Camera clustering for scalable stream-based active distillation

Autor: Manjah, Dani, Cacciarelli, Davide, De Vleeschouwer, Christophe, Macq, Benoit

We present a scalable framework designed to craft efficient lightweight models for video object detection utilizing self-training and knowledge distillation techniques. We scrutinize methodologies for the ideal selection of training images from video

Externí odkaz: http://arxiv.org/abs/2404.10411

Three-part humeral head fractures treated with a definite construct of blocked threaded wires: finite element and parametric optimization analysis

Autor: Gumina, Stefano, Candela, Vittorio, Cacciarelli, Arianna, Iannuzzi, Eleonora, Formica, Giovanni, Lacarbonara, Walter

Publikováno v: In JSES International November 2021 5(6):983-991

Stream-based active learning with linear models

Autor: Davide Cacciarelli, Murat Kulahci, John Sølve Tyssedal

Publikováno v: Cacciarelli, D, Kulahci, M & Tyssedal, J S 2022, ' Stream-based active learning with linear models ', Knowledge-Based Systems, vol. 254, 109664 . https://doi.org/10.1016/j.knosys.2022.109664
Knowledge-Based Systems

The proliferation of automated data collection schemes and the advances in sensorics are increasing the amount of data we are able to monitor in real-time. However, given the high annotation costs and the time required by quality inspections, data is

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4eaa5fd11cd31ab7cb2ff262682b250e
http://arxiv.org/abs/2207.09874

A novel fault detection and diagnosis approach based on orthogonal autoencoders

Autor: Davide Cacciarelli, Murat Kulahci

Publikováno v: Cacciarelli, D & Kulahci, M 2022, ' A novel fault detection and diagnosis approach based on orthogonal autoencoders ', Computers and Chemical Engineering, vol. 163, 107853 . https://doi.org/10.1016/j.compchemeng.2022.107853
Computers and Chemical Engineering

In recent years, there have been studies focusing on the use of different types of autoencoders (AEs) for monitoring complex nonlinear data coming from industrial and chemical processes. However, in many cases the focus was placed on detection. As a

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c4bba7d6a2a044f657df3f9a5be4083e
https://orbit.dtu.dk/en/publications/95736a1d-5a34-4262-b595-6ca9db0c5a9a

Preemptive therapy for cytomegalovirus based on real-time measurement of viral load in liver transplant recipients

Autor: Sun, Hsin-Yun, Cacciarelli, Thomas V., Wagener, Marilyn M., Singh, Nina

Publikováno v: In Transplant Immunology 2010 23(4):166-169