CN110841142B - Method and system for predicting blockage of infusion pipeline - Google Patents

Method and system for predicting blockage of infusion pipeline Download PDF

Info

Publication number
CN110841142B
CN110841142B CN201911006456.8A CN201911006456A CN110841142B CN 110841142 B CN110841142 B CN 110841142B CN 201911006456 A CN201911006456 A CN 201911006456A CN 110841142 B CN110841142 B CN 110841142B
Authority
CN
China
Prior art keywords
deep learning
learning model
data
input data
hidden layer
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
Application number
CN201911006456.8A
Other languages
Chinese (zh)
Other versions
CN110841142A (en
Inventor
周霆
张智慧
沈蔚慈
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu Apon Medical Technology Co ltd
Original Assignee
Jiangsu Apon Medical Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Jiangsu Apon Medical Technology Co ltd filed Critical Jiangsu Apon Medical Technology Co ltd
Priority to CN201911006456.8A priority Critical patent/CN110841142B/en
Publication of CN110841142A publication Critical patent/CN110841142A/en
Application granted granted Critical
Publication of CN110841142B publication Critical patent/CN110841142B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
    • A61M5/00—Devices for bringing media into the body in a subcutaneous, intra-vascular or intramuscular way; Accessories therefor, e.g. filling or cleaning devices, arm-rests
    • A61M5/14—Infusion devices, e.g. infusing by gravity; Blood infusion; Accessories therefor
    • A61M5/168—Means for controlling media flow to the body or for metering media to the body, e.g. drip meters, counters ; Monitoring media flow to the body
    • A61M5/16831—Monitoring, detecting, signalling or eliminating infusion flow anomalies
    • A61M5/16854—Monitoring, detecting, signalling or eliminating infusion flow anomalies by monitoring line pressure
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/048—Activation functions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
    • A61M5/00—Devices for bringing media into the body in a subcutaneous, intra-vascular or intramuscular way; Accessories therefor, e.g. filling or cleaning devices, arm-rests
    • A61M5/14—Infusion devices, e.g. infusing by gravity; Blood infusion; Accessories therefor
    • A61M5/168—Means for controlling media flow to the body or for metering media to the body, e.g. drip meters, counters ; Monitoring media flow to the body
    • A61M5/16831—Monitoring, detecting, signalling or eliminating infusion flow anomalies
    • A61M2005/16863—Occlusion detection
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
    • A61M2205/00—General characteristics of the apparatus
    • A61M2205/33—Controlling, regulating or measuring
    • A61M2205/3327—Measuring
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
    • A61M2205/00—General characteristics of the apparatus
    • A61M2205/33—Controlling, regulating or measuring
    • A61M2205/3331—Pressure; Flow
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
    • A61M2205/00—General characteristics of the apparatus
    • A61M2205/50—General characteristics of the apparatus with microprocessors or computers

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Computational Linguistics (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Vascular Medicine (AREA)
  • Anesthesiology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Hematology (AREA)
  • Animal Behavior & Ethology (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Infusion, Injection, And Reservoir Apparatuses (AREA)

Abstract

The application discloses a method and a system for predicting blockage of a transfusion pipeline, comprising the following steps: collecting continuous pressure values in the infusion pipeline; converting the continuous pressure values to obtain vector data; preprocessing the vector data to obtain input data; and inputting the input data into a deep learning model to obtain the blocking time. According to the continuous pressure values, the time at which the blockage is likely to occur is predicted by using a deep learning model, corresponding measures can be taken in advance for processing, the influence caused by pressure value difference caused by factors such as environment, materials, medicines and the like can be effectively reduced, and the applicability and the robustness of the method are improved; in addition, the probability that blockage will occur can be effectively predicted through a deep learning method, so that early warning is facilitated, risks caused by blockage are effectively reduced, safety protection and convenience are brought to patients and clinicians, and the method has good practicability and applicability.

Description

Method and system for predicting blockage of infusion pipeline
Technical Field
The application relates to the field of medical instruments, in particular to a method and a system for predicting blockage of an infusion pipeline.
Background
The medical appliance product of the injection pump type can cause the condition of pipeline blockage in clinical use, and has certain medical risk to patients if the medical appliance product cannot be processed in time. The existing blockage alarming method is more traditional, the alarm is often generated according to a preset threshold value, the alarm is triggered only after the blockage occurs, and the predictability is not available.
In view of the foregoing, it would be desirable to provide a method and system that can predict an occlusion.
Disclosure of Invention
In order to solve the problems, the application provides a method and a system for predicting blockage of a transfusion pipeline.
In one aspect, the present application provides a method for predicting an occlusion of an infusion line, comprising:
collecting continuous pressure values in the infusion pipeline;
converting the continuous pressure values to obtain vector data;
preprocessing the vector data to obtain input data;
and inputting the input data into a deep learning model to obtain the blocking time.
Preferably, the inputting the input data into a deep learning model to obtain the occlusion time includes:
inputting input data into a deep learning model, and determining output data of a last hidden layer;
and sending the output data to a full connection layer of the deep learning model to determine the blocking time.
Preferably, the inputting the input data into the deep learning model and determining the output data of the last hidden layer includes:
s1, inputting the input data into a hidden layer of the deep learning model;
s2, calculating the activation value of the hidden layer;
s3, carrying out nonlinear transformation on all the obtained activation values by using an activation function to obtain a hidden layer output signal;
s4, if the hidden layer output signal is not the output signal of the last hidden layer, executing S2 to S3, if the hidden layer output signal is the output signal of the last hidden layer, the output signal is the output data.
Preferably, the sending the output data to a full connection layer of the deep learning model to determine the jam time includes:
sending the output data of the last hidden layer to a full connection layer, and calculating an activation value;
calculating the output value of the full connection layer according to the activation value and the activation function;
and determining the jam time according to the output value by using a classifier at an output layer.
Preferably, the full connection layer includes: one or more fully connected layers.
Preferably, the classifier comprises: softmax classifier.
Preferably, the pre-treatment comprises: denoising, normalizing, and/or normalizing.
Preferably, before the inputting the input data into the deep learning model to obtain the occlusion time, the method further includes:
and training the deep learning model.
In a second aspect, the present application provides a system for predicting an occlusion of an infusion line, comprising:
the acquisition module is used for acquiring continuous pressure values in the infusion pipeline;
the preprocessing module is used for converting the continuous pressure values to obtain vector data, and preprocessing the vector data to obtain input data;
and the prediction module is used for inputting the input data into a deep learning model to obtain the blocking time.
Preferably, the prediction module is specifically configured to input the input data into the deep learning model, and determine output data of a last hidden layer; and sending the output data to a full connection layer of the deep learning model to determine the blocking time.
The application has the advantages that: according to the continuous pressure value, the time of possible blockage is predicted by using the deep learning model, corresponding measures can be taken in advance for processing, the influence of environmental factors is reduced, and safety protection and convenience are brought to patients and clinicians.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating preferred embodiments and are not to be construed as limiting the application. Also, like reference numerals are used to denote like parts throughout the drawings. In the drawings:
FIG. 1 is a schematic diagram of the steps of a method for predicting an occlusion in an infusion line according to the present application;
FIG. 2 is a schematic illustration of a method for predicting an infusate line occlusion provided herein;
FIG. 3 is a schematic diagram of a system for predicting an occlusion in an infusion line as provided herein.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
According to an embodiment of the application, a method for predicting blockage of an infusion pipeline is provided, as shown in fig. 1, the method comprises the following steps: the method comprises the following steps:
s101, collecting continuous pressure values in a transfusion pipeline;
s102, converting the continuous pressure values to obtain vector data;
s103, preprocessing vector data to obtain input data;
and S104, inputting the input data into the deep learning model to obtain the blocking time.
Inputting input data into a deep learning model to obtain the blocking time, wherein the method comprises the following steps:
inputting input data into a deep learning model, and determining output data of a last hidden layer;
and sending the output data to a full connection layer of the deep learning model to determine the blocking time.
Inputting input data into a deep learning model, and determining output data of a last hidden layer, wherein the method comprises the following steps:
s1, inputting the input data into a hidden layer of the deep learning model;
s2, calculating the activation value of the hidden layer;
s3, carrying out nonlinear transformation on all the obtained activation values by using an activation function to obtain a hidden layer output signal;
s4, if the hidden layer output signal is not the output signal of the last hidden layer, executing S2 to S3, if the hidden layer output signal is the output signal of the last hidden layer, the output signal is the output data.
Sending the output data to a full connection layer of a deep learning model, and determining the blocking time, wherein the method comprises the following steps:
sending the output data of the last hidden layer to a full connection layer, and calculating an activation value;
calculating the output value of the full connection layer according to the activation value and the activation function;
and determining the jam time according to the output value by using a classifier at an output layer.
The full-connection layer includes: one or more fully connected layers.
The classifier includes: softmax classifier.
The pretreatment comprises the following steps: denoising, normalizing, and/or normalizing.
Before inputting the input data into the deep learning model to obtain the jam time, the method further comprises the following steps:
and training the deep learning model.
The method adopts a deep learning model to acquire continuous pressure values in infusion pipelines of an electronic infusion pump, an analgesia pump, a chemotherapy pump, an infusion device and the like in real time, carries out intelligent analysis learning on the acquired continuous pressure values, and predicts the time point of blockage in the infusion pipeline through the deep learning model.
Next, as shown in fig. 2, the embodiment of the present application will be further described by taking an analgesic pump device as an example.
The continuous pressure values in the infusion pipeline of the analgesia pump equipment are collected in real time, and the collected continuous pressure values are converted into vector data I, so that the later neural network learning is facilitated.
The vector data I includes: a data matrix or a data set.
Preferably, a Gaussian filtering method is adopted to perform denoising and smoothing processing on the vector data I, so that the influence caused by pressure value difference caused by factors such as environment, materials, medicines and the like is reduced.
The vector data in a period of time (for example, 10 seconds) is processed by a normalization method to obtain input data.
The duration of a period of time can be set as desired.
Transferring input data to a network of n layers of dense connections in a deep learning model, with learned link weights WhiddenAnd offset BhiddenCalculating an activation value X for each hidden layerhidden：
Xhidden＝Whidden·I+Bhidden
Using an activation function F (X) for the activation value calculated for each hidden layerhidden) Carrying out nonlinear transformation to obtain a hidden layer output signal;
Fhidden_out＝σ(Xhidden)
where σ is the activation function.
Namely, inputting input data into a hidden layer of the deep learning model; using learned link weights WhiddenAnd offset BhiddenCalculating the activation value X of the hidden layerhidden(ii) a And carrying out nonlinear transformation on all the obtained activation values by using an activation function to obtain a hidden layer output signal.
And inputting the output signal of the hidden layer into the next hidden layer, and calculating the output signal of the next hidden layer according to the above mode until the output signal of the last hidden layer is obtained, wherein the output signal of the last hidden layer is output data.
The number of hidden layers can be set as desired.
After n hidden layer operations, the output (output data) of the last hidden layer is transmitted to the full-connection layer. The number of fully connected layers may be multiple, that is, multiple fully connected layers may be included in the deep learning model.
The full-connection layer calculates an activation value according to the output data, and then obtains the output value of the full-connection layer through an activation function; and finally, predicting the probability value of the blockage at a certain future moment by using the output of the full connection layer in the output layer and adopting a Softmax classifier.
If the full connection layer comprises a plurality of full connection layers, the first full connection layer calculates an activation value according to output data, then obtains an output value of the full connection layer through an activation function, transmits the output value into the next full connection layer, and calculates the output value of the next full connection layer until the output value of the last full connection layer is obtained.
And inputting the output value of the last full-connection layer into a Softmax classifier to obtain the blocking time (probability value of blocking at a certain future moment).
The number of fully connected layers can be set as desired.
The input layer is used for preprocessing input data, and comprises the following steps: normalization, de-averaging, dimensionality reduction, whitening, enhancement, etc. of the data.
The dimensionality reduction comprises the following steps: principal Component Analysis (PCA), Singular Value Decomposition (SVD), and the like.
Normalization and/or normalization in the preprocessing may be performed before the data enters the input layer, or may be performed at the input layer.
The above method can also be used for training of deep learning models.
According to an embodiment of the present application, there is also provided a system for predicting an infusion line blockage, as shown in fig. 3, including:
the collecting module 101 is used for collecting continuous pressure values in the infusion pipeline;
the preprocessing module 102 is configured to convert the continuous pressure values to obtain vector data, and preprocess the vector data to obtain input data;
and the prediction module 103 is used for inputting the input data into the deep learning model to obtain the blocking time.
The prediction module is specifically used for inputting input data into the deep learning model and determining output data of the last hidden layer; and sending the output data to a full connection layer of the deep learning model to determine the blocking time.
According to the method, the time of possible blockage is predicted by using the deep learning model according to the continuous pressure values, corresponding measures can be taken in advance for processing, the influence caused by pressure value difference caused by factors such as environment, materials, medicines and the like can be effectively reduced, and the applicability and the robustness of the method are improved; in addition, the probability that blockage will occur can be effectively predicted through a deep learning method, so that early warning is facilitated, risks caused by blockage are effectively reduced, safety protection and convenience are brought to patients and clinicians, and the method has good practicability and applicability.
The above description is only for the preferred embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present application should be covered within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (8)

1. A method for predicting an infusion line occlusion, comprising:
collecting continuous pressure values in the infusion pipeline;
converting the continuous pressure values to obtain vector data;
preprocessing the vector data to obtain input data;
inputting the input data into a deep learning model to obtain the blocking time, wherein the blocking time is the time point of future blocking in the infusion pipeline;
wherein, the inputting the input data into a deep learning model to obtain the blocking time comprises:
inputting input data into a deep learning model, and determining output data of a last hidden layer;
and sending the output data to a full connection layer of the deep learning model to determine the blocking time.
2. The method of claim 1, wherein inputting the input data into a deep learning model and determining the output data of the last hidden layer comprises:
s1, inputting the input data into a hidden layer of the deep learning model;
s2, calculating the activation value of the hidden layer;
s3, carrying out nonlinear transformation on all the obtained activation values by using an activation function to obtain a hidden layer output signal;
s4, if the hidden layer output signal is not the output signal of the last hidden layer, executing S2 to S3, if the hidden layer output signal is the output signal of the last hidden layer, the output signal is the output data.
3. The method of claim 1, wherein sending the output data to a fully connected layer of the deep learning model, determining a jam time, comprises:
sending the output data of the last hidden layer to a full connection layer, and calculating an activation value;
calculating the output value of the full connection layer according to the activation value and the activation function;
and determining the jam time according to the output value by using a classifier at an output layer.
4. The method of claim 3, wherein the fully connected layer comprises: one or more fully connected layers.
5. The method of claim 3, wherein the classifier comprises: softmax classifier.
6. The method of claim 1, wherein the pre-processing comprises: denoising, normalizing, and/or normalizing.
7. The method of claim 1, wherein prior to said inputting said input data into a deep learning model resulting in a jam time, further comprising:
and training the deep learning model.
8. A system for predicting an occlusion in an infusion line, comprising:
the acquisition module is used for acquiring continuous pressure values in the infusion pipeline;
the preprocessing module is used for converting the continuous pressure values to obtain vector data, and preprocessing the vector data to obtain input data;
the prediction module is used for inputting the input data into a deep learning model to obtain the blocking time, wherein the blocking time is a time point of future blocking in the infusion pipeline;
the prediction module is specifically used for inputting input data into the deep learning model and determining output data of the last hidden layer; and sending the output data to a full connection layer of the deep learning model to determine the blocking time.
CN201911006456.8A 2019-10-22 2019-10-22 Method and system for predicting blockage of infusion pipeline Active CN110841142B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911006456.8A CN110841142B (en) 2019-10-22 2019-10-22 Method and system for predicting blockage of infusion pipeline

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911006456.8A CN110841142B (en) 2019-10-22 2019-10-22 Method and system for predicting blockage of infusion pipeline

Publications (2)

Publication Number Publication Date
CN110841142A CN110841142A (en) 2020-02-28
CN110841142B true CN110841142B (en) 2022-03-08

Family

ID=69597663

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911006456.8A Active CN110841142B (en) 2019-10-22 2019-10-22 Method and system for predicting blockage of infusion pipeline

Country Status (1)

Country Link
CN (1) CN110841142B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN203208378U (en) * 2013-05-03 2013-09-25 中国人民解放军南京军区南京总医院 Enteral nutrition pump with dynamic pressure detection function
US20150306310A1 (en) * 2013-02-15 2015-10-29 Micrel Medical Devices S.A. Method for Processing Infusion Data and an Infusion Pump System
CN105546352A (en) * 2015-12-21 2016-05-04 重庆科技学院 Natural gas pipeline tiny leakage detection method based on sound signals
CN109559302A (en) * 2018-11-23 2019-04-02 北京市新技术应用研究所 Pipe video defect inspection method based on convolutional neural networks
CN110242865A (en) * 2019-07-09 2019-09-17 北京讯腾智慧科技股份有限公司 A kind of gas leakage detection determination method and system being easy to Continuous optimization
CN110309911A (en) * 2019-07-05 2019-10-08 北京中科寒武纪科技有限公司 Neural network model verification method, device, computer equipment and storage medium

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150306310A1 (en) * 2013-02-15 2015-10-29 Micrel Medical Devices S.A. Method for Processing Infusion Data and an Infusion Pump System
CN203208378U (en) * 2013-05-03 2013-09-25 中国人民解放军南京军区南京总医院 Enteral nutrition pump with dynamic pressure detection function
CN105546352A (en) * 2015-12-21 2016-05-04 重庆科技学院 Natural gas pipeline tiny leakage detection method based on sound signals
CN109559302A (en) * 2018-11-23 2019-04-02 北京市新技术应用研究所 Pipe video defect inspection method based on convolutional neural networks
CN110309911A (en) * 2019-07-05 2019-10-08 北京中科寒武纪科技有限公司 Neural network model verification method, device, computer equipment and storage medium
CN110242865A (en) * 2019-07-09 2019-09-17 北京讯腾智慧科技股份有限公司 A kind of gas leakage detection determination method and system being easy to Continuous optimization

Also Published As

Publication number Publication date
CN110841142A (en) 2020-02-28

Similar Documents

Publication Publication Date Title
Furnari et al. Rolling-unrolling lstms for action anticipation from first-person video
Xiang et al. Long short-term memory neural network with weight amplification and its application into gear remaining useful life prediction
CN109902832B (en) Training method of machine learning model, anomaly prediction method and related devices
Mounce et al. Novelty detection for time series data analysis in water distribution systems using support vector machines
CN109728939B (en) Network flow detection method and device
US20200050182A1 (en) Automated anomaly precursor detection
CN109213121A (en) A kind of fan braking system card cylinder method for diagnosing faults
CN105023044B (en) Traffic flow causality method for digging based on plenty of time sequence
CN110111885B (en) Attribute prediction method, attribute prediction device, computer equipment and computer readable storage medium
CN110841143B (en) Method and system for predicting state of infusion pipeline
Ahmad et al. Leak detection and size identification in fluid pipelines using a novel vulnerability index and 1-D convolutional neural network
CN105654134B (en) It is a kind of based on the context aware system and its working method and application that have supervision self feed back
Roychoudhury et al. A Bayesian approach to efficient diagnosis of incipient faults
Tijani et al. Gene expression programming based mathematical modeling for leak detection of water distribution networks
CN111007452A (en) Fault diagnosis method and device of data acquisition system
CN115114448A (en) Intelligent multi-mode fusion electricity utilization inspection method, device, system, equipment and medium
CN110841142B (en) Method and system for predicting blockage of infusion pipeline
Abououf et al. Explainable AI for Event and Anomaly Detection and Classification in Healthcare Monitoring Systems
Dayanik et al. Sequential detection and identification of a change in the distribution of a markov-modulated random sequence
CN115099129B (en) Natural gas well yield prediction method based on input characteristic error correction
Purintrapiban et al. Neural networks for detecting cyclic behavior in autocorrelated process
KR20180126311A (en) System and Method for State Diagnosis and Cause Analysis
CN116631626A (en) Patient clinical risk assessment method, device, equipment and medium
Tylman et al. Fully automatic AI-based leak detection system
CN104980442A (en) Network intrusion detection method based on element sample sparse representation

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