This paper reports an analysis of aspects of the project planning stage. The object of research is the decision-making processes that take place at this stage. This work considers the problem of building a hierarchy of tasks, their distribution among performers, taking into account restrictions on financial costs and duration of project implementation. Verbal and mathematical models of the task of constructing a hierarchy of tasks and other tasks that take place at the stage of project planning were constructed. Such indicators of the project implementation process efficiency were introduced as the time, cost, and cost-time efficiency. In order to be able to apply these criteria, the tasks of estimating the minimum value of the duration of the project and its minimum required cost were considered. Appropriate methods have been developed to solve them. The developed iterative method for assessing the minimum duration of project implementation is based on taking into account the possibility of simultaneous execution of various tasks. The method of estimating the minimum cost of the project is to build and solve the problem of Boolean programming. The values obtained as a result of solving these problems form an «ideal point», approaching which is enabled by the developed iterative method of constructing a hierarchy of tasks based on the method of sequential concessions. This method makes it possible to devise options for management decisions to obtain valid solutions to the problem. According to them, the decision maker can introduce a concession on the value of one or both components of the «ideal point» or change the input data to the task. The models and methods built can be used when planning projects in education, science, production, etc.

The article presents a method for detecting low-intensity DDoS attacks, focused on identifying difficult-to-detect “low-and-slow” scenarios that remain undetectable by traditional defence systems. The key feature of the developed method is the statistical criteria’s (χ² and T statistics, energy ratio, reconstruction errors) integration with a combined neural network architecture, including convolutional and transformer blocks coupled with an autoencoder and a calibrated regressor. The developed neural network architecture combines mathematical validity and high sensitivity to weak anomalies with the ability to generate interpretable artefacts that are suitable for subsequent forensic analysis. The developed method implements a multi-layered process, according to which the first level statistically evaluates the flow intensity and interpacket intervals, and the second level processes features using a neural network module, generating an integral blend-score S metric. ROC-AUC and PR-AUC metrics, learning curve analysis, and the estimate of the calibration error (ECE) were used for validation. Experimental results demonstrated the superiority of the proposed method over existing approaches, as the achieved values of ROC-AUC and PR-AUC were 0.80 and 0.866, respectively, with an ECE level of 0.04, indicating a high accuracy of attack detection. The study’s contribution lies in a method combining statistical and neural network analysis development, as well as in ensuring the evidentiary value of the results through the generation of structured incident reports (PCAP slices, time windows, cryptographic hashes). The obtained results expand the toolkit for cyber-attack analysis and open up prospects for the methods’ practical application in monitoring systems and law enforcement agencies.

The study is devoted to the analysis of the problem of decision-making regarding the organization of the educational process in the conditions of external influences of irresistible nature. The case of a forced reduction in the academic semester with the need for full implementation of educational plans for the training of education seekers is considered. It was determined that for effective planning of the educational process, it is initially necessary to divide the classrooms of the educational institution between educational groups belonging to different structural units of the educational institution. The verbal and mathematical formulation of the task of dividing classrooms between educational groups was completed. A mathematical model of the problem was built. The model is a set of restrictions that are imposed on the options for admissible distributions of audiences. The developed model allows you to introduce restrictions on the length of the working day, breaks between classes in individual groups, the number of working days per week, etc. An algorithm for developing variants of management decisions regarding the distribution of classrooms between educational groups of different structural units of the university has been built. Variants of management decisions depend on the initial conditions that are included in the problem model and on the strength of the set of admissible solutions. The possibility of developing options for management decisions regarding combined options for the organization of the educational process (face-to-face, distance, and mixed forms of education) is foreseen. In such cases, the management of the educational institution may impose restrictions on the possibility of alternating classes that take place in classrooms with classes that take place online. The developed approach also allows the redistribution of audiences between structural units for separately defined periods. The implementation of the developed models and algorithms for the autumn semester 2022–2023 at the university will allow the completion of studies by mid-November. At the same time, all educational plans will be completed in full. The developed tool makes it possible to increase the efficiency of management decision-making processes regarding the organization of the educational process in higher education institutions.

This article presents an adaptive neural network method for the automated detection, reconstruction, and prioritisation of multi-stage criminal operations in the digital environment, aiming to protect human rights and ensure the legal security of digital evidence. The developed method combines multimodal temporal encoders, a graph module based on GNN for entity correlation, and a correlation head with a link-prediction mechanism and differentiable path recovery. Sliding time windows, logarithmic transformation of volumetric features, and pseudonymization of identifiers with the ability to utilise privacy-preserving procedures (federated learning, differential privacy) are used for data aggregation and normalisation. Unique features of the developed method include an integrated risk function combining an anomaly component and graph significance, a module for automated forensic packet generation with chain of custody recording, and a mechanism for incremental model updates. Experimental results demonstrate high diagnostic metric values (AUC ≈ 0.97, F1 ≈ 0.99 on the test dataset after balancing), robust recovery of priority paths (“path_probability” > 0.7 for top operations), and pipeline performance in PII leak prioritisation and human trafficking reconstruction scenarios. The study’s contribution lies in a practice-oriented neural network method that integrates detection, correlation, and the collection of legally applicable evidence.

The decision-making problem for the case of human-machine analysis of input data is considered. It was noted that the use of human-machine decision support systems allows to reduce time and money costs. A multi-channel automated decision-making system is considered, which can generate real-time decisions based on signals coming to it from different channels. All channels are numeric. Channels can be both software tools of artificial intelligence and competent experts who give conclusions on the researched issue. Two cases were studied: – the case of making decisions regarding the numerical assessment of an object or phenomenon, when the agreed decision must be numerical; – a case of making decisions regarding the fact of the appearance of an object or phenomenon, when the agreed decision must be logical. Seven rules have been developed for determining the numerical assessment of an object or phenomenon. The rules allow you to take into account the estimates obtained from different channels and the reliability of these channels. Separate rules take into account ratings received from all channels. There are rules that take into account only the evaluations of those channels whose reliability meets the specified limits. This approach ensures a sufficiently reliable decision, according to the needs of the task and the person making the decision. Four rules have been developed for the case of decision-making regarding the fact of the appearance of an object or phenomenon. These rules, analyzing the numerical estimates received from the channels, produce a solution from the set {True, False}, which corresponds to cases of occurrence/absence of the phenomenon under investigation. The rules take into account the reliability of the channels and, based on the constructed functional dependence, convert the numerical evaluation into a logical one. The constructed decision-making scheme in multi-channel human-machine decision support systems makes it possible to arbitrarily increase the number of channels in the system. The use of rules that filter out estimates obtained from channels that are not reliable enough for a specific problem will prevent the dispersion of the estimation result due to a large number of channels. The choice of rules rests with the decision maker or problem owner.

The work is devoted to the research of methods of optimizing project management in conditions of limited resources. Emphasis was placed on building a hierarchy of tasks and decision-making processes. Strategies for estimating the minimum project duration and costs are presented. Also, with the help of iterative methods, options for management solutions were developed. After analyzing the constraints and formalizing the tasks, practical solutions are provided to improve the efficiency of the project, ensuring time and financial constraints.