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.

Retention in care of HIV-infected pregnant and lactating women starting art under Option B+ in rural Mozambique.

OBJECTIVE In 2013, Mozambique adopted Option B+, universal lifelong antiretroviral therapy (ART) for all pregnant and lactating women, as national strategy for prevention of mother-to-child transmission of HIV. We analyzed retention in care of pregnant and lactating women starting Option B+ in rural northern Mozambique. METHODS We compared ART outcomes in pregnant ("B+pregnant"), lactating ("B+lactating") and non-pregnant-non-lactating women of childbearing age starting ART after clinical and/or immunological criteria ("own health") between July 2013 and June 2014. Lost to follow-up was defined as no contact >180 days after the last visit. Multivariable competing risk models were adjusted for type of facility (type 1 vs. peripheral type 2 health center), age, WHO stage and time from HIV diagnosis to ART. RESULTS Over 333 person-years of follow-up (of 243 "B+pregnant", 65″B+lactating" and 317 "own health" women), 3.7% of women died and 48.5% were lost to follow-up. "B+pregnant" and "B+lactating" women were more likely to be lost in the first year (57% vs. 56.9% vs. 31.6%; p<0.001) and to have no follow-up after the first visit (42.4% vs. 29.2% vs. 16.4%; p<0.001) than "own health" women. In adjusted analyses, risk of being lost to follow-up was higher in "B+pregnant" (adjusted subhazard ratio [asHR]: 2.77; 95% CI: 2.18-3.50; p<0.001) and "B+lactating" (asHR: 1.94; 95% CI: 1.37-2.74; p<0.001). Type 2 health center was the only additional significant risk factor for loss to follow-up. CONCLUSIONS Retaining pregnant and lactating women in option B+ ART was poor; losses to follow-up were mainly early. The success of Option B+ for prevention of mother-to-child transmission of HIV in rural settings with weak health systems will depend on specific improvements in counseling and retention measures, especially at the beginning of treatment. This article is protected by copyright. All rights reserved.