Education, like the large majority of domains, has been impacted by the rapid development of communications and technology. What was perceived before as an ideal, i.e., the enhancement of the learning process through modern techniques, now it has been rapidly transformed into a mandatory requirement due to the current COVID-19 pandemic . Edutainment applications…
Determining the critical nodes in a network given a certain network measure is a computational challenging problem that requires the design of adaptive and scalable algorithms. The number of connected components in a graph is an example of such a measure: in this case the nodes considered critical are those that, if removed from…
Critical node detection is a crucial task in network analysis. In this article a new problem is proposed, the critical node detection in hypergraphs, which are a generalization of the ‘traditional’ graphs. A genetic algorithm is proposed to solve this problem and as an application an inflation dataset is transformed in a hypergraph and…
An important problem in network science is finding relevant community structures in complex networks. A community structure is a partition of the network nodes into clusters or modules, such that each cluster is densely connected. Current community detection algorithms have time complexity, centralization, and scalability issues. In this paper, to solve this problem, we…
Proteins are essential molecules, that must correctly perform their roles for the good health of living organisms. The majority of proteins operate in complexes and the way they interact has pivotal influence on the proper functioning of such organisms. In this study we address the problem of protein–protein interaction and we propose and investigate…
Fall detection (FD) has been the focus of many research studies during the last years. Developing reliable FD systems is relevant, for instance, to provide support to the elderly population in their everyday life. Besides, the generalization of the use of wearable devices (and more specifically, on-wrist devices) to measure the daily activity strongly…
Citare Marginean, R., Andreica, A., Diosan, L., Bálint, Z., Stochastic remote neighborhoods control GrowCut’s segmentation semanticsMECO45 45th Conference of the Middle European Cooperation in Statistical Physics , 2020
Education has suffered multiple changes due to technological progress. Even though the current generation of preschoolers (aged 3 to 6 years in our country) is called digital native, there is a lack of focus on introducing technology enabled learning tools for them. This paper presents our approach to designing smart learning experiences for a…
We present a new type of optimization algorithms, adapted for neural network training. These algorithms are based upon sequential operator splitting technique for some associated dynamical systems. Furthermore, we investigate through numerical simulations the empirical rate of convergence of these iterative schemes toward a local minimum of the loss function, with some suitable choices…
This paper proposes a novel method for supervised optimization of cellular automata rules using curriculum learning. The optimized edge detector manages to generalize a rule from synthetic data that is applicable to magnetic resonance images, removing the need for manual annotation of medical data. The method achieves competitive results with classical edge detectors on…