Zofia Stawska

The Electrical Capacitance Tomography (ECT) imaging pipeline relies on accurate estimation of electric field distributions to compute electrode capacitances and reconstruct permittivity maps. Traditional ECT forward model methods based on the Finite Element Method (FEM) offer high accuracy but are computationally intensive, limiting their use in real-time applications. In this proof-of-concept study, we investigate the use of Graph Convolutional Networks (GCNs) for direct, one-step prediction of electric field distributions associated with a circular ECT sensor numerical model. The network is trained on FEM-simulated data and outputs of full 2D electric field maps for all excitation patterns. To evaluate physical fidelity, we compute capacitance matrices using both GCN-predicted and FEM-based fields. Our results show strong agreement in both direct field prediction and derived quantities, demonstrating the feasibility of replacing traditional solvers with fast, learned approximators. This approach has significant implications for further real-time ECT imaging and control applications.

The modern job market demands soft and future skills from both technical and non-technical professionals. It is often challenging to teach these competencies in a traditional academic setting. This paper presents an effective approach for developing these skills through a short, intensive, joint project. While our case study is an Erasmus+ program, the methodology can be applied within various frameworks. We use problem-based and active learning, along with group work, to teach. The approach also emphasizes diversity by arranging multidisciplinary student groups to work on software development tasks. In our project, less than half of the participants had a computer science background, demonstrating that these tasks are engaging for non-technical students. The multicultural and international environment of the project is crucial in a global working environment, and its brief, intense nature helps simulate real-world stressful situations. This methodology provides a practical way to prepare students for the demands of the modern workplace. The results confirmed the effectiveness of the project in developing certain key skills, though not all competencies showed a measurable increase during the event’s short duration.

Information about the paper titled "PROJECT GGULIVRR: GENERIC GAME FOR UBIQUITOUS LEARNING IN INTERACTIVE VIRTUAL AND REAL REALITIES" at IATED Digital Library

In the paper, Support Vector Machine (SVM) methods are discussed. The SVM algorithm is a very strong classification tool. Its capability in gender recognition in comparison with the other methods is presented here. Different sets of face features derived from the frontal facial image such as eye corners, nostrils, mouth corners etc. are taken into account. The efficiency of different sets of facial features in gender recognition using SVM method is examined.

The paper presents deriving of shape asymmetry measure in the dermatological sense (DASMShape). The skin lesion symmetry consists of three factors: shape, hue/color and structure. We analyze the shape asymmetry and on its basis we propose a new asymmetry degree realized in several ways. DASMShape methods verification and comparison is performed using PH2 database. The results received after optimization of the DASMShape algorithm are tested on PH2 dataset and discussion about their accuracy is provided. These results shows bigger overestimation than underestimation tendency results. DASMShape measure and its results are the initial points to derive dermatological asymmetry measure.