Driving seat back cushion for collecting vital sign signals based on ultra-low frequency microphone

Abstract

The invention discloses a driver seat cushion for collecting vital sign signals based on an ultra-low frequency microphone, which comprises a driver seat cushion body, the ultra-low frequency microphone is embedded in the left side of the driver seat cushion body, and a signal processing module and a fatigue detection module are arranged in the driver seat cushion body. The fatigue detection module is electrically connected with the signal processing module, the fatigue detection module is electrically connected with an early warning module and a user interface module, the early warning module is electrically connected with an intervention module and a monitoring module, and the intervention module is provided with a vehicle self-driving system in a matched mode. The fatigue state of a human body can be judged half an hour in advance through the ultra-low frequency microphone, the detection timeliness is improved, the condition of detection lag can be effectively avoided, fatigue judgment can be performed on detected information, the fatigue state of a driver can be accurately reflected, early warning and intervention are performed in time, and the driving safety is improved. And the accident risk caused by fatigue driving is obviously reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of driver seat cushions, and particularly to a driver seat cushion based on collecting vital sign signals by an ultra-low frequency microphone. Background Art

[0002] With the rapid development of society and the acceleration of people's life rhythm, fatigue driving has become one of the important factors leading to traffic accidents. According to statistics, traffic accidents caused by fatigue driving account for a large proportion of the total number of traffic accidents. However, traditional fatigue detection methods mostly rely on the behavioral characteristics of drivers (such as eye movement, head posture, etc.). In addition, conventional cameras are usually used for detection, and these cameras are set on the front side of the driver seat. These methods have problems such as detection lag and low accuracy, and cannot reflect the fatigue state of the driver in real time and accurately. For this reason, we propose a driver seat cushion based on collecting vital sign signals by an ultra-low frequency microphone. Summary of the Invention

[0003] Based on the technical problems existing in the background art, the present invention proposes a driver seat cushion based on collecting vital sign signals by an ultra-low frequency microphone.

[0004] A driver seat cushion based on collecting vital sign signals by an ultra-low frequency microphone proposed by the present invention includes a driver seat cushion body. An ultra-low frequency microphone is embedded on the left side of the driver seat cushion body. A signal processing module and a fatigue detection module are arranged in the driver seat cushion body. The fatigue detection module is electrically connected to the signal processing module. The fatigue detection module is electrically connected to a warning module and a user interface module. The warning module is electrically connected to an intervention module and a monitoring module. The intervention module is matched with a vehicle self-driving system;

[0005] The user interface module is built in the in-vehicle display screen.

[0006] Preferably, the ultra-low frequency microphone is used to collect the physical characteristics of the human body such as heartbeat or blood pressure, and convert the collected information into an electrical signal and transmit it to the signal processing module.

[0007] Preferably, the signal processing module preprocesses the electrical signal by using a digital filter to eliminate the bioelectrical noise of electromyogram, electrooculogram, and electrocardiogram and power frequency interference. By means of time-frequency analysis and independent component analysis (ICA) methods, the feature parameters related to fatigue, such as the power changes in frequency bands such as α wave, β wave, and θ wave, are extracted from the preprocessed signal, and a fatigue classification model is constructed by applying a machine learning algorithm to classify the extracted feature parameters to judge the fatigue state of the driver. The machine learning algorithm can be one of a support vector machine and a neural network.

[0008] Preferably, the fatigue detection module is used to analyze the input brain wave characteristics in real time and calculate the fatigue score. The logical steps are as follows:

[0009] S101: Use historical fatigue state data and corresponding brain wave characteristics to train a machine learning model using a supervised learning algorithm, where the supervised learning algorithm can be one of support vector machine (SVM), random forest, or convolutional neural network (CNN);

[0010] S102: Input the processed brain wave characteristics into the trained machine learning model, analyze the input brain wave characteristics in real time, calculate the fatigue score, and determine the fatigue state if the score exceeds the preset threshold.

[0011] Preferably, the warning module is used to set warnings at different levels according to the fatigue score. A low-level warning uses a slight sound to prompt the driver; a medium-level warning adds a vibration prompt; a high-level warning activates stronger intervention measures, such as continuous alarm sounds or emergency light signals;

[0012] The monitoring module is used to monitor the driver's response situation, detect whether the driver adjusts the posture and changes the driving behavior. When an effective response is detected, the warning intensity of the warning module is weakened or cancelled.

[0013] Preferably, the intervention module is used to take corresponding measures according to the preset control strategy after receiving the warning signal from the warning module. In the case of a high-level warning, when the driver fails to respond effectively, the vehicle's autopilot mode is activated, the vehicle speed is gradually reduced, and the vehicle is parked on the side of the road under safe conditions, and the vehicle interior environment is adjusted, such as increasing air conditioning ventilation, playing music, etc., to help the driver regain a sober state.

[0014] Preferably, the user interface module is used to display the system status and fatigue detection results on the in-vehicle display screen, including real-time fatigue score and warning information, etc., provide touch screen or voice control, and allow the driver to query the system status, adjust the warning threshold and response mode.

[0015] Compared with the existing technology, the beneficial effects of the present invention are:

[0016] 1. By setting the ultra-low frequency microphone, it is possible to judge the fatigue state of the human body, such as drowsiness, having diseases, etc., half an hour in advance, improving the timeliness of detection and effectively avoiding the situation of detection lag;

[0017] 2. By cooperating the fatigue detection module and the information processing module, it is possible to judge the fatigue degree of the detected information and accurately reflect the fatigue state of the driver;

[0018] 3. Through the settings of the warning module and the intervention module, timely warning and intervention can be carried out when the fatigue level is relatively high, significantly reducing the accident risk caused by fatigue driving.

[0019] Through the ultra-low frequency microphone, the present invention can judge the fatigue state of the human body half an hour in advance, improving the timeliness of detection, effectively avoiding the situation of detection lag, being able to judge the fatigue level of the detected information, accurately reflecting the fatigue state of the driver and carrying out timely warning and intervention, significantly reducing the accident risk caused by fatigue driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a system block diagram of a driver's seat cushion based on collecting vital sign signals by an ultra-low frequency microphone proposed by the present invention.

[0021] Figure 2 It is a schematic cross-sectional structure diagram of a driver's seat cushion based on collecting vital sign signals by an ultra-low frequency microphone proposed by the present invention.

[0022] Figure 3 It is a flowchart of the use of a driver's seat cushion based on collecting vital sign signals by an ultra-low frequency microphone proposed by the present invention.

[0023] In the figure: 100, driver's seat cushion body; 1, ultra-low frequency microphone. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] The present invention will be further explained below with reference to specific embodiments.

[0025] Embodiment

[0026] Referring to Figures 1 - 3 , this embodiment proposes a driver's seat cushion based on collecting vital sign signals by an ultra-low frequency microphone, including a driver's seat cushion body 100. An ultra-low frequency microphone 1 is embedded on the left side of the driver's seat cushion body 100. A signal processing module and a fatigue detection module are provided in the driver's seat cushion body 100. The ultra-low frequency microphone 1 is connected to the signal processing module. The ultra-low frequency microphone 1 is used to collect the body characteristics of the human heartbeat or blood pressure and convert the collected information into an electrical signal and transmit it to the signal processing module. The signal processing module preprocesses the electrical signal by using a digital filter to eliminate the bioelectrical noise of electromyogram, electrooculogram, electrocardiogram and power frequency interference. By means of time-frequency analysis and independent component analysis (ICA) methods, the fatigue-related characteristic parameters are extracted from the preprocessed signal, such as the power changes in frequency bands such as alpha wave, beta wave, theta wave, etc., and a fatigue classification model is constructed by applying machine learning algorithms to classify the extracted characteristic parameters to judge the fatigue state of the driver. The machine learning algorithm can be one of support vector machine and neural network.

[0027] The fatigue detection module is electrically connected to the signal processing module. The fatigue detection module is used to analyze the input brain wave characteristics in real time and calculate the fatigue score. Its logical steps are as follows:

[0028] S101: Use historical fatigue state data and corresponding brain wave characteristics to train a machine learning model using a supervised learning algorithm. The supervised learning algorithm can be one of support vector machine (SVM), random forest, or convolutional neural network (CNN);

[0029] S102: Input the processed brain wave characteristics into the trained machine learning model to analyze the input brain wave characteristics in real time and calculate the fatigue score. If the score exceeds the preset threshold, it is determined to be a fatigue state;

[0030] The fatigue detection module is electrically connected to an early warning module and a user interface module. The early warning module is electrically connected to an intervention module and a monitoring module. The early warning module is used to set different levels of early warnings according to the fatigue score. The low-level early warning uses a slight sound to prompt the driver; the medium-level early warning adds a vibration prompt; the high-level early warning activates stronger intervention measures, such as continuous alarm sounds or emergency light signals;

[0031] The monitoring module is used to monitor the driver's response situation, detect whether there is a situation of adjusting the posture and changing the driving behavior. When an effective response is detected, the early warning intensity of the early warning module is weakened or cancelled;

[0032] The intervention module is matched with a vehicle self-driving system. The intervention module is used to receive the early warning signal from the early warning module and take corresponding measures according to the preset control strategy. In the case of a high-level early warning, when the driver fails to respond effectively, the vehicle's autopilot mode will be activated, the vehicle speed will be gradually reduced, and the vehicle will be parked on the side of the road under safe conditions, and the vehicle interior environment will be adjusted, such as increasing air conditioning ventilation, playing music, etc., to help the driver recover a sober state;

[0033] The user interface module is built into the in-vehicle display screen. The user interface module is used to display the system status and fatigue detection results on the in-vehicle display screen, including real-time fatigue score and early warning information, etc., and provides touch screen or voice control, allowing the driver to query the system status, adjust the early warning threshold and response mode;

[0034] This embodiment can judge the fatigue state of the human body half an hour in advance through the ultra-low frequency microphone 1, improve the timeliness of detection, effectively avoid the situation of detection lag, can judge the fatigue degree of the detected information, accurately reflect the fatigue state of the driver and give early warnings and interventions in a timely manner, and significantly reduce the accident risk caused by fatigue driving.

[0035] In this embodiment, when the driver sits on the driver's seat cushion body 100, the ultra-low frequency microphone 1 listens to body characteristics such as the human heartbeat or blood pressure, converts them into electrical signals and transmits them to the signal processing module. When listening, the human body does not need to be in contact with the driver's seat cushion body 100. The signal processing module uses a digital filter to preprocess the electrical signals to eliminate bioelectrical noises such as electromyogram, electrooculogram, and electrocardiogram, and power frequency interference. The preprocessed data is subjected to spectral analysis through fast Fourier transform (FFT) to extract energy characteristics in frequency bands related to fatigue, such as theta waves, alpha waves, and beta waves, etc. And independent component analysis (ICA) and principal component analysis (PCA) are applied to further remove noises and enhance useful signals. Then, a machine learning algorithm is applied to construct a fatigue classification model to classify the extracted characteristic parameters to determine the fatigue state of the driver. The fatigue detection module performs real-time analysis on the processed characteristic data, calculates a fatigue score, and if the score exceeds a preset threshold, it is determined to be in a fatigue state. The warning module sets different levels of warnings according to the fatigue score. A low-level warning uses a slight sound to prompt the driver to pay attention; a medium-level warning adds a vibration prompt to remind the driver to stay alert; a high-level warning activates stronger intervention measures, such as continuous alarm sounds or emergency light signals. The driver responds according to the warning. At the same time, the monitoring module monitors the driver's response situation to detect whether the driver adjusts the posture and changes the driving behavior. When an effective response is detected, the warning intensity of the warning module is weakened or cancelled. If not, it is judged whether further intervention is needed. In the case of no response to a high-level warning, the intervention module will activate the vehicle's automatic driving mode, gradually decelerate and stop safely, and at the same time adjust the vehicle interior environment, such as increasing air-conditioning ventilation, playing music, etc., to help the driver regain a sober state. Through the setting of the ultra-low frequency microphone 1, the fatigue state of the human body, such as drowsiness, having a disease, etc., can be judged half an hour in advance, improving the timeliness of detection, effectively avoiding the situation of detection lag, being able to judge the fatigue degree of the detected information, accurately reflecting the fatigue state of the driver, and being able to give a timely warning and intervention when the fatigue degree is relatively high, significantly reducing the accident risk caused by fatigue driving;

[0036] In addition, the real-time fatigue state, warning information, and system state can be displayed on the in-vehicle display screen, providing touch screen or voice control. The driver can query the system state, adjust the warning threshold, etc., to achieve the effect of user interaction.

[0037] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, makes equivalent substitutions or changes, and all should be covered by the protection scope of the present invention.

Claims

1. A driver's seat cushion for collecting vital sign signals based on an ultra-low frequency microphone, comprising a driver's seat cushion body (100), characterized in that: An ultra-low frequency microphone (1) is embedded on the left side of the driver's seat cushion body (100); a signal processing module and a fatigue detection module are arranged in the driver's seat cushion body (100); the fatigue detection module is electrically connected to the signal processing module; the fatigue detection module is electrically connected to the early warning module and the user interface module; the early warning module is electrically connected to the intervention module and the monitoring module; the intervention module is matched with a vehicle self-driving system; The user interface module is built into the vehicle-mounted display screen.

2. The driver's seat cushion based on collecting vital sign signals by an ultra-low frequency microphone according to claim 1, characterized in that: The ultra-low frequency microphone (1) is used to collect body characteristics such as human heartbeat or blood pressure, and convert the collected information into electrical signals for transmission to the signal processing module.

3. The driver's seat cushion based on collecting vital sign signals by an ultra-low frequency microphone according to claim 1, characterized in that: The signal processing module uses a digital filter to preprocess the electrical signal to eliminate the bioelectric noise and power frequency interference of electromyography, electrooculography, and electrocardiography. Through time-frequency analysis and independent component analysis (ICA) methods, characteristic parameters related to fatigue are extracted from the preprocessed signal, and a fatigue classification model is constructed using a machine learning algorithm. The extracted characteristic parameters are classified to determine the driver's fatigue state, wherein the machine learning algorithm can be one of a support vector machine and a neural network.

4. The driver's seat cushion based on collecting vital sign signals by an ultra-low frequency microphone according to claim 1, characterized in that: The fatigue detection module is used to analyze the input brain wave characteristics in real time and calculate the fatigue score. Its logical steps are as follows: S101: using historical fatigue state data and corresponding brain wave features, and using a supervised learning algorithm to train a machine learning model, wherein the supervised learning algorithm may be one of a support vector machine (SVM), a random forest, or a convolutional neural network (CNN); S102: Input the processed brain wave features into the trained machine learning model, analyze the input brain wave features in real time, calculate the fatigue score, and determine the fatigue state if the score exceeds a preset threshold.

5. The driver's seat cushion based on collecting vital sign signals by an ultra-low frequency microphone according to claim 1, characterized in that: The warning module is used to set different levels of warnings according to the fatigue score. Low-level warnings use slight sounds to remind the driver; medium-level warnings add vibration prompts; and high-level warnings initiate stronger intervention measures. The monitoring module is used to monitor the driver's response and detect whether the driver adjusts his posture and changes his driving behavior. When an effective response is detected, the warning intensity of the warning module is weakened or cancelled.

6. The driver's seat cushion based on collecting vital sign signals by an ultra-low frequency microphone according to claim 1, characterized in that: The intervention module is used to take corresponding measures according to the preset control strategy after receiving the warning signal from the warning module. In the case of a high-level warning, when the driver fails to respond effectively, the vehicle's automatic driving mode will be activated, the speed will be gradually reduced, and the vehicle will be parked on the roadside under safe conditions, and the interior environment will be adjusted to help the driver regain consciousness.

7. The driver's seat cushion based on collecting vital sign signals by an ultra-low frequency microphone according to claim 1, characterized in that: The user interface module is used to display the system status and fatigue detection results, including real-time fatigue scores and warning information, on the vehicle display screen, and provides touch screen or voice control to allow the driver to query the system status, adjust the warning threshold and response mode.

Images