The aim of the study is to increase the effectiveness of automated face recognition to authenticate identity, considering features of change of the face parameters over time. The improvement of the recognition accuracy, as well as consideration of the features of temporal changes in a human face can be based on the methodology of artificial neural networks. Hybrid neural networks, combining the advantages of classical neural networks and fuzzy logic systems, allow using the network learnability along with the explanation of the findings. The structural scheme of intelligent system for identification based on artificial neural networks is proposed in this work. It realizes the principles of digital information processing and identity recognition taking into account the forecast of key characteristics' changes over time (e.g., due to aging). The structural scheme has a three-tier architecture and implements preliminary processing, recognition and identification of images obtained as a result of monitoring. On the basis of expert knowledge, the fuzzy base of products is designed. It allows assessing possible changes in key characteristics, used to authenticate identity based on the image. To take this possibility into consideration, a neuro-fuzzy network of ANFIS type was used, which implements the algorithm of Tagaki-Sugeno. The conducted experiments showed high efficiency of the developed neural network and a low value of learning errors, which allows recommending this approach for practical implementation. Application of the developed system of fuzzy production rules that allow predicting changes in individuals over time, will improve the recognition accuracy, reduce the number of authentication failures and improve the efficiency of information processing and decision-making in applications, such as authentication of bank customers, users of mobile applications, or in video monitoring systems of sensitive sites.
Б а с р е д а к т о р ы х. ғ. д., проф., ҚР ҰҒА академигі М. Ж. Жұрынов Р е д а к ц и я а л қ а с ы:Ресей) Абишев М.Е. проф., корр.-мүшесі (Қазақстан) Аврамов К.В. проф. (Украина) Аппель Юрген проф. (Германия) Баймуқанов Д.А. проф., корр.-мүшесі (Қазақстан) Байтулин И.О. проф., академик (Қазақстан) Банас Иозеф проф. (Польша) Берсимбаев Р.И. проф., академик (Қазақстан) Велесько С. проф. (Германия) Велихов Е.П. проф., РҒА академигі (Ресей) Гашимзаде Ф. проф., академик (Әзірбайжан) Гончарук В.В. проф., академик (Украина) Давлетов А.Е. проф., корр.-мүшесі (Қазақстан) Джрбашян Р.Т. проф., академик (Армения) Қалимолдаев М.Н. проф., академик (Қазақстан), бас ред. орынбасары Лаверов Н.П. проф., академик РАН (Россия) Лупашку Ф. проф., корр.-мүшесі (Молдова) Мохд Хасан Селамат проф. (Малайзия) Мырхалықов Ж.У. проф., академик (Қазақстан) Новак Изабелла проф. (Польша) Огарь Н.П. проф., корр.-мүшесі (Қазақстан) Полещук О.Х. проф. (Ресей) Поняев А.И. проф. (Ресей) Сагиян А.С. проф., академик (Армения) Сатубалдин С.С. проф., академик (Қазақстан) Таткеева Г.Г. проф., корр.-мүшесі (Қазақстан) Умбетаев И. проф., академик (Қазақстан) Хрипунов Г.С. проф. (Украина) Юлдашбаев Ю.А. проф., РҒА корр-мүшесі (Ресей) Якубова М.М. проф., академик (Тәжікстан) «Қазақстан Республикасы Ұлттық ғылым академиясының Хабаршысы».
Nowadays, one of the relevant areas that is developing in the field of information security is associated with the use of Honeypot (virtual lures, online traps), and the selection of criteria for determination of the most effective Honeypot and their further classification is an urgent task. There are presented the main products in which virtual lures technology is implemented. Often they are used to study the behavior, approaches and methods that an unauthorized party uses for unauthorized access to information system resources. Online traps can imitate any resource, but more often they look like real production servers and workstations. There are known a number of fairly effective developments that are used to solve the problems of identifying attacks on the information systems resources, which are based on the fuzzy sets apparatus. They showed the effectiveness of using the appropriate mathematical apparatus, the use of which, for example, to formalize the approach for the formation of a set of criteria, will improve the process of determining the most effective Honeypot. For this purpose, there have been proposed criteria that characterize online traps, with the use of which there has been developed a method of linguistic variable standards formation for choosing the most effective Honeypot. The method is based on the formation of a set of Honeypot, subsets of characteristics and identifier values of linguistic estimates of Honeypot characteristics, a base and derivative frequency matrix, as well as on the construction of fuzzy terms and standard fuzzy numbers with their visualization. This will allow further classification and selection of them osteffective virtual lures.
The article herein presents the method and algorithms for forming the feature space for the base of intellectualized system knowledge for the support system in the cyber threats and anomalies tasks. The system being elaborated might be used both autonomously by cyber threat services analysts and jointly with information protection complex systems. It is shown, that advised algorithms allow supplementing dynamically the knowledge base upon appearing the new threats, which permits to cut the time of their recognition and analysis, in particular, for cases of hard-to-explain features and reduce the false responses in threat recognizing systems, anomalies and attacks at informatization objects. It is stated herein, that collectively with the outcomes of previous authors investigations, the offered algorithms of forming the feature space for identifying cyber threats within decisions making support system are more effective. It is reached at the expense of the fact, that, comparing to existing decisions, the described decisions in the article, allow separate considering the task of threat recognition in the frame of the known classes, and if necessary supplementing feature space for the new threat types. It is demonstrated, that new threats features often initially are not identified within the frame of existing base of threat classes knowledge in the decision support system. As well the methods and advised algorithms allow fulfilling the time-efficient cyber threats classification for a definite informatization object.
The article is devoted to the problem of voice signals recognition means introduction in the system of distance learning. The results of the conducted research determine the prospects of neural network means of phoneme recognition. It is also shown that the main difficulties of creation of the neural network model, intended for recognition of phonemes in the system of distance learning, are connected with the uncertain duration of a phoneme-like element. Due to this reason for recognition of phonemes, it is impossible to use the most effective type of neural network model on the basis of a multilayered perceptron, at which the number of input parameters is a fixed value. To mitigate this shortcoming, the procedure, allowing to transform the non-stationary digitized voice signal to the fixed quantity of mel-cepstral coefficients, which are the basis for calculation of input parameters of the neural network model, is developed. In contrast to the known ones, the possibility of linear scaling of phoneme-like elements is available in the procedure. The number of computer experiments confirmed expediency of the fact that the use of the offered coding procedure of input parameters provides the acceptable accuracy of neural network recognition of phonemes under near-natural conditions of the distance learning system. Moreover, the prospects of further research in the field of development of neural network means of phoneme recognition of a voice signal in the system of distance learning is connected with an increase in admissible noise level. Besides, the adaptation of the offered procedure to various natural languages, as well as to other applied tasks, for instance, a problem of biometric authentication in the banking sector, is also of great interest.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.