CN106491126A - A kind of device of dynamic early-warning epileptic attack - Google Patents
A kind of device of dynamic early-warning epileptic attack Download PDFInfo
- Publication number
- CN106491126A CN106491126A CN201611083211.1A CN201611083211A CN106491126A CN 106491126 A CN106491126 A CN 106491126A CN 201611083211 A CN201611083211 A CN 201611083211A CN 106491126 A CN106491126 A CN 106491126A
- Authority
- CN
- China
- Prior art keywords
- eeg signals
- epileptic attack
- warning
- early
- irregularity
- 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.)
- Granted
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/25—Bioelectric electrodes therefor
- A61B5/279—Bioelectric electrodes therefor specially adapted for particular uses
- A61B5/291—Bioelectric electrodes therefor specially adapted for particular uses for electroencephalography [EEG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/40—Detecting, measuring or recording for evaluating the nervous system
- A61B5/4076—Diagnosing or monitoring particular conditions of the nervous system
- A61B5/4094—Diagnosing or monitoring seizure diseases, e.g. epilepsy
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/74—Details of notification to user or communication with user or patient ; user input means
- A61B5/7465—Arrangements for interactive communication between patient and care services, e.g. by using a telephone network
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Veterinary Medicine (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Public Health (AREA)
- Neurology (AREA)
- Psychiatry (AREA)
- Neurosurgery (AREA)
- Physiology (AREA)
- Artificial Intelligence (AREA)
- Nursing (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Signal Processing (AREA)
- Psychology (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a kind of device of dynamic early-warning epileptic attack, including brain wave acquisition portion, which includes that electrode for encephalograms and signal conditioning circuit, the electrode for encephalograms are used for gathering EEG signals and being sent to signal conditioning circuit being pre-processed;Storage part, its are used for receiving and storing the pretreated EEG signals of the signal conditioning circuit;Microprocessor, its are configured to:From the EEG signals that storage part obtains default set time length, and two-stage secondary classification is carried out to the EEG signals for obtaining;Wherein, first order secondary classification is output as normal EEG signals and abnormal EEG signals, and second level secondary classification is output as epileptic attack early stage EEG signals and epileptic attack phase EEG signals;Output section, its are connected with microprocessor, for carrying out real-time early warning to epileptic attack early stage and epileptic attack phase.
Description
Technical field
A kind of the invention belongs to portable medical technical field, more particularly to device of dynamic early-warning epileptic attack.
Background technology
Epileptic attack, a certain position of body or whole body assume transience nonautonomy and twitch, sometimes with consciousness
Lose and urinary incontinence, with serious potential life threat.Avoid causing individual injury even life threat by epileptic attack
Effective means be the early stage information for detecting epileptic attack in time, and send out to medical personnel and patient monitoring people or relatives in time
Go out early warning.
By body surface or the physiology or motion signal analysis of monitored in vitro, it is possible to find epileptic attack phase or outbreak early stage
Feature.Epileptic attack is caused by one group of brain cell paradoxical discharge, thus is possible in maximum journey by the analysis of EEG signals
The outbreak of epilepsy is predicted on degree as early as possible.Based on the non-linear nature feature of EEG signals, many open source literatures are attempted using non-
Linear algorithm analysis brain electricity is further sorted out to brain electricity.The detection of epilepsy is converted into two-value classification problem by prior art,
Can be normal or stage of attack signal by eeg signal classification, be that alarm is sent after epileptic attack, rather than outbreak early stage
Early warning.
In recent years research discloses significant advantage of the entropy algorithm on analysis physiological signal, but theoretical research is illustrated, and entropy is calculated
The feature portrayed by method may reflect dynamic behavior of the signal in different linear domains, the rule of such as signal or scrambling
And the simple or complexity of signal etc..But, existing epileptic attack detection method is not had not intactly using single algorithm
Describe the nonlinear characteristic of EEG signals, it is impossible to react EEG signals exactly, its direct result is probably disclosed classification
Or method for early warning does not have good generalization ability, namely when these methods are transplanted on a crowd for having more universality
Its accuracy can not be inherited, that is, can not early warning epileptic attack exactly.Replace in addition simply by a kind of method
A kind of method still suffers from same problem.The dynamic behavior that EEG signals on different dimensions are obtained by polyalgorithm, enters
And these attributes are mapped to by unified linear domain based on specific syncretizing mechanism, for complete picture, its nonlinear characteristic is provided
May, also ensure that the generalization ability of method to the full extent, the open source literature that can currently retrieve is also without reference to this
Concept, makes how to merge and how to carry out fusion to carry out accurate description EEG signals to belong to tera incognita.The present invention
It is based on background above technology and proposes.
Content of the invention
In order to solve the shortcoming of prior art, the present invention provides a kind of device of dynamic early-warning epileptic attack.
A kind of device of the dynamic early-warning epileptic attack of the present invention, including:
Brain wave acquisition portion, it include that electrode for encephalograms and signal conditioning circuit, the electrode for encephalograms are used for gathering EEG signals
And be sent to signal conditioning circuit and pre-processed;
Storage part, its are used for receiving and storing the pretreated EEG signals of the signal conditioning circuit;
Microprocessor, for the real-time analysis of EEG signals, completes detecing for epileptic attack early stage and stage of attack EEG signals
The Communication Control of survey, EEG signals compression and engagement positions, which is configured to:From the brain that storage part obtains default set time length
Electric signal, and two-stage secondary classification is carried out to the EEG signals for obtaining;Wherein, first order secondary classification is output as normal brain activity telecommunications
Number and abnormal EEG signals, second level secondary classification is output as epileptic attack early stage EEG signals and epileptic attack phase brain telecommunications
Number;
Output section, its are connected with microprocessor, for carrying out real-time early warning to epileptic attack early stage and epileptic attack phase.
Further, the microprocessor, is additionally configured to:
From the EEG signals x that storage part obtains default set time length t;
Using preset length t0Time window come EEG signals x is carried out respectively standard deviation normalization and amplitude normalization,
Wherein, t0T is less than, and t is t0K times, k is positive integer;
Respectively according to standard deviation normalized signal and amplitude normalized signal, in k-th time window of calculating, signal does not advise
F is then spentktWith complexity Dkt, and then obtain the average degree of irregularity of EEG signals xAnd average complexity
Directly carry out standard deviation normalization and amplitude normalization to EEG signals x respectively, further directly calculate brain electricity
The degree of irregularity F of signal xtWith complexity Dt;
Average degree of irregularity by EEG signals xAverage complexityDegree of irregularity FtWith complexity DtAs feature
Value carrys out construction feature set, carries out two-stage secondary classification to EEG signals x;Wherein, the input feature vector of first order quadratic classifier
Degree of irregularity F for t seconds brain electricitytAnd average complexityCombination, be output as normal EEG signals and abnormal EEG signals, the
Two grades of quadratic classifiers act on the abnormal EEG signals detected by first order grader, and input feature vector is the average of t seconds brain electricity
Degree of irregularityWith complexity DtCombination, be output as epileptic attack early stage EEG signals and epileptic attack phase EEG signals.
The EEG signals of acquisition are asked for the average degree of irregularity of its dynamic behavior by the present invention respectivelyAverage complexityDegree of irregularity FtWith complexity Dt, and then these dynamic behaviors are based on as characteristic value come construction feature set and mapping
To unified linear domain, the nonlinear characteristic of EEG signals is intactly depicted, finally being capable of dynamic early-warning epilepsy exactly
Outbreak.
Further, the device of the dynamic early-warning epileptic attack also includes input unit, and which is used for being input into user data to produce
Raw and recorded electronic case history.
Further, the microprocessor is connected to data server by wireless communication module.
Further, the data server is connected with cloud central server.
The present invention while dynamic detection epileptic attack early stage and stage of attack signal, after the set time, microprocessor
Device is compressed to the EEG signals being stored in storage part, then by wireless communication module to data server transmission letter
Breath, then EEG signals are sent to cloud central server by data server, it is finally reached the long-range storage and application of data.
The present invention in addition to the EEG signals after cyclical transmission compression, also can be detected by microprocessor by wireless communication module
The epileptic attack early stage for arriving or stage of attack signal activation, and then urgent telemonitoring center and the emergency contact of patient to hospital
Human hair goes out alarm.
Further, the output section includes display module, audio-frequency module and micro motor, for showing brain telecommunications in real time
Number, be highlighted epileptic attack early stage and stage of attack EEG signals in real time, and sent in epileptic attack early stage and stage of attack in real time
Sound and mechanical oscillation early warning;The display module, audio-frequency module are connected with microprocessor with micro motor.
Beneficial effects of the present invention are:
The device of the dynamic early-warning epileptic attack of the present invention portablely, continuously dynamically can record EEG signals, to obtaining
The EEG signals for taking carry out two-stage secondary classification, and real-time detection goes out normal EEG signals, epileptic attack early stage EEG signals and insane
Epilepsy stage of attack EEG signals, so as to realizing the outbreak of early stage precognition epilepsy and sending early warning information.
Description of the drawings
Structure principle charts of the Fig. 1 for apparatus of the present invention.
Fig. 2 is the schematic flow sheet of dynamic early-warning epileptic attack of the present invention.
Fig. 3 (a) is a normal brain activity electricity.
Fig. 3 (b) is abnormal EEG signals.
Fig. 3 (c) is a normal brain activity electricity and an abnormal mapping area schematic diagram of the EEG signals in non-linear plane.
Fig. 4 (a) is an epileptic attack early stage brain electricity.
Fig. 4 (b) is epileptic attack phase EEG signals.
Fig. 4 (c) is that an epileptic attack early stage brain is electric and epileptic attack phase EEG signals are in non-linear plane
Mapping area schematic diagram.
Wherein, 1, output section, 2, brain wave acquisition portion, 3, storage part, 4, microprocessor, 5, wireless communication module.
Specific embodiment
The present invention will be further described with embodiment below in conjunction with the accompanying drawings:
As shown in figure 1, the device of the dynamic early-warning epileptic attack of the present invention includes brain wave acquisition portion 2, storage part 3, Wei Chu
Reason device 4 and output section 1.
Wherein, brain wave acquisition portion 2 includes that electrode for encephalograms and signal conditioning circuit, electrode for encephalograms are used for gathering EEG signals simultaneously
It is sent to signal conditioning circuit to be pre-processed.Signal conditioning circuit includes the amplifying circuit being connected in series and filter circuit, institute
The output end for stating filter circuit is connected with analog-to-digital conversion circuit.The EEG signals recorded by electrode for encephalograms through signal condition and
After amplifying circuit is filtered and amplifies, data signal is converted to by analog-to-digital conversion circuit and is exported.
Storage part 3, its are used for receiving and storing the pretreated data signal of the signal conditioning circuit.Storage part can be with
Realized using flash memories.
Microprocessor 4, for the real-time analysis of EEG signals, completes detecing for epileptic attack early stage and stage of attack EEG signals
The Communication Control of survey, EEG signals compression and engagement positions, which is configured to:From the brain that storage part obtains default set time length
Electric signal, and two-stage secondary classification is carried out to the EEG signals for obtaining;Wherein, first order secondary classification is output as normal brain activity telecommunications
Number and abnormal EEG signals, second level secondary classification be output as epileptic attack early stage EEG signals and epileptic attack during brain telecommunications
Number.
Wherein, microprocessor 4 is additionally configured to:
From the EEG signals x that storage part 3 obtains default set time length t;
Using preset length t0Time window come EEG signals x is carried out respectively standard deviation normalization and amplitude normalization,
Wherein, t0T is less than, and t is t0K times, k is positive integer;
Respectively according to standard deviation normalized signal and amplitude normalized signal, in k-th time window of calculating, signal does not advise
F is then spentktWith complexity Dkt, and then obtain the average degree of irregularity of EEG signals xAnd average complexity
Directly carry out standard deviation normalization and amplitude normalization to EEG signals x respectively, further directly calculate brain electricity
The degree of irregularity F of signal xtWith complexity Dt;
Average degree of irregularity by EEG signals xAverage complexityDegree of irregularity FtWith complexity DtAs feature
Value carrys out construction feature set, carries out two-stage secondary classification to EEG signals x;Wherein, the input feature vector of first order quadratic classifier
Degree of irregularity F for t seconds brain electricitytAnd average complexityCombination, be output as normal EEG signals and abnormal EEG signals, the
Two grades of quadratic classifiers act on the abnormal EEG signals detected by first order grader, and input feature vector is the average of t seconds brain electricity
Degree of irregularityWith complexity DtCombination, be output as epileptic attack early stage EEG signals and epileptic attack phase EEG signals.
The EEG signals of acquisition are asked for the average degree of irregularity of its dynamic behavior by the present invention respectivelyAverage complexityDegree of irregularity FtWith complexity Dt, and then these dynamic behaviors are based on as characteristic value come construction feature set and mapping
To unified linear domain, the nonlinear characteristic of EEG signals is intactly depicted, finally being capable of dynamic early-warning epilepsy exactly
Outbreak.
Output section 1, which is connected with microprocessor, for carrying out real-time early warning to epileptic attack early stage and stage of attack;Output
Portion 1 includes display module, audio-frequency module and micro motor, and the display module, audio-frequency module and micro motor are and microprocessor
Device is connected;Wherein, display module is used for showing EEG signals in real time, is highlighted epileptic attack early stage and stage of attack brain telecommunications
Number, audio-frequency module and micro motor are used for exporting early warning information
Further, the device of the dynamic early-warning epileptic attack also includes input unit, and which is used for being input into user data to produce
Raw and recorded electronic case history.
Further, microprocessor 4 is connected to data server by wireless communication module 5.
Further, data server is connected with cloud central server.The present invention in dynamic detection epileptic attack early stage and
While stage of attack signal, after the set time, microprocessor is compressed to the EEG signals being stored in storage part, and
Transmitted to cloud central server by wireless communication module afterwards.
The present invention in addition to the EEG signals after cyclical transmission compression, also can be detected by microprocessor by wireless communication module
The epileptic attack early stage for arriving or stage of attack signal activation, and then urgent telemonitoring center and the emergency contact of patient to hospital
Human hair goes out alarm.
The device of the dynamic early-warning epileptic attack of the present invention portablely, continuously dynamically can record EEG signals, to obtaining
The EEG signals for taking carry out two-stage secondary classification, and real-time detection goes out normal EEG signals, epileptic attack early stage EEG signals and insane
Epilepsy stage of attack EEG signals, so as to realizing the outbreak of early stage precognition epilepsy and sending early warning information.
Fig. 2 illustrates the flow chart that microprocessor carries out dynamic early-warning epileptic attack.5t second brain telecommunications with continuous acquisition
Number, and as a example by the length of time window is t:
First, microprocessor 4 is according to sample rate F for settingsQueue of the initialization length for the 5t seconds, and by continuous acquisition
5t second EEG signals { x5t(i) } sequentially enter queue;
Using the time window that length is t to signal { x5t(i) } carry out standard deviation normalization and amplitude normalization respectively, obtain
SignalWithWherein k=1,2,3,4,5;To standard deviation normalized signalCalculate degree of irregularity Fkt, to width
Value normalized signalComputation complexity Dkt, obtain the average degree of irregularity of EEG signals under 5t/t=5 time windowAnd average complexity
To signal { x5t(i) } standard deviation normalization and amplitude normalization is directly carried out, obtain signalWith
To standard deviation normalized signalCalculate degree of irregularity F5t, to amplitude normalized signalCalculate complicated
Degree D5t;
Feature based setTo EEG signals { x5t(i) } classified, EEG signals are classified
Grader be the two-stage quadratic classifier staggeredly combined based on degree of irregularity and complexity, wherein:
The input feature vector of first order quadratic classifier is the degree of irregularity F of 5t seconds brain electricity5tAnd average complexityCombination,
It is output as normal EEG signals and abnormal EEG signals;As Fig. 3 (a) and Fig. 3 (b) illustrate normal EEG signals and one
Abnormal EEG signals, and the normal EEG signals of Fig. 3 (c) and abnormal EEG signals reflecting in degree of irregularity-average complexity plane
Penetrate region;
Second level quadratic classifier acts on the "abnormal" signal detected by first order grader, and input feature vector is 5t second brains
The average degree of irregularity of electricityWith complexity D5tCombination, be output as epileptic attack early stage EEG signals and stage of attack brain telecommunications
Number;Fig. 4 (a) and Fig. 4 (b) illustrate an epileptic attack early stage signal and an epileptic attack phase signal, and Fig. 4 (c) sends out
Make the mapping area of early stage signal and stage of attack signal in average degree of irregularity-complexity plane;
The EEG signals for continuing the collection t seconds enter enqueue, and with queue after the signal of 4t seconds to constitute new length be the 5t seconds
EEG signals { x5t(i) }, above analysis process is reentered, is circulated with this until user or doctor suspend or close dress
Put.
Preferably, the degree of irregularity of signal is calculated by the following method:
(1) space dimensionality is set as m, signal x (i) is reconstructed to phase space, i.e. X (i)=[x (i), x (i+1) ..., x (i
+ m-1)], wherein, the length of i=1,2 ..., N-m, N for signal x (i);
(2) the distance between different vectors X (i) and X (j) d (i, j)=fun (X (i), X (j)) two-by-two is traveled through, wherein, i,
J=1,2 ..., N-m, i ≠ j, fun are distance function;
(3) similitude tolerance limit r is set, (2) described frequency B (m) apart from d (i, j)≤r is calculated based on fuzzy logic, i.e.,
(4) space dimensionality is increased by 1, i.e., on m+1 dimension spaces, repeats (1)~(3), obtain frequency B (m+1);
(5) the degree of irregularity F=-ln (B (m+1)/B (m)) of signal x (i).
Of the invention using difference two-by-two, between vectorial, the traversal of distance is remarkably improved computational efficiency, using fuzzy logic meter
Calculate the stability that frequency B (m) can improve result.
Preferably, the complexity of signal is calculated by the following method:
(1) space dimensionality is set as m, signal x (i) is reconstructed to phase space, i.e. X (i)=[x (i), x (i+1) ..., x (i
+ m-1)], wherein, the length of i=1,2 ..., N-m, N for signal x (i),
(2) the distance between different vectors X (i) and X (j) d (i, j)=fun (X (i), X (j)) two-by-two is traveled through, wherein, i,
J=1,2 ..., N-m, i ≠ j, fun are distance function,
(3) probability density function p (l) of estimated distance d (i, j), l=1,2 ..., Q, wherein Q is the coarse for setting
Level;
(4) complexity of signal x (i)
The present invention is using between different vectors, the traversal of distance is remarkably improved computational efficiency two-by-two, close using the probability
Degree function p (l) portrays the distribution characteristics of distance, can still have at a relatively high accuracy and stability when signal length is extremely short.
Once detect epileptic attack early stage or epileptic attack phase signal, microprocessor 4 can to output section 1 send instruction with
Signal is highlighted, and audible alarm is exported by the built-in audio-frequency module in output section 1, by the built-in miniature horse in output section 1
Up to the vibrations early warning for realizing engagement positions.
According to initial configuration, storage part 3 keeps in the EEG signals that length is set time T, when collection EEG signals reach
After time T, the Signal Compression formula in microprocessor 4 is activated, and EEG signals is compressed by compressed sensing algorithm, pressure
Signal after contracting enters wireless communication module 5 and is wirelessly transferred, and to reduce the communication load of wireless telecommunications, improves communication effect
Rate.Subsequently, the length that keeps in flash memories is cleared for the EEG signals of T, so as to vacate memory space for receiving new signal.
In addition to EEG signals after compression can activate wireless communication module 5, wireless communication module 5 can also be by micro- place
Reason device 4 detected by epileptic attack early stage or epileptic attack phase signal activated, so as to the telemonitoring center to hospital with
The programmed emergency of patient sends early warning, realizes the function of dynamic early-warning epileptic attack.
Preferably, as embodiment, the parameter value that above-mentioned each symbol replaces is:
Fs=128 hertz, T=10 minutes, the t=1 seconds, m=3, r=0.2, Q=64.
It is based on above-mentioned preferred enforcement parameter:The temporal resolution of apparatus of the present invention is 1 second;Carry out epileptic attack early warning
Precision is 0.92, and sensitiveness is 0.9, and specificity is 0.96, and positive prediction rate is 0.97.
Although the above-mentioned accompanying drawing that combines is described to the specific embodiment of the present invention, not to present invention protection model
The restriction that encloses, one of ordinary skill in the art should be understood that on the basis of technical scheme those skilled in the art are not
The various modifications that makes by needing to pay creative work or deformation are still within protection scope of the present invention.
Claims (6)
1. a kind of device of dynamic early-warning epileptic attack, it is characterised in that include:
Brain wave acquisition portion, it include that electrode for encephalograms and signal conditioning circuit, the electrode for encephalograms are used for gathering EEG signals and passing
Deliver to signal conditioning circuit to be pre-processed;
Storage part, its are used for receiving and storing the pretreated EEG signals of the signal conditioning circuit;
Microprocessor, its are configured to:From the EEG signals that storage part obtains default set time length, and the brain electricity to obtaining
Signal carries out two-stage secondary classification;Wherein, first order secondary classification is output as normal EEG signals and abnormal EEG signals, and second
Level secondary classification is output as epileptic attack early stage EEG signals and epileptic attack phase EEG signals;
Output section, its are connected with microprocessor, for carrying out real-time early warning to epileptic attack early stage and epileptic attack phase.
2. a kind of device of dynamic early-warning epileptic attack as claimed in claim 1, it is characterised in that the microprocessor, also
It is configured to:
From the EEG signals x that storage part obtains default set time length t;
Using preset length t0Time window come EEG signals x is carried out respectively standard deviation normalization and amplitude normalization, wherein,
t0T is less than, and t is t0K times, k is positive integer;
Respectively according to standard deviation normalized signal and amplitude normalized signal, the degree of irregularity of signal in k-th time window is calculated
FktWith complexity Dkt, and then obtain the average degree of irregularity of EEG signals xAnd average complexity
Directly carry out standard deviation normalization and amplitude normalization to EEG signals x respectively, further directly calculate EEG signals x
Degree of irregularity FtWith complexity Dt;
Average degree of irregularity by EEG signals xAverage complexityDegree of irregularity FtWith complexity DtCome as characteristic value
Construction feature set, carries out two-stage secondary classification to EEG signals x;Wherein, the input feature vector of first order quadratic classifier is the t seconds
The degree of irregularity F of EEG signals xtAnd average complexityCombination, be output as normal EEG signals and abnormal EEG signals, the
Two grades of quadratic classifiers act on the abnormal EEG signals detected by first order grader, and input feature vector is t second EEG signals x's
Average degree of irregularityWith complexity DtCombination, be output as epileptic attack early stage EEG signals and epileptic attack phase brain telecommunications
Number.
3. a kind of device of dynamic early-warning epileptic attack as claimed in claim 1, it is characterised in that the dynamic early-warning epilepsy is sent out
The device of work also includes input unit, and which is used for being input into user data to produce and recorded electronic case history.
4. a kind of device of dynamic early-warning epileptic attack as claimed in claim 1, it is characterised in that the microprocessor passes through
Wireless communication module is connected to data server.
5. a kind of device of dynamic early-warning epileptic attack as claimed in claim 4, it is characterised in that the data server with
Cloud central server is connected.
6. a kind of device of dynamic early-warning epileptic attack as claimed in claim 1, it is characterised in that the output section includes showing
Show that module, audio-frequency module and micro motor, the display module, audio-frequency module are connected with microprocessor with micro motor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611083211.1A CN106491126B (en) | 2016-11-30 | 2016-11-30 | A kind of device of dynamic early-warning epileptic attack |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611083211.1A CN106491126B (en) | 2016-11-30 | 2016-11-30 | A kind of device of dynamic early-warning epileptic attack |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106491126A true CN106491126A (en) | 2017-03-15 |
CN106491126B CN106491126B (en) | 2019-03-08 |
Family
ID=58327346
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611083211.1A Active CN106491126B (en) | 2016-11-30 | 2016-11-30 | A kind of device of dynamic early-warning epileptic attack |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106491126B (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106821376A (en) * | 2017-03-28 | 2017-06-13 | 南京医科大学 | A kind of epileptic attack early warning system and method based on deep learning algorithm |
CN107616793A (en) * | 2017-09-18 | 2018-01-23 | 电子科技大学 | A kind of eeg monitoring device and method with epileptic seizure prediction function |
CN108784690A (en) * | 2018-06-19 | 2018-11-13 | 苏州修普诺斯医疗器械有限公司 | Mobile EEG signals Transmission system and method for transmitting signals |
CN108784689A (en) * | 2018-06-19 | 2018-11-13 | 苏州修普诺斯医疗器械有限公司 | The mobile EEG signals Transmission system and method for power saving |
CN109247935A (en) * | 2018-10-31 | 2019-01-22 | 山东大学 | A kind of During Night Time parahypnosis condition monitoring system and method |
CN110051349A (en) * | 2019-04-04 | 2019-07-26 | 上海市金山区青少年活动中心 | Epilepsy detection and alarm system and its working method |
CN110269610A (en) * | 2019-07-16 | 2019-09-24 | 河北医科大学第二医院 | A kind of prior-warning device of brain electrical anomaly signal |
CN114099174A (en) * | 2020-06-09 | 2022-03-01 | 首都医科大学宣武医院 | Monitoring system and method for epileptic infant |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080216183A1 (en) * | 2007-02-08 | 2008-09-04 | Scantlebury Morris H | Model of infantile spasm syndrome |
US20110270117A1 (en) * | 2010-05-03 | 2011-11-03 | GLKK, Inc. | Remote continuous seizure monitor and alarm |
CN102429657A (en) * | 2011-09-22 | 2012-05-02 | 上海师范大学 | Epilepsia electroencephalogram signal classified detection device and method |
CN103228208A (en) * | 2010-08-27 | 2013-07-31 | 纽若普若有限公司 | A monitoring or predicting system and method of monitoring or predicting |
CN104055513A (en) * | 2014-06-18 | 2014-09-24 | 电子科技大学 | Device and method for positioning epileptic seizure source |
CN105520731A (en) * | 2016-01-19 | 2016-04-27 | 西京学院 | HBC (human body communication) based wearable type medical equipment capable of preventing epileptic seizure |
CN105708451A (en) * | 2016-01-29 | 2016-06-29 | 中山衡思健康科技有限公司 | Electroencephalogram signal quality real-time judgment method |
CN105956623A (en) * | 2016-05-04 | 2016-09-21 | 太原理工大学 | Epilepsy electroencephalogram signal classification method based on fuzzy entropy |
-
2016
- 2016-11-30 CN CN201611083211.1A patent/CN106491126B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080216183A1 (en) * | 2007-02-08 | 2008-09-04 | Scantlebury Morris H | Model of infantile spasm syndrome |
US20110270117A1 (en) * | 2010-05-03 | 2011-11-03 | GLKK, Inc. | Remote continuous seizure monitor and alarm |
CN103228208A (en) * | 2010-08-27 | 2013-07-31 | 纽若普若有限公司 | A monitoring or predicting system and method of monitoring or predicting |
CN102429657A (en) * | 2011-09-22 | 2012-05-02 | 上海师范大学 | Epilepsia electroencephalogram signal classified detection device and method |
CN104055513A (en) * | 2014-06-18 | 2014-09-24 | 电子科技大学 | Device and method for positioning epileptic seizure source |
CN105520731A (en) * | 2016-01-19 | 2016-04-27 | 西京学院 | HBC (human body communication) based wearable type medical equipment capable of preventing epileptic seizure |
CN105708451A (en) * | 2016-01-29 | 2016-06-29 | 中山衡思健康科技有限公司 | Electroencephalogram signal quality real-time judgment method |
CN105956623A (en) * | 2016-05-04 | 2016-09-21 | 太原理工大学 | Epilepsy electroencephalogram signal classification method based on fuzzy entropy |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106821376A (en) * | 2017-03-28 | 2017-06-13 | 南京医科大学 | A kind of epileptic attack early warning system and method based on deep learning algorithm |
CN106821376B (en) * | 2017-03-28 | 2019-12-06 | 南京医科大学 | epileptic seizure early warning system based on deep learning algorithm |
CN107616793A (en) * | 2017-09-18 | 2018-01-23 | 电子科技大学 | A kind of eeg monitoring device and method with epileptic seizure prediction function |
CN108784690A (en) * | 2018-06-19 | 2018-11-13 | 苏州修普诺斯医疗器械有限公司 | Mobile EEG signals Transmission system and method for transmitting signals |
CN108784689A (en) * | 2018-06-19 | 2018-11-13 | 苏州修普诺斯医疗器械有限公司 | The mobile EEG signals Transmission system and method for power saving |
CN109247935A (en) * | 2018-10-31 | 2019-01-22 | 山东大学 | A kind of During Night Time parahypnosis condition monitoring system and method |
CN109247935B (en) * | 2018-10-31 | 2020-10-16 | 山东大学 | Human body abnormal sleep state monitoring system at night |
CN110051349A (en) * | 2019-04-04 | 2019-07-26 | 上海市金山区青少年活动中心 | Epilepsy detection and alarm system and its working method |
CN110269610A (en) * | 2019-07-16 | 2019-09-24 | 河北医科大学第二医院 | A kind of prior-warning device of brain electrical anomaly signal |
CN114099174A (en) * | 2020-06-09 | 2022-03-01 | 首都医科大学宣武医院 | Monitoring system and method for epileptic infant |
Also Published As
Publication number | Publication date |
---|---|
CN106491126B (en) | 2019-03-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106491126A (en) | A kind of device of dynamic early-warning epileptic attack | |
US20170188895A1 (en) | System and method of body motion analytics recognition and alerting | |
Ru et al. | A detailed research on human health monitoring system based on internet of things | |
CN101272733B (en) | Monitoring method and apparatus | |
Lee et al. | Smartwatch-based driver vigilance indicator with kernel-fuzzy-C-means-wavelet method | |
US20150164377A1 (en) | System and method of body motion analytics recognition and alerting | |
EP3558113A1 (en) | Determining wellness using activity data | |
Hadjem et al. | An ECG monitoring system for prediction of cardiac anomalies using WBAN | |
JP5395954B2 (en) | EEG monitoring system and method for monitoring EEG | |
CN104490388A (en) | Extensible human health remote recording, monitoring and diagnosis system | |
CN101340846A (en) | Device for detecting and warning of a medical condition | |
CN105193408A (en) | Attached dynamic electrocardiogram recorder and system thereof | |
CN110477864A (en) | A kind of management service system and method based on cardiac function dynamic monitoring and analysis | |
CN204336910U (en) | A kind of extendible health remote logging, monitoring and diagnostic system | |
Forkan et al. | Context-aware cardiac monitoring for early detection of heart diseases | |
CN209232420U (en) | A kind of intelligence delirium assessment device | |
CN104270705A (en) | Intelligent hearing aid based on cloud technology | |
Kora et al. | Iot based wearable monitoring structure for detecting abnormal heart | |
US20120144133A1 (en) | Method and system for storage and evaluation of data, especially vital data | |
CN204744140U (en) | Fall down intelligent wrist strap of location warning | |
Rajan et al. | Feasibility analysis of portable electroencephalography based abnormal fatigue detection and tele-surveillance system | |
CN103932699A (en) | Electrocardiograph monitor | |
Arunsankar et al. | IoT Controlled Device to Manage the EMG Signals of the Patient and Alert in Real Time | |
Park et al. | Cascade classification with adaptive feature extraction for arrhythmia detection | |
Callegari et al. | EpiCare—A home care platform based on mobile cloud computing to assist epilepsy diagnosis |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | 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 |