An Approach to Risk Assessment and Threat Prediction for Complex Object Security Based on a Predicative Self-Configuring Neural System
We identified a set of methods for solving risk assessment problems by forecasting an incident of complex object security based on incident monitoring. The solving problem approach includes the following steps: building and training a classification model using the C4.5 algorithm, a decision tree cr...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-01-01
|
Series: | Symmetry |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-8994/14/1/102 |
_version_ | 1797490060691505152 |
---|---|
author | Nikolai Vladimirovich Korneev Julia Vasilievna Korneeva Stasis Petrasovich Yurkevichyus Gennady Ivanovich Bakhturin |
author_facet | Nikolai Vladimirovich Korneev Julia Vasilievna Korneeva Stasis Petrasovich Yurkevichyus Gennady Ivanovich Bakhturin |
author_sort | Nikolai Vladimirovich Korneev |
collection | DOAJ |
description | We identified a set of methods for solving risk assessment problems by forecasting an incident of complex object security based on incident monitoring. The solving problem approach includes the following steps: building and training a classification model using the C4.5 algorithm, a decision tree creation, risk assessment system development, and incident prediction. The last system is a predicative self-configuring neural system that includes a SCNN (self-configuring neural network), an RNN (recurrent neural network), and a predicative model that allows for determining the risk and forecasting the probability of an incident for an object. We proposed and developed: a mathematical model of a neural system; a SCNN architecture, where, for the first time, the fundamental problem of teaching a perceptron SCNN was solved without a teacher by adapting thresholds of activation functions of RNN neurons and a special learning algorithm; and a predicative model that includes a fuzzy output system with a membership function of current incidents of the considered object, which belongs to three fuzzy sets, namely “low risk”, “medium risk”, and “high risk”. For the first time, we gave the definition of the base class of an object’s prediction and SCNN, and the fundamental problem of teaching a perceptron SCNN was solved without a teacher. We propose an approach to neural system implementation for multiple incidents of complex object security. The results of experimental studies of the forecasting error at the level of 2.41% were obtained. |
first_indexed | 2024-03-10T00:26:29Z |
format | Article |
id | doaj.art-3b190931bd5b470f9f30171b63ec359a |
institution | Directory Open Access Journal |
issn | 2073-8994 |
language | English |
last_indexed | 2024-03-10T00:26:29Z |
publishDate | 2022-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Symmetry |
spelling | doaj.art-3b190931bd5b470f9f30171b63ec359a2023-11-23T15:33:27ZengMDPI AGSymmetry2073-89942022-01-0114110210.3390/sym14010102An Approach to Risk Assessment and Threat Prediction for Complex Object Security Based on a Predicative Self-Configuring Neural SystemNikolai Vladimirovich Korneev0Julia Vasilievna Korneeva1Stasis Petrasovich Yurkevichyus2Gennady Ivanovich Bakhturin3Department of Security Management of Complex Systems, National University of Oil and Gas Gubkin University, Leninsky Prospect, 65, 119991 Moscow, RussiaDepartment of Hospitality and Intercultural Communication, Volga Region State University of Service, Gagarin st., 4, 445017 Togliatti, RussiaDepartment of Research of Scientific, Technical and Innovative Activities in Information and Telecommunication Technologies, Scientific Research Institute–Federal Research Centre for Projects Evaluation and Consulting Services, Antonova-Ovseenko st., 13, Bldg. 1, 123995 Moscow, RussiaScientific Research Institute–Federal Research Centre for Projects Evaluation and Consulting Services, Antonova-Ovseenko st., 13, Bldg. 1, 123995 Moscow, RussiaWe identified a set of methods for solving risk assessment problems by forecasting an incident of complex object security based on incident monitoring. The solving problem approach includes the following steps: building and training a classification model using the C4.5 algorithm, a decision tree creation, risk assessment system development, and incident prediction. The last system is a predicative self-configuring neural system that includes a SCNN (self-configuring neural network), an RNN (recurrent neural network), and a predicative model that allows for determining the risk and forecasting the probability of an incident for an object. We proposed and developed: a mathematical model of a neural system; a SCNN architecture, where, for the first time, the fundamental problem of teaching a perceptron SCNN was solved without a teacher by adapting thresholds of activation functions of RNN neurons and a special learning algorithm; and a predicative model that includes a fuzzy output system with a membership function of current incidents of the considered object, which belongs to three fuzzy sets, namely “low risk”, “medium risk”, and “high risk”. For the first time, we gave the definition of the base class of an object’s prediction and SCNN, and the fundamental problem of teaching a perceptron SCNN was solved without a teacher. We propose an approach to neural system implementation for multiple incidents of complex object security. The results of experimental studies of the forecasting error at the level of 2.41% were obtained.https://www.mdpi.com/2073-8994/14/1/102riskthreatpredictive analyticscritical infrastructureneural networkdecision tree |
spellingShingle | Nikolai Vladimirovich Korneev Julia Vasilievna Korneeva Stasis Petrasovich Yurkevichyus Gennady Ivanovich Bakhturin An Approach to Risk Assessment and Threat Prediction for Complex Object Security Based on a Predicative Self-Configuring Neural System Symmetry risk threat predictive analytics critical infrastructure neural network decision tree |
title | An Approach to Risk Assessment and Threat Prediction for Complex Object Security Based on a Predicative Self-Configuring Neural System |
title_full | An Approach to Risk Assessment and Threat Prediction for Complex Object Security Based on a Predicative Self-Configuring Neural System |
title_fullStr | An Approach to Risk Assessment and Threat Prediction for Complex Object Security Based on a Predicative Self-Configuring Neural System |
title_full_unstemmed | An Approach to Risk Assessment and Threat Prediction for Complex Object Security Based on a Predicative Self-Configuring Neural System |
title_short | An Approach to Risk Assessment and Threat Prediction for Complex Object Security Based on a Predicative Self-Configuring Neural System |
title_sort | approach to risk assessment and threat prediction for complex object security based on a predicative self configuring neural system |
topic | risk threat predictive analytics critical infrastructure neural network decision tree |
url | https://www.mdpi.com/2073-8994/14/1/102 |
work_keys_str_mv | AT nikolaivladimirovichkorneev anapproachtoriskassessmentandthreatpredictionforcomplexobjectsecuritybasedonapredicativeselfconfiguringneuralsystem AT juliavasilievnakorneeva anapproachtoriskassessmentandthreatpredictionforcomplexobjectsecuritybasedonapredicativeselfconfiguringneuralsystem AT stasispetrasovichyurkevichyus anapproachtoriskassessmentandthreatpredictionforcomplexobjectsecuritybasedonapredicativeselfconfiguringneuralsystem AT gennadyivanovichbakhturin anapproachtoriskassessmentandthreatpredictionforcomplexobjectsecuritybasedonapredicativeselfconfiguringneuralsystem AT nikolaivladimirovichkorneev approachtoriskassessmentandthreatpredictionforcomplexobjectsecuritybasedonapredicativeselfconfiguringneuralsystem AT juliavasilievnakorneeva approachtoriskassessmentandthreatpredictionforcomplexobjectsecuritybasedonapredicativeselfconfiguringneuralsystem AT stasispetrasovichyurkevichyus approachtoriskassessmentandthreatpredictionforcomplexobjectsecuritybasedonapredicativeselfconfiguringneuralsystem AT gennadyivanovichbakhturin approachtoriskassessmentandthreatpredictionforcomplexobjectsecuritybasedonapredicativeselfconfiguringneuralsystem |