TY  - CHAP
AU  - Pál, Tamás
AU  - Molnár, Bálint
AU  - Tarcsi, Ádám
AU  - László, Martin Csongor
TI  - EVALUATION OF NEURAL NETWORK COMPRESSION METHODS ON THE RESPIRATORY SOUND DATASET
T2  - E-HEALTH 2021
PB  - International Association for Development of the Information Society (IADIS)
CY  - Online konferencia
SN  - 9789898704306
T3  - Proceedings of the IADIS International Conference Informatics 2009, Part of the IADIS Multi Conference on Computer Science and Information Systems, MCCSIS 2009
PY  - 2021
SP  - 118
EP  - 128
PG  - 11
UR  - https://m2.mtmt.hu/api/publication/32129517
ID  - 32129517
LA  - English
DB  - MTMT
ER  - 

TY  - CONF
AU  - Pál, Tamás
AU  - Molnár, Bálint
AU  - Tarcsi, Ádám
ED  - Horváth, Zoltán
ED  - Adrian, Petruşel
TI  - Lightweight, Length Invariant Models and Dimensionality Reduction in Respiratory Disease Detection
T2  - Collection of Abstracts
PB  - Babes-Bolyai Tudományegyetem
C1  - Budapest
PY  - 2020
SP  - 133
EP  - 133
PG  - 1
UR  - https://m2.mtmt.hu/api/publication/31814811
ID  - 31814811
N1  - Import hibák 2021-01-17 11:37
Category cannot be determined for the following item: ABST, default value is set.

AB  - The detection of respiratory diseases has been an important field of study of respiratory illnesses that are responsible for millions of deaths yearly. Machine learning offers a plethora of methods to preprocess, analyze, and classify such recordings. Approaches that have reduced computational demand are preferred to achieve shorter processing time. Two deep learning models are proposed that are length-invariant and have simpler neural network topologies. With length invariance, the processing time is shortened, as splitting the recordings into equal-sized segments is not necessary anymore. Moreover, extracted spectrograms of the recordings can be reduced in dimensionality by calculating aggregated values along the time axis and using efficient methods like PCA or tSNE. Mel Frequency Cepstral Coefficient (MFCC) spectrograms were extracted. The first deep model is a lightweight dense network that receives as input feature vectors from aggregated spectrograms. Inputs of different dimensionality are compared. The second model is inspired by the 1D MaxPooling architecture by Phan that introduce through the use of global max-pooling layers length invariability into the model. An extra hidden layer and other minor modifications are added that increased the classification performance in the case of this dataset. 2D spectrograms are used as input for this model. The respiratory sound database contains 920 annotated breathing recordings so that this database includes the symptoms of 7 classes of diseases or records that constitute as healthy. The data-set was created by a Portuguese and Greek research group. The data were collected from 126 patients so that these samples extend over through all age groups, namely children, adults, elderly. The data-set is also heavily imbalanced. The proposed deep learning, neural networks are systemically investigated on the before-mentioned data-sets and analysed according to the metrics of the discipline.
LA  - English
DB  - MTMT
ER  - 

TY  - CONF
AU  - Pál, Tamás
AU  - Várkonyi, Dániel Tamás
ED  - Martin, Holeňa
ED  - Horváth, Tomas
ED  - Alica, Kelemenová
ED  - František, Mráz
ED  - Dana, Pardubská
ED  - Martin, Plátek
ED  - Petr, Sosík
TI  - Comparison of Dimensionality Reduction Techniques on Audio Signals
T2  - Proceedings of the 20th Conference Information Technologies - Applications and Theory (ITAT 2020)
PB  - CEUR Workshop Proceedings
T3  - CEUR Workshop Proceedings, ISSN 1613-0073 ; 2718.
PY  - 2020
SP  - 161
EP  - 168
PG  - 8
UR  - https://m2.mtmt.hu/api/publication/31650433
ID  - 31650433
LA  - English
DB  - MTMT
ER  -