The COVID‐19 crisis is having a significant impact on the quality of life and future of young people; it can also lead to disruption in education. A disruption would pose a severe threat to the entire society in the postcrisis period. Therefore, educational institutions must respond quickly and ensure the continuity of the educational processes. Our research goal has been to develop and implement a model enabling a rapid transition from the traditional to the distance learning model in a state of emergency. Our focus has been on conceiving technical, organizational, and pedagogical changes that educational organizations need to implement to enable different interaction methods, ensure continuity, and provide high‐quality education. We have defined and implemented a model, which is described in detail in this paper, thus giving guidelines for a rapid transition to distance learning, which is not restricted to the crisis times only. We have evaluated our approach by monitoring the IT solutions and surveying students and teachers at the School of Computing, Union University of Belgrade. The results indicate the high satisfaction of these participants in the educational processes. They imply the acceptability of prolonged distance learning, if needed, and embrace the hybrid education model for the next generation of students.

The academic and professional community has recently started to develop the concept of 6G networks. The scientists have defined key performance indicators and pursued large-scale automation, ambient sensing intelligence, and pervasive artificial intelligence. They put great efforts into implementing new network access and edge computing solutions. However, further progress depends on developing a more flexible core infrastructure according to more complex QoS requirements. Our research aims to provide 5G/6G core flexibility by customizing and optimizing network slices and introducing a higher level of programmability. We bind similar services in a group, manage them as a single slice, and enable a higher level of programmability as a prerequisite for dynamic QoS. The current 5G solutions primarily use predefined queues, so we have developed highly flexible, dynamic queue management software and moved it entirely to the application layer (reducing dependence on the physical network infrastructure). Further, we have emulated a testbed environment as realistically as possible to verify the proposed model capabilities. Obtained results confirm the validity of the proposed dynamic QoS management model for configuring queues’ parameters according to the service management requirements. Moreover, the proposed solution can also be applied efficiently to 5G core networks to resolve complex service requirements.

Papillary thyroid carcinoma (PTC) is generally considered an indolent cancer. However, patients with cervical lymph node metastasis (LNM) have a higher risk of local recurrence. This study evaluated and compared four machine learning (ML)-based classifiers to predict the presence of cervical LNM in clinically node-negative (cN0) T1 and T2 PTC patients. The algorithm was developed using clinicopathological data from 288 patients who underwent total thyroidectomy and prophylactic central neck dissection, with sentinel lymph node biopsy performed to identify lateral LNM. The final ML classifier was selected based on the highest specificity and the lowest degree of overfitting while maintaining a sensitivity of 95%. Among the models evaluated, the k-Nearest Neighbor (k-NN) classifier was found to be the best fit, with an area under the receiver operating characteristic curve of 0.72, and sensitivity, specificity, positive and negative predictive values, F1 and F2 scores of 98%, 27%, 56%, 93%, 72%, and 85%, respectively. A web application based on a sensitivity-optimized kNN classifier was also created to predict the potential of cervical LNM, allowing users to explore and potentially build upon the model. These findings suggest that ML can improve the prediction of LNM in cN0 T1 and T2 PTC patients, thereby aiding in individual treatment planning.

The rapid expansion of new technologies and services significantly affects society’s development and initiates significant changes within public administration. Many have decided to implement citizen-centric, data-driven, and performance-focused governance and prepare to transform the existing e-government system into a smart government. Along the way, they have encountered problems such as flaws in existing legislation and in the integration of heterogeneous infrastructure from technical, financial, and privacy perspectives. We propose a new approach to information system modeling that introduces an integration layer for existing databases and services and suggests the application of several innovative technologies to achieve better problem-solving, optimal utilization of resources, and policy innovation. To test the effectiveness of the proposed solution, we have used corresponding weighted digraph models to confirm that the proposed solution achieves the desired effects. We have used the time required to collect documents to measure similarity. The obtained results prove the efficiency of the proposed model and indicate that the same model could be used elsewhere in public administration.

Dynamic and efficient resource allocation is critical for Software-Defined Networking (SDN) enabled sixth-generation (6G) networks to ensure adaptability and optimized utilization of network resources. This paper proposes a reinforcement learning (RL)-based framework that integrates an actor–critic model with a modular SDN interface for fine-grained, queue-level bandwidth scheduling. The framework further incorporates a stochastic traffic generator for training and a virtualized multi-slice platform testbed for a realistic beyond-5G/6G evaluation. Experimental results show that the proposed RL model significantly outperforms a baseline forecasting model: it converges faster, showing notable improvements after 240 training epochs, achieves higher cumulative rewards, and reduces packet drops under dynamic traffic conditions. Moreover, the RL-based scheduling mechanism exhibits improved adaptability to traffic fluctuations, although both approaches face challenges under node outage conditions. These findings confirm that queue-level reinforcement learning enhances responsiveness and reliability in 6G networks, while also highlighting open challenges in fault-tolerant scheduling.

In this paper, a modular platform which provides student services for smart educational environment is described. The platform represents a point of mutual integration of various services, such as hosting platform for students? projects, platform for integrating SMS service with students? web applications, Internet of Things platform which enables acquiring data from sensors distributed within the University building and controlling various actuators. Platform is deployed as a part of Smart Learning environment. It is integrated with single sign on service and it uses CAS and Oauth2. REST API is also provided. PHP Symfony framework, relational and non-relational databases are used for deploying the platform. The platform was evaluated and tested.