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.

Delirium upon admission to Swiss nursing homes

QUESTIONS UNDER STUDY: We wished to investigate the prevalence of delirium in patients upon admission to nursing homes and whether or not the previous place of residence predicts delirium. METHODS: The Resident Assessment Instrument Minimum Data Set (RAI-MDS) and the Nursing Home Confusion Assessment Method (NHCAM) were used to determine whether the previous place of residence (community, nursing home, acute care, psychiatric, rehabilitation hospital) predicted the prevalence of sub-syndromal or full delirium in nursing home residents in three Swiss cantons (n = 11745). RESULTS: 39.7% had sub-syndromal and 6.5% had full delirium. Lower cognitive performance and increased depressive symptoms were significant predictors of higher NHCAM values independent of previous residence. Age, civil status, continence, newly introduced drugs, and basic activities of daily living were predictors in some resident groups. The variance of NHCAM scores explained varied between 25.1% and 32.3% depending on previous residence. CONCLUSIONS: Sub-syndromal and full delirium are common upon nursing home admission. Increased dependence and depression are consistently associated with higher NHCAM scores. Patients from psychiatric settings have an increased risk of delirium. Although factors associated with delirium depend on a patient's previous residence, all patients must be carefully screened for sub-syndromal and full delirium.

Psychotropic medication use in Swiss nursing homes

Psychotropic medication is commonly used in nursing homes, to treat behavioural and psychological symptoms of dementia (BPSD) for example. Treatment with antipsychotics may improve BPSD in some residents but can be associated with serious side effects, such as higher mortality, faster disease progression and cerebrovascular events. In the current study, psychotropic medication use was analysed in a representative sample of nursing home residents in the German-speaking part of Switzerland, at entry and during follow-up.

A smart multi-hop hierarchical routing protocol for efficient video communication over wireless multimedia sensor networks

For smart applications, nodes in wireless multimedia sensor networks (MWSNs) have to take decisions based on sensed scalar physical measurements. A routing protocol must provide the multimedia delivery with quality level support and be energy-efficient for large-scale networks. With this goal in mind, this paper proposes a smart Multi-hop hierarchical routing protocol for Efficient VIdeo communication (MEVI). MEVI combines an opportunistic scheme to create clusters, a cross-layer solution to select routes based on network conditions, and a smart solution to trigger multimedia transmission according to sensed data. Simulations were conducted to show the benefits of MEVI compared with the well-known Low-Energy Adaptive Clustering Hierarchy (LEACH) protocol. This paper includes an analysis of the signaling overhead, energy-efficiency, and video quality.

Eluding oblivion with smart stochastic selection of synaptic updates

The variables involved in the equations that describe realistic synaptic dynamics always vary in a limited range. Their boundedness makes the synapses forgetful, not for the mere passage of time, but because new experiences overwrite old memories. The forgetting rate depends on how many synapses are modified by each new experience: many changes means fast learning and fast forgetting, whereas few changes means slow learning and long memory retention. Reducing the average number of modified synapses can extend the memory span at the price of a reduced amount of information stored when a new experience is memorized. Every trick which allows to slow down the learning process in a smart way can improve the memory performance. We review some of the tricks that allow to elude fast forgetting (oblivion). They are based on the stochastic selection of the synapses whose modifications are actually consolidated following each new experience. In practice only a randomly selected, small fraction of the synapses eligible for an update are actually modified. This allows to acquire the amount of information necessary to retrieve the memory without compromising the retention of old experiences. The fraction of modified synapses can be further reduced in a smart way by changing synapses only when it is really necessary, i.e. when the post-synaptic neuron does not respond as desired. Finally we show that such a stochastic selection emerges naturally from spike driven synaptic dynamics which read noisy pre and post-synaptic neural activities. These activities can actually be generated by a chaotic system.

Minimized cardiopulmonary bypass combined with a smart suction device: the future of cardiopulmonary bypass?

OBJECTIVE: The standard heart-lung machine is a major trigger of systemic inflammatory response and the morbidity attributed to conventional extracorporeal circulation (CECC) is still significant. Reduction of blood-artificial surface contact and reduction of priming volume are principal aims in minimized extracorporeal circulation (MECC) cardiopulmonary bypass systems. The aim of this paper is to give an overview of the literature and to present our experience with the MECC-smart suction system. METHODS AND RESULTS: At our institution, 1799 patients underwent isolated coronary artery bypass grafting (CABG) surgery, 1372 with a MECC-smart suction system and 427 with CECC. All in-hospital data were assessed and the results were compared between the 2 groups. Patient characteristics and the distribution of EuroSCORE risk profile in our collective were similar between both groups. Average age in the MECC collective was 67.5 +/- 11.4 years and average EuroSCORE was 5.0 +/- 1.5. Average number of distal anastomoses was similar to the average number encountered in patients undergoing CABG surgery with CECC (3.3 +/- 1.0 for MECC versus 3.2 +/- 1.1 for CECC; P = ns). Myocardial protection is superior in MECC patients with lower postoperative maximal cTnI values (11.0 +/- 10.8 micromol/L for MECC versus 24.7 +/- 25.3 micromol/L for CECC; P < .05). Postoperative recovery was faster in patients operated on with the MECC-smart suction system and discharge from the hospital was earlier than for CECC patients (7.4 +/- 1.9 days for MECC versus 8.8 +/- 3.8 days for CECC; P < .05). CONCLUSIONS: The MECC-smart suction system is a safe perfusion technique for CABG surgery. In patients operated on with this system, the clinical outcome seems to be better than in patients operated on with CECC. This promising and less damaging perfusion technology has the potential to replace CECC systems in CABG surgery.

A Smart TCP Acknowledgment Approach for Multihop Wireless Networks

Reliable data transfer is one of the most difficult tasks to be accomplished in multihop wireless networks. Traditional transport protocols like TCP face severe performance degradation over multihop networks given the noisy nature of wireless media as well as unstable connectivity conditions in place. The success of TCP in wired networks motivates its extension to wireless networks. A crucial challenge faced by TCP over these networks is how to operate smoothly with the 802.11 wireless MAC protocol which also implements a retransmission mechanism at link level in addition to short RTS/CTS control frames for avoiding collisions. These features render TCP acknowledgments (ACK) transmission quite costly. Data and ACK packets cause similar medium access overheads despite the much smaller size of the ACKs. In this paper, we further evaluate our dynamic adaptive strategy for reducing ACK-induced overhead and consequent collisions. Our approach resembles the sender side's congestion control. The receiver is self-adaptive by delaying more ACKs under nonconstrained channels and less otherwise. This improves not only throughput but also power consumption. Simulation evaluations exhibit significant improvement in several scenarios

Enterprise Integration of Smart Objects using Semantic Service Descriptions

Integrating physical objects (smart objects) and enterprise IT systems is still a labor intensive, mainly manual task done by domain experts. On one hand, enterprise IT backend systems are based on service oriented architectures (SOA) and driven by business rule engines or business process execution engines. Smart objects on the other hand are often programmed at very low levels. In this paper we describe an approach that makes the integration of smart objects with such backends systems easier. We introduce semantic endpoint descriptions based on Linked USDL. Furthermore, we show how different communication patterns can be integrated into these endpoint descriptions. The strength of our endpoint descriptions is that they can be used to automatically create REST or SOAP endpoints for enterprise systems, even if which they are not able to talk to the smart objects directly. We evaluate our proposed solution with CoAP, UDP and 6LoWPAN, as we anticipate the industry converge towards these standards. Nonetheless, our approach also allows easy integration with backend systems, even if no standardized protocol is used.

A longitudinal study on delirium in nursing homes

OBJECTIVE To investigate the evolution of delirium of nursing home (NH) residents and their possible predictors. DESIGN Post-hoc analysis of a prospective cohort assessment. SETTING Ninety NHs in Switzerland. PARTICIPANTS Included 14,771 NH residents. MEASUREMENTS The Resident Assessment Instrument Minimum Data Set and the Nursing Home Confusion Assessment Method were used to determine follow-up of subsyndromal or full delirium in NH residents using discrete Markov chain modeling to describe long-term trajectories and multiple logistic regression analyses to determine predictors of the trajectories. RESULTS We identified four major types of delirium time courses in NH. Increasing severity of cognitive impairment and of depressive symptoms at the initial assessment predicted the different delirium time courses. CONCLUSION More pronounced cognitive impairment and depressive symptoms at the initial assessment are associated with different subsequent evolutions of delirium. The presence and evolution of delirium in the first year after NH admission predicted the subsequent course of delirium until death.