FIELD: computer technology.
SUBSTANCE: invention relates to an automated method and system for automatic polygraph checking using machine learning algorithms. The specified effect is achieved thanks to implementation of a computer-based method for automatic polygraph testing performed using a computer system containing at least two machine learning models, wherein the method performs the steps in which: records of polygraph tests are obtained containing at least the sensor signals with time scales that mark the beginning and the end of the question; additional data is received containing at least the age of the person being checked, gender, job information; the received signals are processed using the first machine learning (ML) model, using the second machine learning (ML) model process the output value of the 1st ML model, and additional data, and determine that the answer is false if the output value is higher or is equal to the threshold value or the answer is true if the output value is below the threshold value.
EFFECT: improved accuracy of polygraph testing.
8 cl, 11 dwg, 11 tbl
Title | Year | Author | Number |
---|---|---|---|
METHOD AND SYSTEM FOR AUTOMATIC POLYGRAPH TESTING USING THREE ENSEMBLES OF MACHINE LEARNING MODELS | 2023 |
|
RU2809595C1 |
METHOD AND SYSTEM FOR AUTOMATIC POLYGRAPH TESTING USING TWO ENSEMBLES OF MACHINE LEARNING MODELS | 2023 |
|
RU2809490C1 |
METHOD AND SYSTEM FOR AUTOMATIC POLYGRAPH TESTING | 2023 |
|
RU2809489C1 |
METHOD OF CALCULATING CLIENT CREDIT RATING | 2019 |
|
RU2723448C1 |
METHOD AND SYSTEM FOR ASSESSING THE PROBABILITY OF CRITICAL CYBER SECURITY DEFECTS AT ACCEPTANCE TESTS OF PRODUCT RELEASES | 2020 |
|
RU2745369C1 |
METHOD AND A SYSTEM FOR PREDICTION OF CYBER SECURITY RISKS DURING THE DEVELOPMENT OF SOFTWARE PRODUCTS | 2020 |
|
RU2745371C1 |
METHOD OF PSYCHO-PHYSIOLOGICAL POLYGRAPH TESTING | 2017 |
|
RU2669733C1 |
METHOD FOR OBTAINING LOW-DIMENSIONAL NUMERIC REPRESENTATIONS OF SEQUENCES OF EVENTS | 2020 |
|
RU2741742C1 |
METHOD AND SYSTEM FOR STATIC ANALYSIS OF EXECUTABLE FILES BASED ON PREDICTIVE MODELS | 2020 |
|
RU2759087C1 |
METHOD AND A SERVER FOR CONVERTING A CATEGORICAL FACTOR VALUE INTO ITS NUMERICAL REPRESENTATION | 2017 |
|
RU2693324C2 |
Authors
Dates
2023-12-22—Published
2023-01-23—Filed