Search

With the rise of Internet-of-Things devices, the analysis of sensor-generated energy time series data has become increasingly important. This is especially crucial for detecting rare events like unusual electricity usage or water leakages in residential and commercial buildings, which is essential for optimizing energy efficiency and reducing costs. However, existing detection methods on large-scale data may fail to correctly detect rare events when they do not behave significantly differently from standard events or when their attributes are non-stationary. Additionally, the capacity of computational resources to analyze all time series data generated by an increasing number of sensors becomes a challenge. This situation creates an emergent demand for a workload-bounded strategy. To ensure both effectiveness and efficiency in detecting rare events in massive energy time series, we propose a heuristic-based framework called HALE. This framework utilizes an explore–exploit selection process that is specifically designed to recognize potential features of rare events in energy time series. HALE involves constructing an attribute-aware graph to preserve the attribute information of rare events. A heuristic-based random walk is then derived based on partial labels received at each time period to discover the non-stationarity of rare events. Potential rare event data are selected from the attribute-aware graph, and existing detection models are applied for final confirmation. Our study, which was conducted on three actual energy datasets, demonstrates that the HALE framework is both effective and efficient in its detection capabilities. This underscores its practicality in delivering cost-effective energy monitoring services. [ABSTRACT FROM AUTHOR]

Background: The continuous monitoring of body surface temperature has been proven to help detect potential fever events in hospitalized patients. However, the efficacy of using body surface temperature to detect fever in older adults remains unclear due to the relatively low and slower-to-change body surface temperature in this population. Purpose: This study was designed to investigate 1) the relationship between changes in body surface and routine tympanic temperatures, 2) the correlation between body surface temperature measurement frequency and detection of fever, and 3) the factors related to the incidence of fever in hospitalized older adults. Methods: A prospective study was conducted on 33 hospitalized older adults aged 65 years or older who were suspected to have or diagnosed with an infection in an infectious disease and medical ward at a medical center in southern Taiwan from March to November 2020. Demographic, routine tympanic temperature, and heart rate data were collected by reviewing the participants' medical records. Body surface temperatures were monitored continuously using HEARThermo every 10 seconds until one of the following conditions were met: hospital discharge, no fever for three continuous days, and HEARThermo was removed. Descriptive analysis was used to compare the variations in body surface temperature and routine tympanic temperature measurements. Pearson correlation was used to analyze the correlation between different measurement frequencies and fever events. Finally, mixed effects logistic regression was used to analyze the factors significantly related to fever events. Results: Seven hundred and twenty routine body temperature measurements were taken, with 209 (29.0%) fever events detected in 23 (69.7%) of the participants. The body surface temperatures were more closely correlated with tympanic temperatures during fever events than non-fever events (r = .260, p < .001). More fever events were detected using body surface temperature monitoring frequencies of every 10 seconds and every 1 minute. After controlling for demographic factors, the results of the mixed effect model indicate that body surface temperature and heart rate are significant factors related to fever events in hospitalized older adults (odds ratio, OR: 1.74, p < .001; OR: 1.11, p < .001). Conclusions/ Implications for Practice: The continuous monitoring of body surface temperature may improve the detection of fever events in hospitalized older adults. The application of wearable devices and cloud platforms may further facilitate the real-time assessment and care capabilities of nurses, thus reducing their workload and improving care quality. [ABSTRACT FROM AUTHOR]