439 results about "Normal people" patented technology

The invention relates to a human-computer interaction system based on an electro-ocular signal, which is characterized in that an electro-ocular signal acquisition and amplification module acquires the electro-ocular signal through an electro-ocular signal sensor and amplifies the signal; an online electro-ocular signal processing module realizes the online mode identification of the signal from the electro-ocular signal acquisition and amplification module to judge the eye action of an operator in real time; and a controlled unit is used to realize the coding of an eye movement mode and the generation of a controlled command. The human-computer interaction system has strong applicability, high measurement precision, high identification speed and simple and convenient operation and realizes the special human-computer interaction based on the electro-ocular signal. The human-computer interaction system can help physically-disabled realize computer manipulation, text writing, webpage browsing and other operations like normal people or wireless control on other electronic equipment (such as home appliances) and other human-computer interactions; and simultaneously, the human-computer interaction system can be also used in occasions where a computer is inconvenient to operate by normal people with hands, such as a mine, rescue operation, a spacecraft, underwater and other severe or narrow environments.

The invention provides a method for constructing a surgical virtual operation teaching and training system. The method comprises the following concrete steps: (1) acquiring various inspection data classified according to normal people and patients, intensively storing the acquired data, and constructing an integrated male virtual human model and an integrated female virtual human model; (2) carrying out geometric modeling, computational modeling and deformation computation on medical data, and carrying out modeling on bones and soft tissues by adopting a multi-outline three-dimensional reconstruction algorithm; (3) reconstructing by adopting a three-dimensional model of 3DMAX10, mapping and giving physiological characteristics to organic tissues; (4) compiling related objects and simulated scenes of a virtual operation by virtual reality modeling language (VRML); (5) carrying out preoperative preparation in the virtual operation scenes, and checking and confirming patient information; (6) carrying out complete operational details of the actual method of the virtual operation again; (7) establishing a simulated operation teaching evaluation system; and (8) carrying out comprehensive evaluation and examination on a teacher and each trainee. In the method, the simulated operation teaching system is constructed by utilizing the virtual reality technology, thereby providing a wide and transparent simulated teaching and research platform for hospitals and medical schools.

The invention discloses a pair of virtual reality glasses comprising a glasses body and a head band. The glasses body comprises an eyeshade, an optical amplification eyepiece system connected with the eyeshade, a foldable connecting sleeve, a terminal placing box used for accommodating a terminal, and a rear cover connected with the terminal placing box. The foldable connecting sleeve is made of flexible and elastic plastic cement. The optical amplification eyepiece system is provided with an eye disease eyeglass installation part. The terminal placing box is provided with a gesture sensing window which corresponds to a gesture sensor of a display terminal in position. The head band includes a right side band arranged at the right end of the glasses body, a left side band arranged at the left end of the glasses body, and an upper top band arranged at the upper end of the glasses body. The pair of virtual reality glasses is easy to store and carry and convenient to wear and adjust. The pressure of the virtual reality glasses on the head is reduced, operation control on the display terminal of the virtual reality glasses can be performed with gestures and buttons, and patients with eye diseases can view a full and clear virtual reality picture with eyes just like normal people.

An implantable shunt device for draining cerebrospinal fluid from a patient's subarachnoid space. The device includes a shunt having opposed first and second ends. A one-way valve is located at the first end of the shunt. A helical tip is disposed at the second end. The helical tip is constructed to penetrate a sinus wall of the patient. Upon implantation, a hollow passageway extends between the helical tip and one-way valve such that fluid can be drained through the helical tip and out through the valve. The endovascular cerebrospinal fluid shunt of the present invention can be placed into a patient percutaneously via a catheter inserted into the venous system of the body through a needle hole, without the need for open surgery and the skin incisions required with current shunt devices. The device also allows for more physiologic drainage of cerebrospinal fluid since the device is shunting cerebrospinal fluid into the same cerebral venous system that occurs naturally in normal people.

The invention relates to a sign language interpreting, displaying and sound producing system based on electromyographic signals and motion sensors. The sign language interpreting, displaying and sound producing system comprises a gesture recognition subsystem and a semantic displaying and sound producing subsystem. The gesture recognition subsystem comprises the multi-axial motion sensors and a multi-channel muscle current acquisition and analysis module, the gesture recognition subsystem is put on the left arm and the right arm of a user, and the original surface electromyogram signals of the user and motion information of the arms of the user are obtained; gestures are differentiated by processing the electromyogram signals and data of the motion sensors. The displaying and sound producing subsystem comprises a semantic analyzer, a voice control module, a loudspeaker, a displaying module, a storage module, a communication module and the like. According to the sign language interpreting, displaying and sound producing system, by the adoption of the mode recognition technology based on the electromyographic signals of the double arms and the data of the motion sensors, the gesture recognition accuracy rate is increased; through the combination of the semantic displaying and sound producing subsystem, interpreting from commonly-used sign language to voice or text is achieved, and the efficiency of direct communication between people with language disorders and normal people is improved.

A regional people stream density estimation method based on pixels and a support vector machine (VCM) is characterized by comprising the following steps: extracting a background from a video to be processed; performing background subtraction and binary calculations on a target image, counting the number of non-zero pixel values, and judging and performing background updating; computing a perspective correction coefficient with a perspective correction algorithm based on interpolation weight, and improving effect from perspective distortion to the algorithm; counting the number of the pixels after being corrected through the perspective correction coefficient; using a pixel-based method to estimate a people stream density when the number of the pixels is smaller than the number of normal people stream density pixels; and graying the target image when the number of the pixels is larger than the number of the normal people stream pixels, and extracting texture information of the target image and recognizing the target image by categories with the VCM so as to estimate a people stream density. The regional people stream density estimation method based on the pixels and the VCM can be used for people stream density monitoring in a region with a larger area, and has the advantages of being fast, convenient, accurate, reliable, and capable of timely providing a decision-making basis for an administrative department.

Provided is a white matter fiber brain map construction method by means of a diffusion tensor imaging medical image. The method comprises the steps that an original diffusion tensor imaging image is input (101); image preprocessing is conducted on a diffusion tensor image (106), wherein the substeps of data format conversion (102), 4D image converting (103), anisotropy value computing (104) and bone removing operation (105) are included; a registration technology is utilized (107), reflection transformation (108) and a large-deformation differential homomorphic mapping algorithm (109) are used, and different tested diffusion tensor images are registrated to the same standardized space (107); diffusion weighted imaging analysis is conducted (113), wherein the substeps of analyzing a deformation field by means of a diffusion tensor model (110), conducting diffusion weighted imaging redirection (111) and estimating diffusion tensor (112) are included; two brain white matter maps are constructed for patients and normal people (115); machine learning is conducted (114), wherein feature extraction (116) and feature selection (117) are conducted on tested pictures, data sets are divided into a training set and a test set, machine learning is conducted according to the maps (118), and training is conducted to generate a classifier (121).

The invention discloses a lung cancer early diagnostic marker based on metabonomics and a screening method thereof. The diagnostic marker comprises any one or combination of various markers in 25 plasma metabolism markers. The invention also provides a method for establishing a diagnostic model through utilization of the lung cancer early diagnostic marker and application of the lung cancer earlydiagnostic marker in a diagnostic kit. According to the lung cancer early diagnostic marker, the methods and the application, through utilization of a high performance liquid chromatography-mass spectrometry, non-target metabonomics analysis is carried out on plasma of patients; through utilization of an artificial intelligence data analysis technology, different metabolite between lung cancer patients and normal people is discovered; and further through target metabonomics analysis and machine learning modeling, diagnostic capability of specificity different metabolite, namely, the lung cancer early diagnostic marker in lung cancer early diagnosis is verified.

The invention provides a bladder cancer patient urine specific metabolite spectrum, an establishing method and an application, and especially provides a method for establishing a spectrum of specific metabolites in urine of bladder cancer patients, and a method for screening a related specific biomarker. Through metabonomics, especially metabonomics based on liquid chromatography-mass spectrometry combined technology, the invention establishes a bladder cancer patient urine specific metabolite spectrum. The invention provides a basis for early diagnosis of bladder cancer and bladder cancer diseases with different pathological stages, and also provides a spectrum of specific metabolites in urine of bladder cancer patients and a related specific biomarker. The method provided by the invention has the characteristics of noninvasiveness, convenience, and rapidness, can accurately reflect the difference of metabolite spectra of bladder cancer patients and normal people, and has high specificity.

The invention discloses a high-throughput multi-index protein chip for screening esophageal squamous carcinoma specific protein markers, and discloses a kit supporting the use. 55 types of esophageal squamous carcinoma differential proteins in the serum or blood plasma are selected and used as the esophageal squamous carcinoma protein markers and protein contrast prepare the protein chip; and the protein chip comprises a substrate, protein detection indicators and a contrast detection indicator coating, wherein the protein detection indicators are distributed as arrays on the substrate. Detection liquid of a supplementary experiment reagent is filled in the kit. By adopting the protein chip, the protein profiles of three types of people, namely, normal people, people subjected to esophageal squamous cell carcinoma precancerous lesions, and people subjected to the esophageal squamous carcinoma, can be determined; and means are provided for screening the esophageal squamous carcinoma in the early stage, diagnosing in mid stage and late stage, as well as monitoring the state of illness.

The invention discloses an abnormal gait detection method based on a determined learning theory. The abnormal gait detection method based on the determined learning theory includes the steps that features are extracted, neural network modeling and identification are dynamically carried out on a gait system of healthy and normal people and patients with motor neurodegenerative diseases of different types on the basis of the extracted gait features, a constant neural network is built, a dynamic estimator is built by the utilization of the constant neural network, and abnormal gaits caused by the motor neurodegenerative diseases are distinguished from normal gaits of the general healthy people according to the minimum error principle on the basis of differences between the gait mode of the healthy and normal people and the gait mode of the patients with the motor neurodegenerative diseases of different types on the gait system dynamics, so that the abnormal gaits are detected accurately and a detection result is evaluated. The abnormal gait detection method based on the determined learning theory has the advantages that the method is convenient and easy to implement and is in a non-invasion mode, and under the intelligent home environment, daily gait monitoring on family members can be achieved by mounting a pressure sensing floor system or wearing special shoes with sensor insoles.

The invention discloses SNP rs762551 of a CYP1A2 gene and application thereof in relevant drug metabolism activity detection, and also provides a method for prejudging drug metabolism activity. The method comprises the steps of detecting whether the cytochrome oxidase P4501A2 gene (CYP1A2) and a transcript of a human individual have variation or not compared with a normal cytochrome oxidase P4501A2 gene and a normal transcript, and if so, showing that the drug metabolism activity of the individual is different from common or normal people, for the individual. The invention also discloses a corresponding detection kit used for prejudging the drug metabolism activity of the individual.

The invention belongs to the cancer detection technology, relating to a lung cancer marker detection immunochromatographic test paper and an application. The detection of a single tumour marker in the prior art can not meet the requirements of clinical early diagnosis and differential diagnosis. The invention realizes the early diagnosis of lung cancer by jointly detecting NSE and CEA in serum with a double antibody sandwich immunochromatography. The invention comprises the following preparation steps: preparing aurosol-neure NSE and aurosol-carcinoembryonic antigen CEA antibody compounds; preparing double antibody sandwich NSE and CEA detection test strips. The invention comprises the following steps in lung cancer detection: configurating series concentration NSE and CEA standard substances; preparing NSE and CEA mixed antigen solution with serum of normal people; inserting the sample pad ends of the test strips into the above concentration series standard substances respectively to observe the changes in colours of T and C lines on a NC film. The invention has the advantages of convenient detection operation, high sensitivity and precise result, and can determine lung cancer recurrence 4-12 weeks ahead.

The invention relates to an analysis method for gait characteristics after anterior cruciate ligament rupture. The method is characterized by comprising the following steps that 1), the three-dimensional kinematic data and plantar pressure data during the normal walking processes of a plurality of ACL rupture patients and normal people are obtained, multiple groups of data are randomly selected asstandard sample data, and the rest of the data is to-be-detected sample data; 2), analysis processing is conducted on the plantar pressure data to extract plantar pressure characteristic parameters;3), analysis processing is conducted on the three-dimensional kinematic data and gait characteristic three-dimensional kinematic characteristic parameters are extracted; 4), training is conducted on the basis of the gait characteristic three-dimensional kinematic characteristic parameters and the plantar pressure characteristic parameters extracted from the standard sample data to obtain an evaluation model, and cluster analysis is conducted taking the gait characteristic three-dimensional kinematic characteristic parameters and the plantar pressure characteristic parameters of the to-be-detected data as input to obtain a cluster analysis result. The method can be extensively applied to the analysis of the gait characteristics after anterior cruciate ligament rupture.

The invention discloses a molecular marker which utilizes a PIGK gene to carry out osteoporosis early diagnosis. With the adoption of a method using a gene chip and QPCR (Quantitative Polymerase Chain Reaction), when blood of normal people and blood of osteoporosis patients have remarkable difference, whether tested people have osteoporosis or not can be judged through detecting an expression condition of the PIGK gene in the blood. According to the correlation of the gene chip and the QPCR, the invention develops a kit for diagnosing the osteoporosis; the kit is used for diagnosing the osteoporosis through detecting the expression of the PIGK gene. The diagnosis kit provided by the invention can be used for early diagnosis of diseases and has a wide clinical application prospect.

The invention discloses a kit for juvenile osteoporosis detection. Through gene comparison, the fact that compared with a DKK1 gene in the normal people group, a juvenile form osteoporosis patient has the obvious mutant site is discovered, and the obvious mutant site is the 721 site. Through detecting the mutant site, particularly through the pair of provided specific primer pair, whether the people has the juvenile form osteoporosis symptom or not can be specifically identified. Compared with the prior art, the detection method has the advantages that the detection is convenient; accuracy and high speed are realized; the kit is suitable for being popularized and used.

The invention discloses a bone conduction and air conduction earphone. The bone conduction and air conduction earphone comprises a hollow shell (1) and a lead (7) for inputting electrical signals, wherein a pole piece (3) is arranged in the hollow centre of the shell; one end surface of the pole piece (3) sinks inward to form an accommodating space (31) in which a constant magnet (4) is arranged; one end of the shell is fixedly connected with the outer edge of an vibrating reed (2); the inner edge of the vibrating reed (2) is fixedly connected with the other end of the pole piece (3); a vibrating membrane (6) is fixed at the other end of the shell; the inner side of the vibrating membrane (6) is connected with a coil (5) which is embedded in a gap formed between the pole piece (3) and the constant magnet (4); gaps are reserved between the coil (5) and the constant magnet (4) and between the coil (5) and the pole piece (3); and the coil (5) is connected with the lead (7). The bone conduction and air conduction earphone can be used by normal people and deaf people.

The invention relates to a sign language interpreting system based on a motion sensing technology. The sign language interpreting system comprises a motion sensing device for detecting human gesture information, a sound input device for receiving to-be-translated voice, a sign language interpreting device for carrying out mutual translation on the human gesture information or the to-be-translated voice, a display device for cartooning the translated characters or the converted sign language and gestures, and a sound output device for broadcasting the translated voice. The invention further relates to a processing method for sign language interpreting based on the motion sensing technology. The sign language interpreting system and the processing method have the beneficial effects that the sign language can be translated into written text or voice in real time, and the voice can be translated into sign language to be displayed on the display device for assisting communication between deaf people and normal people; the motion sensing device adopts a depth scene CMOS sensor, and can accurately recognize gesture actions under complex background and illumination conditions, the light coding technology of the motion sensing device adopts continuous illumination but not pulse, so that the cost of the design scheme is reduced.

The invention provides a pair of intelligent glasses for speech recognition and sign language recognition. The intelligent glasses comprise an optical frame and an intelligent device arranged on the optical frame. The intelligent device comprises radar, a loudspeaker, a microphone, a displayer and a processor; the radar collects sign language information, and the microphone collects speech information; the processor is used for converting the sign language information into to-be-played speech information to realize sign language recognition or is used for converting the collected speech information into text information to realize speech recognition; the text information is displayed through the displayer, and the speech information is played through the loudspeaker. A person with hearing impairment can communicate with normal people without barriers by wearing the intelligent glasses.

The invention discloses a ketogenic diet and a manufacturing method thereof, and aims to solve the technical problem in facilitating food therapy for a patient by the ketogenic diet. The ketogenic diet disclosed by the invention comprises the following components: 0.5-4.5 parts by weight of fat and 1 part by weight of protein and carbohydrate, wherein the protein and carbohydrate contain 0.05 to 0.9 part by weight of oil-absorbing raw material. The manufacturing method of the ketogenic diet disclosed by the invention comprises the following steps: cleaning, drying moisture and mixing the protein and the carbohydrate, wherein the protein and the carbohydrate contain 0.05-0.9 part of oil-absorbing raw material and are sterilized at a high temperature. Compared with the prior art, the oil-absorbing raw material is added, the ketogenic diet contains high fat but is not greasy, has good ketogenic effect and taste, is suitable for treating epilepsy, diabetes, cancer, abnormal behavior, autism, spinal cord injury and obesity, and can also be used for reducing weight of normal people and changing the major nutrient structure of the body and for animal tests.

The invention discloses a ketogenic diet formula milk and a preparation method thereof and aims to solve the technical problem that convenience is provided for a patient to have food therapy through ketogenic diet. The ketogenic diet formula milk contains the following components per 100 g: 1.5-12.5 g of fat, 0-5 g of protein, 0-0.5 g of carbohydrate, 0-0.6 g of flavoring, 0-1.2 g of nourishing essence and the balance of liquid milk. The preparation method comprises the step of uniformly mixing fat, protein, carbohydrate, flavoring, nourishing essence and the liquid milk according to the prior art. Compared with the prior art, the ketogeic diet formula milk takes human milk and animal milk of which metabolizable sugar is removed as the main raw material, adopts a nutrient formula close to physiological needs, has a good mouthfeel, is easily accepted by the patient, is convenient to take, is suitable for treating epilepsy, diabetes, all kinds of tumors, behavior disorder, autism, brain and spinal cord injuries, and adiposity, and is also suitable for normal people to lose weight and change the structure of the main nutrients of the body, as well as for animal experiments.

The invention discloses a disinfecting and purifying agent for environment atmospheric membrane method and an environment atmospheric disinfection and purification method. The disinfecting and purifying agent is composed of the following components in percentage by weight: 2 to 25% of disinfecting agent, 20 to 60% of film forming agent, and 20 to 60% of foaming agent. The invention further provides an environment atmospheric disinfecting and purifying method. The resources of raw materials are wide, the raw materials are easy to process, the disinfecting and purifying agent is effective and economic, normal people can use the agent to cope with environment atmospheric disastrous pollution in time, the environment atmospheric disaster can be resolved by the agent, and a convenient and feasible technical scheme is especially provided for eliminating environment atmospheric dangerous dust pollution and possible atmospheric biochemical pollution.

The invention provides a mass spectrometry model used for detecting hepatocellular carcinoma serum characteristic protein, and a preparation method used for the mass spectrometry model. The method uses a plurality of characteristic protein combinations which are different in hepatocellular carcinoma patients and normal people to detects the hepatocellular carcinoma serum, adopts a method combining the traditional statistics with the modern biological informatics to process data, measures the protein combination spectrum spectrogram of serum samples of hepatocellular carcinoma patients and normal people by utilizing a mass spectrograph, and screens out the tumor markers of five corresponding hepatocellular carcinoma characteristic proteins, thus preparing the mass spectrometry model used for detecting the hepatocellular carcinoma serum characteristic proteins and provides foundation and resource for finding newer and more ideal tumor markers.

The invention provides a novel blind guiding system which is characterized by comprising a dummy road, a blind guiding controller, a sensor and a signal receiving unit, wherein the blind guiding controller is provided with a control module and a global positioning blind guiding map module; the sensor can sense the pavement condition on the dummy road and sends the sensed information to the signal receiving unit; and the control module controls the blind guiding controller to guide a blind man to go according to the information navigated by the global positioning blind guiding map module and / or the information received by the signal receiving unit. According to the novel blind guiding system provided by the invention, common roads and pavements do not have rugged ground, namely that pits and bulges are removed, thereby being favorable for smoothing the pavements, convenient for normal people and blind men to walk and capable of ensuring safety. According to the novel blind guiding system provided by the invention, a sensor is mounted on a blind guiding stick held by a blind man, and another sensor is mounted on the dummy road, thereby being convenient for the blind man to walk and good in blind guiding effect.

The invention discloses a gait analysis method capable of carrying out auxiliary screening on knee osteoarthritis. The gait analysis method comprises the following steps: on the basis of the gait characteristic data of an extracted knee joint angle and displacement, dynamically carrying out neural network modeling and identification on the gait system of healthy normal people and the gait system of knee osteoarthritis patients; establishing a constant value neural network; and utilizing the constant value neural network to construct a dynamic estimator, distinguishing abnormal gaits caused by the knee osteoarthritis and the normal gaits of general healthy crowd according to a minimum error principle on the basis of differences between the gait modes of the healthy normal people and the knee osteoarthritis patients on an aspect of gait system dynamics to realize the auxiliary screening detection of the knee osteoarthritis. An optical sensor obtains the gait characteristic data, and the abnormal gaits caused by the knee osteoarthritis and the normal gaits of the general healthy crowd can be conveniently and simply distinguished in a non-intrusive way. Compared with screening means including magnetic resonance imaging, arthroscopic surgeries and the like, the gait analysis method can realize the noninvasive screening of the knee osteoarthritis and saves time and cost.

The invention discloses application of N-acetylglucosamine in preparing a kit for detecting tumor. According to the technical scheme disclosed by the invention, the detection rate of the tumor is greater than 90%, and the tumor specificity is greater than 95%. The early-stage diagnostic rate of the tumor is greatly increased. The kit is applicable to early-stage general survey on tumor of normal people.

The invention discloses an automatic road-crossing device for improving pedestrian crossing safety. A signal output end of a pedestrian crossing signal lamp is electrically connected with a signal input end of a traffic signal processor; a lifting protective guard is arranged at the junction of a pedestrian waiting area and a pedestrian crosswalk zebra stripe, and a first signal output end of thetraffic signal processor is electrically connected with a control end of the lifting protective guard; automatic pedestrian conveying mechanisms are arranged on the two sides of the pedestrian crosswalk zebra stripe in the driving direction respectively, and a second signal output end of the traffic signal processor is electrically connected with the control end of the automatic pedestrian conveying mechanisms. According to the automatic road-crossing device, the phenomenon that pedestrians run the red light disorderly is effectively avoided through the lifting protective guard; whether pedestrians cross the street or not is warned through a voice reminder, a LED lamp and the like, meanwhile, the pedestrians can cross the street through the pedestrian automatic conveying mechanism, so thesafety of the pedestrians and vehicles is guaranteed; the automatic road-crossing device is suitable for normal people, old people, disabled people, blind people and other people, safe, efficient, time-saving, labor-saving and high in automation degree.

The invention discloses a brain function network classification method based on a variational autoencoder. The method comprises the following steps: The method comprises the following steps of: acquiring T1 weighted MRI and rs-fMRI of a plurality of normal people and patients with brain cognitive impairment; carrying out pretreatment; carrying out double regression analysis by taking the preprocessed rs-fMRI as a regression dependent variable and the brain function network as a regression independent variable to obtain an individual level brain function network; constructing a deep variationalautoencoder (VAE) model, taking the obtained individual level brain function network diagram as the input and output of the VAE, and taking the encoder part as a feature extraction module for obtaining the implicit code of the individual function network; constructing a multi-layer sensor network to classify the codes obtained by the VAE in the step 4; and deducing samples in the test set by using the trained classifiers for different brain function networks, and fusing deduction results of the classifiers to obtain a final classification result.acquiring T1 weighted magnetic resonance imagesT1 Weighted MRI and resting state functional magnetic resonance images rs-of a plurality of normal persons and patients with brain cognitive impairment; fMRI; carrying out pretreatment; pretreated rs- Performing double regression analysis by taking fMRI as a regression dependent variable and taking the brain function network as a regression independent variable to obtain an individual level brainfunction network; constructing a depth variation auto-encoder (VAE) model, taking the obtained individual level brain function network diagram as input and output of the VAE, and taking the encoder part as a feature extraction module for obtaining hidden codes of the individual function network; constructing a multi-layer perceptron network to classify the codes obtained by the VAE in the step 4;inferring samples in the test set by utilizing a plurality of trained classifiers for different brain function networks, and fusing inference results of the plurality of classifiers to obtain a finalclassification result; according According to the invention, the classification accuracy is improved.

The invention relates to a portable utility-typed sign language recognition vocal device which comprises three parts of a finger bending acquisition glove, a single chip and a voice circuit. The finger bending acquisition glove sends voltage signals which are generated by the finger bending degree according to the action of fingers and voltage signals which are generated by the acceleration of the hand movement to a simulation input port of the single chip. The simulation and the digital conversion are carried out on the voltage signals generated from the finger bending degree and the voltage signals generated from the acceleration of the hand movement by the single chip. The data processing is carried out on digital signals obtained by the conversion to give the kind information of the current sign language. Thus, the voice circuit is driven to vocalize. The portable utility-typed sign language recognition vocal device is beneficial for improving the living, studying and working conditions of deaf-mute disabled, so that normal people can provide better services for the disabled, and the deaf-mute disabled, especially deaf-mute people with low education level can communicate with normal people by sign language.

Disclosed is a CRNN-BP based intelligent blood pressure value measurement method. The method mainly includes the following steps: a) preprocessing real data; b) performing data standardization on preprocessed data and establishing a non-linear mathematical mapping relationship between pulse wave sequence signals and blood pressure values based on a CRNN-BP model; and c) performing intelligent blood pressure value measurement on real pulse wave characteristics by using the trained CRNN-BP model. In the step a), the preprocessing operation of the real data concretely includes baseline drift removal, cardiac cycle division and noise sample removal. The step a) includes the following steps: (1) using real human physiological data in a MIMIC database as an experimental sample, using a frequencyof 125 HZ, performing the baseline drift removal on a collected PPG signal by wavelet decomposition, and then removing a low frequency part of the signal to remove a baseline; (2) performing the cardiac cycle division on the data processed in the step (1) and collected ABP pulse wave signals, and combining the PPG and ABP signals belonging to the same cardiac cycle according to time relationships; and (3) removing the cardiac cycles with obvious abnormal waveform shape by using a rule-based method. The CRNN-BP based intelligent blood pressure value measurement method has the advantages of simper measurement and high detection precision, is more suitable for tracking and detecting cardiovascular diseases, and can also play a certain monitoring role for normal people without cardiovasculardiseases.