Search

This work aims to compare the performance of Machine Learning (ML) and Deep Learning (DL) algorithms in detecting users’ heartbeats on a smart bed. Targeting non-intrusive, continuous heart monitoring during sleep time, the smart bed is equipped with a 3D solid-state accelerometer. Acceleration signals are processed through an STM 32-bit microcontroller board and transmitted to a PC for recording. A photoplethysmographic sensor is simultaneously checked for ground truth reference. A dataset has been built, by acquiring measures in a real-world set-up: 10 participants were involved, resulting in 120 min of acceleration traces which were utilized to train and evaluate various Artificial Intelligence (AI) algorithms. The experimental analysis utilizes K-fold cross-validation to ensure robust model testing across different subsets of the dataset. Various ML and DL algorithms are compared, each being trained and tested using the collected data. The Random Forest algorithm exhibited the highest accuracy among all compared models. While it requires longer training time compared to some ML models such as Naïve Bayes, Linear Discrimination Analysis, and KNearest Neighbour Classification, it keeps substantially faster than Support Vector Machine and Deep Learning models. The Random Forest model demonstrated robust performance metrics, including recall, precision, F1-scores, macro average, weighted average, and overall accuracy well above 90%. The study highlights the better performance of the Random Forest algorithm for the specific use case, achieving superior accuracy and performance metrics in detecting user heartbeats in comparison to other ML and DL models tested. The drawback of longer training times is not too relevant in the long-term monitoring target scenario, so the Random Forest model stands out as a viable solution for real-time ballistocardiographic heartbeat detection, showcasing potential for healthcare and wellness monitoring applications. [ABSTRACT FROM AUTHOR]

As the average age of the EU population increases, ICT solutions are going to play a key role in order to find answers to the new challenges the demographic change is carrying on. At the University of Parma an AAL (Ambient Assisted Living) system named CARDEA has been developed during the last 10 years. Within CARDEA, behavioral analysis is carried out, based on environmental sensors. If multiple users live in the same environment, however, data coming from sensors need to be properly tagged: in this paper, a simple technique for such tagging is proposed, which exploits the same wireless transmission used for transmitting data, thus not requiring additional hardware components and avoiding more complex and expensive (radio)localization techniques. Preliminary results are shown, featuring a satisfactory accuracy. [ABSTRACT FROM AUTHOR]

Behavioral analysis, based on unobtrusive monitoring through environmental sensors, is expected to increase health awareness of AAL systems. In this paper, techniques for assessing behavioral quantitative features are discussed, suitable for detecting behavioral anomalies in an unsupervised fashion, i.e., with no need of defining target reference behaviors and of tuning user-specific threshold parameters. Such technique is being exploited for analyzing data coming from a set of European pilot sites, in the framework of the EU/AAL-JP project "FOOD", specifically focused at kitchen activity. Simple results are illustrated, suitable for proof-of-concept validation. [ABSTRACT FROM AUTHOR]

We present a complete BCI-enabled (Brain Computer Interface) solution for Ambient Assisted Living system control. BCI are alternative, augmentative communication means capable of exploiting just the brain waveforms to infer intent, thus potentially posing as a technological bridge capable of overcoming limitations in the usual neuromuscular pathways. The module was completely developed in a customized way, encompassing hardware and software components. We demonstrate the effectiveness of the approach on a practical control scenario in which the user can issue 4 different commands, at his own pace and will, in real-time. No initial calibration is necessary, in line with the aimed plug&play approach. Results are very promising, especially in false positives rejection, well improving over literature. [ABSTRACT FROM AUTHOR]

Artificial Intelligence in combination with the Internet of Medical Things enables remote healthcare services through networks of environmental and/or personal sensors. We present a remote healthcare service system which collects real-life data through an environmental sensor package, including binary motion, contact, pressure, and proximity sensors, installed at households of elderly people. Its aim is to keep the caregivers informed of subjects' health-status progressive trajectory, and alert them of health-related anomalies to enable objective on-demand healthcare service delivery at scale. The system was deployed in 19 households inhabited by an elderly person with post-stroke condition in the Emilia–Romagna region in Italy, with maximal and median observation durations of 98 and 55 weeks. Among these households, 17 were multi-occupancy residences, while the other 2 housed elderly patients living alone. Subjects' daily behavioral diaries were extracted and registered from raw sensor signals, using rule-based data pre-processing and unsupervised algorithms. Personal behavioral habits were identified and compared to typical patterns reported in behavioral science, as a quality-of-life indicator. We consider the activity patterns extracted across all users as a dictionary, and represent each patient's behavior as a 'Bag of Words', based on which patients can be categorized into sub-groups for precision cohort treatment. Longitudinal trends of the behavioral progressive trajectory and sudden abnormalities of a patient were detected and reported to care providers. Due to the sparse sensor setting and the multi-occupancy living condition, the sleep profile was used as the main indicator in our system. Experimental results demonstrate the ability to report on subjects' daily activity pattern in terms of sleep, outing, visiting, and health-status trajectories, as well as predicting/detecting 75% hospitalization sessions up to 11 days in advance. 65% of the alerts were confirmed to be semantically meaningful by the users. Furthermore, reduced social interaction (outing and visiting), and lower sleep quality could be observed during the COVID-19 lockdown period across the cohort. [ABSTRACT FROM AUTHOR]