CN118121487B - Temperature sensor data exception processing method for moxibustion therapeutic instrument - Google Patents
Temperature sensor data exception processing method for moxibustion therapeutic instrument Download PDFInfo
- Publication number
- CN118121487B CN118121487B CN202410552655.3A CN202410552655A CN118121487B CN 118121487 B CN118121487 B CN 118121487B CN 202410552655 A CN202410552655 A CN 202410552655A CN 118121487 B CN118121487 B CN 118121487B
- Authority
- CN
- China
- Prior art keywords
- data
- acquisition
- analyzed
- temperature
- interval
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H39/00—Devices for locating or stimulating specific reflex points of the body for physical therapy, e.g. acupuncture
- A61H39/06—Devices for heating or cooling such points within cell-life limits
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H2201/00—Characteristics of apparatus not provided for in the preceding codes
- A61H2201/50—Control means thereof
- A61H2201/5007—Control means thereof computer controlled
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H2201/00—Characteristics of apparatus not provided for in the preceding codes
- A61H2201/50—Control means thereof
- A61H2201/5058—Sensors or detectors
- A61H2201/5082—Temperature sensors
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Rehabilitation Therapy (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Physical Education & Sports Medicine (AREA)
- Probability & Statistics with Applications (AREA)
- Pain & Pain Management (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a temperature sensor data exception processing method for a moxibustion therapeutic apparatus, which comprises the following steps: collecting a heating power data sequence, a temperature data sequence and a current data sequence of the moxibustion therapeutic instrument; obtaining the degree of abnormality according to the distribution difference of the temperature data among different acquisition moments; obtaining an integrated data reference interval according to the abnormality degree; obtaining the abnormal degree of the section temperature according to the integrated data reference section; obtaining associated dimension abnormality degree according to heating power data, temperature data and current data in the integrated data reference interval; obtaining a reference neighborhood region according to the temperature data of the integrated data reference region; and carrying out exception processing on the temperature data according to the temperature exception degree of the interval in the reference neighborhood interval and the associated dimension exception degree. The invention improves the accuracy reduction of the detection result of the abnormal temperature and improves the efficiency of carrying out the abnormal treatment on the abnormal temperature.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a temperature sensor data exception processing method for a moxibustion therapeutic apparatus.
Background
The moxibustion therapeutic apparatus is a medical device for performing thermotherapy by using pharmacological action of mugwort, and in order to ensure that pharmacological action of mugwort is not reduced due to overhigh or overlow temperature in the treatment process, temperature of the moxibustion therapeutic apparatus needs to be monitored in real time and abnormal temperature needs to be treated in time.
The conventional method generally uses a non-local mean value filtering algorithm to perform exception handling on abnormal temperature data, but the temperature data of the moxibustion therapeutic apparatus during working can be influenced by other dimensional data, while the conventional non-local mean value filtering algorithm can perform exception handling only according to the temperature data, and the influence of other related dimensional data on the temperature data is not combined, so that the accuracy of a detection result of the abnormal temperature is reduced, and the efficiency of exception handling on the abnormal temperature is reduced.
Disclosure of Invention
The invention provides a temperature sensor data exception handling method for a moxibustion therapeutic apparatus, which aims to solve the existing problems: the existing non-local mean value filtering algorithm can only perform exception handling according to temperature data, and the influence of other relevant dimension data on the temperature data is not combined, so that the accuracy of the detection result of the abnormal temperature is reduced.
The invention relates to a temperature sensor data exception handling method for a moxibustion therapeutic apparatus, which adopts the following technical scheme:
The method comprises the following steps:
Collecting a heating power data sequence, a temperature data sequence and a current data sequence of the moxibustion therapeutic apparatus, wherein the heating power data sequence comprises a plurality of heating power data, the temperature data sequence comprises a plurality of temperature data, the current data sequence comprises a plurality of current data, and each heating power data, each temperature data and each current data corresponds to one collecting moment;
Obtaining the abnormal degree of the temperature data at each acquisition time according to the distribution difference of the temperature data at different acquisition times; screening a plurality of acquisition moments to be analyzed from a plurality of acquisition moments according to the degree of abnormality; dividing a plurality of acquisition moments according to the continuous distribution condition of the acquisition moments around the acquisition moment to be analyzed to obtain an integrated data reference interval of each acquisition moment to be analyzed; obtaining the abnormal degree of the temperature of the interval at each acquisition time to be analyzed according to the abnormal degree of the temperature data in the integrated data reference interval;
Obtaining the associated dimension abnormality degree of each acquisition time to be analyzed according to the change association condition among heating power data, temperature data and current data in the integrated data reference interval;
According to the variation fluctuation condition of temperature data in the integrated data reference interval, a plurality of reference neighborhood intervals are screened out from a plurality of acquisition moments; and carrying out exception processing on the temperature data according to the temperature exception degree of the interval in different reference neighborhood intervals and the variation difference of the associated dimension exception degree.
Preferably, the obtaining the abnormality degree of the temperature data at each acquisition time according to the distribution difference of the temperature data between different acquisition times includes the following specific methods:
in the method, in the process of the invention, Represent the firstInitial abnormality degrees of temperature data at each acquisition time; Represent the first Collecting temperature data at the moment; Representing the average value of the temperature data at all the acquisition moments; Representation divide by The number of temperature data at all acquisition times except the temperature data at each acquisition time; Representation divide by Temperature data of each acquisition timeCollecting temperature data at the moment; The representation takes absolute value; acquiring initial abnormal degrees of temperature data at all acquisition moments, carrying out linear normalization on all initial abnormal degrees, and recording each normalized initial abnormal degree as an abnormal degree.
Preferably, the method for screening a plurality of collection moments to be analyzed from a plurality of collection moments according to the degree of abnormality includes the following steps:
presetting an abnormality degree threshold Will have an abnormality degree greater thanThe temperature data of the temperature sensor is recorded as temperature data to be analyzed, and the acquisition time corresponding to the temperature data to be analyzed is recorded as acquisition time to be analyzed.
Preferably, the dividing the plurality of collection moments according to the continuous distribution of the collection moments around the collection moment to be analyzed to obtain the integrated data reference interval of each collection moment to be analyzed comprises the following specific methods:
presetting a collection time number For any collecting moment to be analyzed, the front part of the collecting moment to be analyzedTime of acquisition and postThe data segments formed by the collection moments are marked as data analysis intervals of the collection moments to be analyzed, and the data analysis intervals of all the collection moments to be analyzed are obtained;
and for any two adjacent acquisition moments to be analyzed, in the two acquisition moments to be analyzed, marking any one acquisition moment to be analyzed as a first acquisition moment to be analyzed, marking the other acquisition moment to be analyzed as a second acquisition moment to be analyzed, if the first acquisition moment to be analyzed and the data analysis interval of the second acquisition moment to be analyzed have a coincident part, merging the data analysis interval of the first acquisition moment to be analyzed and the data analysis interval of the second acquisition moment to be analyzed to obtain a new data segment, and marking the new data segment as an integrated data reference interval of the first acquisition moment to be analyzed and an integrated data reference interval of the second acquisition moment to be analyzed respectively.
Preferably, the obtaining the abnormal temperature degree of the interval at each time of acquisition to be analyzed according to the abnormal degree of the temperature data in the integrated data reference interval comprises the following specific methods:
in the method, in the process of the invention, The abnormal degree of the temperature of the interval at any one collecting moment to be analyzed is represented; The number of all the acquisition moments to be analyzed in the integrated data reference interval of the acquisition moments to be analyzed is represented; representing the number of all acquisition moments in an integrated data reference interval of acquisition moments to be analyzed; the average value of the temperature data of all the acquisition moments in the integrated data reference interval of the acquisition moment to be analyzed is represented; integrated data reference interval representing acquisition time to be analyzed Abnormal degrees of temperature data at each acquisition time; integrated data reference interval representing acquisition time to be analyzed Collecting temperature data at the moment; The representation takes absolute value.
Preferably, the obtaining the associated dimension abnormality degree at each acquisition time to be analyzed according to the change association condition among the heating power data, the temperature data and the current data in the integrated data reference interval includes the following specific methods:
acquiring temperature change factors, heating energy consumption change factors and electric energy consumption change factors at all acquisition moments;
acquiring neighborhood temperature acquisition time of all acquisition time;
in the method, in the process of the invention, Representing the degree of abnormality of the associated dimension at any one acquisition time to be analyzed; representing the number of all acquisition moments in an integrated data reference interval of acquisition moments to be analyzed; The average value of the current data at all the acquisition time points in the integrated data reference interval at the acquisition time point to be analyzed is represented; integrated data reference interval representing acquisition time to be analyzed The electric energy consumption change factors at the respective acquisition moments; integrated data reference interval representing acquisition time to be analyzed Collecting current data at the moment; integrated data reference interval representing acquisition time to be analyzed Temperature change factors at each acquisition time; integrated data reference interval representing acquisition time to be analyzed Heating energy consumption change factors at each acquisition time; Representing the first time in the integrated data reference interval of analysis acquisition time The number of all neighborhood temperature acquisition moments at each acquisition moment; the first is shown in the integrated data reference interval of the acquisition time to be analyzed Temperature change factors at each acquisition time; in the integrated data reference interval representing the acquisition time to be analyzed, the first The first acquisition timeTemperature change factors at each neighborhood temperature acquisition time; The representation takes absolute value.
Preferably, the method for obtaining the temperature change factor, the heating energy consumption change factor and the electric energy consumption change factor at all the collection time includes the following specific steps:
For any two adjacent acquisition moments, in the two acquisition moments, recording the difference value between the temperature data of the first acquisition moment and the temperature data of the second acquisition moment as a temperature change factor of the second acquisition moment; recording the difference value between the heating power data at the first acquisition time and the heating power data at the second acquisition time as a heating energy consumption change factor at the second acquisition time; and recording the difference value between the current data at the first acquisition time and the current data at the second acquisition time as an electric energy consumption change factor at the second acquisition time.
Preferably, the method for acquiring the neighborhood temperature acquisition time of all the acquisition time includes the following specific steps:
presetting a temperature data threshold For any two acquisition moments, in the two acquisition moments, any one acquisition moment is marked as a first acquisition moment, the other acquisition moment is marked as a second acquisition moment, and if the absolute value of the difference value of the temperature data between the first acquisition moment and the second acquisition moment is smaller thanAnd recording the second acquisition time as the neighborhood temperature acquisition time of the first acquisition time.
Preferably, the method for screening a plurality of reference neighborhood regions from a plurality of acquisition moments according to the variation fluctuation condition of temperature data in the integrated data reference region includes the following specific steps:
for any integrated data reference interval of the acquisition time to be analyzed, the length of the integrated data reference interval is recorded as the target length ; At all acquisition moments, several lengths are acquiredEach neighborhood block is marked as a reference data interval;
presetting a standard deviation threshold value For any one reference data interval, the standard deviation of the temperature data at all the acquisition moments in the reference data interval is recorded as a first temperature standard deviation, if the first temperature standard deviation of the reference data interval and the standard deviation of the temperature data at all the acquisition moments in the integrated data reference interval are smaller thanThe reference data interval is marked as a reference neighborhood interval of the integrated data reference interval.
Preferably, the method for performing exception processing on the temperature data according to the variation differences of the temperature exception degree of the interval in the different reference neighborhood intervals and the exception degree of the associated dimension includes the following specific steps:
for any one reference neighborhood region of the integrated data reference region at any one acquisition time to be analyzed, referring to a method for acquiring the region temperature abnormality degree and the associated dimension abnormality degree of the acquisition time to be analyzed, acquiring the region temperature abnormality degree and the associated dimension abnormality degree of the reference neighborhood region;
in the method, in the process of the invention, Representing interval filtering weights of the reference neighborhood interval; Representing an absolute value of a difference between a first acquisition time in a reference neighborhood region and a first acquisition time in the integrated data reference region; the abnormal degree of the temperature of the interval at the acquisition time to be analyzed is represented; representing the temperature abnormality degree of the reference neighborhood region; Representing the degree of abnormality of the associated dimension at the acquisition time to be analyzed; representing the degree of abnormality of the associated dimension of the reference neighborhood region; Representing preset super parameters; representing the number of the same sequence numbers of all acquisition moments in the reference neighborhood region and the integrated data reference region; representing the first in a reference neighborhood region Collecting temperature data at the moment; Representing the first of the integrated data reference intervals Collecting temperature data at the moment; The representation takes absolute value; representing a linear normalization; Representing a sigmoid function; obtaining interval filtering weights of all reference neighborhood intervals, carrying out linear normalization on all the interval filtering weights, and marking each normalized interval filtering weight as an interval filtering weight factor;
in the method, in the process of the invention, A filtered value representing temperature data at any one of the collection times to be analyzed; representing the number of all reference neighborhood regions of the integrated data reference region at the acquisition time to be analyzed; the first integrated data reference interval representing the acquisition time to be analyzed Interval filtering weight factors of the reference neighborhood interval; the first integrated data reference interval representing the acquisition time to be analyzed The average value of all temperature data in each reference neighborhood region; acquiring filtering values of temperature data at all acquisition moments to be analyzed;
and replacing the temperature data of each acquisition time to be analyzed with a corresponding filtering value.
The technical scheme of the invention has the beneficial effects that: obtaining an integrated data reference interval according to the distribution difference of temperature data among different acquisition moments; obtaining the abnormal degree of the temperature of the interval at the acquisition time to be analyzed according to the abnormal degree of the temperature data in the integrated data reference interval; obtaining the associated dimension abnormality degree of the acquisition time to be analyzed according to the change association condition among the heating power data, the temperature data and the current data in the integrated data reference interval; performing exception processing on the temperature data according to the temperature exception degree of different acquisition moments to be analyzed and the variation difference of the associated dimension exception degree; the abnormal degree reflects the abnormal probability of temperature data at the acquisition time, the abnormal degree of the interval temperature reflects the value of the integrated data reference interval to be abnormal at the acquisition time to be analyzed, and the abnormal degree of the associated dimension reflects the influence relationship among the temperature, the current and the heating efficiency around the acquisition time to be analyzed; the influence of a plurality of related dimension data on the temperature data is combined, so that the accuracy of the detection result of the abnormal temperature is improved, and the efficiency of carrying out abnormal processing on the abnormal temperature is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart illustrating a method for processing temperature sensor data abnormality of a moxibustion therapeutic apparatus according to the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the present invention to achieve the preset purposes, the following detailed description refers to specific implementation, structure, features and effects of a temperature sensor data exception handling method for a moxibustion therapeutic apparatus according to the present invention, with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the temperature sensor data abnormality processing method for a moxibustion therapeutic apparatus provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a method for processing temperature sensor data abnormality of a moxibustion therapeutic apparatus according to an embodiment of the present invention is shown, and the method includes the following steps:
Step S001: and collecting a heating power data sequence, a temperature data sequence and a current data sequence of the moxibustion therapeutic instrument.
It should be noted that, in the existing method, abnormal temperature data is usually processed by using a non-local mean value filtering algorithm, but temperature data of the moxibustion therapeutic apparatus during working is affected by other dimension data, while the existing non-local mean value filtering algorithm can only perform abnormal processing according to the temperature data, and does not combine with the influence of other related dimension data on the temperature data, so that the accuracy of a detection result of the abnormal temperature is reduced, and the efficiency of performing abnormal processing on the abnormal temperature is reduced.
Specifically, the temperature data sequence and the current data sequence need to be collected at first, and the specific process is as follows: the method comprises the steps of using a temperature sensor, a current sensor and a heating power detection module of a moxibustion therapeutic instrument as an acquisition time every 0.1 second, acquiring heating power data, temperature data and current data of the moxibustion therapeutic instrument once, and acquiring all heating power data, temperature data and current data for 5 minutes; arranging all heating power data according to the sequence from the small to the large of the acquisition time, and marking the arranged sequence as a heating power data sequence; arranging all the temperature data according to the sequence from the small to the large of the acquisition time, and marking the arranged sequence as a temperature data sequence; and arranging all the current data according to the sequence from the small to the large of the acquisition time, and marking the arranged sequence as a current data sequence. Wherein each acquisition time corresponds to one heating power data, one temperature data and one current data. In addition, it should be noted that, in this embodiment, the collection time, the collection total duration and the collection data type are not specifically limited, where the collection time, the collection total duration and the collection data type may be determined according to specific implementation conditions.
So far, the heating power data sequence, the temperature data sequence and the current data sequence are obtained through the method.
Step S002: obtaining the abnormal degree of the temperature data at each acquisition time according to the distribution difference of the temperature data at different acquisition times; screening a plurality of acquisition moments to be analyzed from a plurality of acquisition moments according to the degree of abnormality; dividing a plurality of acquisition moments according to the continuous distribution condition of the acquisition moments around the acquisition moment to be analyzed to obtain an integrated data reference interval of each acquisition moment to be analyzed; and obtaining the abnormal degree of the temperature of the interval at each acquisition time to be analyzed according to the abnormal degree of the temperature data in the integrated data reference interval.
In the actual environment, different temperatures can influence the activity of the medicine in the moxibustion therapeutic apparatus to different degrees, the medicine activity cannot be effectively activated due to the fact that the temperature is too low, and the medicine activity can be greatly destroyed due to the fact that the temperature is too high, so that the therapeutic effect is poor, and when the moxibustion therapeutic apparatus is in actual work, the temperature data intuitively reflect the therapeutic efficiency of the medicine in the moxibustion therapeutic apparatus; in order to improve the efficiency of temperature data exception handling, the embodiment obtains the interval temperature exception degree of different acquisition moments by analyzing the change association condition of the temperature data among different acquisition moments so as to analyze the association condition among multi-dimensional data later.
Specifically, according to the firstThe difference between the temperature data at each acquisition time and the temperature data at other acquisition times is obtainedInitial degree of abnormality of temperature data at each acquisition time. As one example, the first may be calculated by the following formulaInitial degree of abnormality of temperature data at each acquisition time:
in the method, in the process of the invention, Represent the firstInitial abnormality degrees of temperature data at each acquisition time; Represent the first Collecting temperature data at the moment; Representing the average value of the temperature data at all the acquisition moments; Representation divide by The number of temperature data at all acquisition times except the temperature data at each acquisition time; Representation divide by Temperature data of each acquisition timeCollecting temperature data at the moment; The representation takes absolute value; expressed by the first The temperature data at each acquisition time is taken as a center, and the degree of dispersion of the ambient temperature data is adopted. Wherein if the first isThe greater the initial abnormality degree of the temperature data at each acquisition time, the description of the firstThe larger the difference between the temperature data at each acquisition time and other temperature data is, the reflection of the firstThe more likely that anomalies are present in the temperature data at each acquisition instant. Acquiring initial abnormal degrees of temperature data at all acquisition moments, carrying out linear normalization on all initial abnormal degrees, and recording each normalized initial abnormal degree as an abnormal degree.
Further, presetting an abnormality degree thresholdWherein the present embodiment usesThe present embodiment is not specifically limited, and will be described by way of exampleCan be used for increasing the degree of abnormality according to the specific implementationThe temperature data of the temperature sensor is recorded as temperature data to be analyzed, the acquisition time corresponding to the temperature data to be analyzed is recorded as acquisition time to be analyzed, and all the acquisition time to be analyzed are obtained; presetting a collection time numberWherein the present embodiment usesThe present embodiment is not specifically limited, and will be described by way of exampleTaking any one of the collection time to be analyzed as an example according to the specific implementation situation, the front of the collection time to be analyzedTime of acquisition and postThe data segments formed by the collection time are marked as data analysis intervals of the collection time to be analyzed, and the data analysis intervals of all the collection time to be analyzed are obtained; taking any two adjacent collection moments to be analyzed as an example, in the two collection moments to be analyzed, recording any one collection moment to be analyzed as a first collection moment to be analyzed, recording the other collection moment to be analyzed as a second collection moment to be analyzed, if a part of the first collection moment to be analyzed and the data analysis interval of the second collection moment to be analyzed are overlapped, merging the data analysis interval of the first collection moment to be analyzed and the data analysis interval of the second collection moment to be analyzed to obtain a new data segment, recording the new data segment as an integrated data reference interval of the first collection moment to be analyzed and an integrated data reference interval of the second collection moment to be analyzed, and the like, and acquiring the integrated data reference intervals of all the collection moments to be analyzed. The data analysis interval of the to-be-analyzed acquisition time comprises the to-be-analyzed acquisition time; each data analysis interval of the acquisition time to be analyzed comprises a plurality of acquisition times; a plurality of acquisition moments exist between any two adjacent acquisition moments to be analyzed. It should be noted that if the number of the collection time remaining before and after the collection time to be analyzed does not satisfy the preset valueAnd then the data segment formed by the residual acquisition time before and after the acquisition time to be analyzed is used as a data analysis interval of the acquisition time to be analyzed.
Further, taking any one collection time to be analyzed as an example, according to all temperature data in the integrated data reference interval of the collection time to be analyzed, obtaining the abnormal temperature degree of the interval of the collection time to be analyzed. As an example, the interval temperature abnormality degree at the acquisition time to be analyzed may be calculated by the following formula:
in the method, in the process of the invention, Representing the abnormal degree of the temperature of the interval at the acquisition time to be analyzed; Representing the number of all the acquisition moments to be analyzed in the integrated data reference interval of the acquisition moments to be analyzed; representing the number of all acquisition moments in the integrated data reference interval of the acquisition moment to be analyzed; the average value of the temperature data of all the acquisition moments in the integrated data reference interval of the acquisition moment to be analyzed is represented; the first data reference interval of the integrated data representing the acquisition time to be analyzed Abnormal degrees of temperature data at each acquisition time; the first data reference interval of the integrated data representing the acquisition time to be analyzed Collecting temperature data at the moment; The representation takes absolute value. The greater the temperature abnormality degree of the interval at the acquisition time to be analyzed, the more frequent the abnormal fluctuation condition of the temperature data in the integrated data reference interval at the acquisition time to be analyzed is, and the greater the value of the integrated data reference interval at the acquisition time to be analyzed on the abnormality of the acquisition time to be analyzed is. And acquiring the abnormal degree of the interval temperature at all the acquisition time points to be analyzed.
So far, the abnormal degree of the interval temperature at all the acquisition time points to be analyzed is obtained through the method.
Step S003: and obtaining the associated dimension abnormality degree of each acquisition time to be analyzed according to the change association condition among the heating power data, the temperature data and the current data in the integrated data reference interval.
It should be noted that, when the moxibustion therapeutic apparatus heats the medicine, the current flowing through the components can make different components generate different degrees of heating, the heat generated by these heating conditions can also heat the medicine, so that the activity of the medicine can reach the appropriate activity range more quickly, and when the original moxibustion therapeutic apparatus heats according to the heating efficiency reserved by the apparatus, the energy generated by the predetermined heating efficiency is excessive or insufficient due to the influence of the current. Under the conventional condition, the current is increased, the heating efficiency is increased along with the increase, and the temperature data which is correspondingly affected is also increased to a certain extent, but if components or wires in the moxibustion therapeutic apparatus generate micro faults, the change of the heat energy received by the medicine can not always show a positive correlation with the current data or the heating efficiency; in order to improve the efficiency of temperature data exception handling, the embodiment obtains the associated dimension exception degree by analyzing the association between different dimension data so as to perform exception handling on the temperature data by combining the interval temperature exception degree later.
Specifically, taking any two adjacent acquisition moments as an example, in the two acquisition moments, recording the difference value between the temperature data of the first acquisition moment and the temperature data of the second acquisition moment as a temperature change factor of the second acquisition moment; recording the difference value between the heating power data at the first acquisition time and the heating power data at the second acquisition time as a heating energy consumption change factor at the second acquisition time; recording the difference value between the current data at the first acquisition time and the current data at the second acquisition time as an electric energy consumption change factor at the second acquisition time; and acquiring temperature change factors, heating energy consumption change factors and electric energy consumption change factors at all acquisition moments. In addition, the temperature change factor, the heating energy consumption change factor and the electric energy consumption change factor at the first acquisition time are not considered in the embodiment.
Further, a temperature data threshold value is presetWherein the present embodiment usesThe present embodiment is not specifically limited, and will be described by way of exampleDepending on the particular implementation; taking any two collection moments as an example, in the two collection moments, any one collection moment is marked as a first collection moment, the other collection moment is marked as a second collection moment, and if the absolute value of the difference value of the temperature data between the first collection moment and the second collection moment is smaller thanThen the second acquisition time is recorded as the neighborhood temperature acquisition time of the first acquisition time; and acquiring neighborhood temperature acquisition time of all acquisition time. Wherein each acquisition time corresponds to a plurality of neighborhood temperature acquisition times.
Further, taking any one collection time to be analyzed as an example, according to the temperature change factor, the heating energy consumption change factor, the electric energy consumption change factor and the neighborhood temperature collection time corresponding to the collection time contained in the integrated data reference interval of the collection time to be analyzed, the associated dimension abnormity degree of the collection time to be analyzed is obtained. As an example, the degree of abnormality of the associated dimension at the acquisition time to be analyzed may be calculated by the following formula:
in the method, in the process of the invention, Representing the degree of abnormality of the associated dimension at the acquisition time to be analyzed; representing the number of all acquisition moments in the integrated data reference interval of the acquisition moment to be analyzed; Representing the average value of the current data at all the acquisition moments in the integrated data reference interval at the acquisition moment to be analyzed; the first data reference interval of the integrated data representing the acquisition time to be analyzed The electric energy consumption change factors at the respective acquisition moments; the first data reference interval of the integrated data representing the acquisition time to be analyzed Collecting current data at the moment; integrated data reference interval representing the time of acquisition to be analyzed Temperature change factors at each acquisition time; integrated data reference interval representing the time of acquisition to be analyzed Heating energy consumption change factors at each acquisition time; the first is shown in the integrated data reference interval of the acquisition time to be analyzed The number of all neighborhood temperature acquisition moments at each acquisition moment; the first is shown in the integrated data reference interval of the acquisition time to be analyzed Temperature change factors at each acquisition time; In the integrated data reference interval representing the acquisition time to be analyzed, the first The first acquisition timeTemperature change factors at each neighborhood temperature acquisition time; The representation takes absolute value; the local abnormality degree of the current data in the integrated data reference interval at the acquisition time to be analyzed is represented; A local abnormality degree indicating a relationship of continuous change in integrated temperature, current, and heating efficiency; And the temperature data in the integrated data reference interval at the acquisition time to be analyzed are mutually influenced. If the correlation dimension degree of the to-be-analyzed collection time is larger, the influence relationship among the ambient temperature, the current and the heating efficiency of the to-be-analyzed collection time is obvious, and the collection time which is more likely to be abnormal is reflected. And acquiring the degree of abnormality of the associated dimension at all the acquisition time points to be analyzed.
So far, the associated dimension abnormity degree of all the acquisition moments to be analyzed is obtained through the method.
Step S004: according to the variation fluctuation condition of temperature data in the integrated data reference interval, a plurality of reference neighborhood intervals are screened out from a plurality of acquisition moments; and carrying out exception processing on the temperature data according to the temperature exception degree of the interval in different reference neighborhood intervals and the variation difference of the associated dimension exception degree.
Specifically, taking an integrated data reference interval of any one to-be-analyzed acquisition time as an example, the length of the integrated data reference interval is recorded as a target length; At all acquisition moments, several lengths are acquiredEach neighborhood block is marked as a reference data interval; presetting a standard deviation threshold valueWherein the present embodiment usesThe present embodiment is not specifically limited, and will be described by way of exampleTaking any one reference data interval as an example, the standard deviation of the temperature data at all the acquisition time points in the reference data interval is recorded as a first temperature standard deviation, if the standard deviation of the temperature data at all the acquisition time points in the reference data interval is smaller than the standard deviation of the temperature data at all the acquisition time points in the integrated data reference intervalThen the reference data interval is marked as a reference neighborhood interval of the integrated data reference interval; and acquiring all reference neighborhood regions of the integrated data reference region. Wherein each neighborhood block contains a plurality of acquisition moments; in addition, the process of obtaining the neighborhood blocks in the data sequence is not a well-known content of the local mean filtering algorithm, and the embodiment is not repeated.
Further, taking any one reference neighborhood region of the integrated data reference region as an example, referring to a method for acquiring the region temperature abnormality degree and the associated dimension abnormality degree of the acquisition time to be analyzed, and acquiring the region temperature abnormality degree and the associated dimension abnormality degree of the reference neighborhood region; and obtaining the interval filtering weight of the reference neighborhood interval according to the interval temperature abnormality degree and the difference of the correlation dimension abnormality degree between the reference neighborhood interval and the acquisition time to be analyzed. As an example, the interval filtering weights for the reference neighborhood interval may be calculated by the following formula:
in the method, in the process of the invention, Interval filtering weights representing the reference neighborhood interval; Representing an absolute value of a difference between a first acquisition time in the reference neighborhood region and a first acquisition time in the integrated data reference region; representing the abnormal degree of the temperature of the interval at the acquisition time to be analyzed; representing the temperature abnormality degree of the reference neighborhood region; representing the degree of abnormality of the associated dimension at the acquisition time to be analyzed; representing the degree of abnormality of the associated dimension of the reference neighborhood region; representing preset super parameters, preset in this embodiment For preventing denominator from being 0; representing the same number of all acquisition time sequence numbers in the reference neighborhood region and the integrated data reference region; Representing the first of the reference neighborhood regions Collecting temperature data at the moment; Indicating the first of the integrated data reference intervals Collecting temperature data at the moment; The representation takes absolute value; representing a linear normalization; representing sigmoid functions, data can be normalized to ；After linear normalization is carried out on the section temperature abnormality degrees of all the acquisition moments to be analyzed, the section temperature abnormality degrees of the acquisition moments to be analyzed are represented; representing the abnormal degree of the temperature of the reference neighborhood region after carrying out linear normalization on the abnormal degree of the temperature of the region of all the reference neighborhood regions; After the associated dimension abnormality degree of all the acquisition time points to be analyzed is input into a sigmoid function, the output associated dimension abnormality degree of the acquisition time points to be analyzed is represented; And (3) representing the association dimension abnormality degree of the reference neighborhood region output after the association dimension abnormality degree of all the reference neighborhood regions are input into the sigmoid function. And if the interval filtering weight of the reference neighborhood interval is larger, the influence of the reference neighborhood interval on the temperature data in the integrated data reference interval is larger. Obtaining the interval filtering weights of all the reference neighborhood intervals, carrying out linear normalization on all the interval filtering weights, and marking each normalized interval filtering weight as an interval filtering weight factor.
Further, according to the interval filtering weight factors of all reference neighborhood regions of the integrated data reference interval at the acquisition time to be analyzed, a filtering value of the temperature data at the acquisition time to be analyzed is obtained. As an example, the filtered value of the temperature data at the acquisition time to be analyzed may be calculated by the following formula:
in the method, in the process of the invention, A filtered value representing the temperature data at the time of acquisition to be analyzed; Representing the number of all reference neighborhood regions of the integrated data reference region at the acquisition time to be analyzed; The first integrated data reference interval representing the acquisition time to be analyzed Interval filtering weight factors of the reference neighborhood interval; The first integrated data reference interval representing the acquisition time to be analyzed The average of all temperature data in each reference neighborhood region. And obtaining the filtering values of the temperature data at all the acquisition time to be analyzed.
Further, the temperature data of each acquisition time to be analyzed is replaced by a corresponding filtering value, and the abnormal processing of the temperature data of the moxibustion therapeutic instrument is completed.
This embodiment is completed.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (8)
1. A temperature sensor data anomaly processing method for a moxibustion therapeutic apparatus, characterized in that the method comprises the following steps:
Collecting a heating power data sequence, a temperature data sequence and a current data sequence of the moxibustion therapeutic apparatus, wherein the heating power data sequence comprises a plurality of heating power data, the temperature data sequence comprises a plurality of temperature data, the current data sequence comprises a plurality of current data, and each heating power data, each temperature data and each current data corresponds to one collecting moment;
Obtaining the abnormal degree of the temperature data at each acquisition time according to the distribution difference of the temperature data at different acquisition times; screening a plurality of acquisition moments to be analyzed from a plurality of acquisition moments according to the degree of abnormality; dividing a plurality of acquisition moments according to the continuous distribution condition of the acquisition moments around the acquisition moment to be analyzed to obtain an integrated data reference interval of each acquisition moment to be analyzed; obtaining the abnormal degree of the temperature of the interval at each acquisition time to be analyzed according to the abnormal degree of the temperature data in the integrated data reference interval;
Obtaining the associated dimension abnormality degree of each acquisition time to be analyzed according to the change association condition among heating power data, temperature data and current data in the integrated data reference interval;
according to the variation fluctuation condition of temperature data in the integrated data reference interval, a plurality of reference neighborhood intervals are screened out from a plurality of acquisition moments; performing exception processing on the temperature data according to the temperature exception degree of the interval in different reference neighborhood intervals and the variation difference of the associated dimension exception degree;
The method for acquiring the degree of abnormality of the associated dimension comprises the following steps: acquiring temperature change factors, heating energy consumption change factors and electric energy consumption change factors at all acquisition moments;
acquiring neighborhood temperature acquisition time of all acquisition time;
in the method, in the process of the invention, Representing the degree of abnormality of the associated dimension at any one acquisition time to be analyzed; representing the number of all acquisition moments in an integrated data reference interval of acquisition moments to be analyzed; The average value of the current data at all the acquisition time points in the integrated data reference interval at the acquisition time point to be analyzed is represented; integrated data reference interval representing acquisition time to be analyzed The electric energy consumption change factors at the respective acquisition moments; integrated data reference interval representing acquisition time to be analyzed Collecting current data at the moment; integrated data reference interval representing acquisition time to be analyzed Temperature change factors at each acquisition time; integrated data reference interval representing acquisition time to be analyzed Heating energy consumption change factors at each acquisition time; Representing the first time in the integrated data reference interval of analysis acquisition time The number of all neighborhood temperature acquisition moments at each acquisition moment; the first is shown in the integrated data reference interval of the acquisition time to be analyzed Temperature change factors at each acquisition time; in the integrated data reference interval representing the acquisition time to be analyzed, the first The first acquisition timeTemperature change factors at each neighborhood temperature acquisition time; The representation takes absolute value;
The method for performing exception processing on the temperature data according to the variation differences of the temperature exception degree of the interval in the different reference neighborhood intervals and the exception degree of the associated dimension comprises the following specific steps: for any one reference neighborhood region of the integrated data reference region at any one acquisition time to be analyzed, referring to a method for acquiring the region temperature abnormality degree and the associated dimension abnormality degree of the acquisition time to be analyzed, acquiring the region temperature abnormality degree and the associated dimension abnormality degree of the reference neighborhood region;
in the method, in the process of the invention, Representing interval filtering weights of the reference neighborhood interval; Representing an absolute value of a difference between a first acquisition time in a reference neighborhood region and a first acquisition time in the integrated data reference region; the abnormal degree of the temperature of the interval at the acquisition time to be analyzed is represented; representing the temperature abnormality degree of the reference neighborhood region; Representing the degree of abnormality of the associated dimension at the acquisition time to be analyzed; representing the degree of abnormality of the associated dimension of the reference neighborhood region; Representing preset super parameters; representing the number of the same sequence numbers of all acquisition moments in the reference neighborhood region and the integrated data reference region; representing the first in a reference neighborhood region Collecting temperature data at the moment; Representing the first of the integrated data reference intervals Collecting temperature data at the moment; The representation takes absolute value; representing a linear normalization; Representing a sigmoid function; obtaining interval filtering weights of all reference neighborhood intervals, carrying out linear normalization on all the interval filtering weights, and marking each normalized interval filtering weight as an interval filtering weight factor;
in the method, in the process of the invention, A filtered value representing temperature data at any one of the collection times to be analyzed; representing the number of all reference neighborhood regions of the integrated data reference region at the acquisition time to be analyzed; the first integrated data reference interval representing the acquisition time to be analyzed Interval filtering weight factors of the reference neighborhood interval; the first integrated data reference interval representing the acquisition time to be analyzed The average value of all temperature data in each reference neighborhood region; acquiring filtering values of temperature data at all acquisition moments to be analyzed;
and replacing the temperature data of each acquisition time to be analyzed with a corresponding filtering value.
2. The method for processing abnormal data of a temperature sensor of a moxibustion therapeutic apparatus according to claim 1, wherein the obtaining the degree of abnormality of the temperature data at each acquisition time according to the distribution difference of the temperature data between different acquisition times comprises the following specific steps:
in the method, in the process of the invention, Represent the firstInitial abnormality degrees of temperature data at each acquisition time; Represent the first Collecting temperature data at the moment; Representing the average value of the temperature data at all the acquisition moments; Representation divide by The number of temperature data at all acquisition times except the temperature data at each acquisition time; Representation divide by Temperature data of each acquisition timeCollecting temperature data at the moment; The representation takes absolute value; acquiring initial abnormal degrees of temperature data at all acquisition moments, carrying out linear normalization on all initial abnormal degrees, and recording each normalized initial abnormal degree as an abnormal degree.
3. The method for processing abnormal data of a temperature sensor for a moxibustion therapeutic apparatus according to claim 1, wherein the method for screening a plurality of acquisition moments to be analyzed from a plurality of acquisition moments according to the degree of abnormality comprises the following specific steps:
presetting an abnormality degree threshold Will have an abnormality degree greater thanThe temperature data of the temperature sensor is recorded as temperature data to be analyzed, and the acquisition time corresponding to the temperature data to be analyzed is recorded as acquisition time to be analyzed.
4. The method for processing abnormal data of a temperature sensor for a moxibustion therapeutic apparatus according to claim 1, wherein the dividing the plurality of acquisition moments according to a continuous distribution of acquisition moments around the acquisition moment to be analyzed to obtain an integrated data reference interval of each acquisition moment to be analyzed comprises the following specific steps:
presetting a collection time number For any collecting moment to be analyzed, the front part of the collecting moment to be analyzedTime of acquisition and postThe data segments formed by the collection moments are marked as data analysis intervals of the collection moments to be analyzed, and the data analysis intervals of all the collection moments to be analyzed are obtained;
and for any two adjacent acquisition moments to be analyzed, in the two acquisition moments to be analyzed, marking any one acquisition moment to be analyzed as a first acquisition moment to be analyzed, marking the other acquisition moment to be analyzed as a second acquisition moment to be analyzed, if the first acquisition moment to be analyzed and the data analysis interval of the second acquisition moment to be analyzed have a coincident part, merging the data analysis interval of the first acquisition moment to be analyzed and the data analysis interval of the second acquisition moment to be analyzed to obtain a new data segment, and marking the new data segment as an integrated data reference interval of the first acquisition moment to be analyzed and an integrated data reference interval of the second acquisition moment to be analyzed respectively.
5. The method for processing abnormal temperature sensor data of a moxibustion therapeutic apparatus according to claim 1, wherein the obtaining the abnormal temperature level of each collection time to be analyzed according to the abnormal level of temperature data in the integrated data reference interval comprises the following specific steps:
in the method, in the process of the invention, The abnormal degree of the temperature of the interval at any one collecting moment to be analyzed is represented; The number of all the acquisition moments to be analyzed in the integrated data reference interval of the acquisition moments to be analyzed is represented; representing the number of all acquisition moments in an integrated data reference interval of acquisition moments to be analyzed; the average value of the temperature data of all the acquisition moments in the integrated data reference interval of the acquisition moment to be analyzed is represented; integrated data reference interval representing acquisition time to be analyzed Abnormal degrees of temperature data at each acquisition time; integrated data reference interval representing acquisition time to be analyzed Collecting temperature data at the moment; The representation takes absolute value.
6. The method for processing abnormal data of a temperature sensor for a moxibustion therapeutic apparatus according to claim 5, wherein the steps of obtaining the temperature change factor, the heating energy consumption change factor and the electric energy consumption change factor at all the collection time are as follows:
For any two adjacent acquisition moments, in the two acquisition moments, recording the difference value between the temperature data of the first acquisition moment and the temperature data of the second acquisition moment as a temperature change factor of the second acquisition moment; recording the difference value between the heating power data at the first acquisition time and the heating power data at the second acquisition time as a heating energy consumption change factor at the second acquisition time; and recording the difference value between the current data at the first acquisition time and the current data at the second acquisition time as an electric energy consumption change factor at the second acquisition time.
7. The method for processing abnormal temperature sensor data of a moxibustion therapeutic apparatus according to claim 5, wherein the method for acquiring the neighborhood temperature acquisition time of all the acquisition time comprises the following specific steps:
presetting a temperature data threshold For any two acquisition moments, in the two acquisition moments, any one acquisition moment is marked as a first acquisition moment, the other acquisition moment is marked as a second acquisition moment, and if the absolute value of the difference value of the temperature data between the first acquisition moment and the second acquisition moment is smaller thanAnd recording the second acquisition time as the neighborhood temperature acquisition time of the first acquisition time.
8. The method for processing abnormal temperature sensor data of a moxibustion therapeutic apparatus according to claim 1, wherein the method for selecting a plurality of reference neighborhood regions from a plurality of acquisition moments according to variation and fluctuation conditions of temperature data in an integrated data reference region comprises the following specific steps:
for any integrated data reference interval of the acquisition time to be analyzed, the length of the integrated data reference interval is recorded as the target length ; At all acquisition moments, several lengths are acquiredEach neighborhood block is marked as a reference data interval;
presetting a standard deviation threshold value For any one reference data interval, the standard deviation of the temperature data at all the acquisition moments in the reference data interval is recorded as a first temperature standard deviation, if the first temperature standard deviation of the reference data interval and the standard deviation of the temperature data at all the acquisition moments in the integrated data reference interval are smaller thanThe reference data interval is marked as a reference neighborhood interval of the integrated data reference interval.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410552655.3A CN118121487B (en) | 2024-05-07 | 2024-05-07 | Temperature sensor data exception processing method for moxibustion therapeutic instrument |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410552655.3A CN118121487B (en) | 2024-05-07 | 2024-05-07 | Temperature sensor data exception processing method for moxibustion therapeutic instrument |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118121487A CN118121487A (en) | 2024-06-04 |
| CN118121487B true CN118121487B (en) | 2024-07-12 |
Family
ID=91237939
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410552655.3A Active CN118121487B (en) | 2024-05-07 | 2024-05-07 | Temperature sensor data exception processing method for moxibustion therapeutic instrument |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118121487B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120337103B (en) * | 2025-06-18 | 2025-08-12 | 南京信息工程大学 | A method and device for distinguishing abnormal data based on time series data analysis |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116183051A (en) * | 2023-03-29 | 2023-05-30 | 华晨宝马汽车有限公司 | Motor temperature monitoring method, system, equipment and storage medium |
| CN116659589A (en) * | 2023-07-25 | 2023-08-29 | 澳润(山东)药业有限公司 | Donkey-hide gelatin cake preservation environment monitoring method based on data analysis |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10201688A (en) * | 1997-01-24 | 1998-08-04 | Sanyo Electric Co Ltd | Vacuum cleaner |
| JP2014022686A (en) * | 2012-07-23 | 2014-02-03 | Sony Corp | Abnormality detection device, abnormality detection method, and power generation system |
| US11399721B2 (en) * | 2015-12-28 | 2022-08-02 | Dexcom, Inc. | Systems and methods for remote and host monitoring communications |
| CN114432140B (en) * | 2021-12-31 | 2023-08-22 | 天津康健医疗器械有限公司 | Temperature control method, device, equipment and medium for acupuncture needle therapeutic instrument |
| CN116910520B (en) * | 2023-09-12 | 2023-12-01 | 北京长和信泰能源技术有限公司 | Intelligent storage method based on generated energy of photovoltaic building integrated system |
| CN117451211A (en) * | 2023-11-09 | 2024-01-26 | 徐州优博电子科技有限公司 | Temperature sensor data exception handling method |
-
2024
- 2024-05-07 CN CN202410552655.3A patent/CN118121487B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116183051A (en) * | 2023-03-29 | 2023-05-30 | 华晨宝马汽车有限公司 | Motor temperature monitoring method, system, equipment and storage medium |
| CN116659589A (en) * | 2023-07-25 | 2023-08-29 | 澳润(山东)药业有限公司 | Donkey-hide gelatin cake preservation environment monitoring method based on data analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118121487A (en) | 2024-06-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118121487B (en) | Temperature sensor data exception processing method for moxibustion therapeutic instrument | |
| CN118759298B (en) | Multi-parameter monitoring analysis method and device for transformer and transformer | |
| CN102824172B (en) | EEG (electroencephalogram) feature extraction method | |
| CN117688311B (en) | Real-time monitoring method and system for advanced treatment of refractory salt-containing wastewater | |
| Li et al. | Spatial–temporal discriminative restricted Boltzmann machine for event-related potential detection and analysis | |
| CN118797245B (en) | On-line monitoring system and method for hemodialysis process of patient | |
| CN113116361A (en) | Sleep staging method based on single-lead electroencephalogram | |
| CN103720471B (en) | A Method of Removing Oculograph Artifacts Based on Factor Analysis | |
| Teng et al. | Multimedia monitoring system of obstructive sleep apnea via a deep active learning model | |
| CN111870241B (en) | Epileptic seizure signal detection method based on optimized multidimensional sample entropy | |
| CN113273992A (en) | Signal processing method and device | |
| CN118448047A (en) | Stem cell efficacy prediction method and system based on machine learning | |
| CN110554161B (en) | A water quality monitoring method based on fish behavior signals | |
| CN120130931A (en) | Epileptic seizure detection method and system based on self-attention mechanism and GRU-LSTM fusion | |
| CN119202828B (en) | A lightweight four-classification method for epileptic EEG signals | |
| CN117807551A (en) | Heart rate abnormality capturing method and system based on intelligent ring | |
| CN116236158B (en) | A method and system for identifying focal epileptic seizures based on scalp EEG signals | |
| Firasari et al. | Performance Evaluation of ResNet50 and MobileNetV2 in Skin Cancer Image Classification with Various Optimizers | |
| CN108388846B (en) | Detection and recognition method of EEG alpha wave based on canonical correlation analysis | |
| KR102592762B1 (en) | Arrhythmia classification method using densenet based on convolution neural network | |
| Prakash et al. | A Light Weight Deep Learning based Technique for Patient-Specific ECG Beat Classification | |
| CN118571513B (en) | A method and system for monitoring patient vital signs during thyroid surgery | |
| KR102406994B1 (en) | Bigdata based system and method for diagnose and analyze abnormalities in facility | |
| CN119782928B (en) | A fatigue driving detection method based on dual-source multi-scale feature fusion network | |
| Kumar et al. | Heart plaque detection with improved accuracy using K-nearest neighbors classifier algorithm in comparison with least squares support vector machine |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |