series data broken line graph and the scoliosis prediction analysis results on the front end of the web page.

2. The data acquisition system for large-scale scoliosis screening according to claim 1, characterized in that: The wearable device includes: a flexible strain-stress sensor, an HC-05 Bluetooth module and an Arduino kit; The Arduino kit includes a battery, a breadboard, a resistor, a switch and an Arduino UNO development board. The Arduino UNO development board is connected to the flexible strain-stress sensor and the HC-05 Bluetooth module through an I / O interface.

3. The data acquisition system for large-scale scoliosis screening according to claim 2, characterized in that: The communication module is specifically used to initialize a Bluetooth connection, search for a target wearable device according to the name of the wearable device, establish a connection with the HC-05 Bluetooth module of the target wearable device based on the created Bluetooth socket, receive multi-channel timing signal data collected by the target wearable device through the Bluetooth communication protocol, and transmit the multi-channel timing signal data to the data processing device until the Bluetooth connection is interrupted or the Bluetooth connection is manually closed.

4. The data acquisition system for large-scale scoliosis screening according to claim 1, characterized in that: The data intelligent processing module is further configured to store the received multi-channel timing signal data in chronological order.

5. The data acquisition system for large-scale scoliosis screening according to claim 1, characterized in that: The data collection module is specifically configured to, upon receiving a data collection instruction sent by an external system installed in the data processing device, call the communication module to establish a Bluetooth connection with a target wearable device, and collect the multi-channel time series signal data collected by the wearable device; When a data collection stop instruction is received from an external system installed in the data processing device, the multi-channel timing signal data collected by the wearable device is stopped, the Bluetooth connection is disconnected, and the structured table data is saved; wherein, the web page front end of the data processing device is provided with a start receiving and a stop receiving button, and a data collection instruction is generated when the start receiving button is touched, and a data collection stop instruction is generated when the stop receiving button is touched.

6. The data acquisition system for large-scale scoliosis screening according to claim 5, characterized in that: The data intelligent processing module is specifically used to receive the structured table data and store the structured table data in a list; call the underlying drawing engine to generate a time series data line graph based on the data in the list and preset parameters; Taking users as units, a classification model based on deep learning methods is used to analyze the multi-channel time series signal data of different users to determine the degree of scoliosis of the users; The structured table data includes: multi-channel time series signal data collected by target wearable devices worn by multiple users.

7. The data acquisition system for large-scale scoliosis screening according to claim 6, characterized in that: The classification model is trained and generated in the following way: Divide the pre-labeled dataset into training and test sets; The training set is input into a preset neural network, and the parameters of the preset neural network are iteratively adjusted using a back-propagation algorithm so that the prediction results of the preset neural network are close to the actual labels of the data in the training set.

8. A data collection method for large-scale scoliosis screening, characterized in that: The method comprises: The data acquisition device collects the multi-channel time series signal data collected by the wearable device in response to a data collection instruction sent by an external system installed in the data processing device; and transmits the collected multi-channel time series signal data to the data processing device; The data processing device processes the multi-channel time series signal data to generate a time series data broken line graph, and uses a deep learning method to generate a scoliosis prediction analysis result; the time series data broken line graph and the scoliosis prediction analysis result are visualized on the front end of the web page.

9. The data collection method for large-scale scoliosis screening according to claim 8, characterized in that: The wearable device includes: a flexible strain-stress sensor, an HC-05 Bluetooth module and an Arduino kit; The Arduino kit includes a battery, a breadboard, a resistor, a switch and an Arduino UNO development board. The Arduino UNO development board is connected to the flexible strain-stress sensor and the HC-05 Bluetooth module through an I / O interface.

Images