D
Diego Carrera
Researcher at Polytechnic University of Milan
Publications - 30
Citations - 422
Diego Carrera is an academic researcher from Polytechnic University of Milan. The author has contributed to research in topics: Change detection & Sparse approximation. The author has an hindex of 10, co-authored 26 publications receiving 290 citations. Previous affiliations of Diego Carrera include Tampere University of Technology & STMicroelectronics.
Papers
More filters
Journal ArticleDOI
Defect Detection in SEM Images of Nanofibrous Materials
TL;DR: This work presents a novel solution to detect defects in nanofibrous materials by analyzing scanning electron microscope images using an algorithm that learns, during a training phase, a model yielding sparse representations of the structures that characterize correctly produced nan ofiborus materials.
Proceedings ArticleDOI
Detecting anomalous structures by convolutional sparse models
TL;DR: The experiments demonstrate that a convolutional sparse model provides better anomaly-detection performance than an equivalent method based on standard patch-based sparsity and highlight that monitoring the local group sparsity, namely the spread of nonzero coefficients across different maps, is essential for detecting anomalous regions.
Journal ArticleDOI
Online anomaly detection for long-term ECG monitoring using wearable devices
TL;DR: This work proposes an online ECG monitoring solution where normal heartbeats of each specific user are modeled by dictionaries yielding sparse representations, andheartbeats that do not conform to this model are detected as anomalous, thus enabling online and long-term monitoring.
Proceedings ArticleDOI
Novelty detection in images by sparse representations
TL;DR: Here, a model based on sparse representations is considered, and it is shown that jointly monitoring the sparsity and the reconstruction error of such representation substantially improves the detection performance with respect to other approaches leveraging sparse models.
Proceedings Article
QuantTree: Histograms for change detection in multivariate data streams
TL;DR: QuantTree, a recursive binary splitting scheme that adaptively defines the histogram bins to ease the detection of any distribution change, is presented, which is very effective in detecting changes in high dimensional data streams.