A Smart Room to Promote Autonomy of Disabled People due to Stroke

A cerebral vascular accident,known as common language stroke,is one of the main causes of mortality and remains the primary cause of acquired disabilities in adults.Those disabled people spend most of their time at home in their living rooms.In most cases,appliances of a living room(TV,light,cooler/heater,window blinds,etc.)are generally controlled by direct manipulation of a set of remote controls.Handling many remote controls can be disturbing and inappropriate for these people.In addition,in many cases these people could be alone at home and must open the door for visitors after their identification by either moving to the door or using an intercom system which requires in both cases a physical activity.Furthermore,these people need a continuous health monitoring especially blood pressure to avoid a recurrent stroke.Smart spaces and assisted technologies would be beneficial to assist person with disabilities to live indepen-dently,enhance their quality of life and empower their autonomy.A complete sys-tem which improves and facilitates the daily life and covers all aspects such as appliances automation,appropriate interaction mode and health monitoring of these people is still lacking.The aim of this work is to create a safe and high-quality living environment for persons with disabilities to enable them to live more independently by automating the operation of a living room appliances according to the current context without the need to use remote control devices,the use of a suitable interaction modality with appliances that require direct interaction and a remote health monitoring system which can alert relatives and caregivers in case of an emergency.

QL-CBR Hybrid Approach for Adapting Context-Aware Services

A context-aware service in a smart environment aims to supply services according to user situational information,which changes dynamically.Most existing context-aware systems provide context-aware services based on supervised algorithms.Reinforcement algorithms are another type of machine-learning algorithm that have been shown to be useful in dynamic environments through trialand-error interactions.They also have the ability to build excellent self-adaptive systems.In this study,we aim to incorporate reinforcement algorithms(Q-learning)into a context-aware system to provide relevant services based on a user’s dynamic context.To accelerate the convergence of reinforcement learning(RL)algorithms and provide the correct services in real situations,we propose a combination of the Q-learning and case-based reasoning(CBR)algorithms.We then analyze how the incorporation of CBR enables Q-learning to become more effi-cient and adapt to changing environments by continuously producing suitable services.Simulation results demonstrate the effectiveness of the proposed approach compared to the traditional CBR approach.