The use of games for non-ludic purposes, the serious games, is an interesting branch of science that has shown important results. With the advent of the pandemic that has made access to rehabilitation centres more problematic for patients with cognitive rehabilitation needs, the importance of being able to exercise these patients safely in their own homes has emerged strongly. Many studies show that immediate action and appropriate, specific rehabilitation can guarantee satisfactory results. Appropriate therapy is based on key factors to be taken into account such as frequency, intensity and specificity of the exercises. The aim of our work is to define a pathway for the creation of open source digital products that can allow access in any moment to a virtual environment through which patients who have suffered limitations in their cognitive abilities can exercise and recover all or part of these abilities in the shortest possible time. In view of the spread of IoT devices capable of easily monitoring various vital parameters, we propose with our system a low-cost and very efficient solution that can provide the doctor and therapist not only with quantitative data on the exercises performed (number and type of exercises, time spent, results obtained) but also an overview of vital parameters, so as to observe any states of agitation or excessive effort in completing the exercise.

This study analyses some of the leading technologies for the construction and configuration of IT infrastructures to provide services to users. For modern applications, guaranteeing service continuity even in very high computational load or network problems is essential. Our configuration has among the main objectives of being highly available (HA) and horizontally scalable, that is, able to increase the computational resources that can be delivered when needed and reduce them when they are no longer necessary. Various architectural possibilities are analysed, and the central schemes used to tackle problems of this type are also described in terms of disaster recovery. The benefits offered by virtualisation technologies are highlighted and are bought with modern techniques for managing Docker containers that will be used to build the back-end of a sample infrastructure related to a use-case we have developed. In addition to this, an in-depth analysis is reported on the central autoscaling policies that can help manage high loads of requests from users to the services provided by the infrastructure. The results we have presented show an average response time of 21.7 milliseconds with a standard deviation of 76.3 milliseconds showing excellent responsiveness. Some peaks are associated with high-stress events for the infrastructure, but the response time does not exceed 2 seconds even in this case. The results of the considered use case studied for nine months are presented and discussed. In the study period, we improved the back-end configuration and defined the main metrics to deploy the web application efficiently.

This paper provides a methodology for the production of synthetic images for training neural networks to recognise shapes and objects. There are many scenarios in which it is difficult, expensive and even dangerous to produce a set of images that is satisfactory for the training of a neural network. The development of 3D modelling software has nowadays reached such a level of realism and ease of use that it seemed natural to explore this innovative path and to give an answer regarding the reliability of this method that bases the training of the neural network on synthetic images. The results obtained in the two proposed use cases, that of the recognition of a pictorial style and that of the recognition of migrants at sea, leads us to support the validity of the approach, provided that the work is conducted in a very scrupulous and rigorous manner, exploiting the full potential of the modelling software. The code produced, which automatically generates the transformations necessary for the data augmentation of each image, and the generation of random environmental conditions in the case of Blender and Unity3D software, is available under the GPL licence on GitHub. The results obtained lead us to affirm that through the good practices presented in the article, we have defined a simple, reliable, economic and safe method to feed the training phase of a neural network dedicated to the recognition of objects and features, to be applied to various contexts.

The paper concludes the first research on mouth-based Emotion Recognition (ER), adopting a Transfer Learning (TL) approach. Transfer Learning results paramount for mouth-based emotion ER, because a few data sets are available, and most of them include emotional expressions simulated by actors, instead of adopting a real-world categorization. Using TL we can use fewer training data than training a whole network from scratch, thus more efficiently fine-tuning the network with emotional data and improving the convolutional neural network accuracy in the desired domain. The proposed approach aims at improving the Emotion Recognition dynamically, taking into account not only new scenarios but also modified situations with respect to the initial training phase, because the image of the mouth can be available even when the whole face is visible only in an unfavourable perspective. Typical applications include automated supervision of bedridden critical patients in an healthcare management environment, or portable applications supporting disabled users having difficulties in seeing or recognizing facial emotions. This work takes advantage from previous preliminary works on mouth-based emotion recognition using CNN deep-learning, and has the further benefit of testing and comparing a set of networks on large data sets for face-based emotion recognition well known in literature. The final result is not directly comparable with works on full-face ER, but valorizes the significance of mouth in emotion recognition, obtaining consistent performances on the visual emotion recognition domain.

In recent years, the need to contain healthcare costs due to the growing public debt of many countries, combined with the need to reduce costly travel by patients unable to move autonomously, have captured the attention of public administrators towards tele-rehabilitation. This trend has been consolidated overwhelmingly following the Covid-19 pandemic, which has made it precarious, difficult and even dangerous for patients to access hospital facilities. We present a platform devoted to the rapid prototyping of Virtual Reality based, cognitive tele-rehabilitation exercises. Patients who experienced injury or pathology need to practice a continuous training in order to recover functional abilities, and the therapist need to monitor the outcomes of such practices. The Virtual Reality exercises are designed on Unity 3D to empower the therapist to set up personalised exercises in a easy way, enabling the patient to receive personalized stimuli, which are crucial for a positive outcome of the practice. Furthermore, the reaction speed of the system is of fundamental importance, as the temporal evolution of the scene must proceed parallel to the patient’s movements, to ensure an effective and efficient therapeutic response. So, we optimized the Virtual Reality application in order to make the loading phase and the startup phase as fast as possible and we have tested the results obtained with many devices: in particular computers and smartphones with different operating systems and hardware. The implemented platform integrates in Nu!Reha system®, a tele-rehabilitation set of services that helps patients to recover cognitive and functional capabilities.