Wyniki wyszukiwania - BazTech

1

A stepwise protocol for neural network modeling of persistent postoperative facial pain in chronic rhinosinusitis

Szaleniec J., Szaleniec M., Stręk P.

Bio-Algorithms and Med-Systems

|

2016

|

Vol. 12, no. 2

81--88

EN

In the artificial neural network field, no universal algorithm of modeling ensures obtaining the best possible model for a given task. Researchers frequently regard artificial neural networks with suspicion caused by the lack of repeatability of single experiments. We propose a systematic approach that may increase the probability of finding the optimal network architecture. In the experiments, the average effectiveness in groups of networks rather than single networks should be compared. Such an approach facilitates the analysis of the results caused by changes in the network parameters, while the influence of chance effects becomes negligible. As an example of this protocol, we present optimization of a neural network applied for prediction of persistent facial pain in patients operated for chronic rhinosinusitis. In the stepwise approach, the percentage of correct predictions was gradually increased from 54% to 75% for the external validation set.

2

Research on the changes in voice quality caused by tonsillectomy

Potępa Ł, Tadeusiewicz R., Szaleniec J.

Bio-Algorithms and Med-Systems

|

2012

|

Vol. 8, no. 1

159--173

EN

The article presents the results of the research on the changes in voice quality caused by tonsillectomy. It was carried out in a group of 20 patients (12 male and 8 female). The voice was recorded on a E-MU 0404 USB sound card with a 24-bit A/C AK5385A convertor. Having analyzed the pronunciation of prolonged Polish vowels: /a/, /e/, /i/ and /u/, the researchers defined a set of parameters which differentiate the pronunciation before and after tonsillectomy. The results show that the differences in pronunciation might be observed due to dynamic properties of the articulatory track. Additional researches emphasize the usefulness of such recordings applying external E-MU 0404 USB sound card in the clinical environment.

3

Application of new acoustic parameters in ANN-aided pathological speech diagnosis

Szaleniec J., Modrzejewski M., Szaleniec M., Wszołek W.

Archives of Acoustics

|

2007

|

Vol. 32, No. 1

177-186

EN

Most diseases of the vocal tract cause changes in the voice quality. Acoustic analysis of the speech signal is a widely used, noninvasive, objective and low-cost method of laryngeal pathology recognition and classification. There have been numerous attempts [1-3] to develop an automatic system which could aid the laryngological diagnosis. The goal of the presented research is to verify, whether the new approach to the acoustic analysis and parameters introduced in the Voice Analysis and Screening System (VASS 3.0 [4]) such as turbulence noise index (TNI) and normalized first harmonic energy (NFHE), can improve the effectiveness of automated diagnosis. The automated diagnosis was performed using Artificial Neural Networks (ANN). Multilayer perceptron and radial basis function neural networks of various architectures were trained to classify between pathologic and non-pathologic voices, while the parameters computed with VASS were used as input data. Preliminary results show that the Voice Analysis and Screening System coupled with ANN can be a highly effective tool for ANN-aided pathological speech diagnosis.