Persons

• Counter: 847 | Comments : 0

The voice cleaning methods and algorithms play a key role both in preprocessing speech for further analysis and recognition, and in improving the quality of communication between users of information networks. The real-time streaming noise cleaning methods are the most important and complex area. The ability to process streaming data without delays imposes a number of significant restrictions on the algorithm: it cannot be iterative with a previously unknown number of iterations, and cannot explicitly use the data before or after the current block being processed. In the work, a modern adaptive noise reduction method for speech that can work with minimal signal transmission delays has been proposed. A large-scale study of existing approaches has been conducted, with special attention paid to two groups of algorithms: noise detection algorithms and noise suppression algorithms. Based on them the developed algorithm meeting the specified requirements has been built and analyzed. A set of audio data of Russian speech with various noises superimposed on it has been created. The testing of the algorithm has been made and its comparison with existing actual noise cleaning methods has been performed. The proposed adaptive method of noise cleaning without using specialized apparatus means and subsidiary information is able to operate in the real time conditions. The testing of the developed algorithm using the metrics of segment NC and PESQ have shown the high efficiency of the development and its superiority to common noise cleaning implementations Speex and WebRTC with respect to the noise cleaning quality and operation speed.

• Counter: 741 | Comments : 0

Nowadays, the task of increasing the efficiency of the information retrieval is of particular importance because of the implementation semantic Web concept. In this study a model for estimating the information retrieval efficiency based on the frequencies of the joint occurrence of concepts in documents has been proposed, taking into account the semantic correlations between the information units. It has been shown that the use of the ontological design methods and ontological modeling the document-based knowledge bases will permit to bring the level of the knowledge representation and systematization to the level of natural language. The proposed model significantly improves the level of the information retrieval reliability, which is especially important for processing of large amounts of data and for their intelligent processing.

• Counter: 1352 | Comments : 0

The most promising way to increase voters’ confidence in the remote electronic voting (REV) procedure is a voting method based on Ethereum blockchain platform. However, the existing solutions using this method faced a range of problems: ensuring the secrecy of the vote and openness of the procedure for society, pressure on the voter and a guarantee of the reliability of the whole system. In this work, a method for constructing a REV is proposed that solves these problems. It is similar in structure to the traditional voting method, using the same principle and processes. The Ethereum blockchain based REV process is described in detail. It was shown that received votes are securely stored in the Ethereum blockchain network, and the correctness of the vote addressing to the selected candidate can always be checked in real time. The description of smart contract algorithm that implements the transfer of vote from voter to candidate using transactions and determines the winner who received the highest number of votes was provided. It was demonstrated that keccak256 hashing algorithm and secp256k1 elliptic curve signatures ensure transactions’ maximum protection, reliability, and non-rollability. The developed REV technique based on Ethereum blockchain platform increases the efficiency of data security and confidentiality, transparency and anonymity of the voting procedure, and solves the problem of coercion. The results of the work have been implemented programmatically and can be used not only in the electoral system, but also wherever there is need of remote voting.

• Counter: 410 | Comments : 0

The methods of automated analytical processing of documentary information in the knowledge bases of decision support systems have been offered. The ways of estimating the document correspondence to the adjusted data domain have been developed.

• Counter: 236 | Comments : 0