Stress is a growing issue in modern workplaces, affecting mental well-being, productivity, and health. This paper explores the use of computer mouse movement patterns as non-invasive behavioral indicators of psychological stress. The study presents a system for detecting stress levels based on mouse interaction data. An experimental task was designed to induce different stress levels. The collected data were used to train machine learning models, several of which achieved high classification accuracy. The results demonstrate the potential of mouse-based behavioral analysis as a practical approach to real-time workplace stress detection. This research contributes to the development of accessible stress monitoring tools and highlights the value of behavioral data analysis for improving occupational health.

Traffic accident detection and object detection have become key areas of research due to their direct impact on safety, traffic congestion mitigation, and intelligent traffic planning. This study presents a structured analysis of classical detection methods and artificial intelligence-based techniques, highlighting their methodologies, objectives, and performance results. The study categorizes existing research into threshold-based approaches, statistical approaches, image processing, rule-based approaches, and machine learning approaches, with further emphasis on predictive modeling, graph-based approaches, and optimization approaches. Considerable emphasis is placed on identifying systems that are capable of operating under adverse weather conditions such as fog, rain, and snow. These scenarios significantly affect detection accuracy. Although several authors incorporate environmental resilience into their models, most studies still evaluate performance under ideal conditions, revealing a critical gap in research. This analysis highlights the need to develop robust detection mechanisms that can adapt to real-world variability and environmental disturbances. Findings show that AI-based methods significantly outperform classical approaches in terms of adaptability and scalability, but their dependence on training data limits their performance in adverse conditions. The study concludes with recommendations for future work to prioritize multimodal sensing, generalization across weather conditions, and integration of environmental intelligence to ensure reliable real-time detection of traffic events under all operating conditions.

Discrete orthogonal transforms are fundamental tools in signal processing, with applications covering image compression, data analysis, and speech recognition. We introduce an interactive MATLAB-based software tool developed to facilitate the computation and visualization of these transforms. The software incorporates a user-friendly graphical interface and supports key features such as customizable input signal processing, graphical representation of results, and real-time editing of transformation parameters. By enabling users to explore the basis functions and transformation matrices interactively, the software enhances understanding of discrete orthogonal transforms and their computational efficiency. The tool serves as both an educational resource for students in signal processing courses and a practical utility for analyzing and synthesizing signals. This work aims to bridge theoretical concepts with practical applications in signal processing.

This paper deals with the automation of a manual workstation at Hyundai Transys s.r.o., a company specializing in the production of car seats for Kia automobiles. The aim of this work is to replace human labor with robotic workstations while ensuring the required efficiency, safety, and flexibility of the manufacturing process. Based on these requirements, the necessary equipment for transforming the manufacturing process into an automated system was selected and evaluated. Automating this part of the production process can speed up the manufacturing cycle, improve product quality, and save financial resources. The implementation of a robotic workstation controlled by a PLC system was a key step in achieving these goals. Based on simulations in the Roboguide simulation environment, the possibilities for future development and improvement of the work were evaluated.

The forest constitutes an essential and irreplaceable component of life for all organisms, with its primary significance lying in its role in creating a breathable atmosphere on Earth. Forests are vital for human health and well-being and hold significant ecological and economic value for humanity. This study aims to propose a method for identifying forest stands using artificial intelligence techniques. A custom dataset was developed, comprising high-quality satellite images that capture various structures such as forests, fields, roads, buildings, and lakes. This dataset was employed to train models from the category of convolutional neural networks that operate on the principle of instance segmentation. Several models, including YOLOv8, YOLOv5 and Mask R-CNN, were tested and compared. An optimal model was selected based on parameters such as detection accuracy, total training time, and the precision of labeling detected image elements. The selected model was then evaluated using images not included in the original training dataset to simulate real-world deployment scenarios. The final accuracy of best model achieved 91.67%. This model can detect the presence of forest stands in satellite images, as well as other features such as roads, buildings etc. The proposed method offers potential benefits for forest technicians, who can integrate it with other methods to monitor forest cover effectively.

Tunnel systems and implemented technological infrastructure have high requirements for their operation and maintenance. In the current stage, the digitalization and advanced diagnostical methods are widely applied. Data on operational characteristics are stored and prepared for further analysis. From the perspective of tunnel operation, some of detected events and alarms have a higher value, and therefore the intervention from the tunnel operator is required (e.g., in the case of the fault of an important device). However, the analysis performed shows that the number of monitored and detected events could overwhelm the tunnel operator. This study is focused on how to enhance technological toolkit with advanced algorithm on how to aggregate data to explicitly present a clear information to the operator. This will eliminate the overload of the operators, but even more it could help to plan and predict required maintenance with data-based knowledge and experienced operator.

Workflow and material flow are critical aspects of a company’s operations because they directly influence efficiency, productivity, cost-effectiveness, and overall success. Tracking these aspects is not easy and there are often errors in database entry or storage, especially in the case of reworks. Rework is created in the production process when a product or component fails to meet the required quality standards or specifications. The rework needs to be reworked and then stored to be ready for the next use. The aim of this work is to develop an application to control and monitor material flow for reworks. We analyzed workflows and material flows, what types they are, and what systems are used to manage these flows. This web application was created using C# and also uses SQL Server to read and write rework material data. This application was subsequently deployed at Continental, where its function will be to manage the material flow of the reworks in the production process.

Most companies around the world have their sensitive data stored in databases that are stored in different data warehouses, and companies need to migrate this data between data warehouses. There are various tools that enable such migration. These tools work on different principles and approaches and it is difficult to choose the right tool to perform the migration. The aim of this paper is to compare different migration tools, to create a reference architecture for the migration process, to perform the migration process and finally to perform the verification of the performed migration. We have created two reference architectures using which we have performed the migration process. We created two workstations on which we tested the selected migration tools Azure Synapse Analytics and SQL Server Migration Assistant (SSMA). The migration process was successful on both sites. The reference architecture and migration tool that was used for the first site was deployed to Continental. The verification process of the migration was performed at both sites, at the first site it was performed by company personnel and the implementation of row level security (RLS) and at the second site the verification was performed using the SQL Server Migration Assistant (SSMA) tool and SQL queries.

Purpose: Mobile robotics plays a crucial role in modern technology, providing innovative solutions across various sectors. This paper aims to enhance rescue operations in hazardous environments by introducing a dedicated prototype, SpheriDrive, designed specifically for rescue teams. Research Question: How can a spherical robot be designed to navigate efficiently through traffic tunnels, addressing the unique challenges of rescue operations in confined spaces? Methodology: The development of the SpheriDrive prototype focuses on overcoming the limitations of spherical robots by designing a novel configuration and placement of components and wheels. The control system utilizes an Arduino Due microcontroller, while LoRa technology is employed for communication and movement control. Validation: The robot is equipped with a specialized measuring head housing various sensors to measure environmental properties within the tunnel. Experimental results from the developed robot demonstrate its practical capabilities in real-world conditions. Results: The SpheriDrive prototype provides valuable data for rescue operations, overcoming the challenges posed by confined environments. Significance of the Results: This research significantly advances the capabilities of rescue teams by addressing design challenges and integrating innovative technologies. The prototype offers a cost-effective solution for enhancing rescue operations in hazardous environments.

Cardiovascular diseases (CVD) are a leading cause of global mortality, responsible for approximately one in five deaths. In response to these concerning statistics, there is a growing need for innovative solutions enabling cardiac monitoring beyond medical facilities. This paper demonstrates the fabrication and development of a novel system designed to be integrated into passenger car seats, facilitating continuous monitoring of passengers' cardiac activity. The system comprises a capacitive electrode prototype, a custom-designed analog signal processing circuit, and a computing unit. Two ultrathin capacitive electrodes were fabricated with a diameter of 56.42 mm protected by a guard layer to reduce noise. The amplification circuitry was comprised of operational amplifiers tasked with filtering and conditioning the electrocardiogram (ECG) signal. Heart rates calculated from our measurements were comparable with clinical ECG. The experimental setup underwent testing on human subjects while they were in a state of tranquil sitting within passenger cars and also in laboratory conditions. The proposed system offers the flexibility for single and dual power supplies in full capacitive or hybrid mode. Our experimental results confirm the system's feasibility and its capability to record high-quality signals from weak biopotentials, highlighting its potential for real-world applications.

Mental stress is a growing concern in modern society, with significant implications for both mental and physical health. Prolonged stress exposure is linked to various disorders, including anxiety, depression, and cardiovascular diseases, underscoring the need for effective detection and intervention strategies. This paper leverages a publicly available stress dataset and employs AI Studio to evaluate stress levels in daily life scenarios. By leveraging deep learning techniques, the research demonstrates the capability of artificial intelligence in identifying patterns within physiological signals associated with stress responses. The findings highlight the potential of long-term monitoring to enable real-time stress detection, providing a transformative tool for proactive health management. Such intelligent tools could be integrated into wearable devices, mobile health applications, and medical platforms to enhance stress awareness and promote timely intervention strategies, ultimately improving overall well-being.

This paper presents the development of a robotic workstation that integrates a collaborative robot as an assistant, leveraging advanced computer vision techniques to enhance human–robot interaction. The system employs state-of-the-art computer vision models, YOLOv7 and YOLOv8, for precise tool detection and gesture recognition, enabling the robot to seamlessly interpret operator commands and hand over tools based on gestural cues. The primary objective is to facilitate intuitive, non-verbal control of the robot, improving collaboration between human operators and robots in dynamic work environments. The results show that this approach enhances the efficiency and reliability of human–robot cooperation, particularly in manufacturing settings, by streamlining tasks and boosting productivity. By integrating real-time computer vision into the robot’s decision-making process, the system demonstrates heightened adaptability and responsiveness, creating the way for more natural and effective human–robot collaboration in industrial contexts.

The paper provides an overview on mobility challenges in the tunnel environment, it summarizes requirements on safety and emergency response that are negatively affected by limited availability or even lack of Global Navigation Satellite Systems in tunnels. The paper provides an alternative way on how to enable positioning in tunnels by using additional Bluetooth Low Energy (BLE) infrastructure with a focus on emergency response. The BLE infrastructure supports advanced systems such as Cooperative-Intelligent Transport Systems (C-ITS), and therefore it is possible to disseminate locally relevant information among the cars and to the tunnel operators. The paper considers various scenarios and provides use case definition supported by testing of C-ITS and functional validation from the Blanka tunnel in Prague. The proposed solution improves usage applications that require accurate positioning data to ensure proper functions, and therefore enables use of navigation in the tunnel environment. These could help to general use for wide range of drivers, however, the main goal is to efficiently assist during the rescue and recovery, or even smooth pass of emergency vehicle. The presented outcomes support preparation of strategic documents for Czech legislation and standards for the gradual installation of technologies in the tunnel, leading to better dissemination about emergency and other unexpected events to improve driver awareness through vehicular communication and reliable navigation.

Passenger detection systems play a crucial role in enhancing the efficiency and safety of intelligent transportation systems (ITS). Achieving optimal performance in these systems depends significantly on the fine-tuning of hyperparameters in machine learning models. As hyperparameters are critical to performance, this paper aims to identify the optimal settings for effective passenger detection. Leveraging genetic algorithms with YOLOv8, the study evaluates their impact on model accuracy using a passenger detection dataset. Experimental results demonstrate that hyperparameter tuning significantly boosts detection rates while reducing false positives, providing valuable insights for deploying passenger detection systems in practical applications. Furthermore, this work highlights the critical importance of hyperparameter optimization in enhancing the reliability and scalability of ITS solutions.

Traffic control in urban environments is a complex and critical challenge, with growing urbanisation and increasing vehicular congestion necessitating innovative solutions. Reinforcement learning has emerged as a promising approach to optimise traffic control and improve overall transportation efficiency, thanks to its ability to grasp the intricacies of complex issues without human involvement autonomously. In this paper, we propose a modified version of the SUMO-RL package and demonstrate its advantages in the context of our ongoing research regarding traffic control in the city of Zilina. The proposed modifications include support for custom reward functions for different agents and custom observation functions, representing a crucial design component when solving traffic signal control as a multi-agent reinforcement learning problem. We also present our preliminary results, which demonstrate the potential of reinforcement learning in addressing traffic control challenges.

This article addresses the challenges operators face in decision-making during the operational management of tunnels and other transport systems. Operators of complex systems must process vast amounts of information and suggestions from various devices, subsystems, and both internal and external sources. In addition, they receive requests from multiple entities. This overwhelming influx of data and demands places significant pressure on operators to evaluate and respond swiftly and accurately, which is often crucial to ensuring smooth operation of the entire transport system. To assist operators in making better decisions, new approaches are being introduced, such as expert systems and artificial intelligence. These tools aim to enhance decision-making not only during crises but also for routine operations and more complex tasks related to controlling and monitoring transport systems. The article outlines components of an expert system that uses fuzzy logic to address the complexities of acquiring certain data, particularly from predictive maintenance, which cannot be easily interpreted through simple operational interventions by the operator. Predictive maintenance also relies on decision-making supported by advanced algorithms, which are integrated with the systems technology and control framework.

Safety PLCs are commonly used in industrial applications to implement safety functions. However, they almost always require output circuits for power adaptation between the safety PLC and the controlled technology. This power adaptation also affects safety. This paper focuses on the design of output circuit architecture that allows the use of diagnostic testing to improve safety, even during continuous operation where diagnostic testing is not usually possible.

The increasing demand for efficient parking space utilisation has triggered the development of vacancy detection systems, with a particular focus on addressing the unique environmental constraints imposed by winter conditions. In this paper we present vacancy detection tool trained on our dataset that was collected in the parking lot of the University of Zilina, capturing unique winter conditions from December to January. The dataset includes diverse weather scenarios, such as snowfall or early morning conditions where light is reflected directly into the camera. Leveraging YOLOv4, Faster R-CNN, and PKLot dataset, WinterWatch demonstrates good performance in real-time vacancy detection under these challenging circumstances. WinterWatch not only contributes to the evolution of smart parking systems but also underscores the importance of tailored solutions for diverse environmental settings, ensuring year-round efficiency in outdoor parking management.

Detection of stress and the development of innovative platforms for stress monitoring have attracted significant attention in recent years due to the growing awareness of the harmful effects of stress on mental and physical health. Stress is a widespread issue affecting individuals and often goes unnoticed as a health concern. It can lead to various negative physiological conditions, including anxiety, depression, cardiovascular diseases and cognitive impairments. The aim of this paper is to provide an overview of studies focusing on embedded devices for non-invasive stress detection, primarily in the form of a modified computer mouse or keyboard. This study not only fills a critical gap in the literature but also provides valuable insights into the design and implementation of hardware-based stress-detection methods. By focusing on embedded devices, specifically computer peripherals, this research highlights the potential for integrating stress monitoring into everyday workplace tools, thereby offering practical solutions for improving occupational health and well-being.

The automated detection of individuals within vehicles, with minimal to no human intervention, hold multifaceted implications in contemporary contexts. These applications span from aiding emergency responders and optimising transportation networks to facilitating automated crash response mechanisms and enforcing regulations concerning High Occupancy Vehicle and High Occupancy Toll lanes. In this paper, we introduce our camera system designed for passenger counting, leveraging five IP cameras equipped with a range of optical filters, employing image registration techniques, and integrating the YOLOv8 object detection model. The Surveillance Camera Array Network (SCAN) operates within the near-infrared domain of the electromagnetic spectrum in conjunction with the visible part. Four VIVOTEK IP cameras are outfitted with near-infrared, neutral density, polarising, and ultraviolet optical filters, while the final camera retains its stock lens. Our primary challenge lies in managing variable lighting conditions throughout the day. However, during nighttime, we achieve nearly perfect image capture of vehicles. To mitigate noise, glare, and other impediments, we initially apply camera calibration, image preprocessing, cropping, image registration, and finally, image fusion. Our findings demonstrate that our cost-effective SCAN system adeptly detects passengers in cars equipped with window tinting. The results obtained during testing conditions resulted in an 66% true positive rate, 8% false positive rate and 26% false negative rate within best dataset. Additionally, we provide created datasets displaying passengers inside Suzuki Vitara, Jaguar XF, and Honda CRV vehicles with various levels of window tinting, to facilitate future community endeavors in addressing this challenging task.