We present i-Light, a cyber-physical platform that aims to help older adults to live safely within their own homes. The system is the result of an international research project funded by the European Union and is comprised of a custom developed wireless sensor network together with software services that provide continuous monitoring, reporting and real-time alerting capabilities. The principal innovation proposed within the project regards implementation of the hardware components in the form of intelligent luminaires with inbuilt sensing and communication capabilities. Custom luminaires provide indoor localisation and environment sensing, are cost-effective and are designed to replace the lighting infrastructure of the deployment location without prior mapping or fingerprinting. We evaluate the system within a home and show that it achieves localisation accuracy sufficient for room-level detection. We present the communication infrastructure, and detail how the software services can be configured and used for visualisation, reporting and real-time alerting.
Proteins are essential molecules, that must correctly perform their roles for the good health of living organisms. The majority of proteins operate in complexes and the way they interact has pivotal influence on the proper functioning of such organisms. In this study we address the problem of protein–protein interaction and we propose and investigate a method based on the use of an ensemble of autoencoders. Our approach, entitled AutoPPI, adopts a strategy based on two autoencoders, one for each type of interactions (positive and negative) and we advance three types of neural network architectures for the autoencoders. Experiments were performed on several data sets comprising proteins from four different species. The results indicate good performances of our proposed model, with accuracy and AUC values of over 0.97 in all cases. The best performing model relies on a Siamese architecture in both the encoder and the decoder, which advantageously captures common features in protein pairs. Comparisons with other machine learning techniques applied for the same problem prove that AutoPPI outperforms most of its contenders, for the considered data sets.
Abstract:Hospital acquired infections (HAI) are infections acquired within the hospital from healthcare workers, patients or from the environment, but which have no connection to the initial reason for the patient's hospital admission. HAI are a serious world-wide problem, leading to an increase in mortality rates, duration of hospitalisation as well as significant economic burden on hospitals. Although clear preventive guidelines exist, studies show that compliance to them is frequently poor. This paper details the software perspective for an innovative, business process software based cyber-physical system that will be implemented as part of a European Union-funded research project. The system is composed of a network of sensors mounted in different sites around the hospital, a series of wearables used by the healthcare workers and a server side workflow engine. For better understanding, we describe the system through the lens of a single, simple clinical workflow that is responsible for a significant portion of all hospital infections. The goal is that when completed, the system will be configurable in the sense of facilitating the creation and automated monitoring of those clinical workflows that when combined, account for over 90% of hospital infections.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.