Multidisciplinary approach for developing a new robotic system for domiciliary assistance to elderly people

Novel Technological Solutions for Assessment, Treatment, and Assistance in Mild Cognitive Impairment

Alzheimer's disease, and dementia, represent a common cause of disability and one of the most relevant challenges in the health world. In addition, these conditions do not have, at moment, a pharmacological treatment that can stop the pathological progress. Mild cognitive impairment (MCI), defined as the borderline between normal aging and early dementia, represents a meaningful field of study because, in the transition to dementia, clinicians have defined a useful therapeutic window. Additionally, due to the lack of effective pharmacological interventions, recent years have seen an increase in research into new technological solutions to assess, stimulate, and assist patients afflicted with Alzheimer's disease. This review aims to outline the use of information and communication technologies in the field studying MCI. Particularly, the goal is to depict the framework and describe the most worthwhile research efforts, in order to display the current technologies available, describe the research objectives, and delineate prospective future researches. Regarding data sources, the research was conducted within three databases, PubMed Central, Web of Science, and Scopus, between January 2009 and December 2017. A total of 646 articles were found in the initial search. Accurate definition of the exclusion criteria and selection strategy allowed identification of the most relevant papers to use for the study. Finally, 56 papers were fully evaluated and included in this review. Three major clinical application areas have been portrayed, namely “Cognitive Assessment,” “Treatment,” and “Assistance.” These have been combined with three main technological solutions, specifically “Sensors,” “Personal Devices,” and “Robots.” Furthermore, the study of the publications time series illustrates a steadily increasing trend, characterized by the enrollment of small groups of subjects, and particularly oriented to the subjects assistance using robots companion. In conclusion, despite the new technological solutions for people with MCI have received much interest, particularly regarding robots for assistance, nowadays it still owns vast room for improvement.

A Human Activity Recognition System Based on Dynamic Clustering of Skeleton Data

Human activity recognition is an important area in computer vision, with its wide range of applications including ambient assisted living. In this paper, an activity recognition system based on skeleton data extracted from a depth camera is presented. The system makes use of machine learning techniques to classify the actions that are described with a set of a few basic postures. The training phase creates several models related to the number of clustered postures by means of a multiclass Support Vector Machine (SVM), trained with Sequential Minimal Optimization (SMO). The classification phase adopts the X-means algorithm to find the optimal number of clusters dynamically. The contribution of the paper is twofold. The first aim is to perform activity recognition employing features based on a small number of informative postures, extracted independently from each activity instance; secondly, it aims to assess the minimum number of frames needed for an adequate classification. The system is evaluated on two publicly available datasets, the Cornell Activity Dataset (CAD-60) and the Telecommunication Systems Team (TST) Fall detection dataset. The number of clusters needed to model each instance ranges from two to four elements. The proposed approach reaches excellent performances using only about 4 s of input data (~100 frames) and outperforms the state of the art when it uses approximately 500 frames on the CAD-60 dataset. The results are promising for the test in real context.