Non-intrusive load monitoring (NILM) is the main method used to monitor the energy footprint of a residential building and disaggregate total electrical usage into appliance-related signals. The most common disaggregation algorithms are based on the Hidden Markov Model, while solutions based on deep neural networks have recently caught the attention of researchers. In this work we address the problem through the recognition of the state of activation of the appliances using a fully convolutional deep neural network, borrowing some techniques used in the semantic segmentation of images and multilabel classification. This approach has allowed obtaining high performances not only in the recognition of the activation state of the domestic appliances but also in the estimation of their consumptions, improving the state of the art for a reference dataset.
Abstract-Important objectives of the four-year enviroGRIDS project encompass the improvement of transnational cooperation, the use of state of the art Information and Communication Technologies for data analysis and sharing and the application of environmental models for monitoring present and predicting future states of the environment for the Black Sea region. In such a transnational context, there is a dire need for the environmental sciences to evolve from a simple, local-scale vision toward a complex, multi-user, multilayered holistic approach. BASHYT (http://swat.crs4.it/) is a Web based, GIS oriented, information and support tool, part of the Black Sea Catchment -Observation System (BSC-OS). It exposes a set of applications for data management, analysis and visualization and a complete server and client side development framework (wiki like) to create Web contents. The core of the portal relies on the hydrological semi distributed SWAT code to model the water cycle and predict the effect of management decisions on water, sediment, nutrient and pesticide yields on large river basins. Furthermore, BASHYT aims at quantifying the interconnectedness between (human and natural) pressures and states of water body receptors at different space and time scales. The aim is to enhance environmental management capacity to assess water resource and to share and process large amounts of key environmental information. Within an experimental and innovative programming environment, modules have been developed to run near real-time applications based on numerical solvers (SWAT is just one example), run pre-and post-processing codes, query and map results through the Web browser. A set of web OGC services and a complete Application Programming Interface (API) are also exposed by the portal. We expect to improve the ways in which land management systems can operate and improve model usability to aid in making management decisions and watershed-scale modeling.
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.