Ambient Assisted Living (AAL) is an emerging multi-disciplinary field aiming at exploiting information and communication technologies in personal healthcare and telehealth systems for countering the effects of growing elderly population. AAL systems are developed for personalized, adaptive, and anticipatory requirements, necessitating high quality-of-service to achieve interoperability, usability, security, and accuracy. The aim of this paper is to provide a comprehensive review of the AAL field with a focus on healthcare frameworks, platforms, standards, and quality attributes. To achieve this, we conducted a literature survey of state-of-the-art AAL frameworks, systems and platforms to identify the essential aspects of AAL systems and investigate the critical issues from the design, technology, quality-of-service, and user experience perspectives. In addition, we conducted an email-based survey for collecting usage data and current status of contemporary AAL systems. We found that most AAL systems are confined to a limited set of features ignoring many of the essential AAL system aspects. Standards and technologies are used in a limited and isolated manner, while quality attributes are often addressed insufficiently. In conclusion, we found that more inter-organizational collaboration, user-centered studies, increased standardization efforts, and a focus on open systems is needed to achieve more interoperable and synergetic AAL solutions.

Population aging and increasing pressure on health systems are two issues that demand solutions. Involving and empowering citizens as active managers of their health represents a desirable shift from the current culture mainly focused on treatment of disease, to one also focused on continuous health management and well-being. Current developments in technological areas such as the Internet of Things (IoT), lead to new technological solutions that can aid this shift in the healthcare sector. This study presents the design, development, implementation and evaluation of a platform called Common Recognition and Identification Platform (CRIP), a part of the CareStore project, which aims at supporting caregivers and citizens to manage health routines in a seamless way. Specifically, the CRIP offers sensor-based support for seamless identification of users and health devices. A set of initial requirements was defined with a focus on usability limitations and current sensor technologies. The CRIP was designed and implemented using several technologies that enable seamless integration and interaction of sensors and people, namely Near Field Communication and fingerprint biometrics for identification and authentication, Bluetooth for communication with health devices and web services for wider integration with other platforms. Two CRIP prototypes were implemented and evaluated in laboratory during a period of eight months. The evaluations consisted of identifying users and devices, as well as seamlessly configure and acquire vital data from the last. Also, the entire Carestore platform was deployed in a nursing home where its usability was evaluated with caregivers. The evaluations helped assess that seamless identification of users and seamless configuration and communication with health devices is feasible and can help enable the IoT on healthcare applications. Therefore, the CRIP and similar platforms could be transformed into a valuable enabling technology for secure and reliable IoT deployments on the healthcare sector.

This paper proposes a method for detecting insufficient lubrication in rolling bearings, by utilising a low cost MEMS ultrasonic microphone. We run a set of grease lubricated bearings under load, alternating between good and insufficient lubrication conditions by adjusting speed and temperature, over an 18 day experiment, followed by a short validation experiment on a different set of bearings on a secondary test rig . Vibration signals are recorded from an ultrasonic microphone, using a purpose built prototype sensor, then band-pass and high-pass filtered and subsequently analysed using statistical time-domain features. The viscosity ratio Kappa of the lubricant is used as a metric for quality of oil-film formation, and is calculated throughout the experiment from rotating speed and temperature. The results are compared with the predictions from a linear regression model and a simple Neural Network trained on ensembles of three and ten selected features. The three Hjorth’s Parameters activity, mobility and complexity calculated on high-pass filtered microphone signals from the experiments show a good correlation with the viscosity ratio Kappa. When combining these, using a Linear Regression model or a simple two layer Neural Network model, we are able to predict the viscosity ratio with good precision. The proposed method may be used to assess the quality of oil film formation in bearings during operation under varying speed and temperature conditions.

Wireless technologies are currently among the most prominent candidates for use by the medical and care-giving community as a part of the development of telemedicine systems. The exponential progress of these technologies is expected to open a multitude of opportunities and choices for enhanced patient safety, better data collection, increased convenience for patients, and reduced costs for health systems. Thanks to the cost effectiveness and clinical acceptability of wireless telecommunication technology, patient diagnosis and treatment have been significantly improved. Technology for remote sensing of patients' activity is also being developed.

Variational Inference (VI) is a commonly used technique for approximate Bayesian inference and uncertainty estimation in deep learning models, yet it comes at a computational cost, as it doubles the number of trainable parameters to represent uncertainty. This rapidly becomes challenging in high-dimensional settings and motivates the use of alternative techniques for inference, such as Monte Carlo Dropout (MCD) or Spectral-normalized Neural Gaussian Process (SNGP). However, such methods have seen little adoption in survival analysis, and VI remains the prevalent approach for training probabilistic neural networks. In this paper, we investigate how to train deep probabilistic survival models in large datasets without introducing additional overhead in model complexity. To achieve this, we adopt three probabilistic approaches, namely VI, MCD, and SNGP, and evaluate them in terms of their prediction performance, calibration performance, and model complexity. In the context of probabilistic survival analysis, we investigate whether non-VI techniques can offer comparable or possibly improved prediction performance and uncertainty calibration compared to VI. In the MIMIC-IV dataset, we find that MCD aligns with VI in terms of the concordance index (0.748 vs. 0.743) and mean absolute error (254.9 vs. 254.7) using hinge loss, while providing C-calibrated uncertainty estimates. Moreover, our SNGP implementation provides D-calibrated survival functions in all datasets compared to VI (4/4 vs. 2/4, respectively). Our work encourages the use of techniques alternative to VI for survival analysis in high-dimensional datasets, where computational efficiency and overhead are of concern.