Power quality assessment is an important performance measurement in smart grids. Utility companies are interested in power quality monitoring even in the low level distribution side such as smart meters. Addressing this issue, in this study, we propose segregation of the power disturbance from regular values using one-class support vector machine (OCSVM). To precisely detect the power disturbances of a voltage wave, some practical wavelet filters are applied. Considering the unlimited types of waveform abnormalities, OCSVM is picked as a semi-supervised machine learning algorithm which needs to be trained solely on a relatively large sample of normal data. This model is able to automatically detect the existence of any types of disturbances in real time, even unknown types which are not available in the training time. In the case of existence, the disturbances are further classified into different types such as sag, swell, transients and unbalanced. Being light weighted and fast, the proposed technique can be integrated into smart grid devices such as smart meter in order to perform a real-time disturbance monitoring. The continuous monitoring of power quality in smart meters will give helpful insight for quality power transmission and management.

Background Medication-related hospital admissions (MRAs) are frequently used to measure outcomes in studies involving medication reviews. The process of identifying MRAs is subjective and time-consuming, and practical, validated alternatives are required. Objective The aim of this study was to develop and validate a practical tool to identify MRAs. Setting Uppsala University Hospital, Sweden. Method We reviewed existing literature on methods to identify MRAs. The tool AT-HARM10 was developed using an iterative process including content validity and feasibility testing. The tool’s inter-rater reliability (IRR) and criterion-related validity (CRV) were assessed: four pairs of either final-year undergraduate or postgraduate pharmacy students applied the tool to one of two batches of 50 older patients’ hospital admissions. Assessment of the same 100 admissions by two experienced clinicians acted as gold standard. Main outcome measure Cohen’s and Fleiss’ kappa for IRR, and sensitivity, specificity, and positive and negative predictive value for CRV. Results AT-HARM10 consists of ten closed questions to distinguish between admissions that are unlikely to be and those that are possibly medication-related. The IRR was moderate to substantial (Cohen’s kappa values were 0.45–0.75 and Fleiss’ kappa values were 0.46 and 0.58). The sensitivity and specificity values were 70/86% and 74/70%, positive and negative predictive values were 73/74% and 71/83% respectively. Both AT-HARM10 and the gold standard identified approximately 50% of the admissions as MRAs. Conclusion AT-HARM10 has been developed as a practical tool to identify MRAs and the tool is valid for use in older patients by final-year undergraduate and postgraduate pharmacy students.