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.

HMD - Praxis der Wirtschaftsinformatik - Smart City

Der Begriff Smart City oder Ubiquitous City bezeichnet die Nutzung von Informations- und Kommunikationstechnologien in Städten und Agglomerationen, um den sozialen und ökologischen Lebensraum nachhaltig zu entwickeln. Dazu zählen z.B. Projekte zur Verbesserung der Mobilität, Nutzung intelligenter Systeme für Wasser- und Energieversorgung, Förderung sozialer Netzwerke, Erweiterung politischer Partizipation, Ausbau von Entrepreneurship, Schutz der Umwelt sowie Erhöhung von Sicherheit und Lebensqualität. Das Themenheft widmet sich der Vielfalt dieser webbasierten Entwicklungen und berichtet über erste Erfahrungen von Pionierprojekten aus den folgenden Anwendungsfeldern: Smart Mobility, Smart Energy, Smart Economy, Smart Environment, Smart Governance, Smart Participation und Smart Living. Das Heft soll dazu dienen, den State of the Art der intelligenten Nutzung von Webtechnologien für den urbanen Raum aufzuzeigen, um damit Chancen und Risiken aufzudecken.

Associations of self-compassion and global self-esteem with positive and negative affect and stress reactivity in daily life: Findings from a smart phone study

The present study examined trait self-compassion and trait self-esteem in relation to positive (PA) and negative affect (NA), as well as their associations with stress reactivity in daily life. One hundred and one subjects completed questionnaires on perceived stress and affect twice a day for 14 consecutive days on smart phones. Results indicated that self-compassion and global self-esteem were positively related to PA and negatively to NA. After controlling for self-esteem, self-compassion remained significantly associated with PA and NA, whereas self-esteem was no longer associated with PA and NA after controlling for self-compassion. Furthermore, results indicated that self-compassion buffered the effect of stress on NA, whereas this was not the case for global self-esteem. Neither self-compassion nor self-esteem moderated the relation of stress on PA in separate models. The results of the present study add to the growing literature regarding beneficial relations of self-compassion and psychological well-being and further emphasize the distinction of self-compassion and global self-esteem.

Smart Hybrid Polymers for Advanced Damascene Electroplating: Combination of Superfill and Leveling Properties

A successful bottom-up fill of single Damascene test features is achieved by using a two-component additive package consisting of bis-(sodium-sulfopropyl)-disulfide (SPS) and Imep polymers (polymerizates of imidazole and epichlorohydrin). In addition, a remarkable leveling effect is observed. Clearly, the Imep additive combines bottom-up fill capabilities with leveling characteristics in one single polymer component. These unique hybrid properties of the Imep are rationalized on the basis of an extended N-NDR (N-shaped negative differential resistance) being present in the linear-sweep voltammogram of the SPS/Imep additive system during Cu electrodeposition.

Comment on “Low time resolution analysis of polar ice cores cannot detect impulsive nitrate events” by D.F. Smart et al.

Smart et al. (2014) suggested that the detection of nitrate spikes in polar ice cores from solar energetic particle (SEP) events could be achieved if an analytical system with sufficiently high resolution was used. Here we show that the spikes they associate with SEP events are not reliably recorded in cores from the same location, even when the resolution is clearly adequate. We explain the processes that limit the effective resolution of ice cores. Liquid conductivity data suggest that the observed spikes are associated with sodium or another nonacidic cation, making it likely that they result from deposition of sea salt or similar aerosol that has scavenged nitrate, rather than from a primary input of nitrate in the troposphere. We consider that there is no evidence at present to support the identification of any spikes in nitrate as representing SEP events. Although such events undoubtedly create nitrate in the atmosphere, we see no plausible route to using nitrate spikes to document the statistics of such events.