The paper analyzes various approaches to identifying and recognizing license plates in intelligent transport networks. A deep learning model has been proposed for localizing and recognizing license plates in natural images, which can achieve satisfactory results in terms of recognition accuracy and speed compared to traditional ones. Evaluations of the effectiveness of the deep learning model are provided.
Keywords: VANET, intelligent transport networks, YOLO, city traffic management system, steganography, deep learning, deep learning, information security, convolutional neural network, CNN
The paper discusses a stegoalgorithm with localization of the embedding area in the YCbCr color space to protect images of a license plate, a vehicle from different angles, a traffic event, as well as issues of developing a software system that implements the stegoalgorithm. Image protection allows you to effectively implement the concept of multimodal interaction of socio-cyberphysical systems in an automotive self-organizing network. Evaluations of the effectiveness of the developed method are provided.
Keywords: VANET, intelligent transport networks, city traffic management system, steganography, information security, watermark
This paper demonstrates an approach to data visualization using manipulations with json data. Based on the Dimensional Charting library, you can render graphical information taking into account the processing of big data, since interactive data visualization in the web interface is widely used in analyzing user traffic on the Internet. Dimensional Charting is the link between the two built-in libraries. The Crossfilter library is responsible for sorting, filtering big data, and d3.js it is necessary for drawing graphic material on html pages. Thanks to new technologies, you can process big data without using third-party programming languages.
Keywords: data processing, data visualization, filtering, sorting dimensional charting, javascript, json, crossfilter, data-driven documents
The paper analyzes the use of Arnold transform for digital image scrambling. The proposed algorithm is implemented as part of the developed Luka library of medical image processing in the DICOM format, and provides additional cryptographic and steganographic protection of the patient’s personal data. The issues of evaluating the effectiveness of the developed software module using the structural similarity index are considered.
Keywords: Arnold transform, scrambling, peak signal to noise ratio, standard deviation, structural similarity index, DICOM, SSIM
Considered an important component of corporate networks - the default gateway. The main objective of the project is to minimize the time of convergence by ensuring high availability in order to ensure the continuity of the head office connection to remote offices. An analysis is made of the operation of one of the technological solutions, as well as estimates of the probability of failure-free operation for the default gateway with redundancy and without.
Keywords: HSRP, fault tolerance, high availability, failure, convergence, routing, protocol, load reserve, redundancy, business continuity
Failures in modern communication networks are a factor affecting the indicators of economic efficiency of the organization. The main objective of the project is to study the failure of network elements in order to improve the reliability and resiliency of communication systems by making changes to its structure. The selected recovery strategy for a failed item can significantly affect reliability performance. Results are important to ensure the required level of fault tolerance with limited operating costs.
Keywords: fault tolerance, high availability, failure, reliability, recovery, simulation
The paper analyzes various planning approaches that are part of the QoS QoS assurance subsystem in LTE networks in situations of network traffic congestion. Using different strategies for different types of traffic allows operators to offer different levels of quality of service for voice users. Evaluations of the efficiency of packet transfer scheduling algorithms are given.
Keywords: LTE, Long-Term Evolution, scheduling algorithms, FIFO, Round Robin, Shortest Job First, Random Early Detection, RED, RR, SJF, QoS, VoIP, CSFB, VoLTE
An important component of electronic document management and training systems is considered - a full-text search engine that allows to implement convenient means of searching for information of interest on the contents of electronic documents. Estimates of the efficiency of full-text search in databases are given.
Keywords: Database, full-text search, database management system, MySQL, PostgreSQL, Oracle
In this work, we carried out a study of algorithms implemented by the system of human identification based on various criteria. Three main approaches to face recognition are considered. The advantages and disadvantages of approaches revealed during implementation are given.
Keywords: Databases, face recognition, pattern recognition, hidden Markov models, principal component analysis, neural networks
In recent years, a greater interest in steganography is growing as an effective method of protection of still images, allowing you to keep the information confidential. In this paper we assessed robustness to hide information in the frequency domain of still images. Using qualitative and quantitative characteristics determines the optimal values for the Corvi method.
Keywords: information security, steganography, wavelet transform, data hiding, multiresolution analysis, the watermark
Distortion assessment of a wavelet-based watermarking method for low frequency subband
Keywords: information security, steganography, wavelet transform, data hiding, multiresolution analysis, the watermark, PSNR