Search results for "artificial intelligence"
showing 10 items of 6122 documents
Event signal characterization for disturbance interpretation in power grid
2018
This paper presents the signal processing approach to detect and characterize the physical events that occur in power system using PMUs signals. A small window is applied so that the extracted spectral features belong to a stationary signal. This is based on applying empirical mode decomposition, followed by square root of spectral kurtosis (SRSK) for computation of statistical indices to indicate the event occurrence. Subsequently, features from these events are extracted using mel frequency cepstral coefficients on SRSK. © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/re…
Progressive transmission of secured images with authentication using decompositions into monovariate functions
2014
International audience; We propose a progressive transmission approach of an image authenticated using an overlapping subimage that can be removed to restore the original image. Our approach is different from most visible water- marking approaches that allow one to later remove the watermark, because the mark is not directly introduced in the two-dimensional image space. Instead, it is rather applied to an equivalent monovariate representation of the image. Precisely, the approach is based on our progressive transmission approach that relies on a modified Kolmogorov spline network, and therefore inherits its advantages: resilience to packet losses during transmis- sion and support of hetero…
From Signal Processing to Machine Learning
2018
This chapter reviews the main landmarks of signal processing in the 20th century from the perspective of algorithmic developments. It focuses on cross‐fertilization with the field of statistical (machine) learning in the last decades. In the 21st century, model and data assumptions as well as algorithmic constraints are no longer valid, and the field of machine‐learning signal processing has erupted, with many successful stories to tell. The chapter also focuses on digital signal processing (DSP), which deals with the analysis of digitized and discrete sampled signals. Machine learning is a branch of computer science and artificial intelligence that enables computers to learn from data. Mac…
Mutual Information Analysis of Brain-Heart Interactions in Epileptic Children
2021
In this work we apply the network physiology paradigm to retrieve information from central and autonomic nervous systems before focal epileptic seizure, represented respectively by electroencephalogram (EEG) signals and R-R intervals (RRI), and investigate on the presence and strength of brain-heart interactions by computing mutual information (MI) measures. Statistical significance of MI values was tested through surrogate time series generated with the random shuffle approach. Our results suggest that the proposed method for aligning signals representing brain and heart activity measured with different sampling rates, is capable of revealing coupling between RRI representing heart system,…
Postprocessing algorithm for automated analysis of pelvic intraoperative neuromonitoring signals
2016
Abstract Two dimensional pelvic intraoperative neuromonitoring (pIONM®) is based on electric stimulation of autonomic nerves under observation of electromyography of internal anal sphincter (IAS) and manometry of urinary bladder. The method provides nerve identification and verification of its’ functional integrity. Currently pIONM® is gaining increased attention in times where preservation of function is becoming more and more important. Ongoing technical and methodological developments in experimental and clinical settings require further analysis of the obtained signals. This work describes a postprocessing algorithm for pIONM® signals, developed for automated analysis of huge amount of …
Comparison of remote photoplethysmography signals acquired by ultra-low noise camera and conventional camera during physiological tests
2017
In present study, remote photoplethysmography signals acquired by ultra-low noise camera and conventional camera were compared during different skin microcirculation provocation tests. The aim of work was to reveal how much of camera dynamic range and noise contribute to blood perfusion signal quality. Results demonstrate comparable capabilities of both cameras for skin perfusion monitoring.
Deep learning algorithms for gravitational waves core-collapse supernova detection
2021
The detection of gravitational waves from core-collapse supernova (CCSN) explosions is a challenging task, yet to be achieved, in which it is key the connection between multiple messengers, including neutrinos and electromagnetic signals. In this work, we present a method for detecting these kind of signals based on machine learning techniques. We tested its robustness by injecting signals in the real noise data taken by the Advanced LIGO-Virgo network during the second observation run, O2. We trained three newly developed convolutional neural networks using time-frequency images corresponding to injections of simulated phenomenological signals, which mimic the waveforms obtained in 3D nume…
Miten viittomakielen korpusta luodaan ja mihin sitä tarvitaan? Viittomakielten korpukset ja niiden tehtävät
2020
Artikkeli käsittelee suomalaisen ja suomenruotsalaisen viittomakielen korpusten luontia CFINSL-projektissa (Corpus project of Finland’s sign languages, Suomen viittomakielten korpusprojekti). Viittomakielillä ei ole kirjoitettua muotoa, joten korpusten laatiminen vaatii erilaista lähestymistä kuin korpusten luonti sellaisille puhutuille kielille, joilla on kirjoitettu muoto. Artikkelissa kuvataan ne menetelmät, joilla Jyväskylän yliopiston viittomakielen keskuksessa on koottu aineistoa suomalaisen ja suomenruotsalaisen viittomakielen korpukseen. Lisäksi kuvataan korpusaineiston teknistä käsittelyä, annotointia, metatietojen keruuta ja käsittelyä sekä aineiston säilytystä ja tutkijoiden käyt…
Energy balance in single exposure multispectral sensors
2013
International audience; Recent simulations of multispectral sensors are based on a simple Gaussian model, which includes filters transmittance and substrate absorption. In this paper we want to make the distinction between these two layers. We discuss the balance of energy by channel in multispectral solid state sensors and propose an updated simple Gaussian model to simulate multispectral sensors. Results are based on simulation of typical sensor configurations.
The silver collection of San Gennaro treasure (Neaples): A multivariate statistic approach applied to X-ray fluorescence data
2021
Abstract In this work we report an X-ray fluorescence spectroscopy (XRF) study combined with a multivariate approach allowing to detect compositional differences and similarities among the alloys used in realization of silver collection of San Gennaro items collection. The San Gennaro treasure in Naples (Italy) represents, in fact, one of the most important silver collections in the world. The classification of the collection items is very complex, not only for the large number of objects, but also in consideration that between 1600 and 1700, in Naples, more than 350 laboratories were active, most of them specialized in specific art of work. As a consequence, a given collection object could…