Nowadays there is a growing demand for small- and medium-sized enterprises (SMEs) to improve their level of digitalisation. This situation becomes even more critical in cases when SMEs act in the role of a subcontractor of large enterprises who demand the utilisation of certain digital operations. This paper aims to identify the essential Industry 4.0 attributes for the requirements of SMEs that enterprises can purchase to deploy an adequate solution with a view of increasing their competitiveness in the market. By analysing research articles and statistical data from the worldwide Web of Science database, we identify the major Industry 4.0 attributes for SME: Internet of Things (IoT), Big Data, Artificial Intelligence (AI), Cloud Computing, Simulation and Cybersecurity. Based on the review results and a survey by the European Commission, we propose devices primarily designed to implement AI tasks in industrial environments that meet the essential attributes for SMEs and have low entry costs. The subject of IoT is thoroughly addressed. Its subsets and the relationship between Industrial Internet of Things (IIoT) and Artificial Intelligence of Things (AIoT) are introduced and described. The characteristics of the listed devices as related to usability in the identified attributes are verified. Therefore, the description of the devices is provided with respect to their usability in SMEs. The main purpose of this paper is to identify attributes for SMEs and to develop strategic plans for the digitalisation requirements, particularly in the development of Artificial Intelligence as part of the implementation of the IoT pillar.

Industrial Control Systems (ICS) are critical to the efficient operation of essential sectors such as manufacturing, energy, and water management. However, their increasing integration with IT systems exposes them to sophisticated cyberattacks, particularly lateral attacks targeting Programmable Logic Controllers (PLCs). Advanced preventive measures are necessary because, despite their significance, many ICS continue to rely on outdated technologies with few security features. This paper proposes a machine learning (ML)-based approach to anomaly detection in ICS communication networks, focusing on techniques such as 1D Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, Support Vector Machines (SVMs), and Isolation Forest (iForest) algorithms. We generated a dataset by capturing both normal and manipulated ICS communication patterns, including TCP/IP traffic. Simulated lateral attacks provided realistic data for training and testing the ML models. The results demonstrate that the 1D CNN model achieved the highest accuracy (0.92) and F1 score (0.91) with minimal processing time, making it ideal for real-time intrusion detection. This research highlights the potential of ML techniques to fortify ICS cybersecurity and lays the groundwork for future advancements in critical infrastructure resilience.

The essential component of all the control and sensory systems is a communication layer. The MODBUS protocol used in automation and sensory industry defines a simple format of communication using the master/slave principle, although since it originated in the 1970s it has become obsolete. In this article is presented uBUS protocol as an enhancement of the MODBUS protocol uBUS protocol proposal brings advanced features for today’s requirements for embedded applications. Enhancements include address extension to 4079 addresses, adding a new communication mode (group broadcast), delegating selected master features to slave, linking with other communication interfaces and securing communications layer. The main part of the article deals with the description of design and implementation of the uBUS communication security. An RSA algorithm that uses asymmetric encryption was used to implement communication encryption. The article presents a way of implementing such encryption and its effectiveness on various types of microcontrollers implementing uBUS slaves. Since the communication protocol security is designed as a separate layer, it is possible to implement different types of encryption.

Currently, we are experiencing an ever-increasing demand for high-quality transportation in the distinctive natural environment of forest roads, which can be characterized by significant weather changes. The need for more effective management of the forest roads environment, a more direct, rapid response to fire interventions and, finally, the endeavor to expand recreational use of the woods in the growth of tourism are among the key factors. A thorough collection of diagnostic activities conducted on a regular basis, as well as a dataset of long-term monitored attributes of chosen sections, are the foundations of successful road infrastructure management. Our main contribution to this problem is the design of a probe for measuring the temperature profile for utilization in stand-alone systems or as a part of an IoT solution. We have addressed the design of the mechanical and electrical parts with emphasis on the accuracy of the sensor layout in the probe. Based on this design, we developed a simulation model, and compared the simulation results with the experimental results. An experimental installation was carried out which, based on measurements to date, confirmed the proposed probe meets the requirements of practice and will be deployed in a forest road environment.

A considerable funds is spent for the roads maintenance in large areas during the winter. The road maintenance is significantly affected by the temperature change of the road structure. In remote locations may occur a situation, when it is not clear whether the sanding is actually needed because the lack of information on road conditions. In these cases, the actual road conditions are investigated by a personal inspection or by sending out a gritting vehicle. Here, however, is a risk of unnecessary trip the sanding vehicle. This situation is economically and environmentally unfavorable. The proposed system solves the problem of measuring the temperature profile of the road and the utilization of the predictive model to determine the future development trend of temperature. The system was technically designed as a set of sensors to monitor environmental values such as the temperature of the road, ambient temperature, relative air humidity, solar radiation and atmospheric pressure at the measuring point. An important part of the proposal is prediction model which based on the inputs from sensors and historical measurements can, with some probability, predict temperature trends at the measuring point. The proposed system addresses the economic and environmental aspects of winter road maintenance.

Sensory networks are part of a solution to monitor the required physical variables in the area of interest. Their type, the used communication protocol, plays an important role in the parameter of their complexity. One of the economical solutions is the usage of a 1-wire communication network that requires only 2 physical wires. The individual sensors or the nodes of the communication network are connected in parallel. The goal was to design and implement a universal low-power 1-wire bus module with a fully implemented 1-wire standard. As a platform for the development of such module, STM32-based microcontroller was chosen. The main advantage of this solution is the ability to utilize a sensor from a large variety of available sensors with a standardized communication interface. Our solution of the universal 1-wire module provides a single interface for sensors with different communication interfaces, while it still communicates with the standard 1-wire bus controller.