The article considers the task of predicting the tertiary structure of a protein based on its primary sequence. The task of protein folding is solved by searching for conformation with minimal energy, if you look in terms of optimization problem. The work describes the use of a hybrid artificial immune system. In our work we try to combine clonal selection algorithms with differential and trigonometric differential evolution algorithms. We use special coding and decoding methods for individual individuals. The affinity function reduces the number of solutions with self-intersections (incorrect conformations) in the developed hybrid algorithms. We chose the hydrophobic-polar Dill model on a three-dimensional square lattice to test our algorithms. The study shows the advantages of the developed algorithms in comparison with other existing methods using experimental studies of test sequences.

To meet a challenge of constructing future cities through digital transformation projects cities themselves must act proactively. In this paper, a methodology of synthesizing the project management system for developing an impact on its time characteristics (duration parameters) is proposed in order to meet the planned schedule execution of the project. A discrete event model was developed to increase the operability and effectiveness of project management, enabling to describe in details the actions required for project execution. After replacing the continuous variable, a discrete (grid) function is defined at discrete moments. Project management contribution, based on this discrete event model, is to minimize the target criterion. The last one is determined by the sum of the difference between the deviation between the actual and the expected time of the initial event. The discrete measurement of vector coordinates provides the priority template for solving project management objectives in a turbulent environment. To make the model as the efficient one, the sequential steps of reaching the goal are minimizing. This procedure enables to reduce the cost of organizational resources, which is required to perform the planned work through project actions.

This paper is dedicated to developing the methods providing a high accuracy for the system of measuring the average energy of the microcontrollers, microprocessors and single-board computers or single-board microcontrollers (MC) in executing instructions, commands or parts of code. The proposed method of measuring the average energy of the microcontroller is based on the method of measuring the MC instantaneous power. Block diagram and functional diagram of system for measuring the MC average energy consumption are described. The method of improving the noise immunity of measuring the MC average energy is proposed and conditions for its running are formed. The method provides the immunity of the system to the interference impact of the normal mode noise. To implement this method the hardware components are introduced into the system circuit and they are specified. The implemented methods and the developed LabView software simulator are shown as part of information measuring system of average power consumption of microcontrollers. Conducted simulation studies confirmed an ability of proposed methods for precision measurements of MC energy consumption.

The paper presents a botnet detection approach for the distributed systems. It is based on the developed three level model, which includes botnet’s components: command and control center, control centers, basic elements of the botnet (bots). The novel framework provides the ability to detect known and unknown botnets, and consists of the host and the network levels. At the host level, the detection procedure is based on the implementation of the Bayes classification. The network level extends the results obtained at the host level to the rest of the local area network. Proposed approach provides the exchange of the results obtained by the Bayes classification for further use by other program units of the distributed system. The results of the developed classifier show that representation of the botnets’ samples for different classes and subclasses is sufficient for efficient botnet detection. Proposed technique demonstrates promising results concerning botnet detection in the distributed systems.

The approach to the use of Internet-devices and BigData information technologies while implementing the “Smart Cities” projects by means of information-technological platform of telemetric calculations of water, heat, gas and electricity consumption is proposed by the authors. In the basic version of the offered platform several generations of digital devices for telemetric data transmission capable to be connected to the Internet network by means of network interfaces (LAN) and mobile networks are used. The developed information-technological platform provides combination of Internet devices technology and BigData contributing to quick analysis and processing of a large number of obtained and delivered data sets.

This paper presents and explains an implementation of an Artificial Neural Network approach for sport activities (gestures) detection and recognition using PIQ ROBOT device. Tennis was chosen as an example of sports activities. The development of artificial intelligence has given rise to gesture-recognition-based devices. The global gesture recognition market size was valued at USD 6.22 billion in 2017 and it is likely to reach USD 30.6 billion by 2025. This paper starts our ambitious research in the area of artificial neural networks for activity recognition in the sport.

This article examines and analyzes the use of the word2vec method for solving semantic coding problems. The task of semantic coding has acquired particular importance with the development of search system. The relevance of such technologies is associated primarily with the ability to search in large-volume databases. Based on the obtained practical results, a prototype of a search system based on the use of selected semantic information for the implementation of relevant search in the database of documents has been developed. Proposed two main scenarios for the implementation of such a search. The training set has been prepared on the basis of documents in the English version of Wikipedia, which includes more than 100,000 original articles. The resulting set was used in the experimental part of the work to test the effectiveness of the developed prototype search system.

The method of increasing metrological reliability of measurement channels included in the peripheral modules of distributed automated control systems of technological processes is described. The proposed technical solutions provide high accuracy of determination and subsequent correction of the additive, nonlinear and multiplicative (relative to the voltage source of the calibration) error components included in the measurement channel. In this case, the non-excluded components of the error are much less than the errors of the elements used to determine the errors of analog-to-digital converters. Procedures for determining errors are carried out in the process of the system operation without dismantling its components and outages. Thus, the method provides high metrological reliability and reliability of the received source code of analog-to-digital converters.

A comparative analysis of various methods and architectures used to solve the problem of object detection is carried out. This allows so-called oneway neural networks architectures to provide high quality solutions to the problem. A neural network algorithm for labeling images in text documents is developed on the basis of image preprocessing that simplifies the localization of individual parts of a document and the subsequent recognition of localized blocks using a deep convolutional neural network. The resulting algorithm provides a high quality of localization and an acceptable level of subsequent classification.

The paper proposes a new approach to compression and data transmission in Internet of Things environment, based on the transformation of the Residue Number System and the method of arithmetic coding. The transformation of the Residue Number System is used to divide the data into parts. As a result, the received remainders are compressing in parallel used the arithmetic coding. Then they are transmitting through parallel routes, if the last ones are present. The proposed approach improves the processing speed through the parallel work and provides a compression ratio of depending on the type of data.

This work describes the process of creating a system for measuring the average energy consumption of microcontrollers and microprocessors (hereinafter referred to as MC). The requirements for the structure and hardware of such systems as well as the requirements for the key component of the system - the dual slope ADC are considered in this paper. The features of the dual slope ADC is unknown duration of the first integration cycle as well as a low additive error.

In this paper the approach for detection of cyber attacks is described. The approach is based on deep neural network. The main goal of proposed approach is to detect unknown, previous unseen cyber attacks. The proposed approach can increase the reliability of detection cyber attacks in computer systems and, as a result, it may reduce financial losses of companies.

Voice over IP (VoIP) is one of the most commonly used technologies. Due to the low cost of using VoIP, unlike traditional PSTN networks, it is rapidly growing and widely distributed in both personal and commercial areas. Since the VoIP uses the same routes like common Internet traffic, a risk arises regarding a safety of that service. In this paper a method for protecting the system of Voice over Internet Protocol from unauthorized access and calls to paid services is proposed. The method includes the two parts. A first part contains the 11 steps based on detecting the attacker to observe the log. file on the Asterisk server and File2ban using. Since a large number of IP addresses can be accumulated, the second part of the method is based on applying the fuzzy logic for improving its effectiveness. The case study is described, and its outcomes confirmed the correctness of the used fuzzy subsystem, as well as the correctness of the proposed method in whole.

The paper proposes a technique to regulate traffic lights intersections for special purpose vehicles using the technology of wireless sensor networks and Internet of things. The regulation technique using cloud service and local control using wireless sensor networks is considered. The proposed method will increase the safety and intersection movement efficiency by vehicles serving emergency purpose.

Wireless sensory networks cover various fields of human activity. Unresolved problems in the construction of wireless devices for long-term monitoring of objects, processes, events and phenomena with unlicensed use of radio channels ISM-frequency range is given the limitations on the bandwidth operating frequency for computer networks operation. The solution of this problem is based on the rapid processing of monitoring data by the Object System to determine the most informative data. Such data are subject to the primary delivery (transfer) to the local and central database, as well as to the compact coding the binary information packet sequences.

This work describes the model of joint processing of heterogeneous Web resources in intellectual information systems for their integration and further management, based on data representation model as a coherent combination of values and their description rules, interpretation and structure rules. The Ttouristic Web resources integration model describes general processes at Web resources processing in intellectual information system which helps to simplify the content management and integration automation technology. Touristic Web resources integration model involves the process decomposition on information integration, textual content syntax, semantics and structure subprocesses. This paper the all main problems in functional services of content management and integration are described and analyzed. Web content management and integration method is proposed as Web content lifecycle stages in intellectual information systems for Internet tourism. Web content integration and management model describes general processes of Web resources formation and processing in intellectual information systems and simplifies information technology for content working out. The proposed method makes it possible to create tools for Web resources processing in intellectual information systems and for a content of integration and management subsystem implementing.

Authors proposed to construct the fuzzy ontology of the academic discipline taking into account the educational material content, its complexity characteristics' and studying time. Proposed approach is based on the individual learning path using the fuzzy logic tool. Fuzzy rules, developed in MatLab environment, are applied in Protégé ontology editor using the Fuzzy OWL plugin. That enabled to implement the fuzzy ontology constructing of individual learning path for the academic discipline in education domain.

A method of improving the reliability of sensory data coming from measurement and control modules of distributed information-measuring systems and control actions formed by those modules is described. The proposed technical solutions by correcting additive, multiplicative and nonlinear error components of analog-to-digital converters provide the high reliability, survivability and. The preliminary reliability assessment of the proposed module is carried-out, and it confirmed the redundancy mechanisms need to be applied on the individual microcontroller, the sensor and the individual execution unit.

The authors propose the method for data coding in wireless sensor networks (WSN) based on the transformation of the residue number system and multipath routing. It enables to utilize efficiently the bandwidth of communication channels as well as reduce message delivery time. It is explored the ant algorithm to search an optimal route of data transmission in the wireless sensor network. There is introduced a limitation for the communication radius of the wireless unit that shorts a number of the search decision modes and improves the accuracy of the wireless network simulation. The correspondent software is designed, it allowes exploring the dynamics of finding the optimal transmission path in WSN in case of different algorithm settings, and exploring the impact of the elite ants on the accuracy of the found path.

Over the past few decades, the application of Artificial Immune Systems (AIS) and Artificial Neural Networks (ANN) has been growing rapidly in different domains. We sincerely believe that integration of these both techniques can allow constructing the Intelligent Cyber Defense System. In this paper an original method for detecting the network attacks and malicious code is described. The method is based on main principles of AIS where immune detectors have an ANN’s structure. The main goal of proposed approach is to detect previously unknown (novel) cyber-attack (malicious code, intrusion detection, etc.). The proposed Intelligent Cyber Defense System can improve the reliability of intrusion detection in computer systems and, as a result, it may reduce financial losses of companies from cyber attacks.