Cerebral stroke monitoring neck pillow system based on infrared thermal imaging and early warning method

Abstract

The invention discloses a cerebral apoplexy monitoring neck pillow system based on infrared thermal imaging, which comprises a medical memory foam pillow body, an ultrathin polyester fiber fabric pillowcase, a silicon rubber case and a cerebral apoplexy detection integrated device, and is characterized in that the cerebral apoplexy detection integrated device comprises an infrared thermal imager, a temperature sensor, a pressure sensor and a control panel; the infrared thermal imager, the temperature sensor and the pressure sensor are connected with the control panel; the control panel, the pressure sensors, the temperature sensors and the infrared thermal imager are sequentially arranged from top to bottom with the vertical center line of the top view of the pillow body as a reference, the control panel is arranged in an upper cavity in the pillow body, the pressure sensors are arranged in a middle cavity in the pillow body, the two temperature sensors are arranged on the surface of the pillow body, and the infrared thermal imager is arranged on the surface of the pillow body. The pressure sensor is arranged on the surface of the pillow body and symmetrically arranged relative to the vertical center line, the two infrared thermal imagers are arranged on the surface of the pillow body and symmetrically and obliquely arranged relative to the vertical center line, the pressure sensor and the control panel are wrapped by the silicon rubber case, and the infrared thermal imagers, the temperature sensor and the pillow body are wrapped by the pillow case.

Description

Technical Field

[0001] The present invention relates to the technical field of stroke monitoring and early warning, and more particularly to a stroke monitoring neck pillow system and an early warning method based on infrared thermal imaging applicable to home scenarios. Background Art

[0002] The current stroke early warning technology for home scenarios has the following core defects, seriously hindering its normal application process. Traditional early warning systems rely on professional equipment such as MRI and contrast-enhanced ultrasound, and cannot achieve home-based unobtrusive monitoring. Although existing home devices are equipped with multi-modal sensors, the detection process requires users to actively press buttons and complete specified actions (such as finger fine operation tests), which poses an operation obstacle to the elderly and patients with sudden symptoms.

[0003] Wearable devices (such as smart bracelets) are prone to skin allergies due to long-term wearing, and night-time monitoring may interfere with sleep; in addition, the mattress-based solution is limited by volume and hardness, and it is difficult to balance sleep comfort and physiological signal acquisition accuracy. Research shows that about 68% of users terminate use for more than one month due to comfort problems. The home environment has complex factors such as temperature fluctuations (±5°C) and electromagnetic interference (WiFi / Bluetooth devices), resulting in a decrease in the stability of infrared thermal image feature extraction. Summary of the Invention

[0004] The purpose of the present invention is to overcome the defects and deficiencies of the prior art, and provide a stroke monitoring neck pillow system and an early warning method based on infrared thermal imaging, which can realize the normalization and homeization of stroke detection, facilitate users to understand their own stroke risk information in advance, and users enter the hospital for professional examinations and treatments based on the risk early warning information.

[0005] In order to achieve the above purpose, the technical solutions adopted by the present invention are as follows:

[0006] A stroke monitoring neck pillow system based on infrared thermal imaging, comprising a medical memory foam pillow body, an ultra-thin polyester fiber fabric pillowcase, a silicone sleeve, and a stroke detection integration device. The stroke detection integration device includes an infrared thermal imager, a temperature sensor, a pressure sensor, and a control board. The infrared thermal imager, the temperature sensor, and the pressure sensor are respectively connected to the control board;

[0007] Taking the vertical center line of the top view of the pillow body as a reference, the control board, the pressure sensor, the temperature sensor, and the infrared thermal imager are arranged in sequence from top to bottom. The control board is arranged in the upper cavity inside the pillow body, the pressure sensor is disposed in the middle cavity inside the pillow body, the two temperature sensors are respectively disposed on the surface of the pillow body and are symmetrically arranged with respect to the vertical center line of the pillow body, the two infrared thermal imagers are respectively disposed on the surface of the pillow body and are symmetrically and obliquely arranged with respect to the vertical center line of the pillow body, the silicone sleeve wraps the pressure sensor and the control board respectively, and the pillowcase wraps the infrared thermal imager, the temperature sensor, and the pillow body;

[0008] The infrared thermal imager is used to collect the infrared thermal imaging images on both sides of the spine during the user's sleep, the temperature sensor is used to collect the accurate temperature data on both sides of the spine during the user's sleep, and the pressure sensor is used to collect the pressure data of the user on the pillow body during sleep; The control board is used to process and analyze the infrared thermal imaging images, extract the detected temperature data on both sides of the spine, and combine the accurate temperature data to perform temperature analysis and judgment on the detected temperature data to obtain the temperature difference ΔT on both sides of the spine;

[0009] The control board is used to calculate the longest time PDT of the same sleeping position of the user according to the pressure data, and combine the temperature difference ΔT on both sides of the spine during the user's sleep to calculate the position ischemia index PII, the stenosis temperature difference index STI, and the comprehensive risk index SRI; The control board is used to judge the stroke risk level according to the comprehensive risk index SRI during the user's sleep, generate the stroke monitoring and early warning analysis result, and send the stroke monitoring and early warning analysis result to the mobile user terminal for storage and display.

[0010] Further, the control board is integrated with a main control chip, a voltage conversion unit, a download circuit, a charging circuit, a Bluetooth circuit, and a timer circuit. The external power supply is connected to the voltage conversion unit or the charging circuit. The main control chip is connected to the voltage conversion unit. The main control chip and the voltage conversion unit are respectively connected to the download circuit, the Bluetooth circuit, and the timer circuit.

[0011] Further, the voltage conversion unit includes a 3.7V to 5V circuit, a 5V to 3.3V circuit, and a 5V to -5V circuit. The 3.7V to 5V circuit and the 5V to -5V circuit provide power for the infrared thermal imager and the pressure sensor, and the 5V to 3.3V circuit provides power for the main control chip, the download circuit, the Bluetooth circuit, and the temperature sensor.

[0012] Further, an external power supply inputs a voltage of 3.7V, and the main control chip uses the STM32F103C8T6 chip; the download circuit is connected to the main control chip through the CLK interface and the DIO interface, and the ST-LINK downloader is used to burn the program with the Keil5 software; the charging circuit is connected to the 3.7V voltage of the external power supply through a sliding switch, and the USB interface used is a Type-C interface; the Bluetooth circuit is connected to the main control chip through the USART interface, and the Bluetooth specification used is BLE V5.3+BR+EDR.

[0013] Further, the pressure sensor includes four strain gauges arranged in an array. The grid size of the strain gauge is 3×3 mm, the substrate size of the strain gauge is 6.8×4.2 mm, the sensitivity coefficient of the strain gauge is 2.0±1%, the output voltage of the strain gauge is -3V to +4V, and the output voltage accuracy of the strain gauge is 0.001V.

[0014] A stroke monitoring and early warning method based on infrared thermal imaging, which is applied to the stroke monitoring neck pillow system based on infrared thermal imaging described in any one of the above, includes the following steps:

[0015] S1: The infrared thermal imager collects the infrared thermal imaging images on both sides of the spine when the user is sleeping, the temperature sensor collects the accurate temperature data on both sides of the spine when the user is sleeping, and the pressure sensor collects the pressure data of the user on the pillow body when the user is sleeping;

[0016] S2: The control board processes and analyzes the infrared thermal imaging images, extracts the detected temperature data on both sides of the spine, combines the accurate temperature data, conducts temperature analysis and judgment on the detected temperature data, and obtains the temperature difference ΔT on both sides of the spine;

[0017] S3: The control board calculates the longest time PDT in the same sleeping position of the user according to the pressure data, combines the temperature difference ΔT on both sides of the user's spine during sleep, and calculates the position ischemia index PII, the stenosis temperature difference index STI, and the comprehensive risk index SRI;

[0018] S4: The control board judges the stroke risk level according to the comprehensive risk index SRI during the user's sleep, generates the stroke monitoring and early warning analysis result, and sends the stroke monitoring and early warning analysis result to the mobile user terminal for storage and display.

[0019] Further, step S2 includes:

[0020] Preprocess the infrared thermal imaging image, use Gaussian filtering to denoise the infrared thermal imaging image, and remove background noise and sensing errors; convert the thermal map data in the infrared thermal imaging image into temperature values, and select the temperature range of a normal human body to distinguish human body temperature from environmental temperature; perform region segmentation on the infrared thermal imaging image to separate the human body region from the environmental region, and use Canny edge detection to extract the human body contour from the infrared thermal imaging image;

[0021] Use the position of the spine in the infrared thermal imaging image as the reference line for division, and divide the left and right parts according to the relative positions of the brain and the spine; infer the center line from the temperature change in the spine region of the infrared thermal imaging image, and use an algorithm based on temperature gradient to determine the position of the center line; calculate the change in the temperature value of each column in the infrared thermal imaging image, find the place where the temperature change is most obvious, and divide the infrared thermal imaging image into left and right parts according to the center line.

[0022] Further, step S2 further includes:

[0023] After dividing the left and right parts, extract the temperature data of the left part and the right part respectively, and calculate the temperature distribution of the corresponding regions; calculate the difference in the average temperature of the two regions Judge whether there is a large temperature difference on both sides; if the difference in average temperature That is, it indicates that there is an obvious temperature difference on both sides, and the temperature difference calculation is required; calculate the difference between the lowest temperatures on both sides of the spine, that is, |T 左 -T 右 | = ΔT;

[0024] Use the accurate temperature data provided by the temperature sensor to assist in judging the temperature regions on the left and right sides; check whether there is a low-temperature region in the measurement region of the temperature sensor; if the temperature value of the temperature sensor differs greatly from the result of the infrared thermal imaging, and the low-temperature region in the infrared image does not appear in the temperature sensor region, the value of the temperature sensor helps to determine the exact position of the low-temperature region; if the low-temperature region is within the measurement region of the temperature sensor, use the value of the temperature sensor to correct the temperature value in the infrared thermal imaging image to improve the accuracy of the temperature difference calculation; output the temperature difference ΔT result on both sides of the spine.

[0025] Further, the control board calculates the longest time PDT of the user's sleep in the same position according to the pressure data, specifically:

[0026] Set the pressure values of the four strain gauges as P A 、P B 、P C and P D , before starting to analyze the turning behavior, normalize all pressure data as:

[0027]

[0028] Wherein, P i is the pressure value of strain gauge i; P i ′ is the pressure value of strain gauge i after normalization; P max is the maximum pressure value of the strain gauge; P min is the minimum pressure value of the strain gauge;

[0029] When monitoring whether the user turns over, the user's sleep behavior is divided into a static state and a dynamic state. The static state indicates that the user does not turn over, and the dynamic state indicates that the user turns over;

[0030] By calculating the change rate of the pressure values of the four strain gauges, it is judged whether the user is currently in a dynamic state;

[0031] The calculation formula for the change rate of the pressure value is: ΔP i =P i ′ (t) - P i ′ (t - 1);

[0032] Wherein, ΔP i is the change rate of the pressure value of strain gauge i; P i ′ (t) is the pressure value of strain gauge i at time t after normalization; P i ′ (t - 1) is the pressure value of strain gauge i at time t - 1 after normalization;

[0033] Calculate the pressure changes of all strain gauges, and calculate the sum of the pressure changes of all strain gauges as an index for the user to turn over. The calculation formula is:

[0034] Wherein, ΔP total is the sum of the change rates of the pressure values of all strain gauges; if ΔP total is greater than the preset threshold, it is considered that the user has turned over;

[0035] Start timing from the moment the pressure appears, stop timing every time it is determined that the user has turned over, and record the timing duration; start a new timing, and the subsequent timing duration covers the previous timing duration without storage; end the timing when the pressure is 0, and obtain the longest time PDT of the user's same body position during each period of sleep.

[0036] Furthermore, calculate the body position ischemia index PII, the stenosis temperature difference index STI, and the comprehensive risk index SRI. Specifically:

[0037] The calculation formula for the body position ischemia index PII is:

[0038]

[0039] The calculation formula of the narrow temperature difference index STI is as follows:

[0040] The calculation formula of the comprehensive risk index SRI is: SRI = 0.6×min(STI, 150) + 0.4×PII.

[0041] Compared with the prior art, the present invention collects the infrared thermal imaging images on both sides of the spine of the user during sleep through an infrared thermal imager, collects the accurate temperature data on both sides of the spine of the user during sleep through a temperature sensor, and collects the pressure data on the pillow body of the user during sleep through a pressure sensor. The control board calculates through the comprehensive risk index SRI, generates a stroke monitoring and early warning analysis result, and sends it to the mobile user terminal. This application can realize the normalization and householdization of stroke detection, facilitate the user to understand their own stroke risk information in advance, and the user enters the hospital for professional examination and treatment based on the risk warning information. Description of the Drawings

[0042] Figure 1 It is a top view schematic diagram of the pillow body after being made transparent and integrated with the stroke detection device.

[0043] Figure 2 It is a side view schematic diagram of the pillow body after being made transparent and integrated with the stroke detection device.

[0044] Figure 3 It is a connection schematic diagram of the stroke detection integrated device and the mobile user terminal.

[0045] Figure 4 It is a flow schematic diagram of the stroke monitoring and early warning method based on infrared thermal imaging.

[0046] Explanation of the Reference Numerals in the Drawings:

[0047] 1 - Infrared thermal imager; 2 - Temperature sensor; 3 - Pressure sensor; 4 - Control board. Detailed Embodiments

[0048] The following further describes the stroke monitoring neck pillow system and early warning method based on infrared thermal imaging of the present invention in conjunction with the drawings and specific embodiments.

[0049] Please refer to Figure 1 and Figure 2, the present invention discloses a stroke monitoring cervical pillow system based on infrared thermal imaging, which includes a medical memory foam pillow body, an ultra-thin polyester fiber fabric pillowcase, a silicone sleeve, and a stroke detection integration device. The stroke detection integration device includes an infrared thermal imager 1, a temperature sensor 2, a pressure sensor 3, and a control board 4. The infrared thermal imager 1, the temperature sensor 2, and the pressure sensor 3 are respectively connected to the control board 4.

[0050] Taking the vertical center line of the top view of the pillow body as a reference, the control board 4, the pressure sensor 3, the temperature sensor 2, and the infrared thermal imager 1 are arranged in sequence from top to bottom. The control board 4 is arranged in the upper cavity inside the pillow body. The pressure sensor 3 is arranged in the middle cavity inside the pillow body. Two temperature sensors 2 are respectively arranged on the surface of the pillow body and are symmetrically arranged with respect to the vertical center line of the pillow body. Two infrared thermal imagers 1 are respectively arranged on the surface of the pillow body and are symmetrically inclined with respect to the vertical center line of the pillow body. The silicone sleeve wraps the pressure sensor 3 and the control board 4 respectively, and the pillowcase wraps the infrared thermal imager 1, the temperature sensor 2, and the pillow body.

[0051] The infrared thermal imager 1 is used to collect the infrared thermal imaging images on both sides of the spine when the user is sleeping. The temperature sensor 2 is used to collect the accurate temperature data on both sides of the spine when the user is sleeping. The pressure sensor 3 is used to collect the pressure data on the pillow body when the user is sleeping. The control board 4 is used to process and analyze the infrared thermal imaging images, extract the detected temperature data on both sides of the spine, and combine the accurate temperature data to perform temperature analysis and judgment on the detected temperature data to obtain the temperature difference ΔT on both sides of the spine.

[0052] The control board 4 is used to calculate the longest time PDT of the same body position during the user's sleep according to the pressure data, and combine the temperature difference ΔT on both sides of the spine during the user's sleep to calculate the position ischemia index PII, the stenosis temperature difference index STI, and the comprehensive risk index SRI. The control board 4 is used to judge the stroke risk level according to the comprehensive risk index SRI during the user's sleep, generate the stroke monitoring and early warning analysis result, and send the stroke monitoring and early warning analysis result to the mobile user terminal for storage and display.

[0053] The control board 4 is integrated with a main control chip, a voltage conversion unit, a download circuit, a charging circuit, a Bluetooth circuit, and a timer circuit. The external power supply is connected to the voltage conversion unit or the charging circuit. The main control chip is connected to the voltage conversion unit. The main control chip and the voltage conversion unit are respectively connected to the download circuit, the Bluetooth circuit, and the timer circuit.

[0054] The voltage conversion unit includes a 3.7V to 5V circuit, a 5V to 3.3V circuit, and a 5V to -5V circuit. The 3.7V to 5V circuit and the 5V to -5V circuit provide power for the infrared thermal imager 1 and the pressure sensor 3. The 5V to 3.3V circuit provides power for the main control chip, the download circuit, the Bluetooth circuit, and the temperature sensor 2.

[0055] The external power supply inputs a voltage of 3.7V, and the main control chip uses the STM32F103C8T6 chip. The download circuit is connected to the main control chip through the CLK interface and the DIO interface, and the ST-LINK downloader is used to burn the program with the Keil5 software. The charging circuit is connected to the 3.7V voltage of the external power supply through a sliding switch, and the USB interface used is a Type-C interface. The Bluetooth circuit is connected to the main control chip through the USART interface, and the Bluetooth specification used is BLE V5.3+BR+EDR. The timer circuit serves as the timer of the main control chip, and the timer circuit calculates the time when the user uses the neck pillow.

[0056] The pressure sensor 3 includes four strain gauges arranged in an array. The grid size of the strain gauge is 3×3mm, the substrate size of the strain gauge is 6.8×4.2mm, the sensitivity coefficient of the strain gauge is 2.0±1%, the output voltage of the strain gauge is -3V to +4V, and the output voltage accuracy of the strain gauge is 0.001V.

[0057] Please refer to Figure 3 and Figure 4 The present invention also discloses a stroke monitoring and early warning method based on infrared thermal imaging, which is applied to the stroke monitoring neck pillow system based on infrared thermal imaging described in any one of the above, and includes the following steps:

[0058] S1: The infrared thermal imager collects the infrared thermal imaging images on both sides of the spine when the user is sleeping, the temperature sensor collects the accurate temperature data on both sides of the spine when the user is sleeping, and the pressure sensor collects the pressure data of the user on the pillow body when the user is sleeping;

[0059] S2: The control board processes and analyzes the infrared thermal imaging images, extracts the detected temperature data on both sides of the spine, combines the accurate temperature data, conducts temperature analysis and judgment on the detected temperature data, and obtains the temperature difference ΔT on both sides of the spine;

[0060] S3: The control board calculates the longest time PDT of the same body position during the user's sleep according to the pressure data, combines the temperature difference ΔT on both sides of the spine during the user's sleep, and calculates the body position ischemia index PII, the stenosis temperature difference index STI, and the comprehensive risk index SRI;

[0061] S4: The control board judges the stroke risk level according to the comprehensive risk index SRI during the user's sleep, generates the stroke monitoring and early warning analysis result, and sends the stroke monitoring and early warning analysis result to the mobile user terminal for storage and display.

[0062] Step S2. The control board processes and analyzes the infrared thermal imaging image, extracts the detected temperature data on both sides of the spine, combines the accurate temperature data, and performs temperature analysis and judgment on the detected temperature data to obtain the temperature difference ΔT between both sides of the spine, including:

[0063] Preprocess the infrared thermal imaging image. Denoise the infrared thermal imaging image using Gaussian filtering to remove background noise and sensing errors; convert the thermal map data in the infrared thermal imaging image into temperature values, and select the temperature range of a normal human body to distinguish the human body temperature from the ambient temperature; perform regional segmentation on the infrared thermal imaging image to separate the human body area from the ambient area, and use Canny edge detection to extract the human body contour from the infrared thermal imaging image.

[0064] Take the position of the spine in the infrared thermal imaging image as the reference line for division, and divide the left and right parts according to the relative positions of the brain and the spine; infer the center line through the temperature change in the spine area of the infrared thermal imaging image, and use an algorithm based on temperature gradient to determine the position of the center line; calculate the change in temperature values of each column of the infrared thermal imaging image, find the place where the temperature change is most obvious, and divide the infrared thermal imaging image into left and right parts according to the center line.

[0065] In step S2, the control board processes and analyzes the infrared thermal imaging image, extracts the detected temperature data on both sides of the spine, combines the accurate temperature data, and performs temperature analysis and judgment on the detected temperature data to obtain the temperature difference ΔT between both sides of the spine. It also includes:

[0066] After dividing the left and right parts, extract the temperature data of the left part and the right part respectively, and calculate the temperature distribution of the corresponding areas; calculate the difference in the average temperature of the two areas. Judge whether there is a large area of temperature difference between the two sides; if the difference in average temperature That is, it indicates that there is an obvious temperature difference between the two sides, and it is necessary to calculate the temperature difference; calculate the difference between the lowest temperatures on both sides of the spine, that is, |T 左 -T 右 | = ΔT;

[0067] Use the accurate temperature data provided by the temperature sensor to assist in judging the temperature areas on the left and right sides; check whether there is a low-temperature area in the measurement area of the temperature sensor; if the temperature value of the temperature sensor is quite different from the result of the infrared thermal imaging, and the low-temperature area in the infrared image does not appear in the temperature sensor area, the value of the temperature sensor helps to determine the exact position of the low-temperature area; if the low-temperature area is within the measurement area of the temperature sensor, use the value of the temperature sensor to correct the temperature value in the infrared thermal imaging image to improve the accuracy of the temperature difference calculation; output the result of the temperature difference ΔT between both sides of the spine.

[0068] In step S3, the control board calculates the longest time PDT of the user's sleep in the same position based on the pressure data, specifically as follows:

[0069] Set the pressure values of the four strain gauges as P A , P B , P C and P D . Before starting to analyze the turning behavior, normalize all the pressure data as:

[0070]

[0071] In the formula, P i is the pressure value of strain gauge i; P i ′ is the pressure value of strain gauge i after normalization; P max is the maximum pressure value of the strain gauge; P min is the minimum pressure value of the strain gauge;

[0072] When monitoring whether the user turns over, divide the user's sleep behavior into a static state and a dynamic state. The static state indicates that the user does not turn over, and the dynamic state indicates that the user turns over;

[0073] By calculating the change rate of the pressure values of the four strain gauges, determine whether the user is currently in a dynamic state;

[0074] The calculation formula for the change rate of the pressure value is: ΔP i = P i ′ (t) - P i ′ (t - 1);

[0075] In the formula, ΔP i is the change rate of the pressure value of strain gauge i; P i ′ (t) is the pressure value of strain gauge i at time t after normalization; P i ′ (t - 1) is the pressure value of strain gauge i at time t - 1 after normalization;

[0076] Calculate the pressure changes of all the strain gauges, and calculate the sum of the pressure changes of all the strain gauges as an index for the user to turn over. The calculation formula is:

[0077] In the formula, ΔP total is the sum of the change rates of the pressure values of all the strain gauges; if ΔP total is greater than the preset threshold, it is considered that the user has turned over.

[0078] The timer circuit of the control board starts timing when the pressure appears, stops timing each time it determines that the user has turned over, and records the timing duration. A new timing is started, and the subsequent timing duration overwrites the previous one without storage. When the pressure is 0, the timing ends, and the longest time PDT of the user's sleeping in the same position for each period is obtained.

[0079] In step S3, the postural ischemia index PII, the stenosis temperature difference index STI, and the comprehensive risk index SRI are calculated. Specifically:

[0080] The calculation formula for the postural ischemia index PII is:

[0081]

[0082] The calculation formula for the stenosis temperature difference index STI is:

[0083] The calculation formula for the comprehensive risk index SRI is: SRI = 0.6×min(STI, 150) + 0.4×PII.

[0084] In step S4, after obtaining the calculation result of the comprehensive risk index SRI, the calculation result of the comprehensive risk index SRI is used as a parameter of the mean square error algorithm. After secondary calculation, the processing result is obtained. The processing result is compared with the set preset value to judge the user's stroke risk level. When the processing result is less than or equal to the preset interval 1, it is determined that the user's stroke risk level is low risk; when the processing result is in the preset interval 2, it is determined that the user's stroke risk level is medium risk; when the processing result is greater than or equal to the preset interval 3, it is determined that the user's stroke risk level is high risk. The main control chip generates a stroke monitoring and early warning analysis result according to the above judgment and sends it to the mobile user terminal through the Bluetooth circuit.

[0085] The mobile user terminal processes the stroke monitoring and early warning analysis result and generates different feedbacks to the user according to the result. For example, when the user's stroke risk level is low risk, the mobile user terminal pushes a health reminder. When the user's stroke risk level is medium risk, the mobile user terminal displays that the user needs to find a professional doctor for preventive diagnosis and sends a text message to remind the user. When the user's stroke risk level is high risk, the page of the mobile user terminal turns red with a warning, generates a high-risk stroke early warning page, and enables the mobile phone permission to send a high-level warning text message about family member's stroke to the emergency contact.

[0086] To ensure the security of user data during transmission between the neck pillow system and the mobile user terminal, the present invention adopts the Galois / Counter Mode (GCM) of the Advanced Encryption Standard (AES), namely the AES-256-GCM encryption algorithm. The specific implementation is as follows: Generate a 256-bit symmetric key, which is dynamically generated in each session and shared between the two communication parties through a secure key exchange mechanism (such as Diffie-Hellman).

[0087] The core parameters of this algorithm are as follows: Key Size = 256 bits. AES-256-GCM uses a 256-bit key, which makes it highly resistant to brute-force attacks. The Initialization Vector (IV) is used to ensure the uniqueness of each encryption operation and prevent the same plaintext from generating the same ciphertext. The length of the IV is usually 12 bytes (96 bits), which is the standard length of the GCM mode. The Message Authentication Code (MAC) is used to verify the integrity and authenticity of the data. The MAC length is 128 bits. The Additional Authenticated Data (AAD) is data that does not need to be encrypted but needs to be authenticated and is used to generate the authentication tag during the encryption process but will not be decrypted during decryption.

[0088] The encryption process is as follows: Use a key generator to generate a 256-bit AES key. Use a secure random number generator to generate a 12-byte IV. Use the AES-256-GCM algorithm to encrypt the data. The encryption is through the following formula, including: C = AES-256-GCM(P, K, IV), where C is the encrypted ciphertext, P is the plaintext data, K is the 256-bit key, and IV is the initialization vector used to ensure the uniqueness of each encryption.

[0089] The receiving party uses the same key and initialization vector to decrypt the ciphertext and verifies the MAC to ensure that the data has not been tampered with. The decryption process is as follows: Load the key and IV used during encryption and decrypt using the algorithm. The decryption is through the following formula, including: P = AES-256-GCM-DEC(C, K, IV), where P is the decrypted plaintext data.

[0090] The storage method of mobile user terminal data is as follows: The user data of the neck pillow system is stored in a time-series database through the following data model, including: DataPoint = {Time, SensorID, UserID, Value}, where Time is the timestamp, SensorID is the unique identifier of the main control chip, UserID is the unique identifier of the user, and Value is the analysis result of the main control chip.

[0091] The following uses a specific calculation example to elaborate in detail on the stroke monitoring and early warning method based on infrared thermal imaging of the present invention.

[0092] When the user continuously maintains the same sleeping position for a time PDT of 120 minutes and the minimum temperature difference ΔT between both sides detected by the infrared thermal imaging of the spinal region is 1.0 °C, the stroke risk grading calculation is performed through the following steps:

[0093] Calculation of the postural ischemia index PII: According to the piecewise function formula, since PDT = 120 minutes (meeting the condition of 90 < PDT ≤ 180 minutes), substituting into the calculation gives

[0094]

[0095] Calculation of the stenosis temperature difference index STI: Based on the temperature difference ΔT = 1.0 °C, according to the formula

[0096] STI = 50·ln(1.0 + 1) + 20·1.0 = 50·0.693 + 20·1.0 = 34.65 + 20 = 54.65

[0097] Calculation of the comprehensive risk index SRI:

[0098] SRI = 0.6×min(54.65, 150) + 0.4×70 = 0.6×54.65 + 28 = 32.79 + 28 = 60.79

[0099] System determination: According to the preset grading standard:

[0100]

[0101] The current SRI = 60.79 falls into the low-risk range, triggering a first-level warning, and at the same time recording the timestamp and physiological parameters into the database.

[0102] In summary, the present invention collects the infrared thermal imaging images on both sides of the spine of the user during sleep through an infrared thermal imager, collects the accurate temperature data on both sides of the spine of the user during sleep through a temperature sensor, and collects the pressure data on the pillow body of the user during sleep through a pressure sensor. The control board calculates through the comprehensive risk index SRI, generates the stroke monitoring and early warning analysis result, and sends it to the mobile user terminal. This application can realize the normalization and householdization of stroke detection, facilitate the user to understand their own stroke risk information in advance, and the user enters the hospital for professional examinations and treatments based on the risk early warning information.

[0103] The above description is a detailed description of the preferred and feasible embodiments of the present invention, but the embodiments are not used to limit the patent application scope of the present invention. Any equivalent changes or modifications completed under the technical spirit disclosed by the present invention shall fall within the patent scope covered by the present invention.

Claims

1. A stroke monitoring neck pillow system based on infrared thermal imaging, characterized in that, It includes a medical memory foam pillow body, an ultra-thin polyester fiber fabric pillowcase, a silicone sleeve, and a stroke detection integrated device. The stroke detection integrated device includes an infrared thermal imager, a temperature sensor, a pressure sensor, and a control board. The infrared thermal imager, the temperature sensor, and the pressure sensor are respectively connected to the control board; Taking the vertical center line of the top view of the pillow body as a reference, the control board, the pressure sensor, the temperature sensor, and the infrared thermal imager are arranged in sequence from top to bottom. The control board is arranged in the upper cavity inside the pillow body, the pressure sensor is arranged in the middle cavity inside the pillow body, two temperature sensors are respectively arranged on the surface of the pillow body and are symmetrically arranged relative to the vertical center line of the pillow body, two infrared thermal imagers are respectively arranged on the surface of the pillow body and are symmetrically inclined relative to the vertical center line of the pillow body. The silicone sleeve wraps the pressure sensor and the control board respectively, and the pillowcase wraps the infrared thermal imager, the temperature sensor, and the pillow body; The infrared thermal imager is used to collect the infrared thermal imaging images on both sides of the spine when the user is sleeping. The temperature sensor is used to collect the accurate temperature data on both sides of the spine when the user is sleeping. The pressure sensor is used to collect the pressure data of the user on the pillow body when sleeping; The control board is used to process and analyze the infrared thermal imaging images, extract the detected temperature data on both sides of the spine, and combine the accurate temperature data to perform temperature analysis and judgment on the detected temperature data to obtain the temperature difference ΔT on both sides of the spine; The control board is used to calculate the longest time PDT in the same sleeping position of the user according to the pressure data, and combine the temperature difference ΔT on both sides of the spine when the user is sleeping to calculate the postural ischemia index PII, the stenosis temperature difference index STI, and the comprehensive risk index SRI; The control board is used to judge the stroke risk level according to the comprehensive risk index SRI when the user is sleeping, generate the stroke monitoring and early warning analysis result, and send the stroke monitoring and early warning analysis result to the mobile user terminal for storage and display.

2. The stroke monitoring neck pillow system based on infrared thermal imaging according to claim 1, characterized in that, The control board integrates a main control chip, a voltage conversion unit, a download circuit, a charging circuit, a Bluetooth circuit, and a timer circuit. The external power supply is connected to the voltage conversion unit or the charging circuit. The main control chip is connected to the voltage conversion unit. The main control chip and the voltage conversion unit are respectively connected to the download circuit, the Bluetooth circuit, and the timer circuit.

3. The stroke monitoring neck pillow system based on infrared thermal imaging according to claim 2, wherein, The voltage conversion unit includes a 3.7V to 5V circuit, a 5V to 3.3V circuit, and a 5V to -5V circuit. The 3.7V to 5V circuit and the 5V to -5V circuit provide power for the infrared thermal imager and the pressure sensor. The 5V to 3.3V circuit provides power for the main control chip, the download circuit, the Bluetooth circuit, and the temperature sensor.

4. The stroke monitoring neck pillow system based on infrared thermal imaging according to claim 2, characterized in that, The external power supply inputs 3.7V voltage. The main control chip uses the STM32F103C8T6 chip; The download circuit is connected to the main control chip through the CLK interface and the DIO interface, and is burned using the Keil5 software with an ST-LINK downloader; The charging circuit is connected to the 3.7V voltage of the external power supply through a sliding switch, and the USB interface used is a Type-C interface; The Bluetooth circuit is connected to the main control chip through the USART interface, and the Bluetooth specification used is BLEV5.3+BR+EDR.

5. The monitoring neck pillow system for stroke based on infrared thermal imaging according to claim 1, characterized in that, The pressure sensor includes four strain gauges arranged in an array. The grid size of the strain gauge is 3×3 mm, the substrate size of the strain gauge is 6.8×4.2 mm, the sensitivity coefficient of the strain gauge is 2.0±1%, the output voltage of the strain gauge is -3V to +4V, and the output voltage accuracy of the strain gauge is 0.001V.

6. A stroke monitoring and early warning method based on infrared thermal imaging, which is applied to the stroke monitoring neck pillow system based on infrared thermal imaging according to any one of claims 1 to 5, characterized in that, It includes the following steps: S1: The infrared thermal imager collects the infrared thermal imaging images on both sides of the spine when the user is sleeping, the temperature sensor collects the accurate temperature data on both sides of the spine when the user is sleeping, and the pressure sensor collects the pressure data on the pillow body when the user is sleeping; S2: The control board processes and analyzes the infrared thermal imaging images, extracts the detected temperature data on both sides of the spine, combines the accurate temperature data, conducts temperature analysis and judgment on the detected temperature data, and obtains the temperature difference ΔT on both sides of the spine; S3: The control board calculates the longest time PDT in the same sleeping position of the user according to the pressure data, and combines the temperature difference ΔT on both sides of the spine when the user is sleeping to calculate the position ischemia index PII, the stenosis temperature difference index STI, and the comprehensive risk index SRI; S4: The control board judges the stroke risk level according to the comprehensive risk index SRI when the user is sleeping, generates the stroke monitoring and early warning analysis result, and sends the stroke monitoring and early warning analysis result to the mobile user terminal for storage and display.

7. The stroke monitoring and early warning method based on infrared thermal imaging according to claim 6, characterized in that, Step S2 includes: Preprocess the infrared thermal imaging images, use Gaussian filtering to denoise the infrared thermal imaging images, and remove background noise and sensing errors; convert the thermal map data in the infrared thermal imaging images into temperature values, and select the temperature range of a normal human body to distinguish the human body temperature from the environmental temperature; perform region segmentation on the infrared thermal imaging images to separate the human body region from the environmental region, and use Canny edge detection to extract the human body contour from the infrared thermal imaging images; Take the position of the spine in the infrared thermal imaging image as the reference line for division, and divide the left and right parts according to the relative positions of the brain and the spine; infer the center line through the temperature change in the spine region of the infrared thermal imaging image, and use an algorithm based on temperature gradient to determine the position of the center line; calculate the change in the temperature value of each column of the infrared thermal imaging image, find the place where the temperature change is the most obvious, and divide the infrared thermal imaging image into left and right parts according to the center line.

8. The stroke monitoring and early warning method based on infrared thermal imaging according to claim 7, wherein Step S2 also includes: After dividing into the left and right parts, the temperature data of the left part and the right part are extracted respectively, and the temperature distribution of the corresponding area is calculated; calculate the difference in the average temperature of the two areas Judge whether there is a large temperature difference between the two sides; if the difference in the average temperature That is, it means that there is an obvious temperature difference between the two sides, and it is necessary to calculate the temperature difference; calculate the difference between the lowest temperatures on both sides of the spine, that is, |T 左 -T 右 | = ΔT; Use the accurate temperature data provided by the temperature sensor to assist in judging the temperature regions on both sides; check whether there is a low-temperature region in the temperature sensor measurement region; if the temperature value of the temperature sensor differs greatly from the result of the infrared thermal imaging, and the low-temperature region in the infrared image does not appear in the temperature sensor region, the value of the temperature sensor helps to determine the exact position of the low-temperature region; if the low-temperature region is within the temperature sensor measurement region, use the value of the temperature sensor to correct the temperature value in the infrared thermal imaging image to improve the accuracy of the temperature difference calculation; output the temperature difference ΔT result on both sides of the spine.

9. The method for monitoring and warning of stroke based on infrared thermal imaging according to claim 8, wherein, The control board calculates the longest time PDT in the same sleeping position of the user according to the pressure data, specifically: Set the pressure values of the four strain gauges to P A 、P B 、P C and P D , before starting the analysis of the turning behavior, normalize all the pressure data as follows: Where, P i is the pressure value of strain gauge i; P i ′ is the pressure value of strain gauge i after normalization; P max is the maximum pressure value of the strain gauge; P min is the minimum pressure value of the strain gauge; When monitoring whether the user turns over, the user's sleep behavior is divided into a static state and a dynamic state. The static state indicates that the user does not turn over, and the dynamic state indicates that the user turns over; By calculating the change rate of the pressure values of the four strain gauges, it is judged whether the user is currently in a dynamic state; The calculation formula for the change rate of the pressure value is: ΔP i = P i ′ (t) - P i ′ (t - 1); where, ΔP i is the change rate of the pressure value of strain gauge i; P i ′ (t) is the pressure value of strain gauge i at time t after normalization; P i ′ (t - 1) is the pressure value of strain gauge i at time t - 1 after normalization; Calculate the pressure changes of all strain gauges and calculate the sum of the pressure changes of all strain gauges as an index for the user's turning over. The calculation formula is as follows: where ΔP total is the sum of the change rates of all strain gauge pressure values; if ΔP total is greater than a preset threshold value, it is considered that the user has turned over; Start timing from the moment when the pressure appears, stop timing every time it is determined that the user has turned over, and record the timing duration; start a new timing, and the subsequent timing duration overwrites the previous timing duration without storage; end the timing when the pressure is 0, and obtain the longest time PDT of the user's same body position during each period.

10. The stroke monitoring and early warning method based on infrared thermal imaging according to claim 9, characterized in that, Calculate the body position ischemia index PII, the stenosis temperature difference index STI and the comprehensive risk index SRI, specifically: The calculation formula of the body position ischemia index PII is: The calculation formula for the narrow temperature difference index STI is as follows: The calculation formula of the comprehensive risk index SRI is: SRI = 0.6×min(STI, 150) + 0.4×PII.

Images