Abstract
The reduction in physical and social activity in elderly people degrades the aging process, causing or increasing suffering to the individual and to his family and friends. Most times, the individual well-being is related to the strength of the social bonds with the family and friends group, so it is important to keep this bonds in the various stages of life, especially in the later life, when the individual has health limitations and is living in a community centre. This paper proposes an exploratory approach, regarding the use of information technologies systems, as autonomous systems, to assist in supporting and encouraging elderly people to preserve and develop their social activities and the relationships with their family and friends social group. During the course of the aging process, some aging people have their social activity degraded due to health limitations and institutionalization in elderly care centers, in which they are admitted as residents. We propose the design of a software system, capable of running in autonomous devices, such as, robots and other consumer appliances, enabling them to recognize and interact with the users, according to their state of mind and the specific current moment context. The interactions should be simple and focused on keeping the users informed about the current life events of their family and friends, and create the opportunities for the users to interact with the participants of those events by creating interaction proposals. The systems would monitor the user's family and friends group, regarding their information and actions on the social media. The system's interactions with the user would be based on that knowledge and on the knowledge of the user's current context. An adaptive user interface would present and manage the user interactions, acting as a mediator between the user and his family and friends group.

Abstract
Aging is a process inherent to the human condition and part of the human being’s life cycle, which can be degraded by the reduction in the individual’s physical and social activity. This problem can be augmented by the context in which the person is aging, e.g., family, health and social bonds. The elderly individuals’ well-being is related to the strength of their social bonds with their family and friends group, which can be difficult to maintain in some stages of the aging process. A, recently- proposed solution is the adoption of autonomous systems capable of autonomous interactions with the elderly. Such systems are designed to be able to interpret the individual’s state of mind and the current context in order to conduct an effective interaction with the elderly person. This study focuses on the interaction design between the autonomous system and the human person, by considering the elderly individual’s context and pursuing the type of interaction that will positively influence the reinforcement or maintenance of the person’s social bonds with the family and friends groups. The study was carried out by interviewing a group of elderly people, currently living in nursing homes and with limited access to their family and friends. © Springer International Publishing AG 2017.

Abstract
Aging is a natural process that progressively introduces limitations in a person's life, which can have dramatic effects on the person's lifestyle and wellbeing and in most cases is related to the strength of the person's social bonds with the family and friends group. Therefore, it is important to maintain these bonds in the various stages of life, especially in the later life, when the individual has health limitations and may be living in a care centre. In this work, we developed an exploratory approach to the usage of ICT systems in order to autonomy assist the elderly in maintaining their social connections and relationships with family and friends. It doesn't substitutes the human care, but it should assist and encourage the elderly to preserve and develop their social activities and the relationships with their family and friends social group. We propose the design of a software system, capable of running in autonomous devices, such as, robots and other consumer appliances, enabling them to recognize and interact with the users, according to their state of mind and the specific current moment context. The interactions should be simple and focused on keeping the users engaged and informed about the current life events of their family and friends, and create the opportunities for the users to interact with the participants of those events by creating interaction proposals. On a technical level, the system should have knowledge about the user and be able to acquire and update context information from social media, video cameras, email, etc, regarding the user and the persons from his family and friends groups, in order to develop meaningful interactions with the user. An adaptive user interface would present and manage the interactions, acting as a mediator between the user and his family and friends group.

Abstract
In the later stages of the aging process, an elderly person might need the help of a family member or a caregiver. Technology can be used to help to take care of elderly persons. Autonomous systems, using special interfaces, can collect information from elderly people, which might be useful to predict and recognize health related problems or physical security problems in real time. The emerging technology of image processing, in particular, the emotion recognition, can be a good option to use in elderly care support systems. In this article, we implemented a Microsoft Azure – Emotion SDK to recognize emotion of elderly that able to detect faces and recognize emotions in real time and to be used for elderly care support. The analysis is done with an online video stream, which analyzes facial expression, so that in case of a critical emotion, e.g., if an elderly is very sad or crying, it will inform a caregiver or related entity. From the experiment, we concluded that emotion recognition is a reliable technology to be implemented in real time elderly care. © Springer International Publishing AG, part of Springer Nature 2018.

Abstract
Facial expression analysis has a wide area of applications including health, psychology, sports etc. In this study, we explored different methods of automatic classification of exercise intensities using facial image processing of a subject performing exercise on a cycloergometer during an incremental standardized protocol. The method can be implemented in real time using facial video analysis. The experiments were done with images extracted from a 12 min HD video collected in laboratorial normalized settings (TechSport from the University of Trás-os-Montes e Alto Douro) with a static camera (90° angle with face and camera). The time slot for video to extract images for a particular class of exercise intensity is correspondence to the incremental heart rate. The facial expression recognition has been performed mainly in two steps: facial landmark detection and classification using the facial landmarks. Luxand application was used to detect 70 landmarks were detect using the adaptation of code available in Luxand application and we applied machine learning classification algorithms including discriminant analysis, KNN and SVM to classify the exercise intensities from the facial images. KNN algorithms presents up to 100% accuracy in classification into 2 and 3 classes. The distances between a lowermost landmark of the faces, which is indicated in landmark number 11 in the Luxand application, and the 26 landmarks around mouth were calculated and considered as features vector to train and test the classifier. Separate experiments were done for classification into two, three, and four classes and the accuracy of each algorithm was analyzed. From the overall results, classification into two and three classes was easy and resulted in very good classification performance whereas the classification with four classes had poor classification performance in each algorithm. Preliminary results suggest that distinguishing more levels of exertion, might require additional feature variables. © 2018 IEEE.

Abstract
Facial expressions are a spontaneous way of perceiving emotions, which can provide information related to the cognitive state of a person. Facial expression recognition of the elderly is an important aid to better care them, according to their state of mind, although it can be a difficult task because their expressions might not be as easily perceived as those from younger persons. We proposed a model to classify the facial expressions of the elderly, presenting the differences between facial expression recognition in the elder and in other age group, as well as methods to surpass these difficulties. Viola Jones with Haar Features was used to extract the faces and Gabor Filter to extract the facial characteristics. These characteristics are classified using a Multiclass Support Vector Machine. We got an accuracy of 90.32%, 84.61% and 66.6%, when detecting the neutral state, happiness and sadness respectively in the elderly. In the other age group, we got an accuracy of 95.24%, 88.57%, and 80%, while detecting the neutral, happiness, and sadness states and concluded that aging influences negatively the facial expressions recognition tasks.