Search results for "FEA"

Signal processing techniques for robust sound event recognition

2019

The computational analysis of acoustic scenes is today a topic of major interest, with a growing community focused on designing machines capable of identifying and understanding the sounds produced in our environment, similar to how humans perform this task. Although these domains have not reached the industrial popularity of other related audio domains, such as speech recognition or music analysis, applications designed to identify the occurrence of sounds in a given scenario are rapidly increasing. These applications are usually limited to a set of sound classes, which must be defined beforehand. In order to train sound classification models, representative sets of sound events are record…

Submarine Slope Failures Along the Northern Sicilian Continental Margin (Southern Tyrrhenian Sea) and Possible Implications for Geo-Hazard

2013

Mass wasting and downslope movements are common processes that have contributed to shape the northern Sicilian continental margin (southern Tyrrhenian Sea) since the Late Quaternary. Nevertheless, processes controlling their evolution are still partially unknown and a variety of geologic factors can be responsible for their formation. In this work we present an overview of the main mass wasting features (submarine canyons, landslides, debris flows) observed and mapped in different sectors of the northern Sicilian margin. The margin is characterized by a narrow, steep continental shelf (1-2°) and a very irregular and steep (6-8°) upper slope. The main aims of this work are: (1) to outline th…

Local methods for complex spatio-temporal point processes

2022

Holocene Spatiotemporal Redox Variations in the Southern Baltic Sea

2021

Low oxygen conditions in the modern Baltic Sea are exacerbated by human activities; however, anoxic conditions also prevailed naturally over the Holocene. Few studies have characterized the specific paleoredox conditions (manganous, ferruginous, euxinic) and their frequency in southern Baltic sub-basins during these ancient events. Here, we apply a suite of isotope systems (Fe, Mo, S) and associated elemental proxies (e.g., Fe speciation, Mn) to specifically define water column redox regimes through the Baltic Holocene in a sill-proximal to sill-distal transect (Lille Belt, Bornholm Basin, Landsort Deep) using samples collected during the Integrated Ocean Drilling Program Expedition 347. At…

Performance-related fear experiences, coping and perceived functional impact on highly skilled athletes

2013

ABSTRACT Melina Puolamäki, 2013. Performance-related fear experiences, coping and perceived functional impact on highly skilled athletes. Master’s Thesis in Sport and Exercise Psychology. Department of Sport Science, University of Jyväskylä. 68p. Three types of experiences are distinguished in sport: emotional states (state-like), emotion patterns (trait-like), and meta-experiences or attitudes towards one’s experiences (Hanin, 2004). Most emotion research has traditionally focused on the study of anxiety and its impact on athletic performance. Although unpleasant emotions have been assumed harmful for performance, previous research on anxiety (Hanin, 2000) and anger (Ruiz & Hanin, 2011) ha…

Sensitivity analysis of Gaussian processes for oceanic chlorophyll prediction

2015

Gaussian Process Regression (GPR) for machine learning has lately been successfully introduced for chlorophyll content mapping from remotely sensed data. The method provides a fast, stable and accurate prediction of biophysical parameters. However, since GPR is a non-linear kernel regression method, the relevance of the features are not accessible. In this paper, we introduce a probabilistic approach for feature sensitivity analysis (SA) of the GPR in order to reveal the relative importance of the features (bands) being used in the regression process. We evaluated the SA on GPR ocean chlorophyll content prediction. The method revealed the importance of the spectral bands, thus allowing the …

A comparison between two feature selection algorithms

2017

This article provides a comparison of two feature selection algorithms, Information Gain Thresholding and Koller and Sahami's algorithm in the context of text document classification on the Reuters Corpus Volume 1 dataset. The algorithms were evaluated by testing the performance of classifiers trained on the features they select from a given dataset. Results show that Koller and Sahami's algorithm consistently outperforms Information Gain Thresholding by capturing interactions between features and avoiding redundancy among features, although it achieves its gains through increased complexity and longer running time.

Songs Perceived as Relaxing : Musical Features, Lyrics, and Contributing Mechanisms

2020

How we listen to music has been changing rapidly in the last years, with online streaming becoming more predominant. Besides the gain in accessibility for the listeners, the growth of online services also affords easier access to data for musical analyses. A growing body of research has been showing that daily life music listening serves varied functions, from affect regulation to social bonding. More specifically, the reduction of stress responses is quite pertinent in the contemporary world, and recent studies have high-lighted the importance of adequate musical choices. This study aimed to identify the characteristics of music that individuals perceive as favorable to relax and to compar…

Generalizability and Simplicity as Criteria in Feature Selection: Application to Mood Classification in Music

2011

Classification of musical audio signals according to expressed mood or emotion has evident applications to content-based music retrieval in large databases. Wrapper selection is a dimension reduction method that has been proposed for improving classification performance. However, the technique is prone to lead to overfitting of the training data, which decreases the generalizability of the obtained results. We claim that previous attempts to apply wrapper selection in the field of music information retrieval (MIR) have led to disputable conclusions about the used methods due to inadequate analysis frameworks, indicative of overfitting, and biased results. This paper presents a framework bas…

A Network-Based Framework for Mobile Threat Detection

2018

Mobile malware attacks increased three folds in the past few years and continued to expand with the growing number of mobile users. Adversary uses a variety of evasion techniques to avoid detection by traditional systems, which increase the diversity of malicious applications. Thus, there is a need for an intelligent system that copes with this issue. This paper proposes a machine learning (ML) based framework to counter rapid evolution of mobile threats. This model is based on flow-based features, that will work on the network side. This model is designed with adversarial input in mind. The model uses 40 timebased network flow features, extracted from the real-time traffic of malicious and…