WO1997035267A1 - Verfahren zur klassifikation einer zeitreihe, die eine vorgebbare anzahl von abtastwerten aufweist, beispielsweise eines elektrischen signals, durch einen rechner - Google Patents
Verfahren zur klassifikation einer zeitreihe, die eine vorgebbare anzahl von abtastwerten aufweist, beispielsweise eines elektrischen signals, durch einen rechner Download PDFInfo
- Publication number
- WO1997035267A1 WO1997035267A1 PCT/DE1997/000416 DE9700416W WO9735267A1 WO 1997035267 A1 WO1997035267 A1 WO 1997035267A1 DE 9700416 W DE9700416 W DE 9700416W WO 9735267 A1 WO9735267 A1 WO 9735267A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- time series
- samples
- determined
- conditional
- computer
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000005070 sampling Methods 0.000 title claims abstract description 15
- 238000005192 partition Methods 0.000 claims description 8
- 210000004556 brain Anatomy 0.000 claims description 3
- 230000002596 correlated effect Effects 0.000 abstract description 2
- 230000008569 process Effects 0.000 abstract description 2
- 206010049418 Sudden Cardiac Death Diseases 0.000 description 9
- 238000010586 diagram Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 2
- 230000000739 chaotic effect Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 229910052760 oxygen Inorganic materials 0.000 description 2
- 239000001301 oxygen Substances 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 206010049993 Cardiac death Diseases 0.000 description 1
- 206010011906 Death Diseases 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 150000001768 cations Chemical class 0.000 description 1
- 230000000875 corresponding effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000004836 empirical method Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- 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
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
- A61B5/346—Analysis of electrocardiograms
- A61B5/349—Detecting specific parameters of the electrocardiograph cycle
-
- 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
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration or pH-value ; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid or cerebral tissue
- A61B5/1455—Measuring characteristics of blood in vivo, e.g. gas concentration or pH-value ; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid or cerebral tissue using optical sensors, e.g. spectral photometrical oximeters
- A61B5/14551—Measuring characteristics of blood in vivo, e.g. gas concentration or pH-value ; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid or cerebral tissue using optical sensors, e.g. spectral photometrical oximeters for measuring blood gases
- A61B5/14553—Measuring characteristics of blood in vivo, e.g. gas concentration or pH-value ; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid or cerebral tissue using optical sensors, e.g. spectral photometrical oximeters for measuring blood gases specially adapted for cerebral tissue
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y10—TECHNICAL SUBJECTS COVERED BY FORMER USPC
- Y10S—TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y10S128/00—Surgery
- Y10S128/901—Suppression of noise in electric signal
Definitions
- the invention relates to technical fields in which it is of interest to infer the future behavior of the time series from measured time series. This prediction of the future “behavior” of the time series takes place on the assumption that the time series has non-linear correlations between the samples of the time series.
- a time series of an electrocardiogram which is not correlated, describes a heart that is not at risk with regard to sudden cardiac death.
- a vulnerable heart with regard to sudden cardiac death is described by a time series of the electrocardiogram, which has non-linear correlations between the samples of the time series [1].
- [1] from the graphical phase-space representation (Fourier transformation) of two successive heartbeats, time series of an electronic to determine cardiogram, which describe hearts that are at risk of sudden cardiac death.
- the method described in [1] has all the disadvantages inherent in empirical methods.
- the susceptibility of graphic interpretations by a human being, the problem of setting a barrier from which a time series is classified as at risk, and inaccuracies in the representation of the Fourier transforms on the screen are to be regarded as disadvantages of the known method.
- a method is known from [4] with which the temporal profile of the local oxygen voltage of the brain (tip02) can be determined.
- the invention is based on the problem of creating a method for quickly and reliably classifying a time series which has a predeterminable number of samples using a computer.
- entropies are determined for a predeterminable number of samples.
- An information flow for a predeterminable number of future sampling points is determined from the conditional entropies, on the basis of which the time series is classified.
- the method according to claim 5 makes it possible to accelerate the classification, since a binary classification only has to be carried out using the shape of the graph of the information flow. It is very easy to differentiate the time series into a first time series type and a second time series type, since the first time series type is classified when the graph of the information flow has an approximately curved shape.
- EKG electrocardiogram signal
- FIGS. 1 to 5 represent an exemplary embodiment.
- Fig. 1 is a flowchart in which the inventive method is shown
- Fig. 2 is a flow diagram in which the development of the inventive method according to claim
- Fig. 3 is a block diagram in which various possible
- FIG. 4 shows a block diagram which shows a computer which is necessarily used to carry out the method according to the invention
- Fig. 5 is a diagram in the qualitative a graph of a determined information flow for future
- FIG. 1 shows that in a first step of the method according to the invention the time series, which has a predeterminable number of sample values, is measured 101.
- the measurement is carried out by a measuring device MG, which measures both analog or digital signals and a computer R leads (see FIG. 4).
- n-1 ... l) for the individual samples of the time series are determined 102 by the computer R.
- n-1 ... l) are known
- n is a length of a sequence of sampled values taken into account
- m is a number of values that the samples can take
- p (j, i) association probabilities are designated
- the number of values m that the sampled values can assume can be specified.
- the values can, but do not have to be, distributed over constant intervals.
- a set of predeterminable values of the number m is referred to below as a partition ⁇ .
- the partition ß denotes a set of disjoint intervals B- [d. H.
- i and j denote a first running index and a second running index. This results in a block entropy
- p (n) denotes the probability of the occurrence of a sample which has the sample i for the partition ⁇ with a sequence of length n.
- p (n, p) denotes the association probability of the occurrence of a sample value i for the sequence of length n and the occurrence of sample value j at a point in time which is the predeterminable number of future sample points in time within the partition ⁇ .
- ⁇ diameter (ß) -> 0, the diameter (ß) being the largest cell length.
- the information flow T " ß is generally a measure of the static
- Method for a predeterminable number of future sampling times p is formed as a function of a predeterminable number of past sampling values n which the time series has.
- At least one information flow TP is determined from the conditional entropies.
- Time series the samples of which have non-linear correlations, a monotonically falling, parabolic-like curved function ZT1. This corresponds to a first time series type ZT1.
- a qualitatively steep, approximately linearly decreasing graph of the information flow T ⁇ is for future ones Given samples. This can be seen from the consideration that, if there is no correlation, future samples cannot be predicted in any way, and therefore no information about future samples is available. This is not the case for a time series whose samples have non-linear correlations.
- a classification is carried out on the basis of the information flow fß.
- This classification may cation X P, depending on the application, be of different types.
- a very simple classification which, however, proves to be an advantageous and sufficient further development of the method for some types of time series, lies in a “binary” classification.
- X P for future samples 201 checks in a test step 202 whether the graph is approximately curved or whether it falls steeply linear (see FIG. 2).
- the time series is classified as the first time series type ZT1.
- a time series given by a measured cardiogram signal (EKG) this corresponds to a classification of the electrocardiogram signal (EKG) into an electrocardiogram signal (EKG) of an endangered heart with regard to the sudden cardiac death.
- the time series is classified 203 into the second time series type ZT2.
- this corresponds to the classification of the EKG signal as an ECG signal from an undamaged heart regarding sudden cardiac death.
- 3 shows various possibilities for the types of a time series for which the method can be used 301.
- this list has no restrictive character whatsoever.
- the method can be used for any type of time series in which it is necessary to determine non-linear correlations between the samples of the time series and to classify the time series on the basis of these non-linear correlations, which are reflected in the information flow.
- the time series can be, for example:
- EKG electrocardiogram signal
- EEG electroencephalogram signal
- FIG. 4 shows the computer R with which the method according to the invention is necessarily carried out.
- the computer R processes the time series recorded by the measuring device MG and fed to the computer R.
- the measuring device MG can be, for example, an electrocardiograph (EKG), an electroencepahlograph (EEG) or also a device which works according to the method shown in [2].
- EKG electrocardiograph
- EEG electroencepahlograph
- the classification result, which is ascertained by the computer R in the manner described above, is further processed in a means for further processing WV, for example presented to a user.
- This means WV can be, for example, a printer, a screen or a loudspeaker, via which an acoustic or visual signal is passed on to a user.
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Psychiatry (AREA)
- Artificial Intelligence (AREA)
- Cardiology (AREA)
- Psychology (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Signal Processing (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
Description
Claims
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP97914162A EP0888590A1 (de) | 1996-03-19 | 1997-03-05 | Verfahren zur klassifikation einer zeitreihe, die eine vorgebbare anzahl von abtastwerten aufweist, beispielsweise eines elektrischen signals, durch einen rechner |
JP9533019A JP2000506416A (ja) | 1996-03-19 | 1997-03-05 | 計算機による例えば電気信号の所定数のサンプリング値を有するタイムシーケンスの分類方法 |
US09/142,265 US6266624B1 (en) | 1996-03-19 | 1997-03-05 | Method conducted in a computer for classification of a time series having a prescribable number of samples |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE19610847A DE19610847C1 (de) | 1996-03-19 | 1996-03-19 | Verfahren zur Klassifikation einer meßbaren Zeitreihe, die eine vorgebbare Anzahl von Abtastwerten aufweist, beispielsweise eines elektrischen Signals, durch einen Rechner und Verwendung des Verfahrens |
DE19610847.0 | 1996-03-19 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO1997035267A1 true WO1997035267A1 (de) | 1997-09-25 |
Family
ID=7788790
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/DE1997/000416 WO1997035267A1 (de) | 1996-03-19 | 1997-03-05 | Verfahren zur klassifikation einer zeitreihe, die eine vorgebbare anzahl von abtastwerten aufweist, beispielsweise eines elektrischen signals, durch einen rechner |
Country Status (5)
Country | Link |
---|---|
US (1) | US6266624B1 (de) |
EP (1) | EP0888590A1 (de) |
JP (1) | JP2000506416A (de) |
DE (1) | DE19610847C1 (de) |
WO (1) | WO1997035267A1 (de) |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE59904500D1 (de) * | 1998-12-16 | 2003-04-10 | Siemens Ag | Verfahren und anordnung zur vorhersage von messdaten anhand vorgegebener messdaten |
WO2001065421A1 (de) * | 2000-02-28 | 2001-09-07 | Siemens Aktiengesellschaft | Verfahren und anordnung zur modellierung eines systems |
US7363000B2 (en) * | 2002-12-13 | 2008-04-22 | Agere Systems Inc. | Method, system, and computer program product for providing multi-tiered broadcasting services |
US8805482B2 (en) * | 2008-07-28 | 2014-08-12 | General Electric Conpany | System and method for signal quality indication and false alarm reduction in ECG monitoring systems |
CN102499676B (zh) * | 2011-11-03 | 2014-01-29 | 北京工业大学 | 基于有效时间序列和电极重组的脑电信号分类系统和方法 |
CN105395192A (zh) * | 2015-12-09 | 2016-03-16 | 恒爱高科(北京)科技有限公司 | 一种基于脑电的可穿戴情感识别方法和系统 |
KR102552833B1 (ko) * | 2018-05-28 | 2023-07-06 | 삼성에스디에스 주식회사 | 데이터 엔트로피 기반의 데이터 프로세싱 방법 |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4893632A (en) * | 1988-04-13 | 1990-01-16 | Siemens Aktiengesellschaft | Method and apparatus for comparing waveform shapes of time-varying signals |
TW342478B (en) * | 1996-01-08 | 1998-10-11 | Matsushita Electric Ind Co Ltd | Time series signal predicting apparatus |
DE19608733C1 (de) * | 1996-03-06 | 1997-05-22 | Siemens Ag | Verfahren zur Klassifikation einer meßbaren Zeitreihe, die eine vorgebbare Anzahl von Abtastwerten aufweist, insbesondere eines elektrischen Signals, durch einen Rechner und Verwendung des Verfahrens |
-
1996
- 1996-03-19 DE DE19610847A patent/DE19610847C1/de not_active Expired - Fee Related
-
1997
- 1997-03-05 EP EP97914162A patent/EP0888590A1/de not_active Withdrawn
- 1997-03-05 JP JP9533019A patent/JP2000506416A/ja active Pending
- 1997-03-05 WO PCT/DE1997/000416 patent/WO1997035267A1/de not_active Application Discontinuation
- 1997-03-05 US US09/142,265 patent/US6266624B1/en not_active Expired - Fee Related
Non-Patent Citations (1)
Title |
---|
GLASS L ET AL: "TIME SERIES ANALYSIS OF COMPLEX DYNAMICS IN PHYSIOLOGY AND MEDICINE", 1 January 1993, MEDICAL PROGRESS THROUGH TECHNOLOGY, VOL. 19, NR. 3, PAGE(S) 115 - 128, XP000423270 * |
Also Published As
Publication number | Publication date |
---|---|
EP0888590A1 (de) | 1999-01-07 |
JP2000506416A (ja) | 2000-05-30 |
US6266624B1 (en) | 2001-07-24 |
DE19610847C1 (de) | 1997-04-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP0856181B1 (de) | Verfahren und vorrichtung zur auswertung eines narkose- oder intensiv-eeg | |
EP0355506B1 (de) | Anordnung zum Messen lokaler bioelektrischer Ströme in biologischen Gewebekomplexen | |
DE202022103434U1 (de) | Ein auf einem Enzephalogramm (EEG) basierendes Gerät zur Erkennung von epileptischen Anfällen | |
DE69727236T2 (de) | Vorrichtung zum aufzeichnen von galvanischen hautreaktionen | |
EP0828225A1 (de) | Verfahren und Vorrichtung zum Auswerten von EEG-Daten | |
EP1034486B1 (de) | Verfahren zur bestimmung wenigstens einer diagnostischen information aus signalmustern medizinischer sensorsysteme | |
DE102018221695A1 (de) | Verfahren zur quantitativen Magnetresonanzbildgebung, Magnetresonanzeinrichtung, Computerprogramm und elektronisch lesbarer Datenträger | |
DE4039648A1 (de) | Messwertverarbeitungssystem fuer ein biologisches objekt | |
EP1519301B1 (de) | Vorrichtung zur klassifikation physiologischer Ereignisse | |
DE19610847C1 (de) | Verfahren zur Klassifikation einer meßbaren Zeitreihe, die eine vorgebbare Anzahl von Abtastwerten aufweist, beispielsweise eines elektrischen Signals, durch einen Rechner und Verwendung des Verfahrens | |
DE19608733C1 (de) | Verfahren zur Klassifikation einer meßbaren Zeitreihe, die eine vorgebbare Anzahl von Abtastwerten aufweist, insbesondere eines elektrischen Signals, durch einen Rechner und Verwendung des Verfahrens | |
EP1227425B1 (de) | Vorrichtung zum Auffinden der Auslöser anfallsartig auftretender Krankheiten | |
EP3407273A1 (de) | Verfahren und anordnung zur ermittlung eines anomalen zustands eines systems | |
EP0885423B1 (de) | Verfahren und vorrichtung zur klassifikation einer zeitreihe eines elektrischen signals durch einen rechner | |
DE60035505T2 (de) | Feststellung von neurologischen zuständen mittels reizevozierten potentialen | |
EP1034464B1 (de) | Anordnung zur vorhersage einer abnormalität eines systems und zur durchführung einer der abnormalität entgegenwirkenden aktion | |
WO1997050047A1 (de) | Verfahren zur klassifikation einer zeitreihe, die eine vorgebbare anzahl von abtastwerten aufweist, beispielsweise eines elektrischen signals, durch einen rechner | |
EP3961447A1 (de) | Verfahren zur detektion von anomalen betriebszuständen eines computersystems | |
EP1114398A2 (de) | Verfahren zum trainieren eines neuronalen netzes, verfahren zur klassifikation einer folge von eingangsgrössen unter verwendung eines neuronalen netzes, neuronales netz und anordnung zum trainieren eines neuronalen netzes | |
DE19701932C1 (de) | Verfahren zur Detektion von Synchronizität zwischen mehreren digitalen Meßreihen mit Hilfe eines Rechners | |
WO2004021245A2 (de) | Verfahren und anordnung sowie computerprogramm mit programmcode-mitteln und computerprogramm-produkt zur analyse von neuronalen aktivitäten in neuronalen arealen | |
EP1687756B9 (de) | Verfahren zur klassifikation von messwerten in der medizinischen und biochemischen analytik | |
EP3410329B1 (de) | Verfahren und system zur erkennung unregelmässiger eingaben für datenverarbeitungsanwendungen | |
DE69934687T2 (de) | Frequenzschätzung bei elektro-islet-graphie | |
WO1999023576A1 (de) | Verfahren und vorrichtung zur klassifikation einer ersten zeitreihe und mindestens einer zweiten zeitreihe |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AK | Designated states |
Kind code of ref document: A1 Designated state(s): JP US |
|
AL | Designated countries for regional patents |
Kind code of ref document: A1 Designated state(s): AT BE CH DE DK ES FI FR GB GR IE IT LU MC NL PT SE |
|
DFPE | Request for preliminary examination filed prior to expiration of 19th month from priority date (pct application filed before 20040101) | ||
121 | Ep: the epo has been informed by wipo that ep was designated in this application | ||
WWE | Wipo information: entry into national phase |
Ref document number: 1997914162 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 09142265 Country of ref document: US |
|
WWP | Wipo information: published in national office |
Ref document number: 1997914162 Country of ref document: EP |
|
WWW | Wipo information: withdrawn in national office |
Ref document number: 1997914162 Country of ref document: EP |