Search

Network intrusion detection is a relevant cybersecurity research field. The growing number of intrusions requires more sophisticated methods to protect computer networks. Various machine learning algorithms are used to detect network intrusions and anomalies, but their accuracy is limited. In this research, we address the problem of improving network-level intrusion detection by applying hybrid machine-learning algorithms. The paper proposes three new hybrid machine learning methods and investigates their accuracy using two publicly available datasets CSE-CIC-IDS2018 and NSW-NB-15. In order to increase the accuracy of the classification models, hyperparameter optimization was performed. The iteration method and the Chi-square χ² test were used to identify significant features of the data set. Analyzing the research results, it was found that the highest network anomaly recognition accuracy of 99.34% was achieved by applying a hybrid algorithm consisting of a decision tree, naive Bayesian, and multilayer perceptron algorithms. Achieved result is 3.13% higher than the best accuracy achieved by individual machine learning algorithms. In order to comprehensively evaluate the studied machine learning algorithms and their suitability for detecting intrusions in a computer network, the algorithms were ranked using the SCR, DR, FR ranking methods. [ABSTRACT FROM AUTHOR]

This paper analyzes an experimental heat pump used for heat recovery in a mechanical room ventilation system. The aim of the work is to examine the operation, control logic of the heat pump and evaluate the possibilities of its operation modes, cycle control by outdoor air temperature. A review of scientific literature and experimental tests of the heat pump were performed to achieve this goal. Tests were performed in three stages, after each stage, according to the results obtained the heat pump stand was improved and experimental modes were adjusted. During the experiment, the tendencies of the heat pump freon and air involved in the heat exchange parameters are analyzed with different combinations of expansion valve positions and compressor power. Knowing these experimental characteristics, the extent to which the combination of these two controls can be used to efficiently control of the heat pump according to the outside air temperature is assessed. Based on the results of the research the heat pump control algorithms (depending on the variable outdoor air temperature) are prepared. [ABSTRACT FROM AUTHOR]

The Internet of Things collects a variety of sensor data, independently offers problem-solving solutions and allows them to be avoided. In order for these systems to function continuously, it is necessary to apply intelligent information routing algorithms. In order to discover new algorithms for the routing of the Internet of Things, this article reviews bioinspired algorithms, their advantages and disadvantages. We introduce membrane computing, P system and its membrane structure. Paper analyses different types of communication on the Internet of Things and classification of routing algorithms for the Internet of Things communication. The practical application of membrane computing and the possibility of applying membrane computing on the Internet of Things is also reviewed. [ABSTRACT FROM AUTHOR]

The paper analyzes variations in the temperature of axle-box heating of railroad rolling stock considering two modes of the train - driving and parking position. Additionally, the article describes the influence of the axle load and season on the heat of the axle-box, forecasts intolerable residual resources and explains a possibility of detecting likely breakage at the very beginning of defects. The paper also deals with scientific literature related to axle-box heating and focuses on the conducted practical and theoretical experiments. The carried out research has established the rates of operating heating and critical heating. The application of numerical values for the algorithm of automatic control devices could help with detecting the breakdowns of the axle-box before they reach a critical state and assist in forecasting residual operating resources. [ABSTRACT FROM AUTHOR]

The paper describes the FPGA-based implementation of Lithuanian isolated word recognition algorithm. FPGA is selected for parallel process implementation using VHDL to ensure fast signal processing at low rate clock signal. Cepstrum analysis was applied to features extraction in voice. The dynamic time warping algorithm was used to compare the vectors of cepstrum coefficients. A library of 100 words features was created and stored in the internal FPGA BRAM memory. Experimental testing with speaker dependent records demonstrated the recognition rate of 94%. The recognition rate of 58% was achieved for speaker-independent records. Calculation of cepstrum coefficients lasted for 8.52 ms at 50 MHz clock, while 100 DTWs took 66.56 ms at 25 MHz clock. [ABSTRACT FROM AUTHOR]

The analysis focuses on control features of the hexapod walking robot with three degree-of-freedom legs. This paper describes different servo control methods and presents the developed algorithm for formation of servos control signals. The geometric inverse kinematics method was used to calculate the angles of each joint of a leg. The authors present the results of the experimental investigation on the hexapod robot leg movement trajectory. [ABSTRACT FROM AUTHOR]

The paper describes the FPGA-based implementation of the modified speeded-up robust features (SURF) algorithm. FPGA was selected for parallel process implementation using VHDL to ensure features extraction in real-time. A sliding 84x84 size window was used to store integral pixels and accelerate Hessian determinant calculation, orientation assignment and descriptor estimation. The local extreme searching was used to find point of interest in 8 scales. The simplified descriptor and orientation vector were calculated in parallel in 6 scales. The algorithm was investigated by tracking marker and drawing a plane or cube. All parts of algorithm worked on 25 MHz clock. The video stream was generated using 60 fps and 640x480 pixel camera. [ABSTRACT FROM AUTHOR]

In this paper head position locating systems were analyzed. There were reviewed scientific articles with different proposed methods. The chosen system is with the camera located on the user head. The main parameters of the head positioning systems were analyzed. The procedure laid down in what order parameters are found. The diagram of the system and detail block diagram of the algorithm were provided. Realization of the algorithm used: edge detection method (Sobel), the adjustment algorithm (Subpixel). System is realized in Matlab and C# environment. Determine the optimal parameters for the algorithm execution. Execution of the algorithm in Matlab environment is 1.2 s and C # environment -- 126 ms. During the examination of the longest executing algorithm segment, it was found that image filtering is carded out in 107 ms. It is noted that the uncertainty of the algorithm can be divided into static and measurement. The maximum static uncertainty while measuring head position parameters is 1.63 mm and orientation parameters -- 0.16°. The maximum measurement uncertainty while measuring head position parameters is 4 mm and orientation parameters -- 0.11°. [ABSTRACT FROM AUTHOR]

A new algorithm is utilized to examine the phase and attenuation constants of open dissipative epsilon- and (or) mu-gyrotropic rod waveguides. Our algorithm allows analyzing the waveguides made of materials having very high losses. The dispersion characteristics of p-Ge with a waveguide of two component hole charge carders are calculated when the ratio of heavy hole concentration in the material is equal to 5%, 50% and 95% of the total free carrier concentration. The effective mass of p-Ge heavy and light holes are 0.279me and 0.043me respectively. The dispersion characteristics of the main and eight higher modes are presented in the paper. The transformation of higher hybrid modes at some heavy hole concentrations can be noticed. Waveguide broad bandwidth can be considerably extended due to the fact that the losses of higher modes are larger in comparison to those of the main mode at certain heavy hole concentration. [ABSTRACT FROM AUTHOR]