Corpus ID: 4833398

Machine Learning and Social Robotics for Detecting Early Signs of Dementia

  title={Machine Learning and Social Robotics for Detecting Early Signs of Dementia},
  author={Patrik Jonell and Joseph Mendelson and Thomas Storskog and G{\"o}ran Hagman and Per {\"O}stberg and Iolanda Leite and Taras Kucherenko and Olga Mikheeva and Ulrika Akenine and Vesna Jelic and Alina Solomon and Jonas Beskow and Joakim Gustafson and Miia Kivipelto and Hedvig Kjellstr{\"o}m},
This paper presents the EACare project, an ambitious multi-disciplinary collaboration with the aim to develop an embodied system, capable of carrying out neuropsychological tests to detect early signs of dementia, e.g., due to Alzheimer's disease. The system will use methods from Machine Learning and Social Robotics, and be trained with examples of recorded clinician-patient interactions. The interaction will be developed using a participatory design approach. We describe the scope and method… Expand
A Wizard of Oz Approach to Robotic Therapy for Older Adults With Depressive Symptoms
A Wizard of Oz system allowing a human therapist to control a humanoid robot through a graphical user interface, including natural speech for natural conversations, which enables the robot to be stationed in, for example, a care home. Expand
Robots, AI, and Cognitive Training in an Era of Mass Age-Related Cognitive Decline: A Systematic Review
The results of this systematic review suggest that, overall, the utilization of humanoid and pet robots produce improvements in cognition and markers of social and emotional health and engagement; however, when embedded with AI with the capacity for Deep Learning the potential of robotic technology to aggressively meet the needs of individuals experiencing age-related cognitive decline will be significant. Expand
Data Driven Non-Verbal Behavior Generation for Humanoid Robots
This work aims to learn a data-driven model for generating non-verbal behavior (in a form of a 3D motion sequence) for humanoid robots based on a popular and powerful deep generative model: Variation Autoencoder (VAE). Expand
Interaction and collaboration in robot-assisted language learning for adults
This article analyses how robot–learner interaction in robot-assisted language learning (RALL) is influenced by the interaction behaviour of the robot. Since the robot behaviour is to a large exten...
Learning Non-verbal Behavior for a Social Robot from YouTube Videos
Non-verbal behavior is crucial for positive perception of humanoid robots. If modeled well it can improve the interaction and leave the user with a positive experience, on the other hand, if it is ...
Using Social and Physiological Signals for User Adaptation in Conversational Agents
This thesis work aims at developing methods for utilizing both social and physiological signals emitted by humans in order to adapt the output of the conversational agent, allowing for an increase in conversation quality. Expand
Robot Interaction Styles for Conversation Practice in Second Language Learning
Four different interaction styles for the social robot Furhat acting as a host in spoken conversation practice with two simultaneous language learners have been developed, based on interaction stylesExpand
Let's Face It: Probabilistic Multi-modal Interlocutor-aware Generation of Facial Gestures in Dyadic Settings
This paper introduces a probabilistic method to synthesize interlocutor-aware facial gestures - represented by highly expressive FLAME parameters - in dyadic conversations and shows that the model successfully leverages the input from the interLocutor to generate more appropriate behavior. Expand


Speech Interaction with Personal Assistive Robots Supporting Aging at Home for Individuals with Alzheimer’s Disease
A baseline assessment of the types of technical and communicative challenges that will need to be overcome for robots to be used effectively in the home for speech-based assistance with daily living is provided. Expand
Narratives and emotions in seniors affected by dementia: A comparative study using a robot and a toy
  • Iolanda Iacono, P. Marti
  • Psychology, Computer Science
  • 2016 25th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)
  • 2016
Results show that interacting with Paro, unlike Sugar, stimulates storytelling, encouraging interaction among participants and supporting the construction of more emotionally intense content. Expand
Montreal Cognitive Assessment (MoCA): Concept and Clinical Review
The Montreal Cognitive Assessment (MoCA) is a cognitive screening instrument developed to detect mild cognitive impairment in patients with Alzheimer’s disease and other pathologies in cognitively impaired subjects who scored in the normal range on the MMSE. Expand
PARO robot affects diverse interaction modalities in group sensory therapy for older adults with dementia
It is shown PARO provides indirect benefits for users by increasing their activity in particular modalities of social interaction, including visual, verbal, and physical interaction, which vary between primary and non-primary interactors. Expand
Mutual gaze in Alzheimer's disease, frontotemporal and semantic dementia couples.
Reduced mutual gaze was associated with greater behavioral disturbance as measured by the Neuropsychiatric Inventory, especially on the disinhibition and apathy subscales and point to subtle differences between the three types of dementia in the social realm that help to illuminate the nature of the disease process and could aid in differential diagnosis. Expand
Assistive Robotics and an Ecology of Elders Living Independently in Their Homes
An ethnographic study of aging adults who live independently in their homes to understand how robotic products might assist these people, helping them to stay independent and active longer. Expand
Evidence of the Sensitivity of the MoCA Alternate Forms in Monitoring Cognitive Change in Early Alzheimer's Disease
The results demonstrate that the MoCA is capable of detecting change over time and seems to be a valid tool with small to moderate sensitivity for monitoring cognitive change in early AD. Expand
Deep Representation Learning for Human Motion Prediction and Classification
The results show that deep feedforward networks, trained from a generic mocap database, can successfully be used for feature extraction from human motion data and that this representation can be used as a foundation for classification and prediction. Expand
Domestic Robots for Older Adults: Attitudes, Preferences, and Potential
The population of older adults in America is expected to reach an unprecedented level in the near future. Some of them have difficulties with performing daily tasks and caregivers may not be able toExpand
Eye movements in Alzheimer's disease.
AD-related changes to fundamental eye movements, such as saccades and smooth pursuit motion, are reviewed, in addition to changes to eye movement patterns during more complex tasks like visual search and scene exploration. Expand