CN111166286A - Dreamy travel detection method, storage medium and dreamy travel detection device - Google Patents
Dreamy travel detection method, storage medium and dreamy travel detection device Download PDFInfo
- Publication number
- CN111166286A CN111166286A CN202010006821.1A CN202010006821A CN111166286A CN 111166286 A CN111166286 A CN 111166286A CN 202010006821 A CN202010006821 A CN 202010006821A CN 111166286 A CN111166286 A CN 111166286A
- Authority
- CN
- China
- Prior art keywords
- target object
- dream
- prediction result
- trip
- sleep
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
- A61B5/4815—Sleep quality
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1113—Local tracking of patients, e.g. in a hospital or private home
- A61B5/1115—Monitoring leaving of a patient support, e.g. a bed or a wheelchair
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
Abstract
The invention discloses a sleepwalking detection method, a storage medium and a sleepwalking detection device, which are characterized in that whether a target object leaves a sleep area or not is monitored, when the target object leaves the sleep area, physiological index data in a first time period before the target object leaves the time are obtained, the physiological index data in the first time period are input into a pre-established sleepwalking front-section prediction analysis model, so that a first prediction result output by the sleepwalking front-section prediction analysis model is obtained, the first prediction result is used for indicating whether the target object is in a sleepwalking sleep state or not, and whether the target object has sleepwalking or not is determined based on the sleepwalking sleep state. The method is simple and effective, and can detect the sleepwalking condition of the target object in time, provide a real-time monitoring function for the sleepwalking patient and perform early warning of the sleepwalking.
Description
Technical Field
The invention relates to the technical field of sleep monitoring, in particular to a dreams detection method, a storage medium and a dreams detection device.
Background
In the prior art, along with the popularization of smart home products, people's lives become more and more intelligent, and meanwhile, the development of smart bedrooms which pay attention to the quality of human sleep also draws great attention. Although the existing intelligent single products such as intelligent mattresses, intelligent pillows and the like which form intelligent bedrooms can detect the physiological states of human bodies such as heart rate, brain waves, body movement and the like during sleeping, the reference significance is greater than the practical significance for general people, and the obtained physiological index data is not reasonably utilized. In addition, judgment and early warning cannot be made under dangerous conditions.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: how to quickly and effectively determine the occurrence of the dream trip of the target object based on the physiological index data of the target object.
In order to solve the above technical problems, the present invention provides a dream travel detection method, a storage medium, and a dream travel detection apparatus.
In a first aspect of the present invention, there is provided a method for detecting sleepwalking, comprising:
monitoring whether the target object leaves a sleep area or not, and when the target object leaves the sleep area, acquiring physiological index data of the target object in a first time period before the time when the target object leaves the sleep area;
inputting the physiological index data in the first time period into a pre-established dream trip front-stage prediction analysis model to obtain a first prediction result output by the dream trip front-stage prediction analysis model, wherein the first prediction result is used for indicating whether a target object is in a sleep state in a dream trip period;
and determining whether the target object has the dream trip or not based on the first prediction result.
Preferably, the monitoring whether the target object leaves the sleep area includes:
and judging whether the target object leaves the sleep area or not according to the detected body movement parameters of the target object.
Preferably, the dream trip forepart predictive analysis model is established by using a neural network algorithm, wherein the neural network algorithm comprises an extreme learning machine algorithm or a binary algorithm.
Preferably, the dream trip front section prediction analysis model is established based on an extreme learning machine algorithm, and the dream trip front section prediction analysis model is established by using the extreme learning machine algorithm, and includes the following steps:
selecting an activation function and setting the number of neurons of the hidden layer, the connection weight of the input layer and the hidden layer and the threshold value of the neurons of the hidden layer;
selecting physiological index data corresponding to the time before the occurrence of the dream trip state and physiological index data corresponding to the time without the occurrence of the dream trip state as training samples, preprocessing the training samples, and extracting characteristic data as input vectors;
substituting the input vector, the connection weight of the input layer and the hidden layer and the threshold value of the hidden layer neuron into the activation function to calculate an output matrix;
and (3) taking the judgment result of whether the sleeping state is in the dream trip stage as target output, and reversely calculating the output weight according to the output matrix so as to complete the establishment of the dream trip front-stage predictive analysis model.
Preferably, the determining whether the target object has the dream trip based on the first prediction result includes:
when the first prediction result indicates that the target object is in a sleep state in the dream trip period, judging whether the time for the current target object to leave the sleep area is greater than a preset time threshold value;
and when the time that the target object leaves the sleep area is larger than a preset time threshold, determining that the target object has the dream trip.
Preferably, after the target object is judged to have the dream trip, the method further includes: and sending the prompting information of the dream trip of the target object to a preset receiving end.
Preferably, the determining whether the target object has the dream trip based on the first prediction result includes:
when the first prediction result indicates that the target object is in a sleep state in the dream trip period, judging whether the time for the current target object to leave the sleep area is less than or equal to a preset time threshold value;
when the time that the target object leaves the sleep area is less than or equal to a preset time threshold, acquiring physiological index data in a second time period after the target object returns to the sleep area;
inputting the physiological index data in the second time interval into a pre-established dream journey posterior prediction analysis model to obtain a second prediction result which is output by the dream journey posterior prediction analysis model and used for indicating whether the target object is in a sleep state in the dream journey;
and determining whether the target object has the dream trip or not by combining the first prediction result and the second prediction result.
Preferably, the determining whether the target object has the dream trip by combining the first prediction result and the second prediction result includes:
when the first prediction result and the second prediction result indicate that the target object is in a sleep state in a dream trip period, determining that the target object has the dream trip, and recording the dream trip as a one-time dream trip state;
when the second prediction result indicates that the target object is not in the sleep state in the dream trip period, determining whether the target object has the dream trip by the following expression:
Y＝Y1*W1+Y2*W2wherein Y is1A parameter value, Y, representing said first prediction result1When the E is (0,1), the target object is in the sleep state in the dream period, and when Y is1∈(-1,0]The target object is not in a sleep state in the dream trip period; y is2A parameter value, Y, representing said second prediction2When the E is (0,1), the target object is in the sleep state in the dream period, and when Y is2∈(-1,0]The target object is not in a sleep state in the dream trip period; w1A weight, W, representing the first prediction result2A weight, W, representing the second prediction result1+W21 is ═ 1; y is a parameter value used for judging whether the target object has the dream trip or not; wherein when Y is>When 0, judging that the target object has the dream trip; and when Y is less than or equal to 0, judging that the target object does not have the dream trip.
Preferably, the physiological index data includes at least one of brain waves, heart rate, and respiration.
In a second aspect of the present application, a storage medium is provided, in which a computer program is stored, and the computer program, when executed by a processor, can implement the dream travel detection method as described above.
In a third aspect of the present application, there is provided a dream travel detection apparatus, which includes a processor and a computer readable storage medium storing a computer program, wherein the computer program, when executed by the processor, can implement the dream travel detection method as described above
Compared with the prior art, one or more embodiments in the above scheme can have the following advantages or beneficial effects:
the method for detecting the sleepwalking is applied to monitor whether a target object leaves a sleep area or not, when the target object leaves the sleep area, physiological index data in a first time period before the target object leaves the time are obtained, the physiological index data in the first time period are input into a pre-established sleepwalking front-section prediction analysis model to obtain a first prediction result output by the sleepwalking front-section prediction analysis model, the first prediction result is used for indicating whether the target object is in a sleepwalking state or not, and whether the target object has the sleepwalking or not is determined based on the sleepwalking state. The method has at least the following beneficial effects:
the method is simple and effective, and the dreams of the target object can be detected in time;
the potential danger can be judged, and the dreams of the target object are notified to the emergency contact;
double prediction can be performed, and the accuracy of detecting the sleepwalking is obviously improved;
provides a monitoring function for the dreaming travel patients and carries out dreaming travel early warning.
Drawings
The scope of the present disclosure may be better understood by reading the following detailed description of exemplary embodiments in conjunction with the accompanying drawings. Wherein the included drawings are:
fig. 1 is a schematic flow chart illustrating a dream trip detection method according to an embodiment of the present disclosure;
fig. 2 is a schematic flow chart illustrating another dream trip detection method provided in the embodiment of the present application;
fig. 3 shows a schematic flowchart of determining whether a target object has a dream trip by combining a first prediction result and a second prediction result in the embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the following will describe in detail an implementation method of the present invention with reference to the accompanying drawings and embodiments, so that how to apply technical means to solve the technical problems and achieve the technical effects can be fully understood and implemented.
In the prior art, along with the popularization of smart home products, people's lives become more and more intelligent, and meanwhile, the development of smart bedrooms which pay attention to the quality of human sleep also draws great attention. Although the existing intelligent single products such as intelligent mattresses, intelligent pillows and the like which form intelligent bedrooms can detect the physiological states of human bodies such as heart rate, brain waves, body movement and the like during sleeping, the reference significance is greater than the practical significance for general people, and the obtained physiological index data is not reasonably utilized. In addition, judgment and early warning cannot be made under dangerous conditions.
In view of this, the method for detecting a sleepwalking according to the present application includes monitoring whether a target object leaves a sleep area, when it is monitored that the target object leaves the sleep area, acquiring physiological index data of the target object in a first time period before a leaving time of the target object, inputting the physiological index data in the first time period into a pre-established sleepwalking forepart prediction analysis model to obtain a first prediction result output by the sleepwalking forepart prediction analysis model, where the first prediction result is used to indicate whether the target object is in a sleepwalking state, and determining whether the target object has a sleepwalking based on the sleepwalking state. The method has at least the following beneficial effects:
the method is simple and effective, and the dreams of the target object can be detected in time;
the potential danger can be judged, and the dreams of the target object are notified to the emergency contact;
double prediction can be performed, and the accuracy of detecting the sleepwalking is obviously improved;
provides a monitoring function for the dreaming travel patients and carries out dreaming travel early warning.
Example one
Referring to fig. 1, fig. 1 illustrates a dream travel detection method provided in an embodiment of the present application, which includes steps S101 to S103.
In step S101, whether the target object leaves the sleep area is monitored, and when it is monitored that the target object leaves the sleep area, physiological indicator data of the target object in a first time period before the time when the target object leaves the sleep area is acquired.
The step may specifically be to determine whether the target object leaves the sleep area according to the detected body motion parameter of the target object, specifically, the body motion parameter may be the number of times of turning over, the number of times of body swinging, or a pressure value obtained by a pressure sensor when the target object contacts an intelligent mattress, and the like, and may determine whether the target object leaves the mattress or the intelligent pillow, and the like, according to the body motion parameter. In addition, the acquiring of the physiological index data of the target object in the first time period before the time when the target object leaves the sleep area may be based on a sensor on a product such as a smart mattress, a smart pillow, or the like, which is in contact with the target object, acquiring the physiological index data of the target object. Wherein the physiological index data includes data of at least one physiological parameter of brain waves, heart rate and respiration of the target subject. In addition, the first period may be set as required, and a period of an appropriate length may be selected as the first period for accuracy of detection.
In step S102, the physiological index data in the first time period is input into a pre-established dream forepart predictive analysis model to obtain a first prediction result output by the dream forepart predictive analysis model, where the first prediction result is used to indicate whether the target subject is in a sleep state in the dream period.
In the embodiment of the present application, the dream trip forepart prediction analysis model may be established by using a neural network algorithm, wherein the neural network algorithm includes an extreme learning machine algorithm or a binary algorithm. As a preferable example, the dream journey forepart prediction analysis model is established by using an extreme learning machine algorithm.
Before the acquired physiological index data in the first time period is input into the pre-established dream trip front-stage predictive analysis model, the physiological index data in the first time period can be preprocessed by filtering and interpolation methods to improve the effectiveness and the analysis speed of a prediction result.
In step S103, it is determined whether the target object has dreams based on the first prediction result.
In this step, when the first prediction result indicates that the target object is in sleep in the dream trip period, it may be preliminarily determined that the target object may have the dream trip, and it may be further determined whether the target object has the dream trip by combining the time when the target object leaves the sleep area and combining with a dream trip post-analysis prediction model; when the first prediction result indicates that the target object is not in the sleep stage of the dream trip, the target object can be determined not to be in the sleep stage of the dream trip.
The method for detecting sleepwalking provided by the embodiment of the application includes monitoring whether a target object leaves a sleep area, acquiring physiological index data in a first time period before a target object leaves the sleep area when the target object leaves the sleep area, inputting the physiological index data in the first time period into a pre-established sleepwalking front-stage predictive analysis model to obtain a first prediction result output by the sleepwalking front-stage predictive analysis model, wherein the first prediction result is used for indicating whether the target object is in a sleepwalking sleep state, and determining whether the target object has sleepwalking based on the sleepwalking sleep state. The method is simple and effective, and can detect the dream trip of the target object in time.
Example two
Referring to fig. 2, fig. 2 illustrates a dream travel detection method provided in an embodiment of the present application, which includes steps S201 to S210.
In step S201, whether the target object leaves the sleep area is monitored, and when the target object leaves the sleep area, the physiological index data of the target object in a first time period before the time of leaving the sleep area is acquired.
The step may specifically be to determine whether the target object leaves the sleep area according to the detected body motion parameter of the target object, specifically, the body motion parameter may be the number of times of turning over, the number of times of body swinging, or a pressure value obtained by a pressure sensor when the target object contacts an intelligent mattress, and the like, and may determine whether the target object leaves the mattress or the intelligent pillow, and the like, according to the body motion parameter. In addition, the acquiring of the physiological index data of the target object in the first time period before the time when the target object leaves the sleep area may be based on a sensor on a product such as a smart mattress, a smart pillow, or the like, which is in contact with the target object, acquiring the physiological index data of the target object. Wherein the physiological index data includes data of at least one physiological parameter of brain waves, heart rate and respiration of the target subject. In addition, the first period may be set as required, and a period of an appropriate length may be selected as the first period for accuracy of detection.
In step S202: the physiological index data in the first time interval is input into a pre-established dream trip front-stage prediction analysis model to obtain a first prediction result output by the dream trip front-stage prediction analysis model, and the first prediction result is used for indicating whether the target object is in a sleep state in the dream trip period.
In the embodiment of the present application, the dream trip forepart prediction analysis model may be established by using a neural network algorithm, wherein the neural network algorithm includes an extreme learning machine algorithm or a binary algorithm. As a preferred example, the dream journey forepart predictive analysis model is established by using an extreme learning machine algorithm, which comprises the following steps:
selecting an activation function and setting the number of neurons of a hidden layer, the connection weight of an input layer and the hidden layer and the threshold value of the neurons of the hidden layer;
selecting physiological index data corresponding to the time before the occurrence of the dream travel state and physiological index data corresponding to the time without the occurrence of the dream travel state as training samples, preprocessing the training samples, and extracting characteristic data as input vectors;
substituting the input vector, the connection weight of the input layer and the hidden layer and the threshold of the neuron of the hidden layer into an activation function, and calculating an output matrix;
and step four, taking the judgment result of whether the sleep state is in the dream trip stage as target output, and reversely calculating the output weight according to the output matrix so as to complete the establishment of the dream trip front-stage predictive analysis model.
In the first step, the training samples can be preprocessed by filtering and interpolation methods, so that the prediction speed and efficiency of the dream trip front-stage prediction model are improved. In addition, as a specific example, the dream travel front section predictive analysis model may be constructed based on an expression of the following extreme learning machine mathematical model:
wherein L is the number of neurons in the hidden layer, g (ω)i·xj+bi) As an activation function, ωiAs the connection weights of the input layer and the ith hidden layer neuron of the hidden layer, bithreshold for the ith hidden layer neuron, βiIs the connection weight value between the ith hidden layer neuron of the hidden layer and the output layer, xjAnd yjThe jth input vector and the jth output vector, respectively, and as a preferred example, the number of hidden layer neurons is set to 1000 for best results.
Before the acquired physiological index data in the first time period is input into the pre-established dream trip front-stage predictive analysis model, the physiological index data in the first time period can be preprocessed by filtering and interpolation methods to improve the effectiveness and the analysis speed of a prediction result.
In step S203, when the first prediction result indicates that the target object is in the sleep state in the dream trip period, it is determined whether the time when the current target object leaves the sleep area is greater than a preset time threshold.
The preset time threshold can be set according to the self condition of the target object, and a proper preset time threshold is set so as to distinguish whether the target object normally leaves or not based on the preset time threshold. When the first prediction result indicates that the target object is in the sleep state in the dream stage and the time when the target object leaves the sleep area is determined to be greater than the preset time threshold, executing the steps S204 to S206; when the first prediction result indicates that the target object has a dream trip and the time for the target object to leave the sleep area is determined to be less than or equal to the preset time threshold, steps S207 to S210 are performed.
In step S204: and when the time that the target object leaves the sleep area is larger than a preset time threshold, determining that the target object has the dream trip.
Specifically, when the time that the target object leaves the sleep area is greater than a preset time threshold, it may be determined that the target object leaves abnormally, and based on a result that the first prediction result indicates that the target object is in a sleep state in a sleep stage and a determination result that the time that the target object leaves the sleep area is greater than the preset time threshold, it may be determined that the target object has sleepwalking. And judging whether the target object has the dream trip or not based on the first prediction result and a preset time threshold, so that the accuracy of detecting the occurrence of the dream trip of the target object is improved.
In step S205, a prompt message of the dream trip of the target object is sent to the preset receiving end.
In the embodiment of the application, when the target object is determined to have the dream trip based on the first prediction result and the judgment result of whether the time that the target object leaves the sleep area is greater than the preset time, the prompting information of the dream trip of the target object can be sent to the preset receiving end. As an example, the step may be that a prompting message of the dream trip of the target object is sent to a preset emergency contact by a short message or a WeChat, so that the target object can be monitored in real time and dangers can be found in time.
In addition, when it is determined that the target object has dreams, step S206 may be further performed.
In step S206, when it is determined that the target subject has dreams, the physiological index data in the first time period is saved and recorded as a one-time dreams state for updating the dreams anterior segment analysis and prediction model.
By updating the dream trip front-stage analysis and prediction model according to the use state of the target object, the accuracy of the dream trip front-stage analysis and prediction model can be improved, and personalized adjustment can be performed according to different target objects.
In step S207, when the time when the target object leaves the sleep area is less than or equal to the preset time threshold, the physiological index data in the second period after the target object returns to the sleep area is acquired.
The second time interval may be the same as or different from the time interval set in the first time interval, and is not limited in this embodiment. The acquiring of the physiological index data of the target object in the second period after the target object returns to the sleep area may be based on the sensor on the product such as the smart mattress, the smart pillow, etc. contacting the target object to acquire the physiological index data of the target object in the same manner as in step S201. Wherein the physiological index data at least comprises one of brain wave, heart rate and respiration.
In step S208, the physiological index data in the second time interval is input into a pre-established dream backward stage predictive analysis model to obtain a second prediction result output by the dream backward stage predictive analysis model and used for indicating whether the target subject is in a sleep state in the dream period.
In the embodiment of the present application, the dream travel rear section prediction analysis model may be constructed by the same method as the dream travel front section prediction analysis model, and for the specific construction process, reference may be made to step S202, and for the sake of brevity, no further description is given here.
In step S209: and determining whether the target object has the dream trip or not by combining the first prediction result and the second prediction result.
Referring to fig. 3, this step may specifically be:
step S2091: and when the first prediction result and the second prediction result both indicate that the target object is in the sleep state in the dream trip period, determining that the target object has the dream trip, and recording the dream trip as the one-time dream trip state.
Step S2092: when the second prediction result indicates that the target object is not in the sleep state in the dream period, whether the target object has the dream trip is determined by the following expression:
Y＝Y1*W1+Y2*W2wherein Y is1Parameter value, Y, representing a first prediction1When the E is (0,1), the target object is in the sleep state in the dream period, and when Y is1∈(-1,0]The target object is not in a sleep state in the dream trip period; y is2Parameter value, Y, representing second prediction2When the E is (0,1), the target object is in the sleep state in the dream period, and when Y is2∈(-1,0]The target object is not in a sleep state in the dream trip period; w1Weight, W, representing the first prediction result2A weight, W, representing the second prediction result1+W21 is ═ 1; y is a parameter value used for judging whether the target object has the dream trip or not; wherein when Y is>When 0, judging that the target object has the dream trip; and when Y is less than or equal to 0, judging that the target object does not have the dream trip.
In step S2091, when both the first prediction result and the second prediction result indicate that the target object is in the sleepwalking stage sleep state, it may be determined that the target object has sleepwalking, and the accuracy of determining whether the target object has sleepwalking may be improved by predicting the sleepwalking state of the target object by using the first-stage and second-stage sleepwalking prediction analysis models in combination, which is beneficial to significantly improving the validity of the sleepwalking detection result.
In step S2092, the weight of the first prediction result and the weight of the second prediction result may be obtained by:
using the physiological index data for verification as an input vector; obtaining an output result after the prediction analysis model is input into the dream trip front section; comparing the output result with the known result corresponding to the verified physiological index data to determine the accuracy M of the dream trip front-stage predictive analysis model1；
Using the physiological index data for verification as an input vector; obtaining an output result after the output result is input into a prediction analysis model of the rear stage of the dream trip; comparing the output result with the known result corresponding to the verified physiological index data to determine the accuracy M of the dream trip rear-stage predictive analysis model2；
The weight W of the first prediction result1And the weight of the second prediction result may be determined by the following expressions, respectively:
as a specific example, when the second prediction result indicates that the target object is not in the sleep state during the sleep stage, there may be a second prediction result with a parameter value Y2When the first prediction result indicates that the target object is in the sleep state in the dream period, the parameter value of the first prediction result may be Y1When W is equal to 11>0.5, calculated based on the following expression: y ═ Y1*W1+Y2*W2＝1*W1-1*W2＝2W1-1>0, judging that the target object has the dream trip. As another specific example, when W1When the second prediction result indicates that the target object is not in the sleep state in the dream period, the parameter value of the second prediction result may be Y2-0.8, when the first prediction result indicates that the target subject is in the sleep state during the sleep stage, there may be a first prediction result with a parameter value Y10.3, calculated based on the following expression: y ═ Y1*W1+Y2*W2＝0.3*0.6-0.8*(1-0.6)＝-0.14<0, the target object is judged not to have the dream trip.
When the first prediction result and the second prediction result are combined to determine that the target object has the dream trip, step S210 may be further performed.
In step S210: and when the dream trip of the target object is determined by combining the first prediction result and the second prediction result, storing the physiological index data in the first time interval and the physiological index data in the second time interval, and recording the physiological index data as a one-time dream trip state.
In the step, the physiological index data in the first time period and the physiological index data in the second time period are stored in a database and recorded as a one-time dream state.
According to the physiological index data in the dream travel state, on one hand, an analysis basis can be provided for the dream travel condition of the target object; on the other hand, the dreams pre-stage prediction analysis model can be updated by utilizing the physiological index data in the first time period and/or the dreams post-stage prediction analysis model can be updated by utilizing the physiological index data in the second time period, so that the accuracy of the dreams pre-stage or dreams post-stage prediction analysis model is correspondingly improved, and effective dreams early warning is favorably provided for the target object.
In the method for detecting sleepwalking provided by the embodiment of the application, whether the target object leaves the sleep area or not is monitored, when it is monitored that the target object leaves the sleep area, physiological index data in a first time period before the target object leaves the sleep area are obtained, the physiological index data in the first time period are input into a pre-established sleepwalking front-section prediction analysis model, and a first prediction result is obtained based on the sleepwalking front-section prediction analysis model. When the first prediction result indicates that the target object is in a sleep state in a sleep stage, whether the time for the target object to leave the sleep area is larger than a preset time threshold or not is further judged, and when the time for the target object to leave the sleep area is larger than the preset time threshold, the target object is determined to have the sleep stage and prompt information can be sent to a preset receiving end, so that early warning can be timely carried out when the target object has potential danger; in addition, when the time that the target object leaves the sleep area is smaller than or equal to the preset time threshold, the second prediction result is obtained by utilizing the dream trip rear-stage prediction analysis model to carry out secondary prediction, so that the detection accuracy can be obviously improved, and finally, the prediction results obtained by utilizing the dream trip front-stage prediction analysis model and the dream trip rear-stage prediction analysis model are combined to determine whether the target object has the dream trip. The method can also store the corresponding physiological index data determined as the occurrence of the dream trip so as to provide an analysis basis for the dream trip condition of the target object, and the target object updates the prediction analysis model of the front section or the rear section of the dream trip, thereby improving the accuracy of the detection of the dream trip.
In another aspect of the present application, a storage medium is provided, in which a computer program is stored, and the computer program, when executed by a processor, can implement the following steps of detecting a dream trip:
monitoring whether the target object leaves a sleep area or not, and when the target object leaves the sleep area, acquiring physiological index data of the target object in a first time period before the time when the target object leaves the sleep area;
inputting the physiological index data in the first time period into a pre-established dream trip front-stage prediction analysis model to obtain a first prediction result output by the dream trip front-stage prediction analysis model, wherein the first prediction result is used for indicating whether a target object is in a sleep state in a dream trip period;
and determining whether the target object has the dream trip or not based on the first prediction result.
In another aspect of the present application, there is provided a dream travel detection apparatus, comprising a processor and a computer readable storage medium storing a computer program, wherein the computer program, when executed by the processor, is capable of implementing the following dream travel detection steps:
monitoring whether the target object leaves a sleep area or not, and when the target object leaves the sleep area, acquiring physiological index data of the target object in a first time period before the time when the target object leaves the sleep area;
inputting the physiological index data in the first time period into a pre-established dream trip front-stage prediction analysis model to obtain a first prediction result output by the dream trip front-stage prediction analysis model, wherein the first prediction result is used for indicating whether a target object is in a sleep state in a dream trip period;
and determining whether the target object has the dream trip or not based on the first prediction result.
Although the embodiments of the present invention have been described above, the above description is only for the convenience of understanding the present invention, and is not intended to limit the present invention. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (11)
1. A method for detecting a dream trip, comprising:
monitoring whether the target object leaves a sleep area or not, and when the target object leaves the sleep area, acquiring physiological index data of the target object in a first time period before the time when the target object leaves the sleep area;
inputting the physiological index data in the first time period into a pre-established dream trip front-stage prediction analysis model to obtain a first prediction result output by the dream trip front-stage prediction analysis model, wherein the first prediction result is used for indicating whether a target object is in a sleep state in a dream trip period;
and determining whether the target object has the dream trip or not based on the first prediction result.
2. The method of claim 1, wherein monitoring whether the target subject leaves the sleep area comprises:
and judging whether the target object leaves the sleep area or not according to the detected body movement parameters of the target object.
3. The method of claim 1 or 2, wherein the dream forepart predictive analysis model is established using a neural network algorithm, wherein the neural network algorithm comprises an extreme learning machine algorithm or a dichotomy algorithm.
4. The method as claimed in claim 1 or 2, wherein the dream forepart predictive analysis model is established based on an extreme learning machine algorithm, and the dream forepart predictive analysis model is established by using the extreme learning machine algorithm, and the method comprises the following steps:
selecting an activation function and setting the number of neurons of the hidden layer, the connection weight of the input layer and the hidden layer and the threshold value of the neurons of the hidden layer;
selecting physiological index data corresponding to the time before the occurrence of the dream trip state and physiological index data corresponding to the time without the occurrence of the dream trip state as training samples, preprocessing the training samples, and extracting characteristic data as input vectors;
substituting the input vector, the connection weight of the input layer and the hidden layer and the threshold value of the hidden layer neuron into the activation function to calculate an output matrix;
and (3) taking the judgment result of whether the sleeping state is in the dream trip stage as target output, and reversely calculating the output weight according to the output matrix so as to complete the establishment of the dream trip front-stage predictive analysis model.
5. The method of claim 4, wherein determining whether the target object dreams based on the first prediction result comprises:
when the first prediction result indicates that the target object is in a sleep state in the dream trip period, judging whether the time for the current target object to leave the sleep area is greater than a preset time threshold value;
and when the time that the target object leaves the sleep area is larger than a preset time threshold, determining that the target object has the dream trip.
6. The method of claim 5, wherein after determining that the target object has dredged, the method further comprises: and sending the prompting information of the dream trip of the target object to a preset receiving end.
7. The method of claim 4, wherein determining whether the target object dreams based on the first prediction result comprises:
when the first prediction result indicates that the target object is in a sleep state in the dream trip period, judging whether the time for the current target object to leave the sleep area is less than or equal to a preset time threshold value;
when the time that the target object leaves the sleep area is less than or equal to a preset time threshold, acquiring physiological index data in a second time period after the target object returns to the sleep area;
inputting the physiological index data in the second time interval into a pre-established dream journey posterior prediction analysis model to obtain a second prediction result which is output by the dream journey posterior prediction analysis model and used for indicating whether the target object is in a sleep state in the dream journey;
and determining whether the target object has the dream trip or not by combining the first prediction result and the second prediction result.
8. The method of claim 7, wherein determining whether the target object has dreams in combination with the first prediction result and the second prediction result comprises:
when the first prediction result and the second prediction result indicate that the target object is in a sleep state in a dream trip period, determining that the target object has the dream trip, and recording the dream trip as a one-time dream trip state;
when the second prediction result indicates that the target object is not in the sleep state in the dream trip period, determining whether the target object has the dream trip by the following expression:
Y＝Y1*W1+Y2*W2wherein Y is1A parameter value, Y, representing said first prediction result1When the E is (0,1), the target object is in the sleep state in the dream period, and when Y is1∈(-1,0]The target object is not in a sleep state in the dream trip period; y is2A parameter value, Y, representing said second prediction2When the E is (0,1), the target object is in the sleep state in the dream period, and when Y is2∈(-1,0]Representing the target object not in dreamA sleep state; w1A weight, W, representing the first prediction result2A weight, W, representing the second prediction result1+W21 is ═ 1; y is a parameter value used for judging whether the target object has the dream trip or not; wherein when Y is>When 0, judging that the target object has the dream trip; and when Y is less than or equal to 0, judging that the target object does not have the dream trip.
9. The method of claim 1, wherein the physiological metric data includes at least one of brain waves, heart rate, and respiration.
10. A storage medium having stored thereon a computer program which, when executed by a processor, is capable of implementing the method of detecting sleepwalking as claimed in any one of claims 1 to 9.
11. A sleepwalking detection apparatus comprising a processor and a computer readable storage medium storing a computer program which, when executed by the processor, is capable of implementing the method as claimed in any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010006821.1A CN111166286A (en) | 2020-01-03 | 2020-01-03 | Dreamy travel detection method, storage medium and dreamy travel detection device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010006821.1A CN111166286A (en) | 2020-01-03 | 2020-01-03 | Dreamy travel detection method, storage medium and dreamy travel detection device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111166286A true CN111166286A (en) | 2020-05-19 |
Family
ID=70618686
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010006821.1A Pending CN111166286A (en) | 2020-01-03 | 2020-01-03 | Dreamy travel detection method, storage medium and dreamy travel detection device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111166286A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112489720A (en) * | 2020-10-16 | 2021-03-12 | 西安得眠堂健康管理工作部 | Intelligent preparation method and device of compound peptide for improving sleep quality |
| WO2023200651A1 (en) * | 2022-04-13 | 2023-10-19 | Sleep Number Corporation | Detecting and preventing sleepwalking events |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7855652B1 (en) * | 2006-09-07 | 2010-12-21 | Ric Investments, Llc | System and method for detecting sleepwalking |
| CN103717125A (en) * | 2011-05-18 | 2014-04-09 | V视股份有限公司 | System and method for determining sleep and sleep stages of a person |
| CN104063994A (en) * | 2014-03-13 | 2014-09-24 | 苏州天趣信息科技有限公司 | Warning device for identifying human consciousness based on camera |
| WO2015042579A1 (en) * | 2013-09-23 | 2015-03-26 | The Board Of Trustees Of The Leland Stanford Junior University | Monitoring and treating sleep disorders |
| CN105231998A (en) * | 2015-10-23 | 2016-01-13 | 深圳市冠旭电子有限公司 | Method and device for monitoring sleep |
| CN105769203A (en) * | 2014-12-18 | 2016-07-20 | 西安发威电子科技有限公司 | Cloth patch with functions of sleepwalking detection and reminding |
| CN106446552A (en) * | 2016-09-28 | 2017-02-22 | 湖南老码信息科技有限责任公司 | Prediction method and prediction system for sleep disorder based on incremental neural network model |
| US20170290528A1 (en) * | 2016-04-12 | 2017-10-12 | Cardiac Pacemakers, Inc. | Sleep study using an implanted medical device |
| CN107374615A (en) * | 2017-08-15 | 2017-11-24 | 北京道贞健康科技发展有限责任公司 | A kind of electrocardio, breathing, the sleep-walking reporting system and method for position monitoring |
| CN107875496A (en) * | 2017-11-22 | 2018-04-06 | 宁波德葳智能科技有限公司 | A kind of intelligent sleep management eye-shade device and its control method |
| CN108010579A (en) * | 2017-11-30 | 2018-05-08 | 西安科锐盛创新科技有限公司 | Health monitoring system |
| CN108125674A (en) * | 2017-12-21 | 2018-06-08 | 速眠创新科技（深圳）有限公司 | Sleep monitoring device |
| CN108882892A (en) * | 2016-03-31 | 2018-11-23 | Zoll医疗公司 | The system and method for tracking patient motion |
| CN109091150A (en) * | 2017-11-29 | 2018-12-28 | 惠州市德赛工业研究院有限公司 | Recognition methods, sleep quality appraisal procedure and the intelligent wearable device that body of sleeping moves |
| CN208769772U (en) * | 2017-08-15 | 2019-04-23 | 北京道贞健康科技发展有限责任公司 | A kind of electrocardio, breathing, position monitoring sleep-walking reporting system |
| US20190117151A1 (en) * | 2017-09-12 | 2019-04-25 | Bluesleep Ny, Llc | Method and System for Diagnosis and Prediction of Treatment Effectiveness for Sleep Apnea |
| CN109843171A (en) * | 2016-10-05 | 2019-06-04 | 个人医疗表饰私人有限公司 | Warning system |
| US20190223781A1 (en) * | 2018-01-20 | 2019-07-25 | Beacon Sleep Solutions | Systems and methods for managing sleep disorders |
| US10395777B2 (en) * | 2014-10-21 | 2019-08-27 | uBiome, Inc. | Method and system for characterizing microorganism-associated sleep-related conditions |
-
2020
- 2020-01-03 CN CN202010006821.1A patent/CN111166286A/en active Pending
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7855652B1 (en) * | 2006-09-07 | 2010-12-21 | Ric Investments, Llc | System and method for detecting sleepwalking |
| CN103717125A (en) * | 2011-05-18 | 2014-04-09 | V视股份有限公司 | System and method for determining sleep and sleep stages of a person |
| WO2015042579A1 (en) * | 2013-09-23 | 2015-03-26 | The Board Of Trustees Of The Leland Stanford Junior University | Monitoring and treating sleep disorders |
| CN104063994A (en) * | 2014-03-13 | 2014-09-24 | 苏州天趣信息科技有限公司 | Warning device for identifying human consciousness based on camera |
| US10395777B2 (en) * | 2014-10-21 | 2019-08-27 | uBiome, Inc. | Method and system for characterizing microorganism-associated sleep-related conditions |
| CN105769203A (en) * | 2014-12-18 | 2016-07-20 | 西安发威电子科技有限公司 | Cloth patch with functions of sleepwalking detection and reminding |
| CN105231998A (en) * | 2015-10-23 | 2016-01-13 | 深圳市冠旭电子有限公司 | Method and device for monitoring sleep |
| CN108882892A (en) * | 2016-03-31 | 2018-11-23 | Zoll医疗公司 | The system and method for tracking patient motion |
| US20170290528A1 (en) * | 2016-04-12 | 2017-10-12 | Cardiac Pacemakers, Inc. | Sleep study using an implanted medical device |
| CN106446552A (en) * | 2016-09-28 | 2017-02-22 | 湖南老码信息科技有限责任公司 | Prediction method and prediction system for sleep disorder based on incremental neural network model |
| CN109843171A (en) * | 2016-10-05 | 2019-06-04 | 个人医疗表饰私人有限公司 | Warning system |
| CN107374615A (en) * | 2017-08-15 | 2017-11-24 | 北京道贞健康科技发展有限责任公司 | A kind of electrocardio, breathing, the sleep-walking reporting system and method for position monitoring |
| CN208769772U (en) * | 2017-08-15 | 2019-04-23 | 北京道贞健康科技发展有限责任公司 | A kind of electrocardio, breathing, position monitoring sleep-walking reporting system |
| US20190117151A1 (en) * | 2017-09-12 | 2019-04-25 | Bluesleep Ny, Llc | Method and System for Diagnosis and Prediction of Treatment Effectiveness for Sleep Apnea |
| CN107875496A (en) * | 2017-11-22 | 2018-04-06 | 宁波德葳智能科技有限公司 | A kind of intelligent sleep management eye-shade device and its control method |
| CN109091150A (en) * | 2017-11-29 | 2018-12-28 | 惠州市德赛工业研究院有限公司 | Recognition methods, sleep quality appraisal procedure and the intelligent wearable device that body of sleeping moves |
| CN108010579A (en) * | 2017-11-30 | 2018-05-08 | 西安科锐盛创新科技有限公司 | Health monitoring system |
| CN108125674A (en) * | 2017-12-21 | 2018-06-08 | 速眠创新科技（深圳）有限公司 | Sleep monitoring device |
| US20190223781A1 (en) * | 2018-01-20 | 2019-07-25 | Beacon Sleep Solutions | Systems and methods for managing sleep disorders |
Non-Patent Citations (4)
| Title |
|---|
| WONGSIRICHOT T , PATTANAPHANCHAI J , SOPAYADA N , ET AL: "A Prototype of Sleepwalking Detection and Monitoring System Using Smart Devices", 《JOURNAL OF COMPUTATIONAL AND THEORETICAL NANOENCE》 * |
| 刘振华: "《睡眠障碍中西医结合诊断学》", 31 October 2015 * |
| 北京医学院: "《精神病学》", 31 October 1980 * |
| 蒋雨平: "《新编精神疾病学》", 31 October 2014, 上海科学普及出版社 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112489720A (en) * | 2020-10-16 | 2021-03-12 | 西安得眠堂健康管理工作部 | Intelligent preparation method and device of compound peptide for improving sleep quality |
| WO2023200651A1 (en) * | 2022-04-13 | 2023-10-19 | Sleep Number Corporation | Detecting and preventing sleepwalking events |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11834052B2 (en) | Estimator generation apparatus, monitoring apparatus, estimator generation method, and computer-readable storage medium storing estimator generation program | |
| US20230342621A1 (en) | Method and apparatus for performing anomaly detection using neural network | |
| CN110459328B (en) | Clinical monitoring equipment | |
| Garcia-Ceja et al. | Motor activity based classification of depression in unipolar and bipolar patients | |
| CN107832737A (en) | Electrocardiogram interference identification method based on artificial intelligence | |
| CN111166286A (en) | Dreamy travel detection method, storage medium and dreamy travel detection device | |
| KR20190105180A (en) | Apparatus for Lesion Diagnosis Based on Convolutional Neural Network and Method thereof | |
| CN113689958A (en) | Big data-based chronic disease condition prediction method and system and storage medium | |
| CN110491506A (en) | Auricular fibrillation prediction model and its forecasting system | |
| CN113096792B (en) | Intelligent health monitoring and early warning method and system based on machine learning | |
| CN111317458A (en) | Blood pressure detection system based on deep learning | |
| CN117034142A (en) | Unbalanced medical data missing value filling method and system | |
| CN117316453A (en) | Pressure sore early warning system and method by mixing Barden scale with artificial intelligence | |
| CN112914506A (en) | Sleep quality detection method, device and computer readable storage medium | |
| CN116092680B (en) | Abdominal aortic aneurysm early prediction method and system based on random forest algorithm | |
| CN116595465A (en) | High-dimensional sparse data outlier detection method and system based on self-encoder and data enhancement | |
| CN114970772B (en) | Model training method, device, apparatus and medium for lung disease detection | |
| CN114004258B (en) | Semi-supervised electrocardiographic abnormality detection method | |
| CN115624437A (en) | Intelligent wheelchair safety response method and system | |
| CN114176598B (en) | Multimode-based epileptic attack early warning method and intelligent bracelet device | |
| CN115376638A (en) | Physiological characteristic data analysis method based on multi-source health perception data fusion | |
| CN115526882A (en) | Medical image classification method, device, equipment and storage medium | |
| KR102541362B1 (en) | Apparatus for predicting intradialytic hypotension using AI and method thereof | |
| CN112255921B (en) | AR glasses intelligent control system and method | |
| CN115496105B (en) | Sleep prediction model training method, sleep condition prediction method and related devices |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200519 |