An infrared ceiling sensor network system is reported in this study to realize behavior analysis and fall detection of a single person in the home environment. The sensors output multiple binary sequences from which we know the existence/non-existence of persons under the sensors. The short duration averages of the binary responses are shown to be able to be regarded as pixel values of a top-view camera, but more advantageous in the sense of preserving privacy. Using the “pixel values” as features, support vector machine classifiers succeeded in recognizing eight activities (walking, reading, etc.) performed by five subjects at an average recognition rate of 80.65%. In addition, we proposed a martingale framework for detecting falls in this system. The experimental results showed that we attained the best performance of 95.14% (F1 value), the FAR of 7.5% and the FRR of 2.0%. This accuracy is not sufficient in general but surprisingly high with such low-level information. In summary, it is shown that this system has the potential to be used in the home environment to provide personalized services and to detect abnormalities of elders who live alone.
Comparisons were made of general and local physical work loads between two groups of 58 Japanese and 15 Swedish nursery school teachers. Heart rate, number of steps, rating of perceived exertion (RPE), frequency and time expended with respect to trunk flexion, sitting/kneeling, and lifting/carrying loads of 1 kg or more were monitored during working hours. The average percentage heart rate increase in the maximal heart rate range was lower in the Japanese than in the Swedish teachers. However, all parameters of local physical work load indicating musculoskeletal stress were higher in the Japanese than in the Swedish teachers. The RPE was slightly higher in the Japanese than in the Swedish teachers. These features of general and local work load in the Japanese teachers were typically observed among the teachers in charge of very young children (0-2 years). The Japanese teachers in charge of children aged 3-5 years, on the other hand, had similar levels of both general and local work load as the Swedish teachers in charge of classes comprising children of various ages (1-5 years). The physical work load measured in the present study was not sufficient to explain the difference in the magnitude of musculoskeletal problems for nursery school teachers in the two countries, and other factors should now be examined.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.