Complex industrial systems run the different pieces of software in several interconnected physical layers. The software update in such an environment must be performed in the shortest possible period with the lowest possible resource usage. Namely, it is critical to minimize the data traffic, decrease software downtime, and reduce the impact of the transitional stage during the update process. To meet these requirements and to unify the update process, the common software node structure along with a hybrid software deployment strategy is proposed. The hybrid strategy is defined as a combination of the existing and well-tested techniques—blue/green, canary, and feature flags. The main aim was to utilize their positive sides and to obtain a better overall effect. The approach was tested in the simulation environment, based on the realistic factory layout, and running the software related to the enterprise resource planning (ERP) level. For successful updates, the proposed hybrid deployment method reduced downtime on server nodes to less than 5% and on client nodes to a half compared with the standard approach. The volume of data traffic reduction in a configuration with sentinel nodes is reduced by one-third. The presented results look promising, especially in cases of erroneous updates when a roll back is needed, where the downtime on the server nodes is reduced to the level of 3%. Achieved results are used to define the set of recommendations that could be extended for the other software layers, followed by a discussion about further potential problems and strategy variations.

As the Internet of Things (IoT) nodes become one of the cornerstones of Industry 4.0, they tend to be incorporated into every aspect of production automation. This paper addresses the challenge of designing low-power IoT nodes based on standardized components for deployment in remote, off-grid, industrial, and hazardous environments where energy efficiency and autonomy are critical. The proposed design integrates hardware-software co-design, replacing standard hardware setup with energy-efficient components, solar-powered batteries, and dynamic working modes to reduce energy consumption. Software elements were designed with the possibility of over-the-air updates and reconfiguration. Next, battery charging routines are optimized, and the node is integrated into a cloud-based digital twin with centralized control over the complete operation cycle. The proposed node architecture achieves an energy reduction of up to 50% and, in some configurations, reduces consumption by up to one-tenth compared to conventional designs. The additional result is a set of design recommendations when the standard components must be adapted for harsh environments.

The Internet of Things (IoT) nodes dedicated to off-grid usage must fully rely on their battery power for continuous operation. In that sense battery charging process design is one of the focal points for the complete system design. Nowadays, battery charging, for such devices, usually relies on solar power which is not, unfortunately, the source of constant energy. Both environmental and constructive elements could easily make a negative impact on the charging process and reduce the amount of collected energy. Furthermore, if the IoT nodes are in hazardous areas, they are less accessible, and the value of effective battery management is even higher. The requirements for the battery charging process implementation are considered as opposite – on one hand, the requirement is to run charging with the lowest possible frequency and not up to 100%, and on the other hand, the battery should always have enough energy to maintain regular operation. In this research, we present the structure of the custom-developed IoT node based on the ECS32 system-on-a-chip dedicated to operating in remote industrial areas, and with an accent of its battery charging routine. The current routine is based on a standard thresholds approach and improved by including consumption estimates for the predefined periods. This paper presents the first results and should pave the ground for further upgrades. In addition, the comparison with state-of-the-art charging approaches is presented, as the guidelines for future work.

This paper aims to leverage artificial intelligence (AI) to assist physicians in utilizing advanced deep learning techniques integrated into developed models within electronic health records (EHRs) in medical information systems (MISes), which have been in use for over 15 years in health centers across the Republic of Serbia. This paper presents a human-centered AI approach that emphasizes physician decision-making supported by AI models. This study presents two developed and implemented deep neural network (DNN) models in the EHR. Both models were based on data that were collected during the COVID-19 outbreak. The models were evaluated using five-fold cross-validation. The convolutional neural network (CNN), based on the pre-trained VGG19 architecture for classifying chest X-ray images, was trained on a publicly available smaller dataset containing 196 entries, and achieved an average classification accuracy of 91.83 ± 2.82%. The DNN model for optimizing patient appointment scheduling was trained on a large dataset (341,569 entries) and a rich feature design extracted from the MIS, which is daily used in Serbia, achieving an average classification accuracy of 77.51 ± 0.70%. Both models have consistent performance and good generalization. The architecture of a realized MIS, incorporating the positioning of developed AI tools that encompass both developed models, is also presented in this study.