Heinrich J. Wörtche

Suitability of Kinect for measuring whole body movement patterns during exergaming

Exergames provide a challenging opportunity for home-based training and evaluation of postural control in the elderly population, but affordable sensor technology and algorithms for assessment of whole body movement patterns in the home environment are yet to be developed. The aim of the present study was to evaluate the use of Kinect, a commonly available video game sensor, for capturing and analyzing whole body movement patterns. Healthy adults (n=20) played a weight shifting exergame under five different conditions with varying amplitudes and speed of sway movement, while 3D positions of ten body segments were recorded in the frontal plane using Kinect and a Vicon 3D camera system. Principal Component Analysis (PCA) was used to extract and compare movement patterns and the variance in individual body segment positions explained by these patterns. Using the identified patterns, balance outcome measures based on spatiotemporal sway characteristics were computed. The results showed that both Vicon and Kinect capture >90% variance of all body segment movements within three PCs. Kinect-derived movement patterns were found to explain variance in trunk movements accurately, yet explained variance in hand and foot segments was underestimated and overestimated respectively by as much as 30%. Differences between both systems with respect to balance outcome measures range 0.3-64.3%. The results imply that Kinect provides the unique possibility of quantifying balance ability while performing complex tasks in an exergame environment.

Effects of urban trees on local outdoor microclimate: synthesizing field measurements by numerical modelling

In this study, we investigated the effects of trees on the local urban microclimate and human thermal comfort under different local weather conditions, in a small urban area in Assen, the Netherlands. In both summer and winter, continuous air temperature and relative humidity measurements were conducted at five selected sites having obviously different environmental characteristics in tree cover. Measurements demonstrated that in summer the microclimatic conditions at each observation site showed significant differences. The cooling effects of trees on clear and hot days were two times higher than on cloudy and cold days. In winter, air temperature was slightly reduced by the evergreen trees, and weather conditions did not cause a notable change on performance of trees on the microclimate. ENVI-met, a three-dimensional microclimate model was used to simulate the spatial distribution of temperature and humidity. After selecting representative days, we simulated the study site as it currently is and for a situation without trees. Spatial differences of trees’ effects were found to vary strongly with weather conditions. Furthermore, human thermal comfort is indicated by the Predicted Mean Vote model. During the hottest hours, trees improved the thermal comfort level via reducing ‘very hot’ and ‘hot’ thermal perception by about 16xa0% on clear days and 11xa0% on cloudy days. Generally, our findings demonstrate that urban microclimate and human thermal comfort convincingly varies in close geographical proximity. Both are strongly affected by the presence of local trees. Weather conditions play an important role on the trees’ performance on the summer-time microclimate.

Ensembles of incremental learners to detect anomalies in ad hoc sensor networks

Display Omitted In the past decade, rapid technological advances in the fields of electronics and telecommunications have given rise to versatile, ubiquitous decentralized embedded sensor systems with ad hoc wireless networking capabilities. Typically these systems are used to gather large amounts of data, while the detection of anomalies (such as system failures, intrusion, or unanticipated behavior of the environment) in the data (or other types or processing) is performed in centralized computer systems. In spite of the great interest that it attracts, the systematic porting and analysis of centralized anomaly detection algorithms to a decentralized paradigm (compatible with the aforementioned sensor systems) has not been thoroughly addressed in the literature. We approach this task from a new angle, assessing the viability of localized (in-node) anomaly detection based on machine learning. The main challenges we address are: (1) deploying decentralized, automated, online learning, anomaly detection algorithms within the stringent constraints of typical embedded systems; and (2) evaluating the performance of such algorithms and comparing them with that of centralized ones. To this end, we first analyze (and port) single and multi-dimensional input classifiers that are trained incrementally online and whose computational requirements are compatible with the limitations of embedded platforms. Next, we combine multiple classifiers in a single online ensemble. Then, using both synthetic and real-world datasets from different application domains, we extensively evaluate the anomaly detection performance of our algorithms and ensemble, in terms of precision and recall, and compare it to that of well-known offline, centralized machine learning algorithms. Our results show that the ensemble performs better than each individual decentralized classifier and that it can match the performance of the offline alternatives, thus showing that our approach is a viable solution to detect anomalies, even in environments with little a priori knowledge.

Exergames for unsupervised balance training at home: A pilot study in healthy older adults

Exercise videogames (exergames) are gaining popularity as tools for improving balance ability in older adults, yet few exergames are suitable for home-based use. The purpose of the current pilot study was to examine the effects of a 6-week unsupervised home-based exergaming training program on balance performance. Ten community dwelling healthy older adults (age: 75.9 ± 7.2 years) played a newly developed ice skating exergame for six weeks at home. In the game, the speed and direction of a virtual ice skater on a frozen canal were controlled using lateral weight shifts, which were captured using Kinect. Sway characteristics during quiet standing in eyes open (EO), eyes closed (EC) and dual task (DT) conditions were assessed in time and frequency domain before, and after two, four and six weeks of training. Balance was also evaluated using the narrow ridge balance test (NRBT). Multilevel modeling was applied to examine changes in balance ability. Participants played 631 (± 124)min over the intervention period and no subjects dropped out. Balance in terms of sway characteristics improved on average by 17.4% (EO) and 23.3% (EC) after six weeks of training (p<0.05). Differences in rate of improvement (p<0.05) were observed between participants. No intervention effects were found for quiet standing in DT conditions and on the NRBT. In conclusion, the pilot study showed that unsupervised home-based exergaming is feasible in community dwelling older adults, but also that participants do not benefit equally from the program, thereby emphasizing the need for more personalized exergame training programs.

Spatial anomaly detection in sensor networks using neighborhood information

A method of neighborhood data fusion in decentralized anomaly detection is proposed.The effects of neighborhood size and spatio-temporal correlation are explored.Performance increases when the system is deployed in a correlated environment.Fusing small neighborhoods is preferred over larger neighborhoods. The field of wireless sensor networks (WSNs), embedded systems with sensing and networking capability, has now matured after a decade-long research effort and technological advances in electronics and networked systems. An important remaining challenge now is to extract meaningful information from the ever-increasing amount of sensor data collected by WSNs. In particular, there is strong interest in algorithms capable of automatic detection of patterns, events or other out-of-the order, anomalous system behavior. Data anomalies may indicate states of the system that require further analysis or prompt actions. Traditionally, anomaly detection techniques are executed in a central processing facility, which requires the collection of all measurement data at a central location, an obvious limitation for WSNs due to the high data communication costs involved. In this paper we explore the extent by which one may depart from this classical centralized paradigm, looking at decentralized anomaly detection based on unsupervised machine learning. Our aim is to detect anomalies at the sensor nodes, as opposed to centrally, to reduce energy and spectrum consumption. We study the information gain coming from aggregate neighborhood data, in comparison to performing simple, in-node anomaly detection. We evaluate the effects of neighborhood size and spatio-temporal correlation on the performance of our new neighborhood-based approach using a range of real-world network deployments and datasets. We find the conditions that make neighborhood data fusion advantageous, identifying also the cases in which this approach does not lead to detectable improvements. Improvements are linked to the diffusive properties of data (spatio-temporal correlations) but also to the type of sensors, anomalies and network topological features. Overall, when a dataset stems from a similar mixture of diffusive processes precision tends to benefit, particularly in terms of recall. Our work paves the way towards understanding how distributed data fusion methods may help managing the complexity of wireless sensor networks, for instance in massive Internet of Things scenarios.

Anomaly Detection in Sensor Systems Using Lightweight Machine Learning

The maturing field of Wireless Sensor Networks (WSN) results in long-lived deployments that produce large amounts of sensor data. Lightweight online on-mote processing may improve the usage of their limited resources, such as energy, by transmitting only unexpected sensor data (anomalies). We detect anomalies by analyzing sensor reading predictions from a linear model. We use Recursive Least Squares (RLS) to estimate the model parameters, because for large datasets the standard Linear Least Squares Estimation (LLSE) is not resource friendly. We evaluate the use of fixed-point RLS with adaptive thresholding, and its application to anomaly detection in embedded systems. We present an extensive experimental campaign on generated and real-world datasets, with floating-point RLS, LLSE, and a rule-based method as benchmarks. The methods are evaluated on prediction accuracy of the models, and on detection of anomalies, which are injected in the generated dataset. The experimental results show that the proposed algorithm is comparable, in terms of prediction accuracy and detection performance, to the other LS methods. However, fixed-point RLS is efficiently implement able in embedded devices. The presented method enables online on-mote anomaly detection with results comparable to offline LS methods.

Thermal comfort in urban green spaces: a survey on a Dutch university campus

To better understand the influence of urban green infrastructure (UGI) on outdoor human thermal comfort, a survey and physical measurements were performed at the campus of the University of Groningen, The Netherlands, in spring and summer 2015. Three hundred eighty-nine respondents were interviewed in five different green spaces. We aimed to analyze people’s thermal comfort perception and preference in outdoor urban green spaces, and to specify the combined effects between the thermal environmental and personal factors. The results imply that non-physical environmental and subjective factors (e.g., natural view, quiet environment, and emotional background) were more important in perceiving comfort than the actual thermal conditions. By applying a linear regression and probit analysis, the comfort temperature was found to be 22.2xa0°C and the preferred temperature was at a surprisingly high 35.7xa0°C. This can be explained by the observation that most respondents, who live in temperate regions, have a natural tendency to describe their preferred state as “warmer” even when feeling “warm” already. Using the Kruskal-Wallis H test, the four significant factors influencing thermal comfort were people’s exposure time in green spaces, previous thermal environment and activity, and their thermal history. However, the effect of thermal history needs further investigation due to the unequal sample sizes of respondents from different climate regions. By providing evidence for the role of the objective and subjective factors on human thermal comfort, the relationship between UGI, microclimate, and thermal comfort can assist urban planning to make better use of green spaces for microclimate regulation.

Online Extreme Learning on Fixed-Point Sensor Networks

Anomaly detection is a key factor in the processing of large amounts of sensor data from Wireless Sensor Networks (WSN). Efficient anomaly detection algorithms can be devised performing online node-local computations and reducing communication overhead, thus improving the use of the limited hardware resources. This work introduces a fixed-point embedded implementation of Online Sequential Extreme Learning Machine (OS-ELM), an online learning algorithm for Single Layer Feed forward Neural Networks (SLFN). To overcome the stability issues introduced by the fixed precision, we apply correction mechanisms previously proposed for Recursive Least Squares (RLS). The proposed implementation is tested extensively with generated and real-world datasets, and compared with RLS, Linear Least Squares Estimation, and a rule-based method as benchmarks. The methods are evaluated on the prediction accuracy and on the detection of anomalies. The experimental results demonstrate that fixed-point OS-ELM can be successfully implemented on resource-limited embedded systems, with guarantees of numerical stability. Furthermore, the detection accuracy of fixed-point OS-ELM shows better generalization properties in comparison with, for instance, fixed-point RLS.

Quantifying postural control during exergaming using multivariate whole-body movement data: A self-organizing maps approach

Background Exergames are becoming an increasingly popular tool for training balance ability, thereby preventing falls in older adults. Automatic, real time, assessment of the user’s balance control offers opportunities in terms of providing targeted feedback and dynamically adjusting the gameplay to the individual user, yet algorithms for quantification of balance control remain to be developed. The aim of the present study was to identify movement patterns, and variability therein, of young and older adults playing a custom-made weight-shifting (ice-skating) exergame. Methods Twenty older adults and twenty young adults played a weight-shifting exergame under five conditions of varying complexity, while multi-segmental whole-body movement data were captured using Kinect. Movement coordination patterns expressed during gameplay were identified using Self Organizing Maps (SOM), an artificial neural network, and variability in these patterns was quantified by computing Total Trajectory Variability (TTvar). Additionally a k Nearest Neighbor (kNN) classifier was trained to discriminate between young and older adults based on the SOM features. Results Results showed that TTvar was significantly higher in older adults than in young adults, when playing the exergame under complex task conditions. The kNN classifier showed a classification accuracy of 65.8%. Conclusions Older adults display more variable sway behavior than young adults, when playing the exergame under complex task conditions. The SOM features characterizing movement patterns expressed during exergaming allow for discriminating between young and older adults with limited accuracy. Our findings contribute to the development of algorithms for quantification of balance ability during home-based exergaming for balance training.

Assessment of the masking effects of birdsong on the road traffic noise environment

This study aims to explore how the soundscape quality of traffic noise environments can be improved by the masking effects of birdsong in terms of four soundscape characteristics, i.e., perceived loudness, naturalness, annoyance and pleasantness. Four factors that may influence the masking effects of birdsong (i.e., distance of the receiver from a sound source, loudness of masker, occurrence frequencies of masker, and visibility of sound sources) were examined by listening tests. The results show that the masking effects are more significant in the road traffic noise environments with lower sound levels (e.g., <52.5 dBA), or of distance from traffic (e.g., >19u2009m). Adding birdsong can indeed increase the naturalness and pleasantness of the traffic noise environment at different distances of the receiver from a road. Naturalness, annoyance, and pleasantness, but not perceived loudness, can be altered by increasing the birdsong loudness (i.e., from 37.5 to 52.5 dBA in this study). The pleasantness of traffic noise environments increases significantly from 2.7 to 6.7, when the occurrence of birdsong over a period of 30u2009s is increased from 2 to 6 times. The visibility of the sound source also influences the masking effects, but its effect is not as significant as the effects of the three other factors.