The production of metal pipes is an important component of metallurgy and the entire industry as a whole. Traditional surface quality control is carried out by human inspectors, which is unsatisfactory due to low prod...
详细信息
An analysis of modern computer network intrusion detection systems was carried out. The application of machine and deep learning methods for classification problems has been investigated. The UNSW-NB15 dataset, develo...
详细信息
ISBN:
(数字)9798350384499
ISBN:
(纸本)9798350384505
An analysis of modern computer network intrusion detection systems was carried out. The application of machine and deep learning methods for classification problems has been investigated. The UNSW-NB15 dataset, developed at the Australian Cyber Security Center's (ACCS) Cyber Range Laboratory, contains data on normal network operations and synthetic intrusions. Data pre-processing was performed, including class balancing using the SMOTEENN method and selection of informative features using the Recursive Feature Elimination method. The possibility of using the stacking meta-algorithm to detect intrusions into computer networks has been investigated. A new algorithm for generating packets of raw data is proposed, which generates two sets of training data: one for training basic models, the other for a meta-model. A study of the effectiveness of using Random Forest, ANN, K Nearest Neighbor methods and Support Vector Machine and Random Forest as a decision-making meta-model was conducted. The use of the stacking meta-algorithm with the proposed algorithm for forming packets of output data, as well as basic models and a meta-model, led to a significant improvement in the quality of the model. It was found that, on average, recall and f1 score increased by 55.6% and 37.4%, respectively, compared to raw data and other models.
Personalization is becoming very important direction in semantic web search for the users that needs to find appropriate information. In this paper, a classification of web personalization is proposed and semantic web...
详细信息
This article examines modern methods for analysis and dynamic process modeling with the context of the capabilities, characteristics and advantages of types of multiagent systems. A practical implementation of the “D...
详细信息
ISBN:
(纸本)9781665482134
This article examines modern methods for analysis and dynamic process modeling with the context of the capabilities, characteristics and advantages of types of multiagent systems. A practical implementation of the “Data to Action” model is proposed through the research simulation modeling system “Photovoltaic (PV) to Smart Energy Storage (SES) Grid”, developed by the authors using a Multi-Agent System for simulating the process of generating electricity produced by a PV park, its storage with the possibility of Time-Shifting and sale of energy.
Industrial Internet of NanoThings (IIoNT) traffic model proposed. The model is based on the developed algorithm for Dynamic Data Composition Control. The application of the algorithm made it possible to reduce the tot...
详细信息
IoTGazePass is a new password scheme that has been designed to tackle the weaknesses of existing types of passwords. It is intended to be suitable for IoT applications. An experiment was conducted to evaluate the stre...
详细信息
the paper proposes the use of 3D convolutional neural network for recognizing user emotions on videos in a recommender system. The data approach aims to use the recognized emotion as important implicit feedback and im...
the paper proposes the use of 3D convolutional neural network for recognizing user emotions on videos in a recommender system. The data approach aims to use the recognized emotion as important implicit feedback and improve the recommendation result. This is expected to significantly improve the performance of the recommender system.
Inspired by the visual system of the fruit fly, we had created a generic building block for neuromorphic hardware that is vital for third generation neural networks. This enables time delay to be parametrized in a che...
Inspired by the visual system of the fruit fly, we had created a generic building block for neuromorphic hardware that is vital for third generation neural networks. This enables time delay to be parametrized in a cheap and inexpensive way. The advantage of our proposal is the possibility of building and testing new networks using dynamicist approach in artificial intelligence.
Joint safety and security analysis of cyber-physical systems is a necessary step to correctly capture inter-dependencies between these properties. Attack-Fault Trees represent a combination of dynamic Fault Trees and ...
详细信息
In this study, we present an improved approach to optimizing the parameters of sensor sensing elements using quartz resonators with an interelectrode gap. We combine graphical and analytical methods to solve the multi...
详细信息
ISBN:
(数字)9798350378627
ISBN:
(纸本)9798350378634
In this study, we present an improved approach to optimizing the parameters of sensor sensing elements using quartz resonators with an interelectrode gap. We combine graphical and analytical methods to solve the multi-criteria optimization problem. The work focuses on the modes of operation of a quartz resonator equipped with an interelectrode gap in sensors with a frequency output, determining a set of optimal parameters and representing them as surfaces in a particular optimization parameter space. The presented results reveal specific areas on the surface of the objective function where optimization of design and technological parameters is possible, taking into account technological influences and features of the sensor design, including the initial value of the interelectrode gap. By using an improved mathematical model for the oscillations of a quartz resonator with an electrode gap, this study achieves results with an accuracy of ($8 . . .11$)% higher than previous studies, demonstrating the effectiveness of the proposed method in improving the design and functionality of piezoelectric sensors for advanced applications.
暂无评论