Abstract—The prevalence of dementia is expected to increment in the next decades as the elderly population grows and ages. Hence, Alzheimer’s Disease (AD), as the most frequent dementia, will be more problematic from a socioeconomic point of view. Different diagnostic criteria have been proposed by clinicians for the early diagnosis of AD. After discarding the longitudinal and prognosis articles, a selection of articles from the last decade and based on Artificial Neural Networks (ANNs) was collated from the PubMed database, and complemented with researches extracted from others. The latest trends on this field were discovered in these selected articles, which were later discussed. Only articles based whether on shallow ANNs, Deep Learning (DL) or a mix of both were included. The total number of cross-sectional articles that complied with our selection criteria was 154. Convolutional Neural Networks (CNNs) combined with neuroimaging has been the most popular approach, yielding very good performance results. Approaches based on nonneuroimaging techniques, such as gait, genetics, speech and neuropsychological tests, were less common but have their own advantages. Multimodality solutions may become even more prevalent in the near future. Similarly, novel diagnostic criteria will appear and the popularity of currently not-so-common ones will expand. A new proposal emerged from these trends, which is based on ontogenetic ANNs.

In lost foam process, application of protective refractory ceramic coatings on patterns made from foamed polystyrene plays a very important part and decides about the quality of produced castings. The coating should be made from a material of suitable strength and good permeability to give free way of escape to gaseous products which are formed due to the thermal destruction of a pattern. In this work an attempt has been made to determine the criteria for technological estimation of these coatings. A device cooperating with the apparatus for determination of the moulding sand permeability was designed and manufactured. To enable a comparison of the strength of various tested coatings, the relevant equations have been derived. In the present investigation several types of ceramic coatings were applied and their composition was based on the following materials: quartz flour, zircon flour, mullite, hydrolysed ethyl silicate - 40, copolymer silicate binder, sizol 0-30. The thickness of the examined coatings was 1.0±0.1 mm and 1.5±0.1 mm for single-layer and double-layer coatings, respectively.