Zobrazeno 1 - 10
of 74
pro vyhledávání: '"Marija Bacauskiene"'
Publikováno v:
PLoS ONE, Vol 12, Iss 10, p e0185613 (2017)
This study investigates signals from sustained phonation and text-dependent speech modalities for Parkinson's disease screening. Phonation corresponds to the vowel /a/ voicing task and speech to the pronunciation of a short sentence in Lithuanian lan
Externí odkaz:
https://doaj.org/article/146d88afa3fe4e699d35dcb1ce9839fe
Publikováno v:
Applied Sciences, Vol 7, Iss 10, p 1096 (2017)
The aim of this study is a transparent tool for analysis of voice (sustained phonation /a/) and query data capable of providing support in screening for laryngeal disorders. In this work, screening is concerned with identification of potentially path
Externí odkaz:
https://doaj.org/article/42a4d41bb236467f9ed45611cec02438
Publikováno v:
Expert Systems with Applications. 88:109-117
A novel technique to explore relations between EMG and biomechanical data is presented.Statistically significant relations between EMG and biomechanical data were revealed.High prediction accuracy of peak angular velocity of thorax and pelvis was obt
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a924268cea5996bf8275183d815dfb84
https://doi.org/10.1016/j.eswa.2017.06.041
https://doi.org/10.1016/j.eswa.2017.06.041
Publikováno v:
Smart Objects and Technologies for Social Good ISBN: 9783319761107
GOODTECHS
GOODTECHS
Application of deep learning tends to outperform hand-crafted features in many domains. This study uses convolutional neural networks to explore effectiveness of various segments of a speech signal, – text-dependent pronunciation of a short sentenc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e1b30b1c72e51a2045054387164920a9
https://doi.org/10.1007/978-3-319-76111-4_21
https://doi.org/10.1007/978-3-319-76111-4_21
Autor:
Jonas Minelga, Adas Gelzinis, Virgilijus Uloza, Evaldas Vaiciukynas, Magnus Hållander, Evaldas Padervinskis, Marija Bacauskiene, Antanas Verikas
Publikováno v:
Expert Systems with Applications. 42:8445-8453
Voice and query data are explored for the task of laryngeal disorders detection.Decision-level fusion by complete-case analysis is compared to imputation strategies.Query data outperform voice, fusion after iterative model-based imputation - the best
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c7f7c4d8577a319de0cdca34a3984c13
https://doi.org/10.1016/j.eswa.2015.07.001
https://doi.org/10.1016/j.eswa.2015.07.001
Publikováno v:
Chemometrics and Intelligent Laboratory Systems. 146:10-23
Multivariate permutation-based energy test of equal distributions is considered here. Approach is attributable to the emerging field of e -statistics and uses natural logarithm of Euclidean distance for within-sample and between-sample components. Re
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::767a7a1b6f2a5fa2d6d237f90861f8d0
https://doi.org/10.1016/j.chemolab.2015.04.018
https://doi.org/10.1016/j.chemolab.2015.04.018
Autor:
Magnus Hållander, Evaldas Padervinskis, Antanas Verikas, Jonas Minelga, Marija Bacauskiene, Evaldas Vaiciukynas, Adas Gelzinis, Virgilijus Uloza
Publikováno v:
Medical Engineering & Physics. 37:210-218
Comprehensive evaluation of results obtained using acoustic and contact microphones in screening for laryngeal disorders through analysis of sustained phonation is the main objective of this study. Aiming to obtain a versatile characterization of voi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6f6b3b9e2185f289ea869aa1924c72c2
https://doi.org/10.1016/j.medengphy.2014.12.005
https://doi.org/10.1016/j.medengphy.2014.12.005
A novel technique to extract accurate cell contours applied for segmentation of phytoplankton images
Publikováno v:
Machine Vision and Applications. 26:305-315
Active contour model (ACM) is an image segmentation technique widely applied for object detection. Most of the research in ACM area is dedicated to the development of various energy functions based on physical intuition. Here, instead of constructing
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4cafc3172e2a52455cef0560a4289ac1
https://doi.org/10.1007/s00138-014-0643-0
https://doi.org/10.1007/s00138-014-0643-0
Autor:
Evaldas Vaiciukynas, Ron Hoory, Adas Gelzinis, Marija Bacauskiene, Zvi Kons, Antanas Verikas, Aharon Satt
Publikováno v:
Applied Soft Computing. 18:91-103
Detection of mild laryngeal disorders using acoustic parameters of human voice is the main objective in this study. Observations of sustained phonation (audio recordings of vocalized /a/) are labeled by clinical diagnosis and rated by severity (from
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2383220d9822e942f277e1c9d003cba2
https://doi.org/10.1016/j.asoc.2014.01.012
https://doi.org/10.1016/j.asoc.2014.01.012
Publikováno v:
Expert Systems with Applications. 40:2051-2057
Highlights? We present a novel technique to create adaptive committees of models. ? SOM enables building committees, specific for each data point analyzed. ? Adaptive committees were significantly more accurate than committees of other types. This ar
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f9849e7fac61bba6173b02246f28023b
https://doi.org/10.1016/j.eswa.2012.10.018
https://doi.org/10.1016/j.eswa.2012.10.018