WO2000036426A2 - Verfahren und anordnung zur vorhersage von messdaten anhand vorgegebener messdaten - Google Patents
Verfahren und anordnung zur vorhersage von messdaten anhand vorgegebener messdaten Download PDFInfo
- Publication number
- WO2000036426A2 WO2000036426A2 PCT/DE1999/003955 DE9903955W WO0036426A2 WO 2000036426 A2 WO2000036426 A2 WO 2000036426A2 DE 9903955 W DE9903955 W DE 9903955W WO 0036426 A2 WO0036426 A2 WO 0036426A2
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- measurement data
- run
- nhpp
- determined
- stochastic process
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/06—Asset management; Financial planning or analysis
Definitions
- the invention relates to a method and an arrangement for predicting measurement data on the basis of predetermined measurement data.
- a technical system often raises the question of a prognosis based on known (measurement) data, in particular with regard to the likelihood of errors or a cost estimate.
- a stochastic point process in particular a Poisson process, is known from [1].
- the object of the invention is to automatically enable a prediction (prognosis) of measurement data on the basis of predetermined measurement data.
- a method for predicting measurement data based on specified measurement data in which a stochastic process is adapted to the specified measurement data. From a given point in time, simulation runs are carried out up to an end point. The forecast measurement data are determined for each simulation run. For the end time, the prediction is made by Measurement data within a range of values which is determined by the forecast measurement data.
- a further development consists in determining a confidence interval for the prediction of measurement data by eliminating the a% smallest and the b% largest predicted measurement data.
- a% b%.
- a 95% confidence interval can thus be determined by ignoring the 2.5% smallest and the 2.5% largest forecast measurement data.
- Confidence interval lying accuracy can be predicted (predicted). This enables the recognition, for example, that a task associated with the measurement data can be fulfilled or not fulfilled, so that suitable measures can be linked to counteract a predicted non-fulfillment. This is particularly important in the case of a complex system, e.g. a software development process in which it can be shown within a later test phase to what extent a schedule can be kept until the software is completed. It is all the more important to have a clear one early on
- the stochastic process is a non-homogeneous Poisson process.
- the measurement data are numbers of errors.
- the completion results directly ie as long as the majority of the errors have not been removed from the software, they cannot be delivered to customers. This is particularly expressed in terms of effort (when testing and correcting errors) and costs (for delaying delivery).
- a method for predicting measurement data based on specified measurement data is also specified, in which a stochastic process is adapted to the specified measurement data.
- An interval is determined in which probability values obtained by the stochastic process increase by one
- Expected value to be sorted The measurement data are predicted by orienting themselves on the interval, in particular on the probability values within the interval.
- a further development consists in that the probability values of the size obtained on the basis of the stochastic process are sorted symmetrically around the expected value. This means in particular that the largest probability value identifies the middle of the interval, that is to say the expected value, whereas the next larger probability value is arranged on the right or left side of the expected value. The next higher probability value is arranged symmetrically on the other side of the expected value.
- an interval is obtained analytically (constructively), which in turn indicates by its width which probability values play a role in the prediction of the measurement data.
- the width of the interval is determined by those Probability values that are below a given limit are not taken into account.
- interval (confidence interval), which has a certain width due to the barrier. This width corresponds to the certainty of the prediction of measurement data.
- the non-homogeneous Poisson process determines a step size on a time axis t which indicates when the next one
- an arrangement for predicting measurement data based on specified measurement data in which a processor unit is provided which is set up in such a way that a) a stochastic process can be adapted to the specified measurement data; b) simulation runs can be carried out from a predetermined time to an end time; c) the predicted measurement data can be determined for each simulation run; d) for the end time, the prediction of measurement data can be predicted within a range of values which is determined by the forecast measurement data.
- an arrangement for predicting measurement data on the basis of predetermined measurement data is specified, in which a processor unit is provided which is set up in such a way that a) a stochastic process can be adapted to the specified measurement data; b) an interval can be determined by increasing the probability values obtained by the stochastic process by one
- Fig.l is a sketch showing an accumulated number of errors over a test period
- FIG. 3 shows a flow chart with steps of a method for
- FIG. 4 shows a further flow chart with steps of a method for predicting measurement data on the basis of predetermined measurement data
- NHPP non-homogeneous Poisson Processes
- equation (1) denotes a non-homogeneous Poisson process
- equation (5) can be used for times t> tg to determine an (as small as possible) interval
- g u , g 0 can be determined as follows:
- Step 1 sort the elementary probabilities
- Step 3 determine an index set
- the interval from equation (8) is also referred to as the forecast interval.
- the described confidence interval can be determined simulatively by the following steps:
- Step 1 start at the time tg of the last error message m 6 N independent simulation runs based on the selected process model;
- Step 2 end a simulation run as soon as the desired end time t e has been reached;
- Step 3 repeat step 2 until all simulation runs are finished
- Step 4 sort the numbers N j _ (t e ) in the i-th
- Step 3 create one evenly distributed on (0,1)
- Fig.l shows an example of a sketch that represents an accumulated number of errors over a predetermined test period. From a point in time tg there is a prediction interval for all points in time tg + x.
- step 301 a stochastic one
- a non-homogeneous Poisson process (as a representative for a stochastic counting process) adapted to predetermined measurement data.
- simulation runs are carried out, which run from the time tg to an end time t e to be predicted.
- predicted measurement data are determined in a step 303 and a prediction of measurement data is restricted to an area which is covered by the measurement data determined by the simulation runs (see step 304).
- a step 305 a step a step 305.
- FIG. 1 shows a further flow chart with steps of a method for predicting measurement data on the basis of predetermined measurement data.
- a stochastic process in particular a non-homogeneous Poisson process, is adapted to the predetermined measurement data in a step 401.
- probability values are determined, which are sorted according to size by an expected value (compare step 402).
- This sorting process determines an interval, here a confidence interval.
- the width of the confidence interval is determined by comparing the accumulated probabilities with a given threshold. As explained above, the confidence interval results in a distribution or blurring from a point in time tg in the future, which enables the measurement data to be estimated in the future (see step 403).
- the method is ended in a step 404.
- the processor unit PRZE comprises a processor CPU, a memory SPE and an input / output interface IO ⁇ , which is used in different ways via an interface IFC: an output is visible on a monitor MON and / or on a printer via a graphic interface PRT issued. An entry is made using a mouse MAS or a keyboard TAST.
- the processor unit PRZE also has a data bus BUS, which ensures the connection of a memory MEM, the processor CPU and the input / output interface IOS.
- additional components can be connected to the data bus BUS, e.g. additional memory, data storage (hard disk) or scanner.
- ⁇ a atof (argv [1])
- b atof (argv [2])
- c atof (argv [3])
- bt atof (argv [4])
- st atof (argv [5])
- ⁇ void ki_nhpp (mv_nhpp, par1_nhpp, par2_nhpp, par3_nhpp, start_time, stop_time, k_ level, Iower, upper) double mv_nhpp (double, double, double, double); double par1_nhpp, par2_nhpp, par3_nhpp, start jime, stopjime, k_ level; long * lower, * upper;
Abstract
Description
Claims
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP99964424A EP1141734B1 (de) | 1998-12-16 | 1999-12-10 | Verfahren und anordnung zur vorhersage von messdaten anhand vorgegebener messdaten |
DE59904500T DE59904500D1 (de) | 1998-12-16 | 1999-12-10 | Verfahren und anordnung zur vorhersage von messdaten anhand vorgegebener messdaten |
US09/868,239 US6839656B1 (en) | 1998-12-16 | 1999-12-10 | Method and arrangement for predicting measurement data by means of given measurement |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE19858093 | 1998-12-16 | ||
DE19858093.2 | 1998-12-16 |
Publications (2)
Publication Number | Publication Date |
---|---|
WO2000036426A2 true WO2000036426A2 (de) | 2000-06-22 |
WO2000036426A3 WO2000036426A3 (de) | 2000-10-19 |
Family
ID=7891314
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/DE1999/003955 WO2000036426A2 (de) | 1998-12-16 | 1999-12-10 | Verfahren und anordnung zur vorhersage von messdaten anhand vorgegebener messdaten |
Country Status (4)
Country | Link |
---|---|
US (1) | US6839656B1 (de) |
EP (1) | EP1141734B1 (de) |
DE (1) | DE59904500D1 (de) |
WO (1) | WO2000036426A2 (de) |
Families Citing this family (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7318187B2 (en) * | 2003-08-21 | 2008-01-08 | Qualcomm Incorporated | Outer coding methods for broadcast/multicast content and related apparatus |
US7483864B2 (en) * | 2003-11-17 | 2009-01-27 | Nec Corporation | Active learning method and system |
US7057182B2 (en) * | 2004-03-12 | 2006-06-06 | Hewlett-Packard Development Company, L.P. | Method and system for determining distortion in a circuit image |
AU2006269467B2 (en) | 2005-07-07 | 2011-07-28 | Sermo, Inc. | Method and apparatus for conducting an information brokering service |
US7680719B1 (en) | 2006-12-12 | 2010-03-16 | Goldman Sachs & Co. | Method, system and apparatus for wealth management |
US10083420B2 (en) | 2007-11-21 | 2018-09-25 | Sermo, Inc | Community moderated information |
DE102015209916A1 (de) * | 2015-05-29 | 2016-12-01 | Zf Friedrichshafen Ag | Regelung eines spanenden Bearbeitungsprozesses mittels P-Regler und belastungsabhängigem Regelfaktor |
CN107330726A (zh) * | 2017-06-29 | 2017-11-07 | 四川昆朋金软科技有限公司 | 基于自动拟合均值函数的泊松过程用户到店行为预测方法 |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE19610847C1 (de) * | 1996-03-19 | 1997-04-30 | Siemens Ag | Verfahren zur Klassifikation einer meßbaren Zeitreihe, die eine vorgebbare Anzahl von Abtastwerten aufweist, beispielsweise eines elektrischen Signals, durch einen Rechner und Verwendung des Verfahrens |
EP0786725A1 (de) * | 1995-10-30 | 1997-07-30 | Texas Instruments Incorporated | Verbesserte Produktfehlervorhersage |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4979118A (en) * | 1989-03-10 | 1990-12-18 | Gte Laboratories Incorporated | Predictive access-control and routing system for integrated services telecommunication networks |
US5891131A (en) * | 1993-02-01 | 1999-04-06 | Arizona Board Of Regents | Method and apparatus for automated simulation and design of corneal refractive procedures |
US5726907A (en) * | 1995-07-31 | 1998-03-10 | Southwest Research Institute | Biaxial non-contacting strain measurement using machine vision |
US6061662A (en) * | 1997-08-15 | 2000-05-09 | Options Technology Company, Inc. | Simulation method and system for the valuation of derivative financial instruments |
US6574587B2 (en) * | 1998-02-27 | 2003-06-03 | Mci Communications Corporation | System and method for extracting and forecasting computing resource data such as CPU consumption using autoregressive methodology |
-
1999
- 1999-12-10 EP EP99964424A patent/EP1141734B1/de not_active Expired - Lifetime
- 1999-12-10 DE DE59904500T patent/DE59904500D1/de not_active Expired - Lifetime
- 1999-12-10 WO PCT/DE1999/003955 patent/WO2000036426A2/de active IP Right Grant
- 1999-12-10 US US09/868,239 patent/US6839656B1/en not_active Expired - Fee Related
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0786725A1 (de) * | 1995-10-30 | 1997-07-30 | Texas Instruments Incorporated | Verbesserte Produktfehlervorhersage |
DE19610847C1 (de) * | 1996-03-19 | 1997-04-30 | Siemens Ag | Verfahren zur Klassifikation einer meßbaren Zeitreihe, die eine vorgebbare Anzahl von Abtastwerten aufweist, beispielsweise eines elektrischen Signals, durch einen Rechner und Verwendung des Verfahrens |
Non-Patent Citations (3)
Title |
---|
ANONYMOUS: "Stochastic Simulator of Software Development Process. February 1978." IBM TECHNICAL DISCLOSURE BULLETIN, Bd. 20, Nr. 9, 1. Februar 1978 (1978-02-01), Seiten 3691-3692, XP002142220 New York, US * |
EHRLICH W K ET AL: "APPLICATION OF SOFTWARE RELIABILITY MODELING TO PRODUCT QUALITY AND TEST PROCESS" PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING,US,LOS ALAMITOS, IEEE COMP. SOC. PRESS, Bd. CONF. 12, 1990, Seiten 108-116, XP000293771 ISBN: 0-8186-2026-9 * |
YAMADA S; OSAKI S: "Software Reliability Growth Modeling: Models and Applications" IEEE TRANSACTIONS ON SOFTWARE ENGINEERING, Bd. SE-11, Nr. 12, Dezember 1985 (1985-12), Seiten 1431-1437, XP000915448 * |
Also Published As
Publication number | Publication date |
---|---|
EP1141734A2 (de) | 2001-10-10 |
US6839656B1 (en) | 2005-01-04 |
WO2000036426A3 (de) | 2000-10-19 |
EP1141734B1 (de) | 2003-03-05 |
DE59904500D1 (de) | 2003-04-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Feather et al. | Role of information in the adoption of best management practices for water quality improvement | |
Perry | Risk management—an approach for project managers | |
DE102004023265A1 (de) | Bestimmen einer Bestellvorlaufzeit für eine Lieferkette unter Verwendung einer Wahrscheinlichkeitsverteilung für erwartete Bestellvorlaufzeit | |
DE10220397A1 (de) | Preisfestlegungsverfahren und Programmprodukt für einen nutzungsbasierten Dienst | |
DE19910098A1 (de) | Verfahren zur Beurteilung der Zuverlässigkeit tehnischer Systeme | |
EP1141734A2 (de) | Method and apparatus for the prediction of data from given data | |
DE10306598A1 (de) | Verfahren und Vorrichtung zum Bemessen der Verfügbarkeit komplexer elektronischer Systeme, einschließlich Computersystemen | |
EP1924913B1 (de) | Steuerung eines zugriffs auf dienste und/oder ressourcen eines datenverarbeitungssystems | |
Lee et al. | A further empirical investigation of the dividend adjustment process | |
DE102020206059A1 (de) | Computerimplementiertes Verfahren und System zum Trainieren eines Auswertungsalgorithmus, Computerprogramm und elektronisch lesbarer Datenträger | |
DE102006019896A1 (de) | Verfahren zur Fehlerbaumanalyse | |
EP1470459A1 (de) | Frühzeitige prognose der zuverlässigkeit einer technischen anordnung | |
DE10205762A1 (de) | Verfahren und Struktur zur Charakterisierung von Bayesianischen Belief-Netzwerken | |
Altaee et al. | The impact of saving and financial development on economic growth in Turkey | |
DE102006007791A1 (de) | Verfahren zur Prozessoptimierung | |
EP3494507B1 (de) | Verfahren zur prüfung der verfügbarkeit und integrität eines verteilt gespeicherten datenobjekts | |
DE102004022144B4 (de) | Verfahren zur rechnergestützten Bewertung von Kenngrößen eines technischen Systems | |
US7213002B2 (en) | Method and system for investing with a no-loss or low-loss assurance | |
EP1032868B1 (de) | Verfahren zur bestimmung der verfügbarkeit einer technischen anlage | |
EP2037448A1 (de) | Verfahren und Vorrichtung zur Klassifikation von Daten | |
WO1998034177A2 (de) | Verfahren zur kombination von ausgangssignalen mehrerer schätzer, insbesondere von mindestens einem neuronalen netz, zu einem gesamtschätzer ermittelten ergebnissignal | |
DE10036712A1 (de) | Verfahren zur Bewertung von mit charakteristischen Merkmalen behafteten Prozessen | |
US20040236657A1 (en) | Method and system for estimating a bucket transition distribution of one or more bonds and for evaluating credit risk of collaterized debt obligations | |
EP1099313B1 (de) | Soft-decision-decodierung eines terminierten faltungscode | |
DE19808372A1 (de) | Trainings- und Herstellverfahren für ein neuronales Netz |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AK | Designated states |
Kind code of ref document: A2 Designated state(s): US |
|
AL | Designated countries for regional patents |
Kind code of ref document: A2 Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LU MC NL PT SE |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application | ||
DFPE | Request for preliminary examination filed prior to expiration of 19th month from priority date (pct application filed before 20040101) | ||
AK | Designated states |
Kind code of ref document: A3 Designated state(s): US |
|
AL | Designated countries for regional patents |
Kind code of ref document: A3 Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LU MC NL PT SE |
|
WWE | Wipo information: entry into national phase |
Ref document number: 1999964424 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 09868239 Country of ref document: US |
|
WWP | Wipo information: published in national office |
Ref document number: 1999964424 Country of ref document: EP |
|
WWG | Wipo information: grant in national office |
Ref document number: 1999964424 Country of ref document: EP |