Sustainable development can be achieved when economic development does not produce environmental deterioration. In this context, the aim of the paper is to evaluate the effects of economic development on GHG emissions in the Baltic States (Latvia, Letonia, and Lithuania), and in Hungary, the Czech Republic, Slovakia, and Poland (the Visegrád Group or V4 countries) in the period of 1996–2019. The study introduces dynamic ARDL panels in the context of the traditional environmental Kuznets curve (EKC) and renewable Kuznets curve (RKC). The results indicated an inverse-N-shaped and a U-shaped pattern. Energy consumption and labour productivity enhanced pollution, while domestic credit to the private sector, as a share of GDP, and renewable energy consumption supported environmental protection. The implications of these results might help these countries to achieve the targets of the European Green Deal related to the reduction of pollution and the attainment of net zero emissions by 2050. However, national regulations should further promote the use of renewable energy sources.

Contemporary office building standards require the installation of advanced HVAC systems, which, alongside industrial processes, are significantly responsible for energy consumption. While the literature describes numerous multi-parameter, deep artificial neural networks that are highly complex but poorly explainable (black box), commercial control systems must be based on simple-to-implement, easily adaptable intelligent predictive models whose reliability stems from their monitorability and explainability. The study verified several edge-oriented approaches using machine learning techniques for short- and medium-term predictions (1 day) with relatively high granularity (15 minutes). High granularity of time intervals, combined with high prediction reliability, not only provide a practical opportunity to optimize energy consumption, but also to increase the efficiency of renewable energy sources exploitation. Operational, high granularity predictions can also be used to detect anomalies and attacks, as required by modern cybersecurity rules.

In the paper a concept of active hypercontours as well as a formalized description of contextual classification and relationship between them are presented. The idea of active hypercontours generalizes traditional active contour methods which are extensively developed in image analysis. The proposed concepts can enable an incorporation of techniques specific for traditional contextual and non-contextual classification problems to active contour approach and vice versa.

Geometric deep learning (GDL) generalizes convolutional neural networks (CNNs) to non-Euclidean domains. In this work, a GDL technique, allowing the application of CNN on graphs, is examined. It defines convolutional filters with the use of the Gaussian mixture model (GMM). As those filters are defined in continuous space, they can be easily rotated without the need for some additional interpolation. This, in turn, allows constructing systems having rotation equivariance property. The characteristic of the proposed approach is illustrated with the problem of ear detection, which is of great importance in biometric systems enabling image based, discrete human identification. The analyzed graphs were constructed taking into account superpixels representing image content. This kind of representation has several advantages. On the one hand, it significantly reduces the amount of processed data, allowing building simpler and more effective models. On the other hand, it seems to be closer to the conscious process of human image understanding as it does not operate on millions of pixels. The contributions of the paper lie both in GDL application area extension (semantic segmentation of the images) and in the novel concept of trained filter transformations. We show that even significantly reduced information about image content and a relatively simple, in comparison with classic CNN, model (smaller number of parameters and significantly faster processing) allows obtaining detection results on the quality level similar to those reported in the literature on the UBEAR dataset. Moreover, we show experimentally that the proposed approach possesses in fact the rotation equivariance property allowing detecting rotated structures without the need for labor consuming training on all rotated and non-rotated images.