Evaluation of Three State-of-the-Art Classifiers for Recognition of Activities of Daily Living from Smart Home Ambient Data

Smart homes for the aging population have recently started attracting the attention of the research community. The "health state" of smart homes is comprised of many different levels; starting with the physical health of citizens, it also includes longer-term health norms and outcomes, as well as the arena of positive behavior changes. One of the problems of interest is to monitor the activities of daily living (ADL) of the elderly, aiming at their protection and well-being. For this purpose, we installed passive infrared (PIR) sensors to detect motion in a specific area inside a smart apartment and used them to collect a set of ADL. In a novel approach, we describe a technology that allows the ground truth collected in one smart home to train activity recognition systems for other smart homes. We asked the users to label all instances of all ADL only once and subsequently applied data mining techniques to cluster in-home sensor firings. Each cluster would therefore represent the instances of the same activity. Once the clusters were associated to their corresponding activities, our system was able to recognize future activities. To improve the activity recognition accuracy, our system preprocessed raw sensor data by identifying overlapping activities. To evaluate the recognition performance from a 200-day dataset, we implemented three different active learning classification algorithms and compared their performance: naive Bayesian (NB), support vector machine (SVM) and random forest (RF). Based on our results, the RF classifier recognized activities with an average specificity of 96.53%, a sensitivity of 68.49%, a precision of 74.41% and an F-measure of 71.33%, outperforming both the NB and SVM classifiers. Further clustering markedly improved the results of the RF classifier. An activity recognition system based on PIR sensors in conjunction with a clustering classification approach was able to detect ADL from datasets collected from different homes. Thus, our PIR-based smart home technology could improve care and provide valuable information to better understand the functioning of our societies, as well as to inform both individual and collective action in a smart city scenario.

Management of Home Parenteral Nutrition: A Prospective Multicenter Observational Study

BACKGROUND There are no specific Swiss home parenteral nutrition (HPN) data showing patient characteristics, quality of life (QoL) and complications. The goal of this study was to collect representative nationwide data on current adult HPN patients in Switzerland for international comparability and benchmarking. METHODS This was a multicenter, nationwide, observational study. We conducted interviews for demographics, PN characteristics, QoL and complications. The data were assessed at baseline and after a follow-up of 3 months using a questionnaire. RESULTS Thirty-three adult patients were included. The most common underlying diseases were cancer, radiation enteritis and state after bariatric surgery, and the most prevalent indication was short bowel syndrome. During the 3-month observation period, significant increase or stabilization of body weight occurred in the patients, physical activity scores improved from 34.0 to 39.4 and mental scores improved from 41.9 to 46.4. HPN dependency and traveling restrictions were of the greatest concern. Diarrhea, xerostomia and/or thirst were frequent complaints. CONCLUSION Anthropometric parameters and QoL improved during the observational period in this HPN cohort. These Swiss HPN data are prerequisite for evaluation and comparison of HPN recommendations and best clinical practice, status of professional care instructions related to HPN effectiveness, quality of treatment and patient safety.

The Art of Enduring Contradictory Goals: Challenges in the Institutional Co‐construction of a ‘Good Death’

This paper focuses on the normative notion of ‘good death’, its practical relevance as a frame of reference for ‘death work’ procedures in institutional elder care in Switzerland and the ways in which it may be challenged within migrant ‘dying trajectories’. In contemporary palliative care, the concept of ‘good death’ focuses on the ideal of an autonomous dying person, cared for under a specialised biomedical authority. Transferred to the nursing home context, characterised by long-term basic care for the very old under conditions of scarce resources, the notion of ‘good death’ is broken down into ready-to-use, pragmatic elements of daily routines. At the same time, nursing homes are increasingly confronted with socially and culturally diversified populations. Based on ethnographic findings, we give insight into current practices of institutional ‘death work’ and tensions arising between contradicting notions of a ‘good death’, by referring to decision-making, life-prolonging measures, notions on food/feeding and the administration of sedative painkillers.