Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Successful ECG monitoring algorithms often rely on learned models to describe the heartbeats morphology. Unfortunately, when the heart rate increases the heartbeats get transformed, and a model that can properly describe the heartbeats of... more
Successful ECG monitoring algorithms often rely on learned models to describe the heartbeats morphology. Unfortunately, when the heart rate increases the heartbeats get transformed, and a model that can properly describe the heartbeats of a specific user in resting conditions might not be appropriate for monitoring the same user during everyday activities. We model heartbeats by dictionaries yielding sparse representations and propose a novel domain-adaptation solution which transforms user-specific dictionaries according to the heart rate. In particular, we learn suitable linear transformations from a large dataset containing ECG tracings, and we show that these transformations can successfully adapt dictionaries when the heart rate changes. Remarkably, the same transformations can be used for multiple users and different sensing apparatus. We investigate the implications of our findings in ECG monitoring by wearable devices, and present an efficient implementation of an anomaly-detection algorithm leveraging such transformations.
Research Interests:
Supercontinuum light is generated by a train of laser pulses propagating in an optical fiber. The parameters characterizing these pulses influence the spectrum of the light as it exits the fiber. While spectrum generation is a direct... more
Supercontinuum light is generated by a train of laser pulses propagating in an optical fiber. The parameters characterizing these pulses influence the spectrum of the light as it exits the fiber. While spectrum generation is a direct process governed by nonlinear equations that can be reproduced through numerical simulation, determining the parameters of the pulse generating a given spectrum is a difficult inverse problem. Solving this inverse problem has a relevant practical implication, as it allows generating beams with desired spectral properties. We solve this multidimensional parameter estimation problem by training a neural network and we introduce, as key technical contribution, a weighted loss function that improves the estimation accuracy. Most remarkably, this loss function is not specific to the considered supercontinuum scenario, but has the potential to improve solutions of similar inverse problems where the forward process can be reproduced via computationally demanding simulations. Our experiments demonstrate the effectiveness of the pursued approach and of our weighted loss function.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Chips in semiconductor manufacturing are produced in circular wafers that are constantly monitored by inspection machines. These machines produce a wafer defect map, namely a list of defect locations which corresponds to a very large,... more
Chips in semiconductor manufacturing are produced in circular wafers that are constantly monitored by inspection machines. These machines produce a wafer defect map, namely a list of defect locations which corresponds to a very large, sparse and binary image. While in these production processes it is normal to see defects that are randomly spread through the wafer, specific defect patterns might indicate problems in the production that have to be promptly identified.
Research Interests:
Research Interests:
Research Interests:
Optical fiber links are customarily monitored by Optical Time Domain Reflectometer (OTDR), an optoelectronic instrument that measures the scattered or reflected light along the fiber and returns a signal, namely the OTDR trace. OTDR... more
Optical fiber links are customarily monitored by Optical Time Domain Reflectometer (OTDR), an optoelectronic instrument that measures the scattered or reflected light along the fiber and returns a signal, namely the OTDR trace. OTDR traces are typically analyzed by experts in laboratories or by hand-crafted algorithms running in embedded systems to localize critical events occurring along the fiber. In this work, we address the problem of automatically detecting optical events in OTDR traces through a deep learning model that can be deployed in embedded systems. In particular, we take inspiration from Faster R-CNN and present the first 1D object-detection neural network for OTDR traces. Thanks to an ad-hoc preprocessing pipeline for OTDR traces, we can also identify unknown events, namely events that are not represented in training data but that might indicate rare and unforeseen situations that need to be reported. The resulting network brings several advantages with respect to exi...
Research Interests:
This dataset is designed to test Machine-Learning techniques on Computational Fluid Dynamics (CFD) data.<br> <br> It contains two-dimensional RANS simulations of the turbulent flow around NACA 4-digits airfoils, at fixed angle... more
This dataset is designed to test Machine-Learning techniques on Computational Fluid Dynamics (CFD) data.<br> <br> It contains two-dimensional RANS simulations of the turbulent flow around NACA 4-digits airfoils, at fixed angle of attack (10 degrees) and at a fixed Reynolds number (3x10^6). The whole NACA family is spawned. The present dataset contains 425 geometries, 2600 further geometries are published in accompanying repository (10.5281/zenodo.4106752). For further information refer to: Schillaci, A., Quadrio, M., Pipolo, C., Restelli, M., Boracchi, G. "Inferring Functional Properties from Fluid Dynamics Features" 2020 25th International Conference on Pattern Recognition (ICPR) Milan, Italy, Jan 10-15, 2021
We present a prototype wearable device able to perform online and long-term monitoring of ECG signals, and detect anomalous heartbeats such as arrhythmias. Our solution is based on user-specific dictionaries which characterizes the... more
We present a prototype wearable device able to perform online and long-term monitoring of ECG signals, and detect anomalous heartbeats such as arrhythmias. Our solution is based on user-specific dictionaries which characterizes the morphology of normal heartbeats and are learned every time the device is positioned. Anomalies are detected via an optimized sparse coding procedure, which assesses the conformance of each heartbeat to the user-specific dictionary. The dictionaries are adapted during online monitoring, to track heart rate variations occurring during everyday activities. Perhaps surprisingly, dictionary adaptation can be successfully performed by transformations that are user-independent and learned from large datasets of ECG signals.
Research Interests:
Research Interests:
Nanoproducts represent a potential growing sector and nano brous materials are widely requested in industrial, medical and environmental applications. Unfortunately, the production processes at the nanoscale are difficult to control, and... more
Nanoproducts represent a potential growing sector and nano brous materials are widely requested in industrial, medical and environmental applications. Unfortunately, the production processes at the nanoscale are difficult to control, and produced artifacts often exhibit local defects that prevent their functional properties. We present a fully-automated solution to detect defects in nano brous materials during their production, yielding smartmanufacturing systems that reduce quality-inspection times and wastes. We analyze SEM images of nano brous materials and learn, during an initial training phase, a model yielding sparse representations of the structures that characterize correctly produced nano bers. Defects are then detected by analyzing patches in test images and assessing the goodness-oft of each patch to the learned model. The proposed solution has been successfully validated over 45 images acquired from samples produced by a prototype electrospinning machine. The low comput...
Research Interests:
Research Interests:
Optical fiber links are customarily monitored by Optical Time Domain Reflectometer (OTDR), an optoelectronic instrument that measures the scattered or reflected light along the fiber and returns a signal, namely the OTDR trace. OTDR... more
Optical fiber links are customarily monitored by Optical Time Domain Reflectometer (OTDR), an optoelectronic instrument that measures the scattered or reflected light along the fiber and returns a signal, namely the OTDR trace. OTDR traces are typically analyzed by experts in laboratories or by hand-crafted algorithms running in embedded systems to localize critical events occurring along the fiber. In this work, we address the problem of automatically detecting optical events in OTDR traces through a deep learning model that can be deployed in embedded systems. In particular, we take inspiration from Faster R-CNN and present the first 1D object-detection neural network for OTDR traces. Thanks to an ad-hoc preprocessing pipeline for OTDR traces, we can also identify unknown events, namely events that are not represented in training data but that might indicate rare and unforeseen situations that need to be reported. The resulting network brings several advantages with respect to exi...
Research Interests:
This dataset is designed to test Machine-Learning techniques on Computational Fluid Dynamics (CFD) data.<br> <br> It contains two-dimensional RANS simulations of the turbulent flow around NACA 4-digits airfoils, at fixed angle... more
This dataset is designed to test Machine-Learning techniques on Computational Fluid Dynamics (CFD) data.<br> <br> It contains two-dimensional RANS simulations of the turbulent flow around NACA 4-digits airfoils, at fixed angle of attack (10 degrees) and at a fixed Reynolds number (3x10^6). The whole NACA family is spawned. The present dataset contains 425 geometries, 2600 further geometries are published in accompanying repository (10.5281/zenodo.4106752). For further information refer to: Schillaci, A., Quadrio, M., Pipolo, C., Restelli, M., Boracchi, G. "Inferring Functional Properties from Fluid Dynamics Features" 2020 25th International Conference on Pattern Recognition (ICPR) Milan, Italy, Jan 10-15, 2021
We present a prototype wearable device able to perform online and long-term monitoring of ECG signals, and detect anomalous heartbeats such as arrhythmias. Our solution is based on user-specific dictionaries which characterizes the... more
We present a prototype wearable device able to perform online and long-term monitoring of ECG signals, and detect anomalous heartbeats such as arrhythmias. Our solution is based on user-specific dictionaries which characterizes the morphology of normal heartbeats and are learned every time the device is positioned. Anomalies are detected via an optimized sparse coding procedure, which assesses the conformance of each heartbeat to the user-specific dictionary. The dictionaries are adapted during online monitoring, to track heart rate variations occurring during everyday activities. Perhaps surprisingly, dictionary adaptation can be successfully performed by transformations that are user-independent and learned from large datasets of ECG signals.