Monitoring electricity consumption in the home is an important way to help reduce energy usage and Non-Intrusive Load Monitoring (NILM) techniques are a promising approach to obtain estimates of the electrical power consumption of individual appliances from aggregate measurements of voltage and/or current in the distribution system. In this paper, we discuss event detection algorithms used in the NILM literature and propose new metrics for evaluating them. In particular, we introduce metrics that incorporate information contained in the power signal instead of strict detection rates. We show that this information is important for NILM applications with the goal of improving appliance energy disaggregation. Our work was carried out on a publicly-available week-long dataset of real residential power usage.

A volcanic eruption early warning has to be launched with effectiveness and within the shortest time possible, which imposes the requirement of using real-time (RT) systems. In this setting, volcano-monitoring systems using wireless sensor networks (WSNs) may play a key role. Previous work did not report detailed-enough performance evaluation, in order to identify their main constraints as RT systems, either in simulation tools or in testbed scenarios. The aim of this paper was to identify the optimum number of sensors to be deployed a posteriori, based on simulation results considering throughput, packet loss, and end-to-end delay, as metrics to satisfy the RT requirements. We corroborated the simulation results obtained by a testbed deployment within a controlled environment. We determined that optimal scenario for volcano monitoring is a random topology, and the results show that 12 nodes should be deployed as maximum to satisfy the RT constraints. To test the system in a real scenario, 10 sensors were deployed in a strategic area at Cotopaxi Volcano, and information was collected during three days of continuous monitoring. This information was sent to a remote surveillance laboratory located 45 km away from the station placed at the volcano using WiFi-based long-distance technology. Our study shows that the coordinator node is the main bottleneck in the real application scenario, given that its processing rate provokes an excessive time delay near to 3 s, which has to be solved to satisfy the RT requirements. We conclude that a comprehensive study, including simulation, testbed, and in-situ deployment, provides valuable information for the specifications to be accounted in permanent WSN RT volcano monitoring.

Geophysics experts are interested in understanding the behavior of volcanoes and forecasting possible eruptions by monitoring and detecting the increment on volcano-seismic activity, with the aim of safeguarding human lives and material losses. This paper presents an automatic volcanic event detection and classification system, which considers feature extraction and feature selection stages, to reduce the processing time toward a reliable real-time volcano early warning system (RT-VEWS). We built the proposed approach in terms of the seismicity presented in 2009 and 2010 at the Cotopaxi Volcano located in Ecuador. In the detection stage, the recordings were time segmented by using a nonoverlapping 15-s window, and in the classification stage, the detected seismic signals were 1-min long. For each detected signal conveying seismic events, a comprehensive set of statistical, temporal, spectral, and scale-domain features were compiled and extracted, aiming to separate long-period (LP) events from volcano-tectonic (VT) earthquakes. We benchmarked two commonly used types of feature selection techniques, namely, wrapper (recursive feature extraction) and embedded (cross-validation and pruning). Each technique was used within a suitable and appropriate classification algorithm, either the support vector machine (SVM) or the decision trees. The best result was obtained by using the SVM classifier, yielding up to 99% accuracy in the detection stage and 97% accuracy and sensitivity in the event classification stage. Selected features and their interpretation were consistent among different input spaces in simple terms of the spectral content of the frequency bands at 3.1 and 6.8 Hz. A comparative analysis showed that the most relevant features for automatic discrimination between LP and VT events were one in the time domain, five in the frequency domain, and nine in the scale domain. Our study provides the framework for an event classification system with high accuracy and reduced computational requirements, according to the orientation toward a future RT-VEWS.