New Biometrics: Embedded Heart Sound Identification System

Heart sound identification refers to a technology that uses human heart sound signals for identification. Heart sound is a reflection of the mechanical motion of the heart and cardiovascular system, and contains physiological and pathological information about each part of the heart and the interaction between them. Therefore, heart sound signals have completely different characteristics in different people and have extremely high stability, and can be used as the identification characteristics of biometrics. In addition to being difficult to disguise, forge and tamper with the heart sound signal, it also has the advantage of being easy to obtain, so the heart sound signal of the human body can be a new type of biometric method.

This paper develops an embedded heart sound identification system based on LabVIEW. The system is easy to use and flexible, and can realize the registration, identification and confirmation of user identity.

1 Heart sound signal identification principle

The use of heart sound signals for personal identification mainly includes two steps: feature extraction and pattern matching. Feature extraction is to extract the only effective and stable features that represent the identity of the subject from the heart sound signal. Pattern matching is for training and identification. The feature patterns are used for similarity matching. This paper uses a recognition algorithm based on MelFrequencyCepstrumCoefficient (MFCC) feature extraction and VectorQuantization (VQ) model matching to design a heart sound identity recognition system.

(The picture comes from the network)

MFCC is mainly used for speaker recognition. It converts the frequency spectrum into a frequency-based nonlinear spectrum, and then converts it to the cepstrum.

By making appropriate improvements to MFCC, it can be applied to the identification of heart sounds. According to the frequency domain characteristics of the heart sound signal, the cut-off frequency of the Mel filter bank is selected to be 500Hz; because the heart sound signal has a quasi-periodic nature and is not as non-stationary as the voice signal, the frame length of the signal is selected as 256ms instead of 20ms of the voice signal ; The MFCC coefficient is selected to be 32-order, and the higher-order MFCC coefficient of the heart sound signal contains more information, and the coefficient of the first-order difference can make the signal dynamic characteristics strong. VQ is derived from scalar quantitative promotion and development. Scalar quantization is to use a number of discrete digital values ​​to represent discrete time-domain signals with continuous values ​​for each amplitude, while vector quantization is to divide several time-domain sampled signals with continuous amplitudes into a group, that is, to form a vector, and then Several discrete digital values ​​are used to represent various vectors. In the study of pattern recognition, the task of classifying each vector to be recognized needs to be completed. Compared with other recognition models (such as Gaussian mixture model), the heart sound identity recognition model based on VQ is simple in calculation and real-time.

2 system implementation

2.1 Hardware system implementation

The hardware of this system is composed of upper computer and lower computer. The overall structure is shown in Figure 2. Communication between the upper and lower computer through the HC-06 Bluetooth module, HC-06 Bluetooth module uses CSRBC04 Bluetooth technology, built-in Bluetooth antenna, the transmission power is Class2, the sensitivity can reach -80dBm.

The lower computer uses the dsPIC digital signal processor as the core to control the collection, amplification and ADC of heart sound signals, and then sends the heart sound signals to the upper computer through the HC-06 Bluetooth module (slave). The lower computer mainly includes two analog circuits and digital circuits. section. The analog circuit includes a heart sound sensor, a 30Hz high-pass, 500Hz low-pass Butterworth filter and a gain-adjustable audio amplifier. The heart sound sensor is composed of a stethoscope probe, an electret microphone, and a catheter; Butterworth filters are all 4th order, and use the Sallen-Key structure, which can be used for independent gain setting. The gain-adjustable audio amplifier uses LM4811, and its CLOCK and UP / DN pins are connected to the RG6 and RG7 pins of dsPIC to realize the amplification control of heart sound signal. The digital circuit is mainly the dsPIC main control chip and HC-06 Bluetooth module. The dsPIC33FJ128MC506 is used as the main control chip. The system clock is set to 40MHz, the sampling frequency is set to 2kHz, and the baud rate is set to 11.5kbps; the analog signal passes through its 12-bit ADC After being converted into a digital signal, it is transmitted by the UART to the HC-06 Bluetooth module (slave) and sent.

The upper computer is a terminal with the industrial control motherboard as the core, and displays, analyzes, stores and recognizes the heart sound signal. Including HC-06 Bluetooth module (main), TTL-RS232 level conversion circuit, industrial control motherboard and LCD touch screen, HC-06 Bluetooth module (main) receives and transmits the heart sound signal through the level conversion circuit to change the TTL level to RS232 level; the industrial control board connects to the Bluetooth module (main) through the RS232 interface to complete the reception of heart sound signals; the LCD touch screen is used as a human-machine interactive device, connected to the industrial control board through the LVDS bus and the USB bus, and the LVDS bus transmits video signals , USB bus transmits touch signals.

2.2 Software system implementation

Choose the WindowsEmbeddedStandard operating system designed by yourself. Because it is a componentized XP system, there is no need to design file systems and development drivers, which greatly shortens the development cycle and development difficulty. Unique enhanced write filter technology reroutes selected disk I / O to memory or other storage media, so that the operating system thinks that your read-only memory is writable; customizable boot screen and custom shell as The system starts the running Shell to prevent man-made malicious modification of the system configuration or misoperation to damage the system, ensuring platform stability and data security.

3 Heart sound identification software development

This paper uses LabVIEW virtual instrument to develop heart sound identification software based on MFCC feature extraction and VQ pattern matching algorithm. The software design process needs to use NI's DatabaseConnectivityToolkit toolkit, DatabaseConnectivityToolkit provides a complete SQL function, using MicrosoftADO technology and most commonly used databases Connect to achieve interactive operations with local or remote databases. The heart sound identification software realizes three functions: user registration, user identification and user confirmation. Each function has an independent function interface, and uses Subpanel to realize the dynamic loading interface.

User registration is divided into two steps: the first step is the input storage of basic information, including user name, age, gender, etc .; the second step is to collect heart sound signals, extract their MFCC feature parameters, and use the LBG algorithm to generate an optimal codebook storage In the local database. User identification is a 1: N mode, which collects the heart sound signals of the user to be identified, extracts MFCC characteristic parameters, and compares with all user codebooks already existing in the local database. According to the minimum average quantization distortion criterion, the optimal codebook is selected Make a match. User confirmation is a 1: 1 mode. First, the user enters the registered user name, and then collects the heart sound signal of the user to be identified, extracts the MFCC feature parameters, and compares it with the codebook of the user's specified identity, if its average quantization distortion If it is less than the established threshold, its identity is confirmed.

In the future, the heart sound denoising scheme based on adaptive enhancement technology will be studied to improve the robustness of the recognition algorithm; although the EER is 6.67% in the case of the small-capacity template experiment, in the case of the large-capacity template, to ensure that the EER is still A relatively small value, the selection of the threshold in the user confirmation mode will be the focus of the next study.

4 Conclusion

Based on the principle of MFCC feature extraction and VQ pattern matching recognition, this paper develops an embedded heart sound identification system based on LabVIEW, which has the functions of user registration, user identification and user confirmation. It has higher CRR and lower EER under the small-capacity heart sound template, which fully proves the feasibility of embedded heart sound identification technology, which will provide a high accuracy rate for various identification and information security problems facing the current society. 1. A new biometric device with strong anti-counterfeiting capability.

Square Fire Pit Burner

HNJBL top-of-the-line Gas Fire Pit burners that will provide an excellent fire source for your picturesque outdoor firepit or your comfy indoor home Fireplace. The stainless steel Fire Pit Burner comes with multiple ignition options making it suitable for most environments.
Natural Gas or Propane? By choosing the HNJBL 480*480mm SS Drop-In ring- Fire Pit Burner System - Match Lit you receive the option of either gas type with a conversion kit provided.
With the HNJBL 480*480mm SS Drop-In H-Burner System - Match Lit there are options from size and shape to heat output. Choose based on your preference or allow for our helpful staff to assist you in the process. Buy today and notice the difference in your firing experience!

Packing

Packing will by carton and pallet

Square Fire Pit Burner,Square Log Burner,Square Fire Pit Burner Kit,Square Fire Pit Insert Kit

Henan Jinbailai Industrial Co.,Ltd , https://www.jblbbqgrill.com