associated scientific and non-scientific publications

Publications

2021

PETRA 2021: The 14th PErvasive Technologies Related to Assistive Environments Conference

Abstract: The world’s population is ageing rapidly while cognitive impairment in older ages is more evident than ever. Hence, the health and wellbeing among the elderly is an issue of paramount importance. The speedy growth of technology and its application within healthcare has advanced computerized cognitive interventions, which aim to delay the onset and potential progression of cognitive decline. Consequently, the traditional cognitive interventions have made a swift to novel multimedia systems to promote independent, active and healthy ageing. The primary objective of the present study is to introduce an innovative computerized cognitive gamified training and social activation program for health and mildly cognitive impaired older adults. The platform is designed as an extension and adaptation of a previous computerized cognitive training program called ‘SOCIABLE’. Evaluation of the newly designed platform through a single-arm feasibility study followed by a full randomized double-blind controlled trial is recommended as future steps for this piece of work.

By Kitty Kioskli and Eva Danassi

IEEE Access (Volume: 9)

Abstract: Most of the established neural network architectures in computer vision are essentially composed of the same building blocks (e.g., convolutional, normalization, regularization, pooling layers, etc.), with their main difference being the connectivity of these components within the architecture and not the components themselves. In this paper we propose a generalization of the traditional average pooling operator. Based on the requirements of efficiency (to provide information without repetition), equivalence (to be able to produce the same output as average pooling) and extendability (to provide a natural way of obtaining novel information), we arrive at a formulation that generalizes average pooling using the Zernike moments. Experimental results on Cifar 10 , Cifar 100 and Rotated MNIST data-sets showed that the proposed method was able to outperform the two baseline approaches, global average pooling and average pooling 2×2 , as well as the two variants of Stochastic pooling and AlphaMEX in every case. A worst-case performance analysis on Cifar-100 showed that significant gains in classification accuracy can be realised with only a modest 10% increase in training time.

By Thomas Theodoridis, Kostas Loumponias, Nicholas Vretos, and Petros Daras

2020

MDPI Open Access Journals

On 30 October, several EU-funded initiatives participated in an online workshop organised within the general framework of the Sustainable Places Conference 2020. The workshop, titled “Sustainable Housing Supporting Health and Wellbeing,” centred on the benefits of and the ways to create living spaces fit for all walks of life. This paper summarises the proceedings.

By Régis Decorme, Silvia Urra, Olatz Nicolas, Carina Dantas, Annelore Hermann, Gustavo Hernández Peñaloza, Federico Álvarez García, Aline Ollevier, M. Charalampos Vassiliou, and Willeke van Staalduinen