Search

Many people in the world are affected by the Alzheimer disease leading to the dysfunctionality of the hand. In one side, this symptom is not the most important of this disease and not much attention is given to this one. In the other side, the literrature provides two main solutions such as computer vision and data glove allowing to recognize hand gestures for virtual reality or robotic applications. From this finding and need, we decided to developed our own data glove prototype allowing to monitor the evolution of the dysfunctionality of the hand by recognizing objects in basic daily activities. Our approach is simple, cheap (~220$) and efficient (~100% of correct predictions) considering that we are abstracting all the theory about the gesture recognition. Also, we can access directly and easily to the raw data. Finally, the proposed prototype is described in a way that researchers can reproduce it. [ABSTRACT FROM AUTHOR]

Many people in the world are affected by the Alzheimer disease leading to the dysfunctionality of the hand. In one side, this symptom is not the most important of this disease and not much attention is given to this one. In the other side, the literrature provides two main solutions such as computer vision and data glove allowing to recognize hand gestures for virtual reality or robotic applications. From this finding and need, we decided to developed our own data glove prototype allowing to monitor the evolution of the dysfunctionality of the hand by recognizing objects in basic daily activities. Our approach is simple, cheap (~220$) and efficient (~100% of correct predictions) considering that we are abstracting all the theory about the gesture recognition. Also, we can access directly and easily to the raw data. Finally, the proposed prototype is described in a way that researchers can reproduce it. [ABSTRACT FROM AUTHOR]

• Creation of a unique dataset containing 15 ADLs acquired from three UWB radars. • Experiments conducted in a real apartment by 10 participants. • Data augmentation to degrade the activity location influences. • A voting system based on trained deep learning models. • Results of ADL recognition reach 90% in some cases. Since years, the number of seniors increases while, at the same time, we observe a diminution of the potential support ratio. In order to overcome this limitation, solutions emerged, such as smart homes and wearable devices. Smart homes integrate sensors, actuators, and artificial intelligence to assist seniors in their everyday life. One of the objectives is to recognize the activities of everyday life. This recognition aims to provide the right assistance at the right moment and gives some autonomy to seniors. However, it is a complex task (a significant quantity of different sensors, hardware implementation), and the number of solutions (combinations between approaches, for example, video-based HAR and wearable sensors-based HAR) that exist is important. In this paper, we propose to perform the activity recognition from three ultra-wideband (UWB) radars, deep learning models, and a voting system. Also, all the experiments have been conducted in a real apartment and are composed of 15 different activities. The presented solution is simple compared to the literature since we exploit only one type of sensor. Finally, we obtained promising results with our approach. Indeed, the classification rate reaches 90% and more in some cases. [ABSTRACT FROM AUTHOR]