Frantisele Jakab

Internet of Things is constantly growing, and along with it comes the risk caused by unsecured devices that it consists of. First option to increase security, is to use the intrusion detection system (IDS). Based on the analysis of communication in IoT (Internet of Things) networks, on intrusion detection methods and on protocols for collecting information about communication, we designed and implemented a system for flow-based intrusion detection. To distinguish as many attacks as possible and for universality reasons, we used machine learning for the prediction of attacks. We optimized the system for Raspberry Pi. Then we performed tests to determine the accuracy of the prediction. The results of mentioned tests were finally evaluated.

This research describes an experimental solution used for estimating the positions of pedestrians from video recordings. Additionally, clustering algorithms were utilized to interpret the data. The system employs the You Only Look Once (YOLO) algorithm for object detection. The detection algorithm is applied to video recordings provided by an unmanned aerial vehicle (UAV). An experimental method for calculating the pedestrian’s geolocation is proposed. The output of the calculation, i.e., the data file, can be visualized on a map and analyzed using cluster analyses, including K-means, DBSCAN, and OPTICS algorithms. The experimental software solution can be deployed on a UAV or other computing devices. Further testing was performed to evaluate the suitability of the selected algorithms and to identify optimal use cases. This solution can successfully detect groups of pedestrians from video recordings and it provides tools for subsequent cluster analyses.

The paper is focused on the development of the experimental web-based solution for image processing from the perspective of an Unmanned Aerial Vehicle (UAV). Specifically, the research is carried out as part of the broader study on drone utilization in traffic at the Technical University of Kosice. This contribution explores the possibility of using the UAV as a tool to detect the temporal state of the traffic in multiple locations. Road traffic analysis is enabled through the detection of vehicles from the user-defined region of interest (ROI). Its content then serves as the input for motion detection, followed by the detection of vehicles using the YOLOv4 model. Detection of other types of objects is possible, thus making the system more universal. The vehicle is tracked after recognition in two consecutive frames. The tracking algorithm is based on the calculation of the Euclidean distance and the intersection of the rectangles. The experimental verification yields lower hardware requirements for CPU and GPU by about two FPS when using optimization techniques, such as ROI or reference dimensions of objects. The accuracy of detection and the subsequent tracking of cars reaches almost 100% while providing accurate trajectory determination.

Communication is one of the most notable processes in a multi-agent system. For this reason, considerable attention is paid to it—from abstract levels presenting theoretical models describing the basic principles to an implementation level with many details. However, most of these models build on a kind of unchanging basis, which characterizes communication between agents of a multi-agent system as a mutual exchange of messages expressed in a specific language or formal logic system, most often first-order predicate logic. Since most logical systems specialize in a particular area of natural language, the choice of a logical system reduces the communication potential of a multi-agent system. Therefore, we decide to choose the transparent intensional logic, a highly expressive methodology of logical analysis of natural language based on the symmetry between the syntax of expressions and their semantics, which minimizes these limitations and brings a new perspective on the issue of formalization of communication in multi-agent systems. By choosing transparent intensional logic as the central logical apparatus of our solution and postulating the general criterion for the synthesis of the concept of a message, the framework idea of our solution, which is based on hypotheses formulated in the analysis of Singh’s formal theory of communication, we have reached the synthesis of the so-called TIL-Message Formalization System. This system, unlike others based on traditionally used formalisms, simplifies the communication process itself by reducing the level of semantic interpretation of messages formalized by it, and in addition to formalism itself, this system also provides an abstract description of the background of the course of communication, proved by its application on specific examples, by standing out from the order of other formalisms providing only a kind of syntactic standard.

In this paper an algorithm for detection of nonstandard situations in smart water metering based on machine learning is designed. The main categories for nonstandard situation or anomaly detection and two common methods for anomaly detection are analyzed. The proposed solution needs to fit the requirements for correct, efficient and real-time detection of non-standard situations in actual water consumption with minimal required consumer intervention to its operation. Moreover, a proposal to extend the original hardware solution is described and implemented to accommodate the needs of the detection algorithm. The final implemented and tested solution evaluates anomalies in water consumption for a given time in specific day and month using machine learning with a semi-supervised approach.

The broad goal of this study is the estimation of dimensions of real-world multidimensional objects. The focus is on the human being and its dimensional parameters, primarily the height. The approach to the estimation of the height in a single camera environment is presented and is experimentally verified. The proposed method presumes that the distance from the optical device to the human body and its Vertical Field of View (VFOV) are known. The VFOV has to be calculated or acquired only once for a specific device. The accuracy of the proposed method is validated by a series of test scenarios including, e.g., statistical height measurements.

In this paper the algorithm for detection of non-standard situation in smart water metering based on machine learning is designed. The main categories for non-standard situation or anomaly detection and two common methods for anomaly detection are analyzed. Proposed solution needs to fit the requirements for correct, efficient and real-time detection of non-standard situation in actual water consumption with minimal required consumer intervention to its operation. The final implemented and tested solution evaluates anomalies in water consumption for a given time in specific day and month using machine learning with semi-supervised approach.

One of the challenges in a modern IoT infrastructure is to support the communication model with the ability to adapt to the situation (e.g. congestion) in a transport environment. Within this paper, the overview of communication protocols to support the QoS needs in IoT infrastructures is presented. IPFIX protocol, its architecture, protocol messages, headers, and communication model has been outlined. The mechanism of the TinyIPFIX transformation using mediation, template management processes and scenarios of its application is described and the architecture for the monitoring of the IoT infrastructure based on TinyIPFIX implementation has been proposed. Since there is no universal protocol defined in IoT, the paper is providing also an insight into the communication protocols from the point of view of their classification based on the OSI layer they are working on and on the transmission range. Presented mechanisms allow the existing infrastructure to be easily extended by the IoT environment protocols where the guarantee for the quality of transmission is crucial.

This paper focuses on the research of signing the documents in the collaborative environment of National Telepresence Infrastructure. The principal goal of this paper is to propose the experimental system where the electronic document with a reference for videoconference can be signed. Analysis of the existing systems used for videoconferencing is carried out. Technologies for processing and signing the electronic documents are analyzed as well. Based on analysis the system design is proposed, following the implementation of the final system. The experimental solution was tested on videoconference devices from National Telepresence Infrastructure (NTI), and its functionality was verified.