WO2024055807A1 - 一种心电信号质量评估方法、电子设备及芯片系统 - Google Patents
一种心电信号质量评估方法、电子设备及芯片系统 Download PDFInfo
- Publication number
- WO2024055807A1 WO2024055807A1 PCT/CN2023/113618 CN2023113618W WO2024055807A1 WO 2024055807 A1 WO2024055807 A1 WO 2024055807A1 CN 2023113618 W CN2023113618 W CN 2023113618W WO 2024055807 A1 WO2024055807 A1 WO 2024055807A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- peak
- ecg signal
- signal
- variability
- threshold
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 93
- 230000002159 abnormal effect Effects 0.000 claims abstract description 59
- 238000001914 filtration Methods 0.000 claims description 39
- 238000004590 computer program Methods 0.000 claims description 20
- 238000001303 quality assessment method Methods 0.000 claims description 19
- 230000011218 segmentation Effects 0.000 claims description 18
- 238000011156 evaluation Methods 0.000 abstract description 5
- 230000008569 process Effects 0.000 description 21
- 238000012545 processing Methods 0.000 description 17
- 238000004891 communication Methods 0.000 description 15
- 238000012544 monitoring process Methods 0.000 description 15
- 230000006870 function Effects 0.000 description 12
- 238000007726 management method Methods 0.000 description 11
- 238000012806 monitoring device Methods 0.000 description 11
- 238000004422 calculation algorithm Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000005236 sound signal Effects 0.000 description 9
- 239000012634 fragment Substances 0.000 description 8
- 238000010295 mobile communication Methods 0.000 description 7
- 230000009467 reduction Effects 0.000 description 7
- 230000001575 pathological effect Effects 0.000 description 6
- 230000005856 abnormality Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 230000003183 myoelectrical effect Effects 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 230000000241 respiratory effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000003321 amplification Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000004020 conductor Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000007170 pathology Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
- A61B5/346—Analysis of electrocardiograms
- A61B5/349—Detecting specific parameters of the electrocardiograph cycle
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
- A61B5/346—Analysis of electrocardiograms
- A61B5/349—Detecting specific parameters of the electrocardiograph cycle
- A61B5/352—Detecting R peaks, e.g. for synchronising diagnostic apparatus; Estimating R-R interval
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7221—Determining signal validity, reliability or quality
Definitions
- the present application relates to the field of signal assessment technology, and in particular to an ECG signal quality assessment method, electronic equipment and chip system.
- the ECG signal is a nonlinear, non-stationary and random weak signal, usually with a maximum magnitude of mV; therefore, ECG signal monitoring usually requires the ECG monitoring device to be close to the surface of the living body to collect the body's heart rate. electric signal.
- the ECG signal is very susceptible to interference from the body (for example, myoelectric interference, respiratory interference, etc.) or outside the body (for example, power frequency interference, signal pickup). process, etc.).
- the collected ECG signals may be accompanied by a large amount of noise or abnormal signals (caused by abnormalities in the collection process), causing the ECG signals to be overwhelmed by the noise and/or abnormal signals and lose some of their original characteristics.
- these pathological characteristics may be interfered by noise and/or abnormal signals, resulting in a reduction in the accuracy of the early warning algorithm related to pathological signals.
- this application provides an ECG signal quality assessment method, electronic device and chip system, which can detect normal signals in the ECG signal.
- this application provides a method for evaluating ECG signal quality, which method includes:
- the first ECG signal is a normal signal, where the first threshold is used Represents the abnormal cut-off point of the peak variability feature.
- the first threshold is determined by the peak variability features of multiple ECG signal samples.
- the second threshold is used to represent the abnormal cut-off point of the peak quantity variability feature.
- the second threshold is determined by the peak variability features of multiple ECG signal samples. The peak number variability characteristics of electrical signal samples are determined.
- the peak variability characteristics and peak number variability characteristics of multiple ECG signal samples are counted. Based on the peak variability characteristics of multiple ECG signal samples as an abnormal dividing point, the peak values of multiple ECG signal samples are The quantitative variability feature is used as another abnormal cut-off point; based on the relationship between the peak variability feature and the peak quantitative variability feature of the ECG signal to be evaluated and the two abnormal cut-off points, the type of the ECG signal to be evaluated is determined. This method can accurately distinguish normal signals.
- obtaining the first ECG signal includes:
- peak-related variability features are used as different types of features of the ECG signal. Therefore, in order to improve the accuracy of the features, filtering is required to remove burrs in the ECG signal waveform.
- filtering the original ECG signal includes:
- calculating the peak variability feature and the peak number variability feature of the first ECG signal includes:
- the peak list includes N peaks, where N represents the number of peaks;
- the peak number variability characteristics of the first electrocardiographic signal are obtained according to the peak numbers of the multiple signal segments.
- the embodiment of the present application obtains multiple signal segments by segmenting the first ECG signal, determines the peak variability characteristics of the first ECG signal based on the data characteristics of the peak lists of the multiple signal segments, and determines the peak quantity variability characteristics of the first ECG signal based on the data characteristics of the peak quantities of the multiple signal segments.
- the signal segment includes multiple discrete data points, and calculating the peak list of each signal segment includes:
- the first signal segment is any signal segment in the signal segment
- the peak list of the first signal segment includes one or more first Peak value
- the first peak value is a difference absolute value that is greater than the previous absolute value of the difference, greater than the next absolute value of the difference, and greater than the peak-seeking threshold.
- the peak-seeking threshold is corresponding to multiple signal segments of the first ECG signal. The absolute value of the difference is determined.
- the method for determining the peak-finding threshold includes:
- obtaining the peak variability feature of the first electrocardiogram signal according to the peak value list of multiple signal segments includes:
- obtaining the peak number variability feature of the first ECG signal based on the peak number of the multiple signal segments includes:
- the ratio of the first difference value and the median value is calculated to obtain the peak number variability characteristic of the first electrocardiogram signal.
- the method of determining the first threshold and the second threshold includes:
- the second threshold is obtained based on the peak number variability characteristics of multiple ECG signal samples.
- obtaining the first threshold based on peak variability characteristics of multiple ECG signal samples includes:
- obtaining the second threshold based on the peak number variability characteristics of multiple ECG signal samples includes:
- the method also includes:
- the first ECG signal is an abnormal signal
- the first ECG signal is a noise signal
- the first ECG signal is a noise signal.
- acquiring multiple ECG signal samples includes:
- the method of calculating the peak variability feature of each ECG signal sample is the same as the method of calculating the peak variability feature of the first ECG signal;
- the method of calculating the peak number variability feature of each ECG signal sample is the same as the method of calculating the peak number variability feature of the first ECG signal.
- an electronic device including a processor.
- the processor is configured to run a computer program stored in a memory to implement the steps of any method of the first aspect of this application.
- a chip system including a processor.
- the processor is coupled to a memory.
- the processor executes a computer program stored in the memory to implement the steps of any method of the first aspect of this application.
- a computer-readable storage medium stores a computer program.
- the computer program is executed by one or more processors, the steps of any method of the first aspect of the present application are implemented.
- this application provides a computer program product.
- the computer program product is run on a device, causing the device to perform the steps of the method of any one of the first aspects of the application.
- Figure 1 is a schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present application.
- FIG. 2 is a schematic flow chart of an ECG signal quality assessment method provided by an embodiment of the present application.
- FIG. 3 is a schematic flow chart of the ECG signal feature learning process provided by the embodiment of the present application.
- Figure 4 is a schematic waveform diagram of an ECG signal before filtering provided by an embodiment of the present application.
- Figure 5 is a schematic waveform diagram of a filtered ECG signal provided by an embodiment of the present application.
- Figure 6 is a schematic diagram of the obtained peak points provided by the embodiment of the present application.
- FIG. 7 is a schematic flow chart of the ECG signal quality assessment process provided by the embodiment of the present application.
- Figure 8 is a schematic diagram of the waveforms of four signal segments before filtering, after filtering and at peak points provided by the embodiment of the present application;
- Figure 9 shows the classification results of four ECG signals and more signal segments provided by the embodiment of the present application.
- one or more refers to one, two or more than two; "and/or” describes the association relationship of associated objects, indicating that three relationships can exist; for example, A and/or B can mean: A alone exists, A and B exist simultaneously, and B exists alone, where A and B can be singular or plural.
- the character "/" generally indicates that the related objects are in an "or” relationship.
- the ECG signal quality assessment method provided by the embodiments of the present application can be applied to electronic devices such as ECG monitoring equipment and wearable devices. Of course, it can also be applied to electronic devices such as mobile phones connected to the ECG monitoring device.
- the embodiments of this application do not limit the specific type of electronic equipment.
- FIG. 1 shows a schematic structural diagram of an electronic device.
- the electronic device 100 may include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2 , mobile communication module 150, wireless communication module 160, audio module 170, speaker 170A, receiver 170B, microphone 170C, headphone interface 170D, Sensor module 180, button 190, motor 191, camera 193, display screen 194, and subscriber identification module (subscriber identification module, SIM) card interface 195, etc.
- the sensor module 180 may include a pressure sensor 180A, a touch sensor 180K, etc.
- the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the electronic device 100 .
- the electronic device 100 may include more or fewer components than shown in the figures, or some components may be combined, some components may be separated, or some components may be arranged differently.
- the components illustrated may be implemented in hardware, software, or a combination of software and hardware.
- the processor 110 may include one or more processing units.
- the processor 110 may include an application processor (application processor, AP), a modem processor, a graphics processing unit (GPU), and an image signal processor. (image signal processor, ISP), controller, memory, video codec, digital signal processor (digital signal processor, DSP), baseband processor, and/or neural-network processing unit (NPU) wait.
- application processor application processor, AP
- modem processor graphics processing unit
- GPU graphics processing unit
- image signal processor image signal processor
- ISP image signal processor
- controller memory
- video codec digital signal processor
- DSP digital signal processor
- baseband processor baseband processor
- NPU neural-network processing unit
- different processing units can be independent devices or integrated in one or more processors.
- the controller may be the nerve center and command center of the electronic device 100 .
- the controller can generate operation control signals based on the instruction operation code and timing signals to complete the control of fetching and executing instructions.
- the processor 110 may also be provided with a memory for storing instructions and data.
- the memory in processor 110 is cache memory. This memory may hold instructions or data that have been recently used or recycled by processor 110 . If the processor 110 needs to use the instructions or data again, it can be called directly from the memory. Repeated access is avoided and the waiting time of the processor 110 is reduced, thus improving the efficiency of the system.
- the USB interface 130 is an interface that complies with the USB standard specification, and may be a Mini USB interface, a Micro USB interface, a USB Type C interface, etc.
- the USB interface 130 can be used to connect a charger to charge the electronic device 100, and can also be used to transmit data between the electronic device 100 and peripheral devices.
- the external memory interface 120 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device 100.
- the external memory card communicates with the processor 110 through the external memory interface 120 to implement a data storage function. For example, files such as music and videos can be stored in the external memory card.
- Internal memory 121 may be used to store computer executable program code, which includes instructions.
- the processor 110 executes instructions stored in the internal memory 121 to execute various functional applications and data processing of the electronic device 100 .
- the internal memory 121 may include a program storage area and a data storage area. Among them, the stored program area can store the operating system and at least one application program required for a function (such as a sound playback function, an image playback function, etc.).
- the internal memory 121 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc.
- non-volatile memory such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc.
- the charging management module 140 is used to receive charging input from the charger.
- the charger can be a wireless charger or a wired charger.
- the charging management module 140 may receive charging input from the wired charger through the USB interface 130 .
- the power management module 141 is used to connect the battery 142, the charging management module 140 and the processor 110.
- the power management module 141 receives input from the battery 142 and/or the charging management module 140, and supplies power to the processor 110, internal memory 121, external memory, display screen 194, camera 193, wireless communication module 160, etc.
- the power management module 141 may also be provided in the processor 110 . In other implementations In this example, the power management module 141 and the charging management module 140 can also be provided in the same device.
- the wireless communication function of the electronic device 100 can be implemented through the antenna 1, the antenna 2, the mobile communication module 150, the wireless communication module 160, the modem processor and the baseband processor.
- Antenna 1 and Antenna 2 are used to transmit and receive electromagnetic wave signals.
- Each antenna in electronic device 100 may be used to cover a single or multiple communication frequency bands. Different antennas can also be reused to improve antenna utilization. For example: Antenna 1 can be reused as a diversity antenna for a wireless LAN. In other embodiments, antennas may be used in conjunction with tuning switches.
- the mobile communication module 150 can provide solutions for wireless communication including 2G/3G/4G/5G applied on the electronic device 100 .
- the mobile communication module 150 may include at least one filter, switch, power amplifier, low noise amplifier (LNA), etc.
- the mobile communication module 150 can receive electromagnetic waves through the antenna 1, perform filtering, amplification and other processing on the received electromagnetic waves, and transmit them to the modem processor for demodulation.
- the mobile communication module 150 can also amplify the signal modulated by the modem processor and convert it into electromagnetic waves through the antenna 1 for radiation.
- the wireless communication module 160 can provide applications on the electronic device 100 including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) network), Bluetooth (bluetooth, BT), and global navigation satellites. Wireless communication solutions such as global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared technology (infrared, IR), etc.
- the wireless communication module 160 may be one or more devices integrating at least one communication processing module.
- the wireless communication module 160 receives electromagnetic waves via the antenna 2 , frequency modulates and filters the electromagnetic wave signals, and sends the processed signals to the processor 110 .
- the wireless communication module 160 can also receive the signal to be sent from the processor 110, frequency modulate it, amplify it, and convert it into electromagnetic waves through the antenna 2 for radiation.
- the antenna 1 of the electronic device 100 is coupled to the mobile communication module 150, and the antenna 2 is coupled to the wireless communication module 160, so that the electronic device 100 can communicate with the network and other devices through wireless communication technology.
- the electronic device 100 can implement audio functions through the audio module 170, the speaker 170A, the receiver 170B, the microphone 170C, the headphone interface 170D, and the application processor. Such as music playback, recording, etc.
- the audio module 170 is used to convert digital audio signals into analog audio signal outputs, and is also used to convert analog audio inputs into digital audio signals. Audio module 170 may also be used to encode and decode audio signals. In some embodiments, the audio module 170 may be provided in the processor 110 , or some functional modules of the audio module 170 may be provided in the processor 110 .
- Speaker 170A also called “speaker” is used to convert audio electrical signals into sound signals.
- the electronic device 100 can listen to music through the speaker 170A, or listen to hands-free calls.
- Receiver 170B also called “earpiece” is used to convert audio electrical signals into sound signals.
- the electronic device 100 answers a call or a voice message, the voice can be heard by bringing the receiver 170B close to the human ear.
- Microphone 170C also called “microphone” or “microphone” is used to convert sound signals into electrical signals. When making a call or sending a voice message, the user can speak close to the microphone 170C with the human mouth and input the sound signal to the microphone 170C.
- the electronic device 100 may be provided with at least one microphone 170C. In other embodiments, the electronic device 100 may be provided with two microphones 170C, which in addition to monitoring voice information, may also implement a noise reduction function. In other embodiments, the electronic device 100 can also be provided with three, four or more microphones 170C to collect sound signals, reduce noise, identify sound sources, and implement directional recording functions, etc.
- the headphone interface 170D is used to connect wired headphones.
- the headphone interface 170D can be a USB interface 130, or a 3.5mm open mobile terminal platform (OMTP) standard interface, United States Cellular telecommunications industry association of the USA (CTIA) standard interface.
- OMTP open mobile terminal platform
- CTIA United States Cellular telecommunications industry association of the USA
- the pressure sensor 180A is used to sense pressure signals and can convert the pressure signals into electrical signals.
- the pressure sensor 180A may be disposed on the display screen 194 .
- pressure sensors 180A such as resistive pressure sensors, inductive pressure sensors, capacitive pressure sensors, etc.
- a capacitive pressure sensor may include at least two parallel plates of conductive material.
- the electronic device 100 determines the intensity of the pressure based on the change in capacitance.
- the electronic device 100 detects the strength of the touch operation according to the pressure sensor 180A.
- the electronic device 100 may also calculate the touched position based on the detection signal of the pressure sensor 180A.
- Touch sensor 180K also called “touch panel”.
- the touch sensor 180K can be disposed on the display screen 194.
- the touch sensor 180K and the display screen 194 form a touch screen, which is also called a "touch screen”.
- the touch sensor 180K is used to detect a touch operation on or near the touch sensor 180K.
- the touch sensor can pass the detected touch operation to the application processor to determine the touch event type.
- Visual output related to the touch operation may be provided through display screen 194 .
- the touch sensor 180K may also be disposed on the surface of the electronic device 100 at a location different from that of the display screen 194 .
- the buttons 190 include a power button, a volume button, etc.
- Key 190 may be a mechanical key. It can also be a touch button.
- the electronic device 100 may receive key inputs and generate key signal inputs related to user settings and function control of the electronic device 100 .
- the motor 191 can generate vibration prompts.
- the motor 191 can be used for vibration prompts for incoming calls and can also be used for touch vibration feedback.
- the electronic device 100 implements display functions through a GPU, a display screen 194, an application processor, and the like.
- the GPU is an image processing microprocessor and is connected to the display screen 194 and the application processor. GPUs are used to perform mathematical and geometric calculations for graphics rendering.
- Processor 110 may include one or more GPUs that execute program instructions to generate or alter display information.
- the display screen 194 is used to display images, videos, etc.
- the electronic device 100 may include 1 or N display screens 194, where N is a positive integer greater than 1.
- Camera 193 is used to capture still images or video.
- the electronic device 100 may include 1 or N cameras 193, where N is a positive integer greater than 1.
- the SIM card interface 195 is used to connect a SIM card.
- the SIM card can be connected to or separated from the electronic device 100 by inserting it into the SIM card interface 195 or pulling it out from the SIM card interface 195 .
- the electronic device 100 may support 1 or N SIM card interfaces, where N is a positive integer greater than 1.
- the embodiments of the present application do not specifically limit the specific structure of the execution body of an ECG signal quality assessment method. As long as the code of the ECG signal quality assessment method provided by the embodiments of the present application can be recorded by running, the method can be implemented according to the present application.
- the ECG signal quality assessment method provided in the embodiment can be used for processing.
- the execution subject of an ECG signal quality assessment method provided in the embodiment of the present application may be a functional module in an electronic device that can call and execute a program, or a processing device, such as a chip, applied in the electronic device.
- the ECG signal is a nonlinear, non-stationary and random weak signal, usually with a maximum magnitude of mV; therefore, ECG signal monitoring usually requires the ECG monitoring device to be close to the surface of the living body to collect the body's heart rate. electric signal.
- the ECG signal is very susceptible to interference from the body (for example, myoelectric interference, respiratory interference, etc.) or outside the body (for example, power frequency interference, signal pickup). process, etc.). Therefore, the collected ECG signals may be accompanied by a large amount of noise or abnormal signals (abnormalities occur during the collection process).
- the ECG signal often leads to), causing the ECG signal to be overwhelmed by noise and/or abnormal signals and lose some of its original characteristics.
- these pathological characteristics may be interfered by noise and/or abnormal signals, resulting in a reduction in the accuracy of the early warning algorithm related to pathological signals.
- embodiments of the present application provide an ECG signal quality assessment method that can detect normal signals in the ECG signal, so that pathology-related early warning can be performed based on the detected normal signals.
- the ECG signal quality assessment algorithm provided by the embodiments of the present application can be applied to electronic devices used for ECG monitoring. Since the wearable ECG monitoring device needs to be worn on the living body when monitoring ECG signals, the wearing method of the wearable ECG monitoring device may not be standardized or may not fully meet the requirements for ECG monitoring. Therefore, the ECG signals monitored by wearable ECG monitoring equipment are more likely to be contaminated by noise or abnormal signals. Therefore, the embodiments of the present application are more suitable for wearable ECG monitoring equipment.
- the ECG signal quality assessment method uses the peak variability feature and the peak number variability feature of the ECG signal as features to evaluate whether the ECG signal is a normal signal, an abnormal signal, or a noise signal.
- the normal signal in the embodiment of the present application may or may not contain pathological characteristics. Whether it contains pathological characteristics depends on the physical condition of the organism itself.
- Abnormal signals are ECG signals collected due to abnormalities in the collection process caused by errors in wearing wearable ECG monitoring equipment; noise signals are various noises during the testing process.
- the final evaluation as a normal signal does not mean that the normal signal does not contain abnormal points and noise points; it is just that the abnormal points and/or noise points contained are not enough to affect the subsequent processing of the signal.
- the final evaluation as a noise signal does not mean that the noise signal does not contain normal points and abnormal points. However, it contains fewer normal points and/or abnormal points, and most of them are noise points.
- the final evaluation as an abnormal signal does not mean that the abnormal signal does not contain normal points and noise points. However, it contains fewer normal points and/or abnormal points, and most of them are still abnormal points.
- the ECG signal is determined to be normal. signal, abnormal signal or noise signal.
- the electronic device In order to ensure that after the electronic device detects the ECG signal, it can be based on the relationship between the peak variability characteristics of the monitored ECG signal and the abnormal dividing point of the peak variability characteristic, as well as the peak number variability characteristics of the monitored ECG signal. It is related to the abnormal cut-off point of the peak number variability feature. To determine the quality of the monitored ECG signal (normal, abnormal, or noise), it is necessary to determine in advance the abnormal cut-off point of the peak number variability feature and the abnormality of the peak number variability feature. Demarcation point.
- steps A1 to A5 in Figure 2 are for determining the abnormal dividing point of the peak variability feature (which can be recorded as a first threshold) and the abnormal dividing point of the peak quantity variability feature (which can be recorded as a second threshold).
- Step A1 signal collection.
- the embodiment of the present application it is necessary to learn abnormal dividing points for distinguishing different types of ECG signals.
- multiple original ECG signals from multiple people and multiple scenes need to be collected.
- multiple original ECG signals can also be obtained from the original ECG signal sample library.
- the embodiment of the present application does not limit the acquisition method of the original ECG signals.
- Step A2 signal segmentation.
- multiple original ECG signals of multiple people and multiple scenes need to be segmented in the time domain.
- Multiple original ECG signals of fixed duration are obtained to learn abnormal demarcation points from multiple original ECG signals of fixed duration.
- Step A3 signal noise reduction.
- Step A4 feature construction.
- the peak variability feature and the peak number variability feature of multiple ECG signal samples are used as features to distinguish different types of signals.
- Step A5 generate a threshold.
- the abnormal dividing point of the peak variability characteristics is determined, that is, the first threshold
- the abnormal dividing point of the peak variability characteristics that is, the second threshold
- the abnormal dividing points of two features can be determined based on multiple ECG signal samples: the first threshold and the second threshold.
- the first threshold, the second threshold, and the algorithm for generating the peak variability feature and the peak number variability feature may be preset to the electronic device for ECG signal monitoring. middle.
- the electronic device can perform quality assessment on the electrocardiogram signal monitored by the electronic device through the first threshold, the second threshold, and the algorithm used to generate the peak variability feature and the peak quantity variability feature. For details, refer to step B1 to step B5 in Figure 2 .
- Step B1 signal collection.
- the ECG signal can be monitored in real time through electronic equipment.
- Step B2 signal segmentation.
- the signal segmentation method for the real-time monitored ECG signal is the same as step A2. It is also necessary to segment the monitored ECG signal into fixed-duration ECG signals. Among them, the ECG signal after segmentation in step B2 The duration of the signal is the same as the duration of the ECG signal after segmentation in step A2.
- the original ECG signal can be segmented to obtain multiple ECG signals of fixed duration.
- ECG signal of a fixed duration Every time an ECG signal of a fixed duration is collected during the ECG signal monitoring of a living body by an electronic device. Each time an ECG signal of a fixed duration is obtained, the ECG signal is The ECG signal of a fixed duration is obtained for subsequent processing.
- Step B3 signal noise reduction.
- the noise reduction method for the segmented fixed-duration ECG signal is the same as the noise reduction method in step A3.
- Step B4 feature construction.
- step A4 the feature construction method of the noise-reduced fixed-duration ECG signal is the same as in step A4.
- steps B2 to B4 are: generating peak variability characteristics and peak values through a preset in the electronic device.
- the algorithm of value quantity variability feature is the process of calculating the peak variability feature and peak number variability feature of the monitored ECG signal.
- Step B5 threshold comparison.
- the obtained peak variability characteristics and peak signal variability characteristics of the monitored ECG signal can be obtained through steps B1 to B4, the obtained peak variability characteristics are compared with the first threshold preset in the electronic device, and the obtained The peak number variability characteristic is compared with a second threshold preset in the electronic device.
- the monitored ECG signal is an abnormal signal if the peak variability feature of the monitored ECG signal (fixed duration) is greater than the first threshold, and the peak number variability feature of the monitored ECG signal is greater than the second threshold, then the monitored ECG signal is an abnormal signal.
- the monitored ECG signal is the noise signal.
- the monitored ECG signal is the noise signal.
- the monitored ECG signal is a normal signal.
- the embodiment of the present application finds that there are large differences between the peak values and the number of peaks of normal signals, abnormal signals and noise signals of fixed duration. Therefore, the embodiment of the present application divides the ECG signals of fixed duration into The peak variability feature and peak number variability feature of the signal are used as features for classifying ECG signals. Then, by learning the above two characteristics of multiple fixed-duration ECG signals, abnormal cutoff points for classifying ECG signals are obtained. Through the relationship between the above two characteristics of the monitored ECG signal and the abnormal dividing point, the type of the monitored ECG signal is determined.
- the original ECG signal in step A1 can be generated in the A-model electronic device. Collected on electronic equipment, signal classification can be made more accurate through consistent ECG signals.
- the first threshold, the second threshold and the corresponding algorithm for calculating the two features can be Preset on multiple electronic devices of type A, for example, type A electronic device 2, type A electronic device 3, type A electronic device 4...
- model B has the same ECG monitoring device and the ECG monitoring method as the electronic equipment of this model (for example, model A)
- the first threshold and The second threshold and the corresponding algorithm for calculating the two features may be preset in the electronic device of another model.
- FIG. 3 corresponds to step A1 to step A5 in the embodiment shown in FIG. 2 .
- multiple ECG signal samples can be understood as multiple ECG signal samples of a fixed duration that have been obtained through step A1 to step A3 and have been filtered.
- obtaining multiple ECG signal samples includes:
- Step A1 Acquire multiple original ECG signals.
- the multiple raw ECG signals may be raw ECG signals of multiple users and multiple scenarios collected by electronic equipment of the same model (or the ECG monitoring device and the ECG monitoring method are the same).
- Step A2 perform data segmentation on the plurality of original ECG signals to obtain a plurality of original ECG signals of first duration.
- each original ECG signal After acquiring multiple original ECG signals, each original ECG signal needs to be segmented.
- original ECG signals whose total duration is less than the fixed duration will be discarded.
- One or more original ECG signals of fixed duration are segmented from each original ECG signal whose total duration is greater than or equal to a fixed duration, and the fixed duration may be a first duration.
- one original ECG signal of the first duration can be divided into each original ECG signal whose total duration is greater than or equal to the first duration.
- each original ECG signal whose total duration is greater than or equal to the first duration.
- the first duration may be t. Assuming that the sampling rate of the original ECG signal is F s , each original ECG signal of the first duration contains t ⁇ F s discrete data points.
- Step A3 Perform low-pass filtering and high-pass filtering on each original ECG signal of the first duration to obtain the multiple ECG signal samples.
- low-pass filtering and high-pass filtering can be performed on the original ECG signal of the first duration to eliminate burrs in the original ECG signal of the first duration and improve subsequent peak determination and peak number determination. accuracy.
- low-pass filtering can be performed first and then high-pass filtering, or high-pass filtering can be performed first and then low-pass filtering.
- an ⁇ -order low-pass filter is used, where the upper frequency limit of the low-pass filter is F h .
- a ⁇ -order high-pass filter is used, where the lower frequency limit of the high-pass filter is F l .
- Figure 4 is the original ECG signal of the first duration without filtering provided by the embodiment of the present application
- Figure 5 is the filtered ECG signal provided by the embodiment of the present application.
- the embodiment of this application uses high-pass filtering and low-pass filtering as examples of eliminating burrs in the original ECG signal. In actual applications, other filtering methods can also be used to eliminate burrs in the original ECG signal. The embodiments of this application do not limit this.
- the original ECG signals that are greater than or equal to the first duration can be segmented first to obtain multiple original ECG signals of the first duration, and then the original ECG signals of each first duration can be segmented.
- Filtering processing it is also possible to perform filtering processing on the original ECG signals that are greater than or equal to the first duration, to obtain each filtered original ECG signal that is greater than or equal to the first duration, and then filter each original ECG signal that is greater than or equal to the first duration.
- the original ECG signal equal to the first duration is used for signal segmentation.
- the original ECG signal is segmented and filtered to obtain ECG signal samples.
- the duration of these ECG signal samples is the first duration, and these ECG signal samples have been processed by high-pass filtering and low-pass filtering.
- the number of obtained ECG signal samples can be recorded as S.
- S102 Calculate the peak variability characteristics and peak number variability characteristics of each ECG signal sample.
- This step corresponds to step A4 above.
- the embodiment of this application takes the calculation of the peak variability feature and the peak number variability feature of one of the ECG signal samples as an example. In practical applications, the peak variability feature and the peak number variability feature of each ECG signal sample are calculated. Same way.
- Step C1 segment an ECG signal sample to obtain multiple sample fragments of an ECG signal sample.
- the segmentation process in this step is also a non-overlapping segmentation in the time domain.
- each ECG signal sample can be set to divide each ECG signal sample into n sample segments with non-overlapping time domains, then the number of discrete data points contained in each sample segment is The embodiment of this application can denoted as k. That is, each sample segment contains k discrete data points.
- Step C2 calculate the peak list and peak number of each sample fragment.
- the multiple peak points found constitute the peak list Pi of Xi .
- the number of peak points in the peak list of Xi is regarded as the number of peaks Si of Xi . but Among them, S i is used as an example of the peak number.
- the peak list of ECG signal sample Among them, Pi includes Si number of peak points, and the number of peak points of ECG signal sample X is S [S 1 , S 2 ,..., Sn ], where Si is the peak list represented by Pi The number of peak points.
- Figure 6 is a schematic diagram of the peak values of the five sample fragments obtained after dividing the ECG signal sample X into five sample fragments.
- the segmentation line is the segmentation moment when the ECG signal sample
- the peak search threshold TM is related to the ECG signal sample X.
- the peak-finding threshold is determined by the absolute values of differences corresponding to multiple sample segments of the current ECG signal sample. That is, the peak-finding threshold is related to M 1 to M n of multiple sample segments X 1 to X n in the ECG signal sample X.
- This sequence represents a set of absolute values of differences between multiple sample segments of an ECG signal sample.
- TM a 1 *percentile( MBH ,75)-a 2 *percentile( MBH ,25).
- percentile(M BH ,75) represents the 75th percentile of the sequence M BH , that is, the elements in the sequence M BH are arranged from small to large; then the total number of elements Q in the sequence M BH is calculated; from the sorted sequence M BH Select the 75% Q (75% times Q) element, and the percentile( MBH ,75) is the selected element.
- Percentile(M BH ,25) can be obtained in the same way, that is, arrange the elements in the sequence M BH from small to large; then calculate the total number of elements Q in the sequence M BH ; select the 25th% Q from the sorted sequence M BH (25% times Q) elements, the percentile ( MBH , 25) is the selected element.
- 75 and 25 in the above example are only used as examples. In actual applications, they may be the first product of the first quantile and the first constant, and the second product of the second quantile and the second constant.
- other more appropriate values can be selected based on the conditions of the ECG signals collected by the electronic equipment that actually monitors the ECG signals. This value can be obtained through multiple experiments.
- the first constant a 1 and the second constant a 2 in the above example can also be selected as different constants according to the situation. For example, a 1 can be 4 and a 2 can be 3.
- Step C3 Obtain the peak variability characteristics of the ECG signal sample based on the peak lists of multiple sample segments.
- the above example can obtain a peak list of ECG signal sample X
- the data feature value of the peak list of the ECG signal sample X can be used as the peak variability feature of the ECG signal sample.
- f 1 represents the peak variability characteristic of the ECG signal sample X
- std(P) represents the standard deviation of the peaks in the peak list P
- mean(P) represents the mean value of the peaks in the peak list P.
- Step C4 Obtain the peak number variability characteristics of the ECG signal sample based on the peak numbers of the multiple sample segments.
- the data feature value of the peak number of the ECG signal sample X can be used as the peak number variability feature of the ECG signal sample.
- f 2 represents the peak number variability characteristic of the ECG signal sample X
- max(S) represents the maximum value of the peak number in the peak number set S
- min(S) represents the minimum value of the peak number in the peak number set S
- median(S) represents the median value of the peak number in the peak number set S.
- the peak variability characteristics and the peak number variability characteristics of each first duration ECG signal sample can be obtained.
- S103 Obtain the first threshold based on the peak variability characteristics of the multiple ECG signal samples, and obtain the second threshold based on the peak number variability characteristics of the multiple ECG signal samples.
- This step corresponds to step A5 in the embodiment shown in FIG. 2 .
- the embodiment of the present application can obtain W peak variability features and W peak number variability features based on the W ECG signal samples.
- the data feature values of the peak variability feature set are calculated to obtain the abnormal dividing point (first threshold) of the peak variability feature.
- the difference between the third product and the fourth product is calculated to obtain the first threshold.
- the third quantile is the 75th quantile
- the fourth quantile is the 25th quantile
- the third constant is 4, and the fourth constant is 3.
- U 1 4 ⁇ percentile(F 1 ,75)-3 ⁇ percentile(F 1 ,25).
- U 1 is the first threshold indicating the abnormal dividing point of the peak variability feature.
- the abnormal dividing point (second threshold) of the peak number variability feature can be obtained.
- the difference between the fifth product and the sixth product is calculated to obtain the second threshold.
- the fifth quantile is the 75th quantile
- the sixth quantile is the 25th quantile
- the fifth constant is 4
- the sixth constant is 3.
- U 2 4 ⁇ percentile(F 2 ,75)-3 ⁇ percentile(F 2 ,25).
- U 2 is the first threshold indicating the abnormal cut-off point of the peak quantity variability feature.
- the first threshold and the second threshold for classifying the types of monitored electrocardiographic signals can be determined.
- the first threshold, the second threshold and the algorithm model for calculating the peak variability feature and the peak number variability feature are preset into the electronic device.
- Electronic equipment can realize real-time detection of ECG signals and quality assessment of ECG signals.
- FIG 7 a schematic flow chart of an ECG signal quality assessment method provided by an embodiment of the present application is shown. This schematic flow chart is based on the flow chart shown in Figure 3 and corresponds to steps B1 to B5 in the embodiment shown in Figure 2. .
- Step S201 Obtain the first ECG signal.
- Embodiments of the present application can use the ECG monitoring device on the electronic device to measure the ECG signal, and then the electronic device processes the ECG signal to evaluate the quality of the ECG signal.
- the ECG monitoring device sends the measured ECG signal to an electronic device used for ECG signal quality assessment, and another electronic device performs the The quality assessment work, that is, the ECG signal monitoring and ECG signal quality assessment processes can be set up on different electronic devices respectively, and the embodiments of the present application do not limit this.
- acquiring the first ECG signal includes:
- the ECG signal is the original ECG signal; the electronic device can segment and filter the measured original ECG signal to obtain the first ECG signal. This step corresponds to step B1 to step B3.
- the first ECG signal is a filtered ECG signal of a first duration.
- the duration of the ECG signal in the test phase and the ECG signal in the learning phase are consistent, thereby ensuring that the quality of the ECG signal can be evaluated using the learned first threshold and second threshold.
- each ECG signal shows respectively: the original ECG signal of the first duration (located in the first row in Figure 8), and the first ECG signal obtained after filtering (located in the second row in Figure 8) , schematic diagram of the peak point (located in the third row in Figure 8) after the peak search operation.
- Step S202 Calculate the peak variability feature and the peak number variability feature of the first ECG signal.
- this step corresponds to step B4 in the embodiment shown in FIG. 2 .
- the method of calculating the peak variability feature of the first ECG signal is the same as the method of calculating the peak variability feature of a first duration ECG signal sample.
- the method of calculating the peak number variability feature of the first ECG signal is the same as the method of calculating the peak number variability feature of an ECG signal sample of the first duration.
- calculating the peak variability feature and the peak number variability feature of the first ECG signal includes:
- the peak number variability feature of the first electrocardiogram signal is obtained according to the peak number of the plurality of signal segments.
- the signal segment includes multiple discrete data points, and the signal segment is equivalent to the learning stage. Segment of sample fragments. For details, reference may be made to the description of the sample fragments in the above embodiments, which will not be described again here.
- calculating the peak list of each signal segment includes:
- the peak list of the first signal segment includes One or more first peak values
- the first peak value is a difference absolute value that is greater than the previous absolute value of the difference, greater than the next absolute value of the difference, and greater than the peak-finding threshold, the peak-finding threshold being determined by the third
- the absolute values of the differences corresponding to multiple signal segments of an ECG signal are determined.
- the method for determining the peak-finding threshold includes:
- obtaining the peak variability feature of the first ECG signal based on the peak list of the multiple signal segments includes:
- obtaining the peak number variability feature of the first ECG signal based on the peak number of the multiple signal segments includes:
- the specific implementation process of calculating the peak variability feature and the peak number variability feature of the first ECG signal can refer to the above embodiment.
- the specific implementation process of calculating the peak variability feature and the peak number variability feature of an ECG signal sample which will not be described in detail here.
- Step S2031 If the peak variability characteristic of the first ECG signal is greater than a first threshold, and the peak quantity variability characteristic of the first ECG signal is greater than a second threshold, the first ECG signal is abnormal. Signal.
- Step S2032 if the peak variability characteristic of the first ECG signal is greater than or equal to the first threshold, and the peak quantity variability characteristic of the first ECG signal is less than or equal to the second threshold, then The first ECG signal is a noise signal.
- Step S2033 if the peak variability characteristic of the first ECG signal is less than or equal to the first threshold, and the peak number variability characteristic of the first ECG signal is greater than or equal to the second threshold, then The first ECG signal is a noise signal.
- Step S2034 If the peak variability characteristic of the first ECG signal is less than the first threshold, and the peak quantity variability characteristic of the first ECG signal is less than the second threshold, then the first ECG signal The electrical signal is a normal signal.
- the two-dimensional feature plane is divided into four areas through the first threshold and the second threshold: normal area, abnormal area, and noise area.
- the ECG signal B is a normal signal if the peak variability characteristic of the ECG signal B is less than the first threshold, and the peak quantity variability characteristic of the ECG signal B is less than the second threshold, then the ECG signal B is a normal signal.
- the ECG signal C is an abnormal signal.
- ECG signal A is a noise signal.
- the ECG signal D is a noise signal.
- the signal segment located in area B is a normal signal
- the signal segment located in area C is a normal signal. It is an abnormal signal
- the signal segments located in areas A and D are noise segments.
- sequence number of each step in the above embodiment does not mean the order of execution.
- the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.
- Embodiments of the present application also provide a computer-readable storage medium.
- the computer-readable storage medium stores a computer program.
- the steps in each of the above method embodiments can be implemented.
- Embodiments of the present application also provide a computer program product.
- the computer program product When the computer program product is run on an electronic device, the electronic device can implement the steps in each of the above method embodiments.
- Integrated units may be stored in a computer-readable storage medium if they are implemented in the form of software functional units and sold or used as independent products. Based on this understanding, this application can implement all or part of the processes in the methods of the above embodiments by instructing relevant hardware through a computer program.
- the computer program can be stored in a computer-readable storage medium, and the computer program can be processed after being processed. When the processor is executed, the steps of each of the above method embodiments can be implemented.
- the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc.
- the computer-readable medium may at least include: any entity or device capable of carrying computer program code to the first device, recording media, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signals, telecommunications signals, and software distribution media.
- ROM read-only memory
- RAM random access memory
- electrical carrier signals telecommunications signals
- software distribution media For example, U disk, mobile hard disk, magnetic disk or CD, etc.
- computer-readable media may not be electrical carrier signals and telecommunications signals.
- Embodiments of the present application also provide a chip system.
- the chip system includes a processor.
- the processor is coupled to a memory.
- the processor executes a computer program stored in the memory to implement the steps of any method embodiment of the present application.
- the chip system can be a single chip or a chip module composed of multiple chips.
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Cardiology (AREA)
- Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Pathology (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
本申请提供一种心电信号质量评估方法、电子设备及芯片系统,涉及信号评估技术领域;该方法中,统计多个心电信号样本的峰值变异度特征和峰值数量变异度特征,基于多个心电信号样本的峰值变异度特征作为一个异常分界点,将多个心电信号样本的峰值数量变异度特征作为另一个异常分界点;根据待评估的心电信号的峰值变异度特征和峰值数量变异度特征与两个异常分界点之间的关系,确定待评估的心电信号为正常信号、异常信号还是噪声信号,通过该方法可以精确的将正常心电信号检出。
Description
本申请要求于2022年09月15日提交国家知识产权局、申请号为202211120062.7、申请名称为“一种心电信号质量评估方法、电子设备及芯片系统”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
本申请涉及信号评估技术领域,尤其涉及一种心电信号质量评估方法、电子设备及芯片系统。
心电信号是一种非线性、非平稳性和随机性的微弱信号,通常最大为mV量级;所以,心电信号监测通常需要心电监测装置紧贴生物体表面,以采集生物体的心电信号。当然,由于心电信号本身的特点以及心电信号监测的场景,导致心电信号非常容易受到来自生物体内(例如,肌电干扰、呼吸干扰等)或者生物体外(例如,工频干扰、信号拾取过程等)的干扰。
目前,采集到的心电信号可能伴随有大量的噪声或者异常信号(采集过程出现异常导致),导致心电信号被噪声和/或异常信号淹没而失去原本的一些特征。尤其,心电信号带有一些病例特征时,这些病理特征可能会被噪声和/或异常信号干扰,导致病理信号的相关预警算法的精度降低。
发明内容
鉴于此,本申请提供一种心电信号质量评估方法、电子设备及芯片系统,可以将心电信号中的正常信号检出。
为达到上述目的,本申请采用如下技术方案:
第一方面,本申请提供一种心电信号质量评估方法,该方法包括:
获取第一心电信号;
计算第一心电信号的峰值变异度特征和峰值数量变异度特征;
若第一心电信号的峰值变异度特征小于第一阈值、且第一心电信号的峰值数量变异度特征小于第二阈值,则第一心电信号为正常信号,其中,第一阈值用于表示峰值变异度特征的异常分界点,第一阈值由多个心电信号样本的峰值变异度特征确定,第二阈值用于表示峰值数量变异度特征的异常分界点,第二阈值由多个心电信号样本的峰值数量变异度特征确定。
本申请中,统计多个心电信号样本的峰值变异度特征和峰值数量变异度特征,基于多个心电信号样本的峰值变异度特征作为一个异常分界点,将多个心电信号样本的峰值数量变异度特征作为另一个异常分界点;根据待评估的心电信号的峰值变异度特征和峰值数量变异度特征与两个异常分界点之间的关系,确定待评估的心电信号的类型。通过该方法可以精确的区分出正常信号。
作为第一方面的一种实现方式,获取第一心电信号包括:
获取第一时长的原始心电信号;
对原始心电信号进行滤波处理,得到第一心电信号。
本申请中,采用与峰值相关的变异度特征作为心电信号的不同类型的特征,所以,为了提高特征的精确度,需要进行滤波处理,以去除心电信号波形中的毛刺。
作为第一方面的另一种实现方式,对原始心电信号进行滤波处理包括:
对原始心电信号进行低通滤波处理和高通滤波处理。
作为第一方面的另一种实现方式,计算第一心电信号的峰值变异度特征和峰值数量变异度特征,包括:
将第一心电信号进行分割处理,得到多个信号片段;
计算每个信号片段的峰值列表和峰值数量,峰值列表包括N个峰值,N表示峰值数量;
根据多个信号片段的峰值列表得到第一心电信号的峰值变异度特征;
根据多个信号片段的峰值数量得到第一心电信号的峰值数量变异度特征。
本申请实施例通过将第一心电信号进行分割处理,得到多个信号片段,基于多个信号片段的峰值列表的数据特征,确定第一心电信号的峰值变异度特征,基于多个信号片段的峰值数量的数据特征,确定第一心电信号的峰值数量变异度特征。
作为第一方面的另一种实现方式,信号片段包括多个离散的数据点,计算每个信号片段的峰值列表包括:
计算第一信号片段中每相邻的两个数据点之间的差值绝对值,第一信号片段为信号片段中的任一信号片段,第一信号片段的峰值列表包括一个或多个第一峰值,第一峰值为大于前一个差值绝对值、大于后一个差值绝对值、且大于寻峰阈值的差值绝对值,寻峰阈值由第一心电信号的多个信号片段分别对应的差值绝对值确定。
作为第一方面的另一种实现方式,寻峰阈值的确定方法包括:
计算第一心电信号的多个信号片段对应的差值绝对值集合中的第一分位数和第一常数的第一乘积;
计算第一心电信号的多个信号片段对应的差值绝对值集合中的第二分位数和第二常数的第二乘积;
计算第一乘积和第二乘积的差值,得到寻峰阈值。
作为第一方面的另一种实现方式,根据多个信号片段的峰值列表得到第一心电信号的峰值变异度特征包括:
计算第一心电信号的多个信号片段的峰值的标准差和均值;
计算多个信号片段的峰值的标准差和均值的比值,得到第一心电信号的峰值变异度特征。
作为第一方面的另一种实现方式,根据多个信号片段的峰值数量得到第一心电信号的峰值数量变异度特征包括:
计算第一心电信号的多个信号片段的峰值数量的最大值和最小值的第一差值;
计算第一心电信号的多个信号片段的峰值数量的中值;
计算第一差值和中值的比值,得到第一心电信号的峰值数量变异度特征。
作为第一方面的另一种实现方式,第一阈值和第二阈值的确定方式包括:
获取多个心电信号样本,多个心电信号样本的时长均为第一时长;
计算每个心电信号样本的峰值变异度特征和峰值数量变异度特征;
根据多个心电信号样本的峰值变异度特征得到第一阈值;
根据多个心电信号样本的峰值数量变异度特征得到第二阈值。
作为第一方面的另一种实现方式,根据多个心电信号样本的峰值变异度特征得到第一阈值包括:
计算多个心电信号样本的峰值变异度特征中的第三分位数和第三常数的第三乘积;
计算多个心电信号样本的峰值变异度特征中的第四分位数和第四常数的第四乘积;
计算第三乘积和第四乘积的差值,得到第一阈值。
作为第一方面的另一种实现方式,根据多个心电信号样本的峰值数量变异度特征得到第二阈值包括:
计算多个心电信号样本的峰值数量变异度特征中的第五分位数和第五常数的第五乘积;
计算多个心电信号样本的峰值数量变异度特征中的第六分位数和第六常数的第六乘积;
计算第五乘积和第六乘积的差值,得到第二阈值。
作为第一方面的另一种实现方式,该方法还包括:
若第一心电信号的峰值变异度特征大于第一阈值、且第一心电信号的峰值数量变异度特征大于第二阈值,则第一心电信号为异常信号;
若第一心电信号的峰值变异度特征大于或等于第一阈值、且第一心电信号的峰值数量变异度特征小于或等于第二阈值,则第一心电信号为噪声信号;
若第一心电信号的峰值变异度特征小于或等于第一阈值、且第一心电信号的峰值数量变异度特征大于或等于第二阈值,则第一心电信号为噪声信号。
作为第一方面的另一种实现方式,获取多个心电信号样本包括:
获取多个原始心电信号;
对多个原始心电信号进行数据分割,得到多个第一时长的原始心电信号;
对每个第一时长的原始心电信号进行低通滤波处理和高通滤波处理,得到多个心电信号样本。
作为第一方面的另一种实现方式,计算每个心电信号样本的峰值变异度特征的方式和计算第一心电信号的峰值变异度特征的方式相同;
计算每个心电信号样本的峰值数量变异度特征的方式和计算第一心电信号的峰值数量变异度特征的方式相同。
第二方面,提供一种电子设备,包括处理器,处理器用于运行存储器中存储的计算机程序,实现本申请第一方面任一项的方法的步骤。
第三方面,提供一种芯片系统,包括处理器,处理器与存储器耦合,处理器执行存储器中存储的计算机程序,以实现本申请第一方面任一项的方法的步骤。
第四方面,提供一种计算机可读存储介质,计算机可读存储介质存储有计算机程序,计算机程序被一个或多个处理器执行时实现本申请第一方面任一项的方法的步骤。
第五方面,本申请提供了一种计算机程序产品,当计算机程序产品在设备上运行时,
使得设备执行本申请第一方面任一项的方法的步骤。
可以理解的是,上述第二方面至第五方面的有益效果可以参见上述第一方面中的相关描述,在此不再赘述。
图1为本申请实施例提供的一种电子设备的硬件结构示意图;
图2为本申请实施例提供的心电信号质量评估方法的流程示意图;
图3为本申请实施例提供的心电信号特征学习过程的流程示意图;
图4为本申请实施例提供的滤波前的心电信号的波形示意图;
图5为本申请实施例提供的滤波后的心电信号的波形示意图;
图6为本申请实施例提供的得到的峰值点的示意图;
图7为本申请实施例提供的心电信号质量评估过程的流程示意图;
图8为本申请实施例提供的四个信号片段的滤波前、滤波后和峰值点的波形示意图;
图9为本申请实施例提供的四个心电信号以及更多的信号片段的分类结果。
以下描述中,为了说明而不是为了限定,提出了诸如特定系统结构、技术之类的具体细节,以便透彻理解本申请实施例。然而,本领域的技术人员应当清楚,在没有这些具体细节的其它实施例中也可以实现本申请。
应当理解,当在本申请说明书和所附权利要求书中使用时,术语“包括”指示所描述特征、整体、步骤、操作、元素和/或组件的存在,但并不排除一个或多个其它特征、整体、步骤、操作、元素、组件和/或其集合的存在或添加。
还应当理解,在本申请实施例中,“一个或多个”是指一个、两个或两个以上;“和/或”,描述关联对象的关联关系,表示可以存在三种关系;例如,A和/或B,可以表示:单独存在A,同时存在A和B,单独存在B的情况,其中A、B可以是单数或者复数。字符“/”一般表示前后关联对象是一种“或”的关系。
另外,在本申请说明书和所附权利要求书的描述中,术语“第一”、“第二”、“第三”、“第四”等仅用于区分描述,而不能理解为指示或暗示相对重要性。
在本申请说明书中描述的参考“一个实施例”或“一些实施例”等意味着在本申请的一个或多个实施例中包括结合该实施例描述的特定特征、结构或特点。由此,在本说明书中的不同之处出现的语句“在一个实施例中”、“在一些实施例中”、“在其他一些实施例中”、“在另外一些实施例中”等不是必然都参考相同的实施例,而是意味着“一个或多个但不是所有的实施例”,除非是以其他方式另外特别强调。术语“包括”、“包含”、“具有”及它们的变形都意味着“包括但不限于”,除非是以其他方式另外特别强调。
本申请实施例提供的心电信号质量评估方法,可以适用于心电监测设备、可穿戴设备等电子设备中,当然,也可以应用在与心电监测装置连接的手机等电子设备中。本申请实施例对电子设备的具体类型不作限定。
图1示出了一种电子设备的结构示意图。电子设备100可以包括处理器110,外部存储器接口120,内部存储器121,通用串行总线(universal serial bus,USB)接口130,充电管理模块140,电源管理模块141,电池142,天线1,天线2,移动通信模块150,无线通信模块160,音频模块170,扬声器170A,受话器170B,麦克风170C,耳机接口170D,
传感器模块180,按键190,马达191,摄像头193,显示屏194,以及用户标识模块(subscriber identification module,SIM)卡接口195等。其中,传感器模块180可以包括压力传感器180A,触摸传感器180K等。
可以理解的是,本申请实施例示意的结构并不构成对电子设备100的具体限定。在本申请另一些实施例中,电子设备100可以包括比图示更多或更少的部件,或者组合某些部件,或者拆分某些部件,或者不同的部件布置。图示的部件可以以硬件,软件或软件和硬件的组合实现。
处理器110可以包括一个或多个处理单元,例如:处理器110可以包括应用处理器(application processor,AP),调制解调处理器,图形处理器(graphics processing unit,GPU),图像信号处理器(image signal processor,ISP),控制器,存储器,视频编解码器,数字信号处理器(digital signal processor,DSP),基带处理器,和/或神经网络处理器(neural-network processing unit,NPU)等。其中,不同的处理单元可以是独立的器件,也可以集成在一个或多个处理器中。
其中,控制器可以是电子设备100的神经中枢和指挥中心。控制器可以根据指令操作码和时序信号,产生操作控制信号,完成取指令和执行指令的控制。
处理器110中还可以设置存储器,用于存储指令和数据。在一些实施例中,处理器110中的存储器为高速缓冲存储器。该存储器可以保存处理器110刚用过或循环使用的指令或数据。如果处理器110需要再次使用该指令或数据,可从存储器中直接调用。避免了重复存取,减少了处理器110的等待时间,因而提高了系统的效率。
USB接口130是符合USB标准规范的接口,具体可以是Mini USB接口,Micro USB接口,USB Type C接口等。USB接口130可以用于连接充电器为电子设备100充电,也可以用于电子设备100与外围设备之间传输数据。
外部存储器接口120可以用于连接外部存储卡,例如Micro SD卡,实现扩展电子设备100的存储能力。外部存储卡通过外部存储器接口120与处理器110通信,实现数据存储功能。例如将音乐,视频等文件保存在外部存储卡中。
内部存储器121可以用于存储计算机可执行程序代码,可执行程序代码包括指令。处理器110通过运行存储在内部存储器121的指令,从而执行电子设备100的各种功能应用以及数据处理。内部存储器121可以包括存储程序区和存储数据区。其中,存储程序区可存储操作系统,至少一个功能所需的应用程序(比如声音播放功能,图像播放功能等)。
此外,内部存储器121可以包括高速随机存取存储器,还可以包括非易失性存储器,例如至少一个磁盘存储器件,闪存器件,通用闪存存储器(universal flash storage,UFS)等。
充电管理模块140用于从充电器接收充电输入。其中,充电器可以是无线充电器,也可以是有线充电器。在一些有线充电的实施例中,充电管理模块140可以通过USB接口130接收有线充电器的充电输入。
电源管理模块141用于连接电池142,充电管理模块140与处理器110。电源管理模块141接收电池142和/或充电管理模块140的输入,为处理器110,内部存储器121,外部存储器,显示屏194,摄像头193,和无线通信模块160等供电。
在其他一些实施例中,电源管理模块141也可以设置于处理器110中。在另一些实施
例中,电源管理模块141和充电管理模块140也可以设置于同一个器件中。
电子设备100的无线通信功能可以通过天线1,天线2,移动通信模块150,无线通信模块160,调制解调处理器以及基带处理器等实现。
天线1和天线2用于发射和接收电磁波信号。电子设备100中的每个天线可用于覆盖单个或多个通信频带。不同的天线还可以复用,以提高天线的利用率。例如:可以将天线1复用为无线局域网的分集天线。在另外一些实施例中,天线可以和调谐开关结合使用。
移动通信模块150可以提供应用在电子设备100上的包括2G/3G/4G/5G等无线通信的解决方案。移动通信模块150可以包括至少一个滤波器,开关,功率放大器,低噪声放大器(low noise amplifier,LNA)等。移动通信模块150可以由天线1接收电磁波,并对接收的电磁波进行滤波,放大等处理,传送至调制解调处理器进行解调。移动通信模块150还可以对经调制解调处理器调制后的信号放大,经天线1转为电磁波辐射出去。
无线通信模块160可以提供应用在电子设备100上的包括无线局域网(wireless local area networks,WLAN)(如无线保真(wireless fidelity,Wi-Fi)网络),蓝牙(bluetooth,BT),全球导航卫星系统(global navigation satellite system,GNSS),调频(frequency modulation,FM),近距离无线通信技术(near field communication,NFC),红外技术(infrared,IR)等无线通信的解决方案。无线通信模块160可以是集成至少一个通信处理模块的一个或多个器件。无线通信模块160经由天线2接收电磁波,将电磁波信号调频以及滤波处理,将处理后的信号发送到处理器110。无线通信模块160还可以从处理器110接收待发送的信号,对其进行调频,放大,经天线2转为电磁波辐射出去。
在一些实施例中,电子设备100的天线1和移动通信模块150耦合,天线2和无线通信模块160耦合,使得电子设备100可以通过无线通信技术与网络以及其他设备通信。
电子设备100可以通过音频模块170,扬声器170A,受话器170B,麦克风170C,耳机接口170D,以及应用处理器等实现音频功能。例如音乐播放,录音等。
音频模块170用于将数字音频信号转换成模拟音频信号输出,也用于将模拟音频输入转换为数字音频信号。音频模块170还可以用于对音频信号编码和解码。在一些实施例中,音频模块170可以设置于处理器110中,或将音频模块170的部分功能模块设置于处理器110中。
扬声器170A,也称“喇叭”,用于将音频电信号转换为声音信号。电子设备100可以通过扬声器170A收听音乐,或收听免提通话。
受话器170B,也称“听筒”,用于将音频电信号转换成声音信号。当电子设备100接听电话或语音信息时,可以通过将受话器170B靠近人耳接听语音。
麦克风170C,也称“话筒”,“传声器”,用于将声音信号转换为电信号。当拨打电话或发送语音信息时,用户可以通过人嘴靠近麦克风170C发声,将声音信号输入到麦克风170C。电子设备100可以设置至少一个麦克风170C。在另一些实施例中,电子设备100可以设置两个麦克风170C,除了监听语音信息,还可以实现降噪功能。在另一些实施例中,电子设备100还可以设置三个,四个或更多麦克风170C,实现采集声音信号,降噪,还可以识别声音来源,实现定向录音功能等。
耳机接口170D用于连接有线耳机。耳机接口170D可以是USB接口130,也可以是3.5mm的开放移动电子设备平台(open mobile terminal platform,OMTP)标准接口,美国
蜂窝电信工业协会(cellular telecommunications industry association of the USA,CTIA)标准接口。
压力传感器180A用于感受压力信号,可以将压力信号转换成电信号。在一些实施例中,压力传感器180A可以设置于显示屏194。压力传感器180A的种类很多,如电阻式压力传感器,电感式压力传感器,电容式压力传感器等。电容式压力传感器可以是包括至少两个具有导电材料的平行板。当有力作用于压力传感器180A,电极之间的电容改变。电子设备100根据电容的变化确定压力的强度。当有触摸操作作用于显示屏194,电子设备100根据压力传感器180A检测触摸操作强度。电子设备100也可以根据压力传感器180A的检测信号计算触摸的位置。
触摸传感器180K,也称“触控面板”。触摸传感器180K可以设置于显示屏194,由触摸传感器180K与显示屏194组成触摸屏,也称“触控屏”。触摸传感器180K用于检测作用于其上或附近的触摸操作。触摸传感器可以将检测到的触摸操作传递给应用处理器,以确定触摸事件类型。可以通过显示屏194提供与触摸操作相关的视觉输出。在另一些实施例中,触摸传感器180K也可以设置于电子设备100的表面,与显示屏194所处的位置不同。
按键190包括开机键,音量键等。按键190可以是机械按键。也可以是触摸式按键。电子设备100可以接收按键输入,产生与电子设备100的用户设置以及功能控制有关的键信号输入。
马达191可以产生振动提示。马达191可以用于来电振动提示,也可以用于触摸振动反馈。
电子设备100通过GPU,显示屏194,以及应用处理器等实现显示功能。GPU为图像处理的微处理器,连接显示屏194和应用处理器。GPU用于执行数学和几何计算,用于图形渲染。处理器110可包括一个或多个GPU,其执行程序指令以生成或改变显示信息。
显示屏194用于显示图像,视频等。在一些实施例中,电子设备100可以包括1个或N个显示屏194,N为大于1的正整数。
摄像头193用于捕获静态图像或视频。在一些实施例中,电子设备100可以包括1个或N个摄像头193,N为大于1的正整数。
SIM卡接口195用于连接SIM卡。SIM卡可以通过插入SIM卡接口195,或从SIM卡接口195拔出,实现和电子设备100的接触和分离。电子设备100可以支持1个或N个SIM卡接口,N为大于1的正整数。
本申请实施例并未特别限定一种心电信号质量评估方法的执行主体的具体结构,只要可以通过运行记录有本申请实施例提供的一种心电信号质量评估方法的代码,以根据本申请实施例提供的一种心电信号质量评估方法进行处理即可。例如,本申请实施例提供的一种心电信号质量评估方法的执行主体可以是电子设备中能够调用程序并执行程序的功能模块,或者为应用于电子设备中的处理装置,例如,芯片。
心电信号是一种非线性、非平稳性和随机性的微弱信号,通常最大为mV量级;所以,心电信号监测通常需要心电监测装置紧贴生物体表面,以采集生物体的心电信号。当然,由于心电信号本身的特点以及心电信号监测的场景,导致心电信号非常容易受到来自生物体内(例如,肌电干扰、呼吸干扰等)或者生物体外(例如,工频干扰、信号拾取过程等)的干扰。所以,采集到的心电信号可能伴随有大量的噪声或者异常信号(采集过程出现异
常导致),导致心电信号被噪声和/或异常信号淹没而失去原本的一些特征。尤其,心电信号带有一些病例特征时,这些病理特征可能会被噪声和/或异常信号干扰,导致病理信号的相关预警算法的精度降低。
因此,本申请实施例提供一种心电信号质量评估方法,可以将心电信号中的正常信号检出,从而可以根据检出的正常信号进行病理的相关预警。
本申请实施例提供的心电信号质量评估算法可以应用在用于心电监测的电子设备上。由于可穿戴心电监测设备在监测心电信号时,需要佩戴在生物体上,可穿戴心电监测设备的佩戴方式可能不太规范或者不能完全满足心电监测的要求。所以,可穿戴心电监测设备监测到的心电信号更容易受到噪声或异常信号的污染,因此,本申请实施例更适用于可穿戴心电监测设备。
本申请实施例提供的心电信号质量评估方法,将心电信号的峰值变异度特征和峰值数量变异度特征作为评价该心电信号为正常信号、异常信号和噪声信号的特征。
本申请实施例中的正常信号可能包含病理特征也可能不包含病理特征,是否包含病理特征取决于生物体本身的身体状况。异常信号为可能用户佩戴可穿戴心电监测设备错误导致的采集过程异常从而采集到的心电信号;噪声信号为测试过程中的各种各样的噪声。
需要说明,本申请实施例中,最终评估为正常信号,并不表示该正常信号里面不包含异常点和噪声点;只是,包含的异常点和/或噪声点不足以影响该信号的后续处理。同理,最终评估为噪声信号,并不表示该噪声信号里面不包含正常点和异常点。只是,包含的正常点和/或异常点较少,大部分还是噪声点。同理,最终评估为异常信号,并不表示该异常信号里面不包含正常点和噪声点。只是,包含的正常点和/或异常点较少,大部分还是异常点。
在具体实现时,需要设置峰值变异度特征的异常分界点和峰值数量变异度特征的异常分界点。基于心电信号的峰值变异度特征和峰值变异度特征的异常分界点的关系,以及心电信号的峰值数量变异度特征和峰值数量变异度特征的异常分界点的关系,确定心电信号为正常信号、异常信号还是噪声信号。
为了确保电子设备在监测到心电信号之后,能够基于监测到的心电信号的峰值变异度特征和峰值变异度特征的异常分界点的关系,以及监测到的心电信号的峰值数量变异度特征和峰值数量变异度特征的异常分界点的关系,确定监测到的心电信号的质量(正常、异常、还是噪声),需要预先确定峰值变异度特征的异常分界点和峰值数量变异度特征的异常分界点。
参见图2,图2中的步骤A1至步骤A5为确定峰值变异度特征的异常分界点(可以记为第一阈值)和峰值数量变异度特征的异常分界点(可以记为第二阈值)的一种示例。
步骤A1,信号采集。
本申请实施例中,需要学习到用于区分不同类型的心电信号的异常分界点,在学习该异常分界点时,需要采集多人多场景的多个原始心电信号。当然,实际应用中,也可以从原始心电信号样本库得到多个原始心电信号,本申请实施例对原始心电信号的获取方式不做限定。
步骤A2,信号分割。
在具体实现时,需要对多人多场景的多个原始心电信号进行时域上的信号分割,最终
得到多个固定时长的原始心电信号,以从多个固定时长的原始心电信号中学习到异常分界点。
步骤A3,信号降噪。
在对多个固定时长的原始心电信号进行学习之前,需要对多个固定时长的原始心电信号进行滤波处理,以消除毛刺,在进行滤波处理之后,得到多个心电信号样本。
步骤A4,特征构造。
本申请实施例通过多个心电信号样本的峰值变异度特征和峰值数量变异度特征作为区分不同类型信号的特征。
所以,需要对每个心电信号样本进行特征构造,得到每个心电信号样本的峰值变异度特征和峰值数量变异度特征。
步骤A5,生成阈值。
通过统计多个心电信号样本的峰值变异度特征,确定峰值变异度特征的异常分界点,即第一阈值;
通过统计多个心电信号样本的峰值数量变异度特征,确定峰值变异度特征的异常分界点,即第二阈值。
经过步骤A1至步骤A5,可以基于多个心电信号样确定两个特征的异常分界点:第一阈值和第二阈值。
在确定第一阈值和第二阈值之后,该第一阈值和第二阈值、以及用于生成峰值变异度特征和峰值数量变异度特征的算法可以被预置到用于心电信号监测的电子设备中。该电子设备就可以通过该第一阈值和第二阈值、以及用于生成峰值变异度特征和峰值数量变异度特征的算法对该电子设备监测到的心电信号进行质量评估。具体可参照图2中的步骤B1至步骤B5。
步骤B1,信号采集。
在本申请实施例中,可以通过电子设备实时监测心电信号。
步骤B2,信号分割。
本申请实施例中,对实时监测的心电信号进行信号分割的方式和步骤A2相同,也需要将监测到的心电信号分割为固定时长的心电信号,其中,步骤B2分割后的心电信号的时长和步骤A2分割后的心电信号的时长相同。
在实际应用中,可以在电子设备对生物体进行心电信号监测结束之后,再对监测到的原始心电信号进行信号分割,得到多个固定时长的心电信号。
也可以在电子设备对生物体进行心电信号监测过程中,每采集到固定时长的心电信号,将该固定时长的心电信号进行分割,每获得一个固定时长的心电信号,就对该获得的固定时长的心电信号进行后续处理。
本申请实施例对具体采用何种方式不做限定。
步骤B3,信号降噪。
该步骤中,对分割后的固定时长的心电信号的降噪方式和步骤A3中的降噪方式相同。
步骤B4,特征构造。
该步骤中,对降噪后的固定时长的心电信号的特征构造方式和步骤A4中相同。
其中,步骤B2至步骤B4为:通过预置在电子设备中的用于生成峰值变异度特征和峰
值数量变异度特征的算法,计算得到监测到的心电信号的峰值变异度特征和峰值数量变异度特征的过程。
步骤B5,阈值比较。
通过步骤B1至步骤B4可以得到监测的心电信号的峰值变异度特征和峰值信号变异度特征之后,将得到的峰值变异度特征和预置在电子设备中的第一阈值进行比较,将得到的峰值数量变异度特征和预置在电子设备中的第二阈值进行比较。
作为一个示例,若监测到的心电信号(固定时长)的峰值变异度特征大于第一阈值、且监测到的心电信号的峰值数量变异度特征大于第二阈值,则监测到的心电信号为异常信号。
若监测到的心电信号(固定时长)的峰值变异度特征大于或等于第一阈值、且监测到的心电信号的峰值数量变异度特征小于或等于第二阈值,则监测到的心电信号为噪声信号。
若监测到的心电信号(固定时长)的峰值变异度特征小于或等于第一阈值、且监测到的心电信号的峰值数量变异度特征大于或等于第二阈值,则监测到的心电信号为噪声信号。
若监测到的心电信号(固定时长)的峰值变异度特征小于第一阈值、且监测到的心电信号的峰值数量变异度特征小于第二阈值,则监测到的心电信号为正常信号。
本申请实施例通过对大量的心电信号进行分析发现:固定时长的正常信号、异常信号和噪声信号的峰值以及峰值数量之间存在较大差异,所以,本申请实施例将固定时长的心电信号的峰值变异度特征和峰值数量变异度特征作为对心电信号分类的特征。然后,通过对多个固定时长的心电信号的上述两个特征进行学习,得到对心电信号分类的异常分界点。通过对监测到的心电信号的上述两个特征和异常分界点之间的关系,确定监测到的心电信号的类型。
另外,上述实施例中,若将第一阈值、第二阈值,以及计算上述两个特征的算法预置在A型号的电子设备中,则步骤A1中的原始心电信号可以在同样为A型号的电子设备上采集,通过一致的心电信号可以使得信号分类更精确。当然,通过A型号的电子设备1上采集得到的多人多场景的原始心电信号得到第一阈值和第二阈值之后,该第一阈值和第二阈值以及相应的计算两个特征的算法可以预置在同样为A类型的多个电子设备上,例如,A类型的电子设备2、A类型的电子设备3、A类型的电子设备4……。
当然,实际应用中,若另一型号(例如,型号B)的电子设备和本型号(例如,型号A)的电子设备的心电监测装置一致、心电监测方式一致,则该第一阈值和第二阈值以及相应的计算两个特征的算法可以预置在该另一型号的电子设备中。
为了对上述实施例的多个步骤具有更清晰的理解,可以参照图3所示的流程示意图,该图3所示的流程图对应于图2所示实施例中的步骤A1至步骤A5。
S101,获取多个心电信号样本,所述多个心电信号样本的时长均为第一时长。
本申请实施例中,多个心电信号样本可以理解为已经经过步骤A1至步骤A3得到的固定时长、且经过滤波处理的多个心电信号样本。
作为本申请另一实施例,所述获取多个心电信号样本包括:
步骤A1,获取多个原始心电信号。
如前所述,多个原始心电信号可以为同型号(或者心电监测装置和心电监测方式一致)的电子设备采集的多用户多场景的原始心电信号。
步骤A2,对所述多个原始心电信号进行数据分割,得到多个第一时长的原始心电信号。
在获取到多个原始心电信号之后,需要对每个原始心电信号进行信号分割。
由于信号分割的过程,用于得到多个固定时长的原始信号样本,所以,总时长小于固定时长的原始心电信号将丢弃。在每个总时长大于或等于固定时长的原始心电信号中分割出一个或多个固定时长的原始心电信号,该固定时长可以为第一时长。
需要说明,可以在每个总时长大于或等于第一时长的原始心电信号中分割一个第一时长的原始心电信号。
也可以在每个总时长大于或等于第一时长的原始心电信号中分割尽可能多的第一时长的原始心电信号。当然,也可以限制每个总时长大于或等于第一时长的原始心电信号分割的第一时长的原始心电信号的数量。
基于上述分割方式可以理解,总时长大于或等于第一时长的多个原始心电信号中,有些原始心电信号可能分割得到一个第一时长的原始心电信号,有的原始心电信号可能分割得到多个第一时长的原始心电信号。
无论采用何种分割方式,最后得到多个第一时长的原始心电信号。需要说明,上述分割过程,在同一原始心电信号上分割得到的多个第一时长的原始心电信号之间不存在时域上的重叠。
本申请实施例中,第一时长可以为t,假设原始心电信号的采样率为Fs,则每个第一时长的原始心电信号中包含了t×Fs个离散的数据点。
步骤A3,对每个第一时长的原始心电信号进行低通滤波处理和高通滤波处理,得到所述多个心电信号样本。
本申请实施例中,可以通过对第一时长的原始心电信号进行低通滤波处理和高通滤波处理,以消除第一时长的原始心电信号中的毛刺,提高后续的峰值确定和峰值数量确定的精确度。
实际应用中,可以先进行低通滤波处理再进行高通滤波处理,也可以先进行高通滤波处理再进行低通滤波处理。
低通滤波处理时,采用α阶低通滤波器,其中,低通滤波器的频率上限为Fh。
高通滤波处理时,采用β阶高通滤波器,其中,高通滤波器的频率下限为Fl。
图4为本申请实施例提供的未经过滤波处理的第一时长的原始心电信号;图5为本申请实施例提供的经过滤波处理的心电信号。
通过图4和图5可以理解,经过滤波处理后,心电信号的毛刺消失。由于本申请实施例采用的区分不同类型的心电信号的特征为峰值和峰值数量,所以,需要将原始心电信号中容易对峰值和峰值数量造成干扰的毛刺去除。
本申请实施例以高通滤波和低通滤波作为消除原始心电信号中的毛刺的示例,实际应用中,也可以采用其他滤波方式消除原始心电信号中的毛刺。本申请实施例对此不做限制。
需要说明,实际应用中,可以对大于或等于第一时长的原始心电信号先进行信号分割,得到多个第一时长的原始心电信号,再对每个第一时长的原始心电信号进行滤波处理;也可以对大于或等于第一时长的原始心电信号先进行滤波处理,得到滤波处理后的每个大于或等于第一时长的原始心电信号,再对滤波处理后的每个大于或等于第一时长的原始心电信号进行信号分割。
本申请实施例对上述信号分割和滤波处理的先后顺序不做限制。
为了便于区分,原始心电信号在经过分割和滤波处理后,得到心电信号样本。这些心电信号样本的时长均为第一时长,这些心电信号样本均经过高通滤波和低通滤波处理。
本申请实施例可以将得到的心电信号样本的数量记为S。
S102,计算每个心电信号样本的峰值变异度特征和峰值数量变异度特征。
该步骤对应于上述步骤A4。
本申请实施例以计算其中一个心电信号样本的峰值变异度特征和峰值数量变异度特征为例,在实际应用中,计算每个心电信号样本的峰值变异度特征和峰值数量变异度特征的方式相同。
步骤C1,将一个心电信号样本进行分割处理,得到一个心电信号样本的多个样本片段。
该步骤中的分割过程也为在时域上进行的不重叠分割。
可以设置将每个心电信号样本都均分为时域不重叠的n个样本片段,则每个样本片段中含有的离散的数据点的数量为本申请实施例可以将记为k。即每个样本片段中含有k个离散数据点。
假设一个心电信号样本可以记为X,则将该心电信号样本X分割后,X=[X1|X2|...|Xn];其中,其中,表示心电信号样本X中的第i个样本片段中的第j个离散数据点,1≤j≤k。
步骤C2,计算每个样本片段的峰值列表和峰值数量。
对其中的第i个样本片段Xi执行如下寻峰操作,以得到每个样本片段的峰值列表和峰值数量。
首先,计算样本片段Xi中每相邻的两个离散数据点之间的差值绝对值,得到差值绝对值其中,其他不再示例。
然后,查找大于前一个差值绝对值、大于后一个差值绝对值、且大于寻峰阈值的差值绝对值,查找到个满足上述条件的差值绝对值组成峰值列表。
作为示例,若且则为峰值点,其中,1<γ<k-1。
查找到的多个峰值点组成Xi的峰值列表Pi。Xi的峰值列表中的峰值点的数量作为Xi的峰值数量Si,。则其中,Si作为峰值数量的一个示例。
当然,在实际应用中,需要对心电信号样本X的多个样本片段(X1至Xn)均执行上述寻峰操作,从而得到每个样本片段的峰值列表和峰值数量。
基于上述理解,心电信号样本X的峰值列表其中,Pi中包括Si个数量的峰值点,心电信号样本X的峰值数量S=[S1,S2,...,Sn],其中Si为Pi表示的峰值列表中的峰值点的数量。
参见图6,为将心电信号样本X均分为5个样本片段后,得到的5个样本片段的峰值示意图。图6中,分割线为心电信号样本X均分为5个样本片段时的分割时刻;峰值点为寻峰操作后得到的峰值点;寻峰阈值的计算过程可以参照如下描述。
如前所述,在寻峰操作时,还需要将与寻峰阈值TM进行比较,一个心电信号样本
的每个样本片段进行寻峰操作时的寻峰阈值相等,所以,该寻峰阈值与心电信号样本X相关。
作为一个示例,所述寻峰阈值由本心电信号样本的多个样本片段分别对应的差值绝对值确定。即寻峰阈值由心电信号样本X中的多个样本片段X1至Xn的M1至Mn相关。
首先构造序列该序列表示一个心电信号样本的多个样本片段的差值绝对值集合。
计算心电信号样本的多个样本片段的差值绝对值集合的75分位数和第一常数的第一乘积;计算心电信号样本的多个样本片段的差值绝对值集合的25分位数和第二常数的第二乘积;计算所述第一乘积和所述第二乘积的差值,得到心电信号样本X的寻峰阈值。
作为示例,TM=a1*percentile(MBH,75)-a2*percentile(MBH,25)。
其中,percentile(MBH,75)表示序列MBH的75分位数,即将序列MBH中的元素从小到大排列;然后计算序列MBH中元素的总数Q;从排序后的序列MBH中选取第75%Q(75%乘以Q)个元素,该percentile(MBH,75)为选取的该元素。
可以按照同样的方式得到percentile(MBH,25),即将序列MBH中的元素从小到大排列;然后计算序列MBH中元素的总数Q;从排序后的序列MBH中选取第25%Q(25%乘以Q)个元素,该percentile(MBH,25)为选取的该元素。
当然,上述示例中的75和25仅用于示例,实际应用中,可以为第一分位数和第一常数的第一乘积,第二分位数和第二常数的第二乘积。当然,可以根据实际监测心电信号的电子设备采集的心电信号的情况,选择其他更为合适的数值。该数值可以经过多次试验得到。同理,上述示例中的第一常数a1和第二常数a2也可以根据情况选择不同的常数,例如,a1可以为4,a2可以为3。
步骤C3,根据多个样本片段的峰值列表得到该心电信号样本的峰值变异度特征。
上述示例可以得到一个心电信号样本X的峰值列表
可以将该心电信号样本X的峰值列表的数据特征值作为该心电信号样本的峰值变异度特征。
作为示例,计算心电信号样本的多个样本片段的峰值的标准差和均值;
计算所述多个样本片段的峰值的标准差和均值的比值,得到所述心电信号样本的峰值变异度特征。
即
其中,f1表示心电信号样本X的峰值变异度特征,std(P)表示峰值列表P中的峰值的标准差,mean(P)表示峰值列表P中的峰值的均值。
步骤C4,根据多个样本片段的峰值数量得到该心电信号样本的峰值数量变异度特征。
上述示例中,可以得到一个心电信号样本X的峰值数量S=[S1,S2,...,Sn]。
可以将该心电信号样本X的峰值数量的数据特征值作为该心电信号样本的峰值数量变异度特征。
作为示例,计算心电信号样本的多个样本片段的峰值数量的最大值和最小值的差值;
计算心电信号样本的多个样本片段的峰值数量的中值;
计算该差值和该中值的比值,得到心电信号样本的峰值数量变异度特征。
即
其中,f2表示心电信号样本X的峰值数量变异度特征,max(S)表示峰值数量集合S中的峰值数量的最大值,min(S)表示峰值数量集合S中的峰值数量的最小值,median(S)表示峰值数量集合S中的峰值数量的中值。
通过上述方式,可以得到每个第一时长的心电信号样本的峰值变异度特征和峰值数量变异度特征。
S103,根据所述多个心电信号样本的峰值变异度特征得到所述第一阈值,根据所述多个心电信号样本的峰值数量变异度特征得到第二阈值。
该步骤对应于图2所示实施例中的步骤A5。
假设本申请实施例以W个心电信号样本作为学习时的样本,则本申请实施例基于W个心电信号样本可以得到W个峰值变异度特征和W个峰值数量变异度特征。
相应的,峰值变异度特征集合
峰值数量变异度集合
然后计算峰值变异度特征集合的数据特征值,以得到峰值变异度特征的异常分界点(第一阈值)。
作为示例,计算所述多个心电信号样本的峰值变异度特征中的第三分位数和第三常数的第三乘积;
计算所述多个心电信号样本的峰值变异度特征中的第四分位数和第四常数的第四乘积;
计算所述第三乘积和所述第四乘积的差值,得到所述第一阈值。
本申请实施例以第三分位数为75分位数,第四分位数为25分位数,第三常数为4,第四常数为3为例。
U1=4×percentile(F1,75)-3×percentile(F1,25)。
U1=4×percentile(F1,75)-3×percentile(F1,25)。
其中,U1为表示峰值变异度特征异常分界点的第一阈值。
可以按照同样的方式,得到峰值数量变异度特征的异常分界点(第二阈值)。
作为示例,计算所述多个心电信号样本的峰值数量变异度特征中的第五分位数和第五常数的第五乘积;
计算所述多个心电信号样本的峰值数量变异度特征中的第六分位数和第六常数的第六乘积;
计算所述第五乘积和所述第六乘积的差值,得到所述第二阈值。
本申请实施例以第五分位数为75分位数,第六分位数为25分位数,第五常数为4,第六常数为3为例。
U2=4×percentile(F2,75)-3×percentile(F2,25)。
U2=4×percentile(F2,75)-3×percentile(F2,25)。
其中,U2为表示峰值数量变异度特征异常分界点的第一阈值。
通过这种方式就可以确定用于对监测到的心电信号的类型进行分类的第一阈值和第二阈值。
在确定第一阈值和第二阈值之后,将第一阈值、第二阈值以及用于计算峰值变异度特征和峰值数量变异度特征的算法模型预置到电子设备中。电子设备就可以实现心电信号的实时检测,以及心电信号的质量评估。
参照图7,为本申请实施例提供的心电信号质量评估方法的流程示意图,该流程示意图在图3所示流程图的基础上,对应于图2所示实施例中的步骤B1至步骤B5。
步骤S201,获取第一心电信号。
本申请实施例可以利用电子设备上的心电监测装置测量得到心电信号,然后该电子设备对心电信号进行处理,从而对心电信号的质量进行评估。
实际应用中,也可以由心电监测装置测量得到心电信号后,心电监测装置将测量得到的心电信号发送到用于进行心电信号质量评估的电子设备上,有另一电子设备执行质量评估工作,即心电信号监测和心电信号质量评估过程可以分别设置在不同的电子设备上,本申请实施例对此不做限制。
作为本申请另一实施例,获取第一心电信号包括:
获取第一时长的原始心电信号。
对所述原始心电信号进行低通滤波处理和高通滤波处理,得到所述第一心电信号。
本申请实施例中,心电监测装置测量得到的心电信号之后,该心电信号为原始心电信号;电子设备可以对测量得到的原始心电信号进行分割处理和滤波处理,以得到第一心电信号。该步骤对应于步骤B1至步骤B3。
该第一心电信号为第一时长、且经过滤波处理的心电信号。测试阶段的心电信号和学习阶段的心电信号的时长一致,从而确保可以采用学习到的第一阈值和第二阈值对心电信号的质量进行评估。
参见图8,为本申请实施例提供的四个心电信号(A、B、C和D)的处理过程波形变化示意图。其中,每个心电信号分别展示了:第一时长的原始心电信号(位于图8中的第一行)、经过滤波处理得到的第一心电信号(位于图8中的第二行)、寻峰操作后的峰值点(位于图8中的第三行)示意图。
步骤S202,计算所述第一心电信号的峰值变异度特征和峰值数量变异度特征。
本申请实施例中,该步骤对应于图2所示实施例中的步骤B4。
计算第一心电信号的峰值变异度特征的方式和计算一个第一时长的心电信号样本的峰值变异度特征的方式一致。
同理,计算第一心电信号的峰值数量变异度特征的方式和计算一个第一时长的心电信号样本的峰值数量变异度特征的方式一致。
作为本申请另一实施例,计算所述第一心电信号的峰值变异度特征和峰值数量变异度特征包括:
将所述第一心电信号进行分割处理,得到多个信号片段;
计算每个信号片段的峰值列表和峰值数量,所述峰值列表包括N个峰值,N表示所述峰值数量;
根据所述多个信号片段的峰值列表得到所述第一心电信号的峰值变异度特征;
根据所述多个信号片段的峰值数量得到所述第一心电信号的峰值数量变异度特征。
本申请实施例中,所述信号片段包括多个离散的数据点,所述信号片段相当于学习阶
段的样本片段。具体可参照上述实施例中对样本片段的描述,在此不再赘述。
作为本申请另一实施例,所述计算每个信号片段的峰值列表包括:
计算第一信号片段中每相邻的两个数据点之间的差值绝对值,所述第一信号片段为所述信号片段中的任一信号片段,所述第一信号片段的峰值列表包括一个或多个第一峰值,所述第一峰值为大于前一个差值绝对值、大于后一个差值绝对值、且大于寻峰阈值的差值绝对值,所述寻峰阈值由所述第一心电信号的多个信号片段分别对应的差值绝对值确定。
作为本申请另一实施例,所述寻峰阈值的确定方法包括:
计算所述第一心电信号的多个信号片段对应的差值绝对值集合中的第一分位数和第一常数的第一乘积;
计算所述第一心电信号的多个信号片段对应的差值绝对值集合中的第二分位数和第二常数的第二乘积;
计算所述第一乘积和所述第二乘积的差值,得到所述寻峰阈值。
作为本申请另一实施例,所述根据所述多个信号片段的峰值列表得到所述第一心电信号的峰值变异度特征包括:
计算所述第一心电信号的多个信号片段的峰值的标准差和均值;
计算所述多个信号片段的峰值的标准差和均值的比值,得到所述第一心电信号的峰值变异度特征。
作为本申请另一实施例,所述根据所述多个信号片段的峰值数量得到所述第一心电信号的峰值数量变异度特征包括:
计算所述第一心电信号的多个信号片段的峰值数量的最大值和最小值的第一差值;
计算所述第一心电信号的多个信号片段的峰值数量的中值;
计算所述第一差值和所述中值的比值,得到所述第一心电信号的峰值数量变异度特征。
上述计算第一心电信号的峰值变异度特征和峰值数量变异度特征的具体实现过程可以参照上述实施例中,计算一个心电信号样本的峰值变异度特征和峰值数量变异度特征的具体实现过程,在此不再赘述。
步骤S2031,若所述第一心电信号的峰值变异度特征大于第一阈值、且所述第一心电信号的峰值数量变异度特征大于第二阈值,则所述第一心电信号为异常信号。
步骤S2032,若所述第一心电信号的峰值变异度特征大于或等于所述第一阈值、且所述第一心电信号的峰值数量变异度特征小于或等于所述第二阈值,则所述第一心电信号为噪声信号。
步骤S2033,若所述第一心电信号的峰值变异度特征小于或等于所述第一阈值、且所述第一心电信号的峰值数量变异度特征大于或等于所述第二阈值,则所述第一心电信号为噪声信号。
步骤S2034,若所述第一心电信号的峰值变异度特征小于所述第一阈值、且所述第一心电信号的峰值数量变异度特征小于所述第二阈值,则所述第一心电信号为正常信号。
参见图9,为经过步骤B5阈值比较之后,对心电信号A、B、C和D进行质量评估后得到的评估结果。
其中,通过第一阈值和第二阈值将二维特征平面划分为4个区域:正常区域、异常区域、噪声区域。
其中,心电信号B的峰值变异度特征小于所述第一阈值、且心电信号B的峰值数量变异度特征小于所述第二阈值,则心电信号B为正常信号。
心电信号C的峰值变异度特征大于第一阈值、且心电信号C的峰值数量变异度特征大于第二阈值,则心电信号C为异常信号。
心电信号A峰值变异度特征大于或等于所述第一阈值、且心电信号A的峰值数量变异度特征小于或等于所述第二阈值,则心电信号A为噪声信号。
心电信号D的峰值变异度特征小于或等于所述第一阈值、且心电信号D的峰值数量变异度特征大于或等于所述第二阈值,则心电信号D为噪声信号。
当然,实际应用中,在心电信号采集的过程中或采集后,可能得到多个信号片段,对多个信号片段进行评估后,位于B所在区域的信号片段为正常信号,位于C区域的信号片段为异常信号,位于A和D区域的信号片段为噪声片段。通过该方法就可以精确的评估心电信号的分类。
应理解,上述实施例中各步骤的序号的大小并不意味着执行顺序的先后,各过程的执行顺序应以其功能和内在逻辑确定,而不应对本申请实施例的实施过程构成任何限定。
本申请实施例还提供了一种计算机可读存储介质,计算机可读存储介质存储有计算机程序,计算机程序被处理器执行时可实现上述各个方法实施例中的步骤。
本申请实施例还提供了一种计算机程序产品,当计算机程序产品在电子设备上运行时,使得电子设备可实现上述各个方法实施例中的步骤。
集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储介质中。基于这样的理解,本申请实现上述实施例方法中的全部或部分流程,可以通过计算机程序来指示相关的硬件来完成,计算机程序可存储于一计算机可读存储介质中,该计算机程序在被处理器执行时,可实现上述各个方法实施例的步骤。其中,计算机程序包括计算机程序代码,计算机程序代码可以为源代码形式、对象代码形式、可执行文件或某些中间形式等。计算机可读介质至少可以包括:能够将计算机程序代码携带到第一设备的任何实体或装置、记录介质、计算机存储器、只读存储器(ROM,Read-Only Memory)、随机存取存储器(RAM,Random Access Memory)、电载波信号、电信信号以及软件分发介质。例如U盘、移动硬盘、磁碟或者光盘等。在某些司法管辖区,根据立法和专利实践,计算机可读介质不可以是电载波信号和电信信号。
本申请实施例还提供了一种芯片系统,芯片系统包括处理器,处理器与存储器耦合,处理器执行存储器中存储的计算机程序,以实现本申请任一方法实施例的步骤。芯片系统可以为单个芯片,或者多个芯片组成的芯片模组。
在上述实施例中,对各个实施例的描述都各有侧重,某个实施例中没有详述或记载的部分,可以参见其它实施例的相关描述。
本领域普通技术人员可以意识到,结合本文中所公开的实施例描述的各示例的单元及方法步骤,能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行,取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能,但是这种实现不应认为超出本申请的范围。
以上实施例仅用以说明本申请的技术方案,而非对其限制;尽管参照前述实施例对本
申请进行了详细的说明,本领域的普通技术人员应当理解:其依然可以对前述各实施例所记载的技术方案进行修改,或者对其中部分技术特征进行等同替换;而这些修改或者替换,并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围,均应包含在本申请的保护范围之内。
Claims (16)
- 一种心电信号质量评估方法,其特征在于,包括:获取第一心电信号;计算所述第一心电信号的峰值变异度特征和峰值数量变异度特征;若所述第一心电信号的峰值变异度特征小于第一阈值、且所述第一心电信号的峰值数量变异度特征小于第二阈值,则所述第一心电信号为正常信号,其中,所述第一阈值用于表示峰值变异度特征的异常分界点,所述第一阈值由多个心电信号样本的峰值变异度特征确定,所述第二阈值用于表示峰值数量变异度特征的异常分界点,所述第二阈值由多个心电信号样本的峰值数量变异度特征确定。
- 如权利要求1所述的方法,其特征在于,所述获取第一心电信号包括:获取第一时长的原始心电信号;对所述原始心电信号进行滤波处理,得到所述第一心电信号。
- 如权利要求2所述的方法,其特征在于,对所述原始心电信号进行滤波处理包括:对所述原始心电信号进行低通滤波处理和高通滤波处理。
- 如权利要求1至3任一项所述的方法,其特征在于,所述计算所述第一心电信号的峰值变异度特征和峰值数量变异度特征,包括:将所述第一心电信号进行分割处理,得到多个信号片段;计算每个信号片段的峰值列表和峰值数量,所述峰值列表包括N个峰值,N表示所述峰值数量;根据所述多个信号片段的峰值列表得到所述第一心电信号的峰值变异度特征;根据所述多个信号片段的峰值数量得到所述第一心电信号的峰值数量变异度特征。
- 如权利要求4所述的方法,其特征在于,所述信号片段包括多个离散的数据点,所述计算每个信号片段的峰值列表包括:计算第一信号片段中每相邻的两个数据点之间的差值绝对值,所述第一信号片段为所述信号片段中的任一信号片段,所述第一信号片段的峰值列表包括一个或多个第一峰值,所述第一峰值为大于前一个差值绝对值、大于后一个差值绝对值、且大于寻峰阈值的差值绝对值,所述寻峰阈值由所述第一心电信号的多个信号片段分别对应的差值绝对值确定。
- 如权利要求5所述的方法,其特征在于,所述寻峰阈值的确定方法包括:计算所述第一心电信号的多个信号片段对应的差值绝对值集合中的第一分位数和第一常数的第一乘积;计算所述第一心电信号的多个信号片段对应的差值绝对值集合中的第二分位数和第二常数的第二乘积;计算所述第一乘积和所述第二乘积的差值,得到所述寻峰阈值。
- 如权利要求4至6任一项所述的方法,其特征在于,所述根据所述多个信号片段的峰值列表得到所述第一心电信号的峰值变异度特征包括:计算所述第一心电信号的多个信号片段的峰值的标准差和均值;计算所述多个信号片段的峰值的标准差和均值的比值,得到所述第一心电信号的峰值变异度特征。
- 如权利要求4至6任一项所述的方法,其特征在于,所述根据所述多个信号片段的 峰值数量得到所述第一心电信号的峰值数量变异度特征包括:计算所述第一心电信号的多个信号片段的峰值数量的最大值和最小值的第一差值;计算所述第一心电信号的多个信号片段的峰值数量的中值;计算所述第一差值和所述中值的比值,得到所述第一心电信号的峰值数量变异度特征。
- 如权利要求1至8任一项所述的方法,其特征在于,所述第一阈值和所述第二阈值的确定方式包括:获取多个心电信号样本,所述多个心电信号样本的时长均为第一时长;计算每个所述心电信号样本的峰值变异度特征和峰值数量变异度特征;根据所述多个心电信号样本的峰值变异度特征得到所述第一阈值;根据所述多个心电信号样本的峰值数量变异度特征得到第二阈值。
- 如权利要求9所述的方法,其特征在于,所述根据所述多个心电信号样本的峰值变异度特征得到所述第一阈值包括:计算所述多个心电信号样本的峰值变异度特征中的第三分位数和第三常数的第三乘积;计算所述多个心电信号样本的峰值变异度特征中的第四分位数和第四常数的第四乘积;计算所述第三乘积和所述第四乘积的差值,得到所述第一阈值。
- 如权利要求9所述的方法,其特征在于,所述根据所述多个心电信号样本的峰值数量变异度特征得到第二阈值包括:计算所述多个心电信号样本的峰值数量变异度特征中的第五分位数和第五常数的第五乘积;计算所述多个心电信号样本的峰值数量变异度特征中的第六分位数和第六常数的第六乘积;计算所述第五乘积和所述第六乘积的差值,得到所述第二阈值。
- 如权利要求1至11任一项所述的方法,其特征在于,所述方法还包括:若所述第一心电信号的峰值变异度特征大于所述第一阈值、且所述第一心电信号的峰值数量变异度特征大于所述第二阈值,则所述第一心电信号为异常信号;若所述第一心电信号的峰值变异度特征大于或等于所述第一阈值、且所述第一心电信号的峰值数量变异度特征小于或等于所述第二阈值,则所述第一心电信号为噪声信号;若所述第一心电信号的峰值变异度特征小于或等于所述第一阈值、且所述第一心电信号的峰值数量变异度特征大于或等于所述第二阈值,则所述第一心电信号为噪声信号。
- 如权利要求9至12任一项所述的方法,其特征在于,所述获取多个心电信号样本包括:获取多个原始心电信号;对所述多个原始心电信号进行数据分割,得到多个第一时长的原始心电信号;对每个第一时长的原始心电信号进行低通滤波处理和高通滤波处理,得到所述多个心电信号样本。
- 如权利要求9至12任一项所述的方法,其特征在于,所述计算每个所述心电信号样本的峰值变异度特征的方式和所述计算所述第一心电信号的峰值变异度特征的方式相 同;所述计算每个所述心电信号样本的峰值数量变异度特征的方式和所述计算所述第一心电信号的峰值数量变异度特征的方式相同。
- 一种电子设备,其特征在于,所述电子设备包括处理器,所述处理器用于运行存储器中存储的计算机程序,以使得所述电子设备实现如权利要求1至14任一项所述的方法。
- 一种芯片系统,其特征在于,所述芯片系统包括处理器,所述处理器与存储器耦合,所述处理器执行存储器中存储的计算机程序,以实现如权利要求1至14任一项所述的方法。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP23864540.2A EP4437940A1 (en) | 2022-09-15 | 2023-08-17 | Method for evaluating electrocardiosignal quality, electronic device, and chip system |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211120062.7 | 2022-09-15 | ||
CN202211120062.7A CN117731234A (zh) | 2022-09-15 | 2022-09-15 | 一种心电信号质量评估方法、电子设备及芯片系统 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2024055807A1 true WO2024055807A1 (zh) | 2024-03-21 |
Family
ID=90253146
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2023/113618 WO2024055807A1 (zh) | 2022-09-15 | 2023-08-17 | 一种心电信号质量评估方法、电子设备及芯片系统 |
Country Status (3)
Country | Link |
---|---|
EP (1) | EP4437940A1 (zh) |
CN (1) | CN117731234A (zh) |
WO (1) | WO2024055807A1 (zh) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105997054A (zh) * | 2016-06-22 | 2016-10-12 | 天津理工大学 | 一种心电信号预分析的方法 |
CN109077715A (zh) * | 2018-09-03 | 2018-12-25 | 北京工业大学 | 一种基于单导联的心电信号自动分类方法 |
CN110226919A (zh) * | 2019-06-26 | 2019-09-13 | 广州视源电子科技股份有限公司 | 心电信号类型检测方法、装置、计算机设备及存储介质 |
CN110384482A (zh) * | 2019-06-26 | 2019-10-29 | 广州视源电子科技股份有限公司 | 心电信号分类方法、装置、计算机设备和存储介质 |
CN112971797A (zh) * | 2021-02-07 | 2021-06-18 | 北京海思瑞格科技有限公司 | 连续生理信号质量评估方法 |
-
2022
- 2022-09-15 CN CN202211120062.7A patent/CN117731234A/zh active Pending
-
2023
- 2023-08-17 WO PCT/CN2023/113618 patent/WO2024055807A1/zh unknown
- 2023-08-17 EP EP23864540.2A patent/EP4437940A1/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105997054A (zh) * | 2016-06-22 | 2016-10-12 | 天津理工大学 | 一种心电信号预分析的方法 |
CN109077715A (zh) * | 2018-09-03 | 2018-12-25 | 北京工业大学 | 一种基于单导联的心电信号自动分类方法 |
CN110226919A (zh) * | 2019-06-26 | 2019-09-13 | 广州视源电子科技股份有限公司 | 心电信号类型检测方法、装置、计算机设备及存储介质 |
CN110384482A (zh) * | 2019-06-26 | 2019-10-29 | 广州视源电子科技股份有限公司 | 心电信号分类方法、装置、计算机设备和存储介质 |
CN112971797A (zh) * | 2021-02-07 | 2021-06-18 | 北京海思瑞格科技有限公司 | 连续生理信号质量评估方法 |
Also Published As
Publication number | Publication date |
---|---|
CN117731234A (zh) | 2024-03-22 |
EP4437940A1 (en) | 2024-10-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110970057B (zh) | 一种声音处理方法、装置与设备 | |
CN108076226B (zh) | 一种通话质量调整的方法、移动终端及存储介质 | |
EP3686845A1 (en) | Image processing method and device and apparatus | |
CN109493877B (zh) | 一种助听装置的语音增强方法和装置 | |
CN106210219B (zh) | 降噪方法及装置 | |
CN113496708B (zh) | 拾音方法、装置和电子设备 | |
CN111399742B (zh) | 界面切换方法、装置和电子设备 | |
US9640193B2 (en) | Systems and methods for enhancing place-of-articulation features in frequency-lowered speech | |
WO2019011098A1 (zh) | 解锁控制方法及相关产品 | |
WO2019015418A1 (zh) | 解锁控制方法及相关产品 | |
CN103948398A (zh) | 适用于Android系统的心音定位分段方法 | |
CN117528349A (zh) | 立体声拾音方法、装置、终端设备和计算机可读存储介质 | |
CN109754823A (zh) | 一种语音活动检测方法、移动终端 | |
CN117130469B (zh) | 一种隔空手势识别方法、电子设备及芯片系统 | |
CN115314804A (zh) | 佩戴检测方法、可穿戴设备及存储介质 | |
CN111355995A (zh) | 蓝牙设备声音延迟时长的确定方法、装置及终端设备 | |
Cao et al. | Earace: Empowering versatile acoustic sensing via earable active noise cancellation platform | |
WO2024055807A1 (zh) | 一种心电信号质量评估方法、电子设备及芯片系统 | |
CN108446025A (zh) | 拍摄控制方法及相关产品 | |
CN112135235B (zh) | 质量检测方法、系统及计算机可读存储介质 | |
CN113409800B (zh) | 一种监控音频的处理方法、装置、存储介质及电子设备 | |
CN111182416B (zh) | 处理方法、装置及电子设备 | |
CN105718174B (zh) | 一种界面的切换方法及切换系统 | |
CN207518804U (zh) | 用于脖戴式语音交互耳机的远程通讯装置 | |
CN207518801U (zh) | 用于脖戴式语音交互耳机的远程音乐播放装置 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 23864540 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2023864540 Country of ref document: EP Effective date: 20240628 |