To enhance public safety, crowd detection and prevention systems have essentially become a natural means to manage diverse crowded areas, such as urban settings, transportation hubs, and event venues. Recent systems take advantage of the synergy between machine learning, data mining, and image processing to extract/analyze features from crowded zones and recognize patterns and anomalies from the crowd behavior. Additionally, image processing tools play a key role in real-time monitoring by analyzing video feeds to detect crowd density, flow direction, and identify potential risks like overcrowding or emergencies. However, most existing solutions focus on the detection phase and often overlook integrated error handling and robust decision-making frameworks to ensure accurate and actionable crowd prevention. Aiming to solve these issues, we take advantage of the prediction capabilities of machine learning models and the analysis and clustering strengths of Formal Concept Analysis (FCA) chosen for its strong mathematical foundation and superior clustering capabilities compared to traditional methods, as highlighted in recent works such as K-means or hierarchical clustering. We used the first technique to extract useful knowledge from areas’ produced images while mitigating potential error accumulation through modular error-checking mechanisms. A neural network is used to mark human bodies, determine the position of walking individuals, and predict crowd levels. Such information is, thereafter, inputted to the FCA-based decision system to ensure an explicit representation and modelling of crowd data, thanks to lattice structures. These latter’s hierarchical view helped us identify the crowded areas and manage them as clustered zones, based on their common crowd information. We also define bottom-up parsing algorithms to recommend the suitable crowd prevention plan w.r.t. the crowd level. Experiments have successfully proved the ability of FCA to exclude low-crowd zones, locate crowded areas, and provide actionable crowd management insights, which may complement crowd counting techniques.

Crowd detection and prevention systems have become essential for managing densely populated areas. Modern systems leverage the combined power of machine learning, data mining, and image processing to extract and analyse features from crowded zones, enabling the identification of behavioural patterns and anomalies. However, most current solutions primarily focus on detection and lack robust decision-making and recommendation mechanisms for selecting appropriate crowd-prevention strategies. To address this gap, we integrate the predictive capabilities of machine learning models with the analytical and clustering strengths of Fuzzy Formal Concept Analysis (fuzzy FCA). Machine learning is employed to extract valuable insights from images of the area, with a neural network used to identify human figures, track individuals' positions, and predict crowd levels. This data is fed into an FFCA-based decision system, where crowd information is structured and clustered using lattice theory. This latter helped exclude low-crowd zones and cluster the rest of the monitored areas based on their crowd features. Additionally, we define bottom-up parsing algorithms to recommend suitable crowd-prevention plans based on crowd density levels within fuzzy formal concepts. Experiments confirmed not only the ability of fuzzy FCA to "exclude" low-crowd zones thanks to a used crowd threshold but also the efficient "feature-based clustering" of crowded zones into hierarchical formal concepts and these latter’s "bottom-up parsing" to finally identify the dense zones.

Crowds can lead up to severe disasterous consequences resulting in fatalities. Videos obtained through public cameras or captured by drones flying overhead can be processed with artificial intelligence-based crowd analysis systems. Being a hot area of research over the past few years, the goal is not only to identify the presence of crowds but also to predict the probability of crowd-formation in order to issue timely warnings and preventive measures. Such systems will significantly reduce the probablity of the potential disasters. Developing effective systems is a challenging task, especially due to factors such as naturally occuring diverse conditions, variations in people or background pixel areas, noise, behaviors of individuals, relative amounts/distributions/directions of crowd movements, and crowd building reasons. This paper proposes an infrared video processing system based on U-Net convolutional neural network for crowd monitoring in infrared video frames to help estimate the people crowd with normal or abnormal trends. The proposed U-Net architecture aims to efficiently extract crowd features, achieve sufficient people marking-up accuracy, competitively with optimal network configurations in terms of the depth and number of filters to consequently minimise the number of coefficients. For further faster processing, hardware resources/implementation area savings, and lower power, the optimized network coefficients measured are represented in Canonic-Signed Digit with minimal number of nonzero (± 1) digits, minimizing the number of underlying shift-add/subtract operations of all multipliers. The achieved significantly reduced computational cost makes the proposed U-Net effectively suitable for resource-constrained and low power applications.

In this paper, a method for routing fractal-like traffic in computer networks was proposed. This method uses the prediction of router load by analyzing the fractal dimension of network traffic to reduce the probability of packet loss. It takes into account the predicted router load as one of the metrics for determining the shortest packet transmission routes in a computer network. Additionally, a computer simulation model of a computer network based on complex network theory, Markov processes, and fractal time series was created. This computer simulation model allows the generation of a computer network structure and simulates traffic movement between network devices for testing routing algorithms. A series of experiments on the developed computer network model to determine the quality of the proposed routing method and compare it with other methods were conducted. During the analytical research and experiments, the impact of different fractal dimensions of traffic on the probability of packet loss and, consequently, on the quality of service at high traffic intensity was investigated. And it also investigated whether the proposed routing method allows for the reduction of the number of lost network packets. Analyzing the results of the experiments, the following conclusions can be drawn. The fewest lost packets were when the process was random or had weakly expressed trends, which was modeled in the experiment by traffic with the fractal dimension equal to 1.5. Persistent and anti-persistent processes (those with memory) cause more packet loss for the same traffic intensity and the same maximum number of packets generated per device per unit of time. Moreover, the anti-persistent processes modeled in the experiment by traffic with the fractal dimension equal to 1.25 cause significantly greater losses than persistent processes modeled with the fractal dimension of 1.75. Also, the results of the experiments showed that the proposed traffic routing method allows for a significantly reduced number of lost packets compared to the existing method without prediction based on fractal traffic analysis

Taking into account the fractal properties of computer network traffic allows one to predict the information processes in them. The known criteria for determining the fractal dimension, such as the Hurst exponent, have significant errors and deviations for some cases, so it is advisable to develop new methods for estimating the fractal characteristics of the researched signal. The authors had proposed a method for determining the fractal dimension of network traffic by its probabilistic properties. The purpose of this paper is to research the quality of the proposed method. In this work, a binary time series is used to model fractal binary network traffic, which persistence is regulated by setting up the probability of one state change to the opposite by means of Markov chain. The generated traffic was used to investigate the quality of the proposed probabilistic method of determining the fractal dimension of network traffic and to compare it with the method based on R/S analysis. A series of experiments was conducted which showed that R/S analysis gives different values with different cumulative sums for the same data, that indicates the ambiguity of the method. The probabilistic method does not have this disadvantage and gives unambiguous results. Also, the developed method has a lower deviations from the mean value of the Hurst exponent, and therefore it is more accurate in determining the fractal dimension than R/S analysis method – R/S analysis has a deviation of 2.5%, and the developed method has 1.8%.

Modern computer vision systems often use neural networks to process images. But to use neural networks, you need to create databases to train these neural networks. In some cases, creating a training database takes the vast majority of the project's financial and human resources. Therefore, the actual task of finding methods to improve the quality of learning neural networks on small data is considered in this article. The ability to process data, which nature was not present in the original training database is relevant, also. To solve the problem of improving the quality of image segmentation by textural anomalies, this research is proposed to use as input to the neural network not only the image but also its local statistic data. It can increase the information content of the input information for the neural network. Therefore, neural networks do not need to learn to choose statistical features but simply use them. This investigation classifies the requirements for image segmentation systems to indicate atypical texture anomalies. The literature analysis revealed various methods and algorithms for solving such problems. As a result, in this science work, the process of finding features in the photo is summarized in stages. The division into stages of search for features allowed to choose arguments for methods and algorithms that can perform the task. At each stage, requirements were formed for methods, that allowed separate the transformation of image fragments into a vector of features by using an artificial neural network (trained on a separate image of the autoencoder). Statistical features supplement by the vector of features of the image fragment. Numerous experiments have shown that the generated feature vectors improve the classification result for an artificial Kohonen neural network, which is able to detect atypical image fragments.

The object of research in this article is simulation modeling of a computer network and the process of traffic routing. The relevance of the research is due to the importance of ensuring the quality of service in computer networks, in particular, by necessity reducing the number of lost IP-packets at high traffic intensity values. Determining the routing of traffic packets is a complex process and is based on various indicators or combinations of indicators. If the routing process takes place in a dynamic mode, then the complexity of the route calculation increases, in this case, one of the tools for research and comparison of different routing algorithms can be a computer simulation model of a computer network. The goal of the work is the development and research of a computer simulation model of a computer network for testing traffic routing algorithms. The tasks: to develop computer simulation model of a computer network to generate the network structure and simulate the traffic distribution process with the ability to test different routing algorithms. Research methods: theory of computer networks, theory of fractal analysis, object-oriented programming, theory of algorithms and data structures, theory of complex networks, theory of Markov processes. Conclusions. The paper investigated the basic principles of traffic routing in computer networks. A simulation model of a computer network for testing traffic routing algorithms has been developed. A method based on the theory of complex networks has been developed to generate the structure of a computer network. Theory of fractal analysis and Markov processes are used for traffic generation. A series of experiments was conducted on a developed model to determine how different fractal dimensions of traffic at high traffic intensity values affect the number of lost packets, and therefore the quality of service. Analyzing the results of the experiment, the following conclusions can be drawn: the least number of lost packets occurs when the process is random or has weak trends. The fewest lost packets were at fractal dimension 1.5, i.e., when the process is completely random, there were also few lost packets at fractal dimensions close to this; persistent and anti-persistent processes (those with memory) cause more packet loss for the same traffic intensity and maximum number of packets sent from one device per unit of time. Moreover, anti-persistent processes cause significantly more losses than persistent ones. Thus, when performing traffic routing and finding optimal paths for sending IP-packets, it can be useful to determine and take into account the fractal dimension of traffic at the entrance of each router and use it when calculating metrics to determine the best routes.

The subject matter of the article is the process of increased the information security of recommendation systems. The goal of this work is to develop a method of identification bot profiles in recommendation systems. In this work, the basic models of information attacks by the profile-injection method on recommendation systems were researched, the method of identification bot profiles in recommendation systems using the multilayer feedforward neural network was developed and the experiments to test the quality of its work were conducted. The developed method is to identify bot profiles that attempt to change item ratings in a recommendation system in order to increase the occurrence frequency of target items in recommendation lists to all authentic users, or to certain segments of authentic users. When removing bot profiles' data from the database of the recommendation system before generating recommendation lists, the accuracy of the system and the correctness of recommendations are significantly increased, and authentic users get protection from information attacks. Random, Average and Popular attacks were used to model the attacks on a recommendation system. To identify bots, their ratings for system items were analyzed. The experiments have shown that the neural network that analyzes only the numbers of different ratings in a profile, detects bot profiles with high accuracy, that use Random attack regardless of the number of target items for each bot. At the same time, the developed neural network can detect bots that use Average or Popular attacks only when they have several target items. Also, the results of the experiments show that type I errors, when the system identifies authentic users as bots, is very rarely appear in the developed method. To improve the accuracy of the neural network, there can add to analysis also other data of user profiles, such as the timestamp of each rating and as segments of items, which was rated.

With the development of modern telecommunications systems and the exponential growth in the demand for information transmission, there is a constant lack of bandwidth for the available telecommunication channels under the management of routers and communicators, because it is necessary to distribute the load of the network segments taking into account their self-similar nature of the traffic.Now, it is not possible to analytically build criteria and algorithms for optimal traffic management to ensure QoS measurements.The correspondence of the practical results with the theoretical ones was experimentally confirmed, although non-standard metric of the coverage measure expression was used in the derivation of analytical dependencies.That's why it was decided to develop theoretical method and provide experimental confirmation using conventional methods of estimating the time series' fractal dimension.The actual possibilities of adjusting the Hearst index on a given time scaling were established as a result of the numerical experiment.The obtained time series with the help of a cascade binary sequence generator have multifractal properties.That is, the cascade generator has more possibilities for receiving traffic, which will correspond to the examples of binary traffic in real telecommunication networks.However, the cascade generator requires further theoretical study to analytically express the coefficients to obtain the desired fractal characteristics and flow intensity.

The problem of generating traffic with given fractal properties in order to use it in simulation processes of the computer network, which is carried out to predict the properties of the telecommunication system in the meantime delay of information packets and their likelihood of loss is dedicated in the paper. The subject of the research in the article is the method of generating fractal traffic using a generator model on the graph. The purpose of the research is to create a method for generating fractal traffic using a generator model on the graph. For this purpose, the following tasks were solved: defined fractal properties of telecommunication traffic and the consequences of fractality; were defined the fractal dimension of the numerical series and the distribution density of the elements of the series were determined; the estimation of the fractal properties of the generated binary sequences is carried out; the management mode of the intensity of generated traffic; suggested the generator was adjusted to match the sample traffic. The result of the work is the implementation of the method of generating fractal traffic using a generator model on the graph, due to the application of the following steps: the relevance of the problem of creating generators of fractal binary sequences without the use of infinite distributions is identified; the generator of a fractal binary sequence given by the Markov chain; the variability of the fractal dimension of the binary sequence and at different intensities τ is demonstrated; analytic expressions are derived for obtaining generator parameters with a given output bits density with the control of their fractal dimension.

The problems of determining the fractal dimension of a time series obtained using a self-similar traffic generator based on Markov chains with a controlled fractal dimension are stated. Based on numerical experiments to determine the fractal dimension of the generated numerical sequences, statistically significant changes are shown at different scales. The insufficient development of high-performance algorithms and methods for generating self-similar numerical sequences for procedure of traffic simulation in telecommunication systems and networks is indicated. The directions of further research on the management of the multifractality in generators based on Markov chains are proposed.