Use of Clustering Algorithms for Sensor Placement and Activity Recognition in Smart Homes

Abstract

This work presents a novel method for motion sensor placement within smart homes. Using recordings from 3D depth cameras within six real homes, clusters are created with the resident's tracked location. The resulting clusters identify the possible position of a sensor and its field of view. By using a sequence of clusters as input to a Recurrent Neural Network, we evaluate our method on the task of activity recognition and prediction. These results are compared to using sensor events as input sequence, from motion sensors that were installed empirically in the same homes. Different clustering methods are investigated and all outperform the installed motion sensors, achieving a significant increase of prediction accuracy and F1-score.

Recent Advances in Self-powered Sensors Based on Nanogenerators: From Material and Structural Design to Cutting-Edge Sensing Applications

“…The growing demand for wearable electronic devices offering both comfort and functionality has made research on flexible nanotechnology-based wearable systems a top priority. − Wearable intelligent products serve as the nexus of the Internet of Things (IoT), enabling the connection between user-perceived peripheral information and machines through the Internet technology to achieve effective human health monitoring. − The emergence of smart sensors is inevitable with the continuous advancement of the IoT. − For instance, smart sensors are utilized in various devices such as automobiles, cameras, and mobile phones. − However, these sensors have numerous constraints, particularly with regard to their power supply. In practical applications, a device requires an external power supply, thereby posing significant challenges to its portability, comfort, and service life. , Consequently, it is anticipated that wearable electronics developed in the future will be capable of obtaining energy without any cumbersome cables or bulky batteries.…”