No abstract

In this work we further refi ne and improve the neural network based ionospheric characteristic's foF2 predictor, which is actually a neural network autoregressive model with additional input signals (NNARX). Our analysis is focused on choice of X parts of NNARX model in order to capture middle and long term dependencies. Daily distribution of prediction error suggests need for structural changes of the neural network model, as well as adaptation of running average lengths used for determination of X inputs. Generalisation properties of proposed neural predictor are improved by carefully designed pruning procedure with additional regularisation term in criterion function. Some results from the NNARX model are presented to illustrate the feasibility of using such a model as ionospheric storm forecasting technique.

The impact of the COVID-19 pandemic has generated new challenges in the work of social welfare institutions, particularly in the area of providing support in alternative forms of care, such as foster care. The need for support during the pandemic was very significant and necessary because foster families fall into the category of vulnerable groups, especially because they provide care for children displaced from their primary (biological) family. In addition to insufficient institutional support during the pandemic, communication with primary families was aggravated, which has had a negative impact on foster children and their needs. The Faculty of Law in Osijek is a partner institution in the Project "Zajedno do doma" (Foster Home for Children), funded by the EU and organized by the World Youth Federation Croatia. For the project purposes, a survey on institutional support to foster families was conducted from August to October 2021. The collected data will be presented and analyzed in this paper, in order to identify the needs of foster families, the relevant forms of institutional support, and the difficulties that foster families experience in case of insufficient support. This pilot research on the attitudes of experts and foster careers is a quantitative basis for further qualitative research on foster care in direct contact with foster carers. Based on this research, the authors have developed foster care guidelines, with special emphasis on the challenges of providing support during the COVID-19 pandemic.

In this work we further refi ne and improve the neural network based ionospheric characteristic's foF2 predictor, which is actually a neural network autoregressive model with additional input signals (NNARX). Our analysis is focused on choice of X parts of NNARX model in order to capture middle and long term dependencies. Daily distribution of prediction error suggests need for structural changes of the neural network model, as well as adaptation of running average lengths used for determination of X inputs. Generalisation properties of proposed neural predictor are improved by carefully designed pruning procedure with additional regularisation term in criterion function. Some results from the NNARX model are presented to illustrate the feasibility of using such a model as ionospheric storm forecasting technique.