The chapter presents a method for diagnosing oncourological diseases based on machine learning algorithms. MobileNet50, ResNet50 convolutional neural networks are used to solve the problem of classifying patient biopsy image segments according to the Gleason scale. Augmentation technologies were applied to the existing data set for better performance of the neural network. The accuracy of the algorithm was estimated by the total error and the Cohen's Kappa coefficient. The results of the algorithm in software show a good level of accuracy: in 65% of cases, the algorithm accurately determined the Gleason index, and the rest of the data had a slight deviation of the confusion matrix.

An intraoperative diagnostic is a vital tool in modern surgery, and it improves the accuracy of tumor removal and reduces the likelihood of damage to healthy tissue. The paper considers increasing the accuracy of intraoperative diagnostics through multimodal methods: a combination of Raman spectroscopy and optical coherence tomography. It is shown that when used in conjunction with machine learning methods, the accuracy of the diagnostic system can be up to 98%. To further increase the accuracy, it is advisable to consider other types of Raman spectroscopy as part of a multimodal system.

The brief review shows the potential of machine learning to improve the accuracy of multimodal medical diagnostic methods to a new level. Various machine learning algorithms, modalities, and cases demonstrating this approach’s significance are considered.

The article considers the problem of decision support in the information maintenance of individual education trajectory. The development of algorithms and software for processes automating in educational systems requires a special approach. The use of ontological models makes it possible to unify the description of the elements of educational systems and apply the technology of digital footprints when managing business processes in educational systems. An ontological model for managing educational trajectories is proposed. An algorithm has also been developed to compare competence-based models of curricula using latent-semantic analysis. The proposed models and methods are implemented as a distributed software system using the semantic web approach on the basis of distributed RDF-storage. The effectiveness of the developed algorithms and software solutions is demonstrated by the example of academic mobility in Ufa State Aviation Technical University. Prospects for further research in this area are outlined.

Currently, 5G/IMT-2020 networks with their possibilities become more and more services of new areas. These services are integrated into different human life activities. And in several cases, human life depends on Artificial Intelligence technologies, Autonomous Systems, and the Internet of Things (IoT), etc. Autonomous vehicles provide very strict requirements to the network in terms of ultra-low latency, high throughput, and wide coverage. To support these requirements, additional technologies must be employed. The current paper discusses the possibility of the use of airborne platforms aiming to support the terrestrial networks for autonomous vehicles realization as a part of delay-critical applications. Airborne platforms will help in the provisioning of safe road trips by delivering time-critical information to the vehicles globally, even in remote areas. In this paper, we discuss requirements and potential solutions for supporting the autonomous vehicle infrastructure, as a part of an intelligent transportation system. It’s proposed to use a sensor network along the road, consists of energy-efficient sensors that can connect in a Mesh network. Also, a novel approach for the detection of biological objects activity on the roadside, based on Artificial Intelligence technologies are suggested.

The problem of system design of complex technical objects based on intelligent technologies is considered. An optimization model for the conceptual design of a micro-mini-satellite based on a genetic algorithm is discussed. An artificial neural network model of a propulsion system is considered, as well as a heuristic algorithm for analyzing the cross-correlation of telemetric parameters of a micro-mini-satellite. The concept of constructing an intelligent system for information support of the life cycle of a complex technical object based on the considered models and algorithms is proposed.

The system of streaming data and complex events distributed processing is considered. A mathematical model for computational resource consumption and allocation in edge computing is offered. On the basis of mathematical model there was developed a multi-agent algorithm as a part of agent-based software architecture for distributed processing of streaming data, which had been developed by the authors previously. The efficiency of the developed algorithm has been investigated by means of simulation in AnyLogic. The resource allocation problem in edge computing was simulated and the algorithm demonstrated satisfying results both at static and dynamic regimes. Also, the perspectives of intellectual technologies using in resource allocation for edge computing are considered.

The solution of the problem of resource management in distributed computing systems of processing stream data in safety systems of distributed objects is considered. The tasks of streaming data processing in a multi-level multi-agent evacuation system in an infrastructure object are considered. The features of the mathematical model of a distributed stream data processing system are discussed.

The problem of generation, storage and processing of large volumes of digital data in complex systems is considered. An algorithm for structuring data based on Delaunay triangulation is proposed, which allows you to build fast and adaptive dynamic models of technical nodes in real time. An agent-based implementation of the proposed data storage and processing algorithms is proposed, as well as the construction of arbitrary-precision models in real time based on the ABSynth platform.

the technical aspects of solving the problem of malignant tumors diagnostic using machine learning are considered. An algorithm of Raman spectra classification using machine learning is offered. This allows the differentiation of malignant and benign tumor tissues using only Raman spectroscopy. Also the special architecture of cloud system is offered, which allows to collect sample data from different medical institutions and research centres, store them using distributed storage technology. Using of the offered system allows to machine learning researchers apply the results of their investigations to medical diagnostic.

The application of predictive analytics in the design, production and operation to achieve the efficiency of the life cycle of complex technical systems is discussed. A predictive model of information support for the life cycle of a microsatellite propulsion system based on a neural network system is proposed. The predictive model can solve the problem of estimating fuel consumption, diagnosing and detecting possible failures of a small propulsion system.

The problem of distributed storing and processing of streaming data in IoT systems is considered. A mathematical model and agent-based software architecture for distributed streaming data processing over heterogeneous computer network is offered. The software architecture determines the following features of IoT nodes software: structure of software components, models of interoperability, algorithms of resource management and also xml-based language which allows to descript distributed IoT applications. The offered architecture is implemented as a software framework ABSynth.