Переглянути
Нові надходження
Зараз показуємо 1 - 5 з 10
- ДокументMACHINE LEARNING IMPLEMENTATION FOR THE CLASSIFICATION OF ATTACKS ON WEB SYSTEMS. PART 1(2017) K. Smirnova, A. Smirnov, O. OlshevskaThe possibility of applying machine learning is considered for the classification of malicious requests to a Web application. This approach excludes the use of deterministic analysis systems (for example, expert systems), and based on the application of a cascade of neural networks or perceptrons on an approximate model to the real human brain. The main idea of the work is to enable to describe complex attack vectors consisting of feature sets, abstract terms for compiling a training sample, controlling the quality of recognition and classifying each of the layers (networks) participating in the work, with the ability to adjust not the entire network, But only a small part of it, in the training of which a mistake or inaccuracy crept in. The design of the developed network can be described as a cascaded, scalable neural network. The developed system of intrusion detection uses a three-layer neural network. Layers can be built independently of each other by cascades. In the first layer, for each class of attack recognition, there is a corresponding network and correctness is checked on this network. To learn this layer, we have chosen classes of things that can be classified uniquely as yes or no, that is, they are linearly separable. Thus, a layer is obtained not just of neurons, but of their microsets, which can best determine whether is there some data class in the query or not. The following layers are not trained to recognize the attacks themselves, they are trained that a set of attacks creates certain threats. This allows you to more accurately recognize the attacker's attempts to bypass the defense system, as well as classify the target of the attack, and not just its fact. Simple layering allows you to minimize the percentage of false positives.
- ДокументМОДЕЛЬ И МЕТОД СЖИГАНИЯ В ТЕПЛОЭНЕРГЕТИЧЕСКОЙ УСТАНОВКЕ УГЛЕВОДОРОДНОГО ГАЗА ПЕРЕМЕННОГО СОСТАВА(2017) А. В. Лысюк, А. В. Бондаренко, М. М. Максимов, А. И. БрунеткинОпределение условной формулы газообразного углеводородного топлива основано на модельных представлениях в соответствии с законами сохранения вещества, Дальтона, химического равновесия по парциальным давлениям. Определение динамических характеристик теплоэнергетического оборудования основано на уравнениях материального и теплового балансов, законов конвективного и лучистого теплообмена и свойств сжимаемой газообразной среды. Предложен метод обеспечения заданной тепловой нагрузки теплогенерирующей установки основаный на вычислении условной формулы газообразного углеводородного топлива и определении динамических характеристик теплогенерирующей установки.
- ДокументINCREASING THE LEVEL OF ENVIRONMENTAL EFFICIENCY OF INDUSTRY IS THE IMPORTANT RESULT OF ITS FUNCTIONING CONTROL(2017) S. A. Voinova, D. V. DetsThe modern complex state of the natural environment, caused by the harmful impact of the rapidly developing world industry on it, is considered. It is pointed out the acute urgency of the utmost reduction of the harmful effects of industry. It is noted that the world's power engineering is the most active source of harmful effects increasing with acceleration on living and non-living nature. The ecological essence of the concept of energy saving is revealed. It is shown that high-quality control of the operation of technical objects is a productive means of increasing the level of ecological efficiency of enterprise operations. A chain of interrelated circumstances that determines the strict dependence of the degree of environmental friendliness of a technical object on the quality of the control process of its operation is considered. The issues of ecological modernization of the enterprise as a means of increasing the ecological efficiency of its enterprise activities are considered. There are specified the components of the company's environmental efficiency in accordance with the state standard.
- ДокументАНАЛИЗ ПЕРЕДАТОЧНЫХ ФУНКЦИЙ ЦИФРОВЫХ ЧАСТОТНО-ЗАВИСИМЫХ КОМПОНЕНТ НИЗКОГО ПОРЯДКА(2017) А. В. УхинаПри проектировании компонент специализированных компьютерных систем возникают задачи, связанные с уменьшением объема вычислений при проектировании и ускорении процесса настройки. В работе проведен анализ и получены соотношения коэффициентов передаточных функций цифровых частотно-зависимых компонент первого, второго и четвертого порядков, что позволяет упростить процесс проектирования.
- ДокументDEVELOPMENT OF THE METHOD OF DETERMINING THE TARGET FUNCTION OF OPTIMIZATION OF POWER PLANT(2017) O. Maksymovа, M. Maksymov, V. Silina, A. OrischenkoIt has been proposed the application of an optimization criterion based on properties of target functions, taken from the elements of technical, economic and thermodynamic analyses. Marginal costs indicators of energy for different energy products have also been identified. Target function of the power plant optimization was proposed, that considers energy expenditure in the presented plant and in plants closing the energy sources generation and consumption balance.