S
Silvia Cascianelli
Researcher at University of Modena and Reggio Emilia
Publications - 52
Citations - 439
Silvia Cascianelli is an academic researcher from University of Modena and Reggio Emilia. The author has contributed to research in topics: Computer science & Convolutional neural network. The author has an hindex of 8, co-authored 37 publications receiving 205 citations. Previous affiliations of Silvia Cascianelli include Polytechnic University of Milan & University of Perugia.
Papers
More filters
Journal ArticleDOI
Robust visual semi-semantic loop closure detection by a covisibility graph and CNN features
Silvia Cascianelli,Gabriele Costante,Enrico Bellocchio,Paolo Valigi,Mario Luca Fravolini,Thomas A. Ciarfuglia +5 more
TL;DR: A novel strategy is proposed that models the visual scene by preserving its geometric and semantic structure and improves appearance invariance through a robust visual representation and is compared with a state-of-the-art visual navigation algorithm.
Book ChapterDOI
Dimensionality Reduction Strategies for CNN-Based Classification of Histopathological Images
Silvia Cascianelli,Raquel Bello-Cerezo,Francesco Bianconi,Mario Luca Fravolini,Mehdi Belal,Barbara Palumbo,Jakob Nikolas Kather +6 more
TL;DR: The results show that it is possible to reduce CNN-based features by a high ratio with a moderate decrease in accuracy with respect to the original values, and a novel reduction strategy based on the cross-correlation between the components of the feature vector is proposed.
Journal ArticleDOI
Precision Computation of Wind Turbine Power Upgrades: An Aerodynamic and Control Optimization Test Case
TL;DR: In this article, a general method is formulated for assessing the wind turbine power upgrades using operational data based on the study of the residuals between the measured power output and a judicious model of the power output itself, before and after the upgrade.
Journal ArticleDOI
Machine learning for RNA sequencing-based intrinsic subtyping of breast cancer
TL;DR: This work found that standard PAM50 is profoundly affected by the composition of the sample cohort used for reference construction, and proposed a strategy, named AWCA, to mitigate this issue, improving classification robustness, with over 90% of concordance, and prognostic ability; it is shown that AWCA-based Pam50 can even be applied as single-sample method.
Journal ArticleDOI
Full-GRU Natural Language Video Description for Service Robotics Applications
TL;DR: This letter investigates the robot side of the interface, in particular the ability to generate natural language descriptions for the scene it observes via a deep recurrent neural network architecture completely based on the gated recurrent unit paradigm.