User profiles for D. Mavroeidis
Dimitrios MavroeidisMicrosoft Verified email at microsoft.com Cited by 747 |
Multiscale event detection in social media
… 14c, d, we see two clusters corresponding to the Raise Cache tech event (cluster 5) and
the Mastercard free lunch promotion event (cluster 9), respectively, both of which are more …
the Mastercard free lunch promotion event (cluster 9), respectively, both of which are more …
[HTML][HTML] The effects of artificial intelligence assistance on the radiologists' assessment of lung nodules on CT scans: a systematic review
…, JR Pluyter, I Jacobs, D Mavroeidis… - Journal of Clinical …, 2023 - mdpi.com
To reduce the number of missed or misdiagnosed lung nodules on CT scans by radiologists,
many Artificial Intelligence (AI) algorithms have been developed. Some algorithms are …
many Artificial Intelligence (AI) algorithms have been developed. Some algorithms are …
Predicting the future from first person (egocentric) vision: A survey
… RGB-D cameras may also be used in the considered scenario, but to the best of our
knowledge, currently there is no works which uses depth for making predictions about the future. …
knowledge, currently there is no works which uses depth for making predictions about the future. …
Towards radiologist-level cancer risk assessment in CT lung screening using deep learning
… 2A–D we can observe that the performance of our framework was stable across the different
datasets and achieved an AUC (Area Under the Curve) score between 86–94%. It is worth …
datasets and achieved an AUC (Area Under the Curve) score between 86–94%. It is worth …
[HTML][HTML] A robust model selection framework for fault detection and system health monitoring with limited failure examples: Heterogeneous data fusion and formal …
R Rocchetta, Q Gao, D Mavroeidis… - Engineering Applications of …, 2022 - Elsevier
… In the remainder of this work, we will assume the samples in D to come from an unknown
(… Moreover, the data set D is highly unbalanced due to the small number of failure examples. …
(… Moreover, the data set D is highly unbalanced due to the small number of failure examples. …
[HTML][HTML] Computer-aided detection for pancreatic cancer diagnosis: radiological challenges and future directions
…, I Jacobs, JR Pluyter, D Mavroeidis… - Journal of Clinical …, 2023 - mdpi.com
Radiological imaging plays a crucial role in the detection and treatment of pancreatic ductal
adenocarcinoma (PDAC). However, there are several challenges associated with the use of …
adenocarcinoma (PDAC). However, there are several challenges associated with the use of …
Word sense disambiguation for exploiting hierarchical thesauri in text classification
… From the above we conclude that, if we construct a matrix D … Based on D, we move on to
define the kernel between two … various configurations for the rows of D. More precisely, we have …
define the kernel between two … various configurations for the rows of D. More precisely, we have …
Untrimmed action anticipation
Egocentric action anticipation consists in predicting a future action the camera wearer will
perform from egocentric video. While the task has recently attracted the attention of the …
perform from egocentric video. While the task has recently attracted the attention of the …
Accelerating spectral clustering with partial supervision
D Mavroeidis - Data Mining and Knowledge Discovery, 2010 - Springer
… It should be noted that large values for parameter γ could lead to a Lsemi = D −1/2Wsemi D
−1/2 matrix with Wsemi containing negative values. Although in this case Lsemi will not be a …
−1/2 matrix with Wsemi containing negative values. Although in this case Lsemi will not be a …
Feature selection for k-means clustering stability: theoretical analysis and an algorithm
D Mavroeidis, E Marchiori - Data Mining and Knowledge Discovery, 2014 - Springer
… In the context of this paper we are interested in efficient greedy solutions, thus we will
focus on certain algorithmic results that were presented in d’Aspremont et al. (2007, 2008). A …
focus on certain algorithmic results that were presented in d’Aspremont et al. (2007, 2008). A …