0000000000821686

AUTHOR

Riccardo La Grassa

showing 2 related works from this author

A Prototype of Wireless Sensor for Data Acquisition in Energy Management Systems

2018

A prototype of a wireless sensor for monitoring electrical loads in a smart building is designed and implemented. The sensor can acquire the main electrical parameters of the connected load and, optionally, other physical quantities (e.g., room temperature). Unlike other wireless sensors in literature, the proposed sensor is cheap and small, exploits the Wi-Fi network that is commonly available inside buildings, and uses a lightweight message-based communication paradigm. Besides the sensor node, two management nodes are also implemented to manage sensor reconfiguration and the persistence of data. The measured data are stored in an SQLite database and can be used for various purposes, e.g.…

Environmental Engineeringbusiness.industryEnergy managementComputer sciencewireless sensorRenewable Energy Sustainability and the Environment020209 energyenergy management systemsmart buildingControl reconfigurationEnergy Engineering and Power Technology02 engineering and technologyIndustrial and Manufacturing EngineeringEnergy management systemData acquisitionHardware and ArchitectureSensor node0202 electrical engineering electronic engineering information engineeringWirelessMQTTElectrical and Electronic EngineeringbusinessWireless sensor networkComputer hardwareBuilding automation
researchProduct

Learning to Navigate in the Gaussian Mixture Surface

2021

In the last years, deep learning models have achieved remarkable generalization capability on computer vision tasks, obtaining excellent results in fine-grained classification problems. Sophisticated approaches based-on discriminative feature learning via patches have been proposed in the literature, boosting the model performances and achieving the state-of-the-art over well-known datasets. Cross-Entropy (CE) loss function is commonly used to enhance the discriminative power of the deep learned features, encouraging the separability between the classes. However, observing the activation map generated by these models in the hidden layer, we realize that many image regions with low discrimin…

Boosting (machine learning)Settore INF/01 - InformaticaComputer scienceGeneralizationbusiness.industryDeep learningGaussianFine-grained image classification; Loss functionPattern recognitionConvolutional neural networkLoss functionImage (mathematics)symbols.namesakeFine-grained image classificationDiscriminative modelSettore MAT/05 - Analisi MatematicasymbolsArtificial intelligencebusinessFeature learning
researchProduct