Now showing items 51-54 of 54
Comparing CNN and Human Crafted Features for Human Activity Recognition
Deep learning techniques such as Convolutional Neural Networks (CNNs) have shown good results in activity recognition. One of the advantages of using these methods resides in their ability to generate features automatically. ...
A Geospatial Semantic Enrichment and Query Service for Geotagged Photographs
With the increasing abundance of technologies and smart devices, equipped with a multitude of sensors for sensing the environment around them, information creation and consumption has now become effortless. This, in ...
Learning Behaviour for Service Personalisation and Adaptation
Context-aware applications within pervasive environments are increasingly being developed as services and deployed in the cloud. As such these services are increasingly required to be adaptive to individual users to meet ...
Smart Assisted Living: Toward An Open Smart-Home Infrastructure
(Springer Nature, 2019-08-20)
Smart Homes (SH) offer a promising approach to assisted living for the ageing population. Yet the main obstacle to the rapid development and deployment of Smart Home (SH) solutions essentially arises from the nature of the ...