Erion-Vasilis Pikoulis

Erion-Vasilis Pikoulis
University of Patras | UP · Department of Computer Engineering and Informatics

Doctor of Philosophy

About

29
Publications
1,934
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
51
Citations

Publications

Publications (29)
Article
Full-text available
Sign language (SL) translation constitutes an extremely challenging task when undertaken in a general unconstrained setup, especially in the absence of vast training datasets that enable the use of end-to-end solutions employing deep architectures. In such cases, the ability to incorporate prior information can yield a significant improvement in th...
Chapter
Deep learning and especially the use of Deep Neural Networks (DNNs) provide impressive results in various regression and classification tasks. However, to achieve these results, there is a high demand for computing and storing resources. This becomes problematic when, for instance, real-time mobile applications are considered, in which the involved...
Article
Automatic moment tensor (MT) determination is essential for real‐time seismological applications. In this article, Gisola, a highly evolved software for MT determination, oriented toward high‐performance computing, is presented. The program employs enhanced algorithms for waveform data selection via quality metrics, such as signal‐to‐noise ratio, w...
Preprint
Full-text available
Automotive Cyber-Physical Systems (ACPS) have attracted a significant amount of interest in the past few decades, while one of the most critical operations in these systems is the perception of the environment. Deep learning and, especially, the use of Deep Neural Networks (DNNs) provides impressive results in analyzing and understanding complex an...
Preprint
Full-text available
Deep learning and especially the use of Deep Neural Networks (DNNs) provides impressive results in various regression and classification tasks. However, to achieve these results, there is a high demand for computing and storing resources. This becomes problematic when, for instance, real-time, mobile applications are considered, in which the involv...
Poster
Full-text available
Although it is nowadays desirable and even typical to characterise site conditions in detail at modern recording stations, this is not yet a general rule in Greece, due to the large number and geographical dispersion of stations. Indeed, most of them are still characterised merely through geological descriptions or proxy-based parameters, rather th...
Data
Άμεσος υπολογισμός Τανυστή Σεισμικής Ροπής σε σύγχρονες παράλληλες αρχιτεκτονικές Δείτε την παρουσίαση (στα Ελληνικά) https://lnkd.in/dsy8NRqY Gisola: A High Performance Computing application for real-time Moment Tensor inversion Watch Presentation (in Greek) https://lnkd.in/dsy8NRqY #fosscomm2021 #hpc #highperformancecomputing #gpu #openmp #opena...
Article
Full-text available
Face morphing poses a serious threat to Automatic Border Control (ABC) and Face Recognition Systems (FRS) in general. The aim of this paper is to present a qualitative assessment of the morphing attack issue, and the challenges it entails, highlighting both the technological and human aspects of the problem. Here, after the face morphing attack sce...
Conference Paper
Full-text available
Automatic Moment Tensor (MT) determination for regional areas is essential for real-time seismological applications such as stress inversion, shakemap generation, and tsunami warning. In recent years, the combination of two powerful tools, SeisComP and ISOLA (Sokos and Zahradník, 2008), paved the way for the release of Scisola (Triantafyllis et al....
Article
Full-text available
We present a framework for stochastically modeling the Fourier spectrum of the noisy seismic recording based on the fundamental assumption that the latter constitutes a random rather than a deterministic quantity. First we demonstrate (mathematically and through simulations) that, under the stochastic-signal assumption, the periodogram ordinates of...
Article
Full-text available
A series of strong earthquakes took place at the Trichonis lake area, during April 2007. Three events, with M~5.0 occurred within one day, causing damages to almost all nearby villages and especially at the small town of Thermo. The sequence lasted for more than one month with small to moderate size events. It was recorded by regional networks and...
Conference Paper
Full-text available
Conservation activities, before and after decay detection, are considered as a prerequisite for maintaining cultural artifacts in their initial/original form. Taking into account the strict regulations where sampling from art works of great historical value is restricted or in many cases prohibited, the application of Non-Destructive Testing techni...
Article
Full-text available
The automatic seismic signal detection constitutes a very interesting and challenging task. The main difficulty in solving this problem is attributed to the fact that both the statistical properties of seismic noise and the characteristics of the recorded events are in general unknown. In this paper, by exploiting the particular nature of the signa...
Chapter
Cultural objects and art works need ongoing conservation interventions in order to be available for the generations to come. The most object-friendly analysis approaches are based on non destructive techniques (NDTs) that allow both the materials characterization/evaluation as well as the decay detection and assessment of cultural artifacts. Non de...
Conference Paper
Full-text available
The problem of seismic events detection constitutes one of the most important and vital tasks for the automatic identification of the seismic phase arrivals. In this work, we propose a new thresholding type technique, tailored to fit real world situations where our knowledge on the statistical characteristics of the background noise process are unk...
Conference Paper
Full-text available
In this paper we propose a new iterative graph based clustering technique. The proposed method has three desirable characteristics as compared to well known clustering techniques. Specifically, because of its iterative nature, the number of clusters contained in a given data set it is not necessary to be known a priori as partitional clustering tec...
Conference Paper
Full-text available
The solution to the problem of seismic signals segmentation constitutes a very interesting and challenging task. The main difficulty in solving this problem is attributed to the fact that both the statistical properties of seismic noise, as well the characteristics of the recorded events are in general unknown. In this paper, by exploiting the part...
Conference Paper
Full-text available
One of the most difficult tasks in the solution of a hypothesis testing problem is the estimation of the probability density functions of the null and the alternative hypothesis. In this paper, the simultaneous detection of seismic events contained in a given data record is formulated as such a problem and an approximation of the probability densit...
Conference Paper
In this paper a new nonlinear transformation of the raw data based on the notion of the length of seismogram and a ratio test statistic for the accurate automatic P - wave onset detection problem are proposed. The basic characteristic of the proposed statistic is that it makes no assumptions for the properties of the noise, apart from very loose st...
Conference Paper
Full-text available
A series of strong earthquakes took place at the Trichonis lake area, during April 2007. Three events, with M~5.0 occurred within one day, causing damages to almost all nearby villages and especially at the small town of Thermo. The sequence lasted for more than one month with small to moderate size events. It was recorded by regional networks and...

Network

Cited By

Projects

Projects (3)
Project
HealthSign proposes to develop an application for the automated interpretation of the Greek Sign Language (GSL) over the internet with a focus on health services, which are the most common reason to seek an interpreter.
Archived project
Project
Develop acceleration/compression techniques for Deep Convolutional Neural Networks