Conventionally, multiple physiological signals are used in the field of stress realization. Although many studies have applied various methods in feature selection and classification, a desirable performance has not yet been achieved. This paper presents a novel method of stress level classification using physiological signals during the real-world driving task. Exploring the most reliable analysis method on a comprehensive physiological signal for stress realization has been commonly investigated in various studies. To obtain a high accuracy approach, a proper classification method should be applied to the most relevant physiological signal. In this study, we evaluate the feasibility and effectiveness of the analysis of variance (ANOVA) classifier learner on the single Galvanic Skin Response (GSR) signal. Three levels of stress are taken into account and two independent features including rising time and amplitude are extracted. These two features are extracted from foot and hand GSR signals in three different scenarios for the sake of training. The result indicates that the foot amplitude feature of the GSR signal solely is a reliable source of stress classification with an accuracy rate of 95.83% by applying the ANOVA approach. Accordingly, this methodology can substantially reduce the necessity of resorting to the high number of sensors and the corresponding computational burden associated with signal analysis. Besides, reducing the number of sensors during the measurement procedure would increase drivers’ safety by reducing the interference between human and measurement devices. In this study, the real data collected by Picard and his co-workers are used, available in the PHYSIONET database.
Distribution system state estimation (DSSE) is a critical analysis tool for active distribution networks (DNs). Unlike weighted least squares techniques, which are static DSSE methods, the augmented complex Kalman filter (ACKF) is a novel technique that considers the system's dynamic behavior. Currently, most DNs integrate a large number of unmonitored residential photovoltaic (PV) generations. Existing unmeasured PV sources violate the white noise assumption in Kalman and least-squaresbased estimators, causing the estimator to be biased. Because the one-step difference of aggregated customer demand is characterized as white noise, the suggested PV estimation technique based on the differencing strategy is used to decouple PV from the measured load. Using the specified contribution factors, the new online pseudo current injections are generated. In addition, the estimator's accuracy is improved by using a new PV-scalingaided ACKF approach based on the PV separation strategy. For validation purposes, this method is applied to real DN case studies. This study also makes use of an actual dataset to illustrate the efficacy of the proposed technique. The proposed technique outperforms the existing snapshot and dynamic DSSE techniques, and significant improvements are achieved in terms of accuracy and computational cost.
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.