Wyniki wyszukiwania - BazTech

1

An investigation about the relationship between dysarthria level of speech and the neurological state of Parkinson’s patients

Karan Biswajit, Sekhar Sahu Sitanshu, Orozco-Arroyave Juan Rafael

Biocybernetics and Biomedical Engineering

|

2022

|

Vol. 42, no. 2

710--726

EN

Parkinson’s disease (PD) is the most common neurological disorder that typically affects elderly people. In the earlier stage of disease, it has been seen that 90% of the patients develop voice disorders namely hypokinetic dysarthria. As time passes, the severity of PD increases, and patients have difficulty performing different speech tasks. During the progression of the disease, due to less control of articulatory organs such as the tongue, jaw, and lips, the quality of speech signals deteriorates. Periodic medical evaluations are very important for PD patients; however, having access to a medical appointment with a neurologist is a privilege in most countries. Considering that the speech recording process is inexpensive and very easy to do, we want to explore in this paper the suitability of mapping information of the dysarthria level into the neurological state of patients and vice versa. Three levels of severity are considered in a multiclass framework using time-frequency (TF) features and random-forest along with an Error-Correcting Output Code (ECOC) approach. The multiclass classification task based on dysarthria level is performed using the TF features with words and diadochokinetic (DDK) speech tasks. The developed model shows an unweighted average recall (UAR) of 68.49% with the DDK task /pakata/ based on m-FDA level, and 48.8% with the word /petaka/ based on the UPDRS level using the Random Forest classifier. With the aim, to evaluate the neurological states using the dysarthria level, the developed models are used to predict the MDS-UPDRS-III level of patients. The highest matching accuracy of 32% with the word /petaka/ is achieved. Similarly, the multiclass classification framework based on MDS-UPDRS-III is applied to predict the dysarthria level of patients. In this case, the highest matching accuracy of 18% was obtained with the DDK tasks /pataka/.

2

Studying OpenMP thread mapping for parallel linear algebra kernels on multicore system

Bylina B., Bylina J.

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2018

|

Vol. 66, nr 6

981--990

EN

Thread mapping is one of the techniques which allow for efficient exploiting of the potential of modern multicore architectures. The aim of this paper is to study the impact of thread mapping on the computing performance, the scalability, and the energy consumption for parallel dense linear algebra kernels on hierarchical shared memory multicore systems. We consider the basic application, namely a matrix-matrix product (GEMM), and two parallel matrix decompositions (LU and WZ). Both factorizations exploit parallel BLAS (basic linear algebra subprograms) operations, among others GEMM. We compare differences between various thread mapping strategies for these applications. Our results show that the choice of thread mapping has the measurable impact on the performance, the scalability, and energy consumption of the GEMM and two matrix factorizations.

3

Moving cast shadow detection using block nonnegative matrix factorization

Yang X., Liu D., Zhou D., Yang R.

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2018

|

Vol. 66, nr 2

229--234

EN

In recent years, moving cast shadow detection has become a critical challenge in improving the accuracy of moving object detection in video surveillance. In this paper, we propose two novel moving cast shadow detection methods based on nonnegative matrix factorization (NMF) and block nonnegative matrix factorization (BNMF). First, the algorithm of moving cast shadow detection using NMF is given and the key points such as the determination of moving shadow areas and the choice of discriminant function are specified. Then BNMF are introduced so that the new training samples and new classes can be added constantly with lower computational complexity. Finally, the improved shadow detection method is detailed described according to BNMF. The effectiveness of proposed methods is evaluated in various scenes. Experimental results demonstrate that the method achieves high detection rate and outperforms several state-of-the-art methods.

4

Rekonstrukcja niekompletnych obrazów za pomocą metod aproksymacji modelami niskiego rzędu

Sadowski T., Zdunek R.

Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska

|

2017

|

T. 7, nr 4

44--48

PL

W pracy badano zadanie rekonstrukcji brakujących pikseli w obrazach poddanych losowym zaburzeniom impulsowym w kanale transmisyjnym. Takie zadanie może być sformułowane w kontekście interpolacji obrazu na nieregularnej siatce lub aproksymacji niekompletnego obrazu za pomocą modeli dekompozycji obrazu na faktory niskiego rzędu. Porównano skuteczność czterech algorytmów opartych na dekompozycjach macierzy lub tensorów: SVT, SmNMF-MC, FCSA-TC i SPC-QV. Badania przeprowadzono na obrazach niekompletnych, otrzymanych z obrazów oryginalnych przez usunięcie losowo wybranych pikseli lub linii tworzących regularną siatkę. Najwyższą efektywność rekonstrukcji obrazu uzyskano gdy na estymowane faktory niskiego rzędu narzucano ograniczenia nieujemności i gładkości w postaci wagowej filtracji uśredniającej.

EN

The paper is concerned with the task of reconstructing missing pixels in images perturbed with impulse noise in a transmission channel. Such a task can be formulated in the context of image interpolation on an irregular grid or by approximating an incomplete image by low-rank factor decomposition models. We compared four algorithms that are based on the low-rank decomposition model: SVT, SmNMF-MC , FCSA-TC and SPC-QV. The numerical experiments are carried out for various cases of incomplete images, obtained by removing random pixels or regular grid lines from test images. The best performance is obtained if nonnegativity and smoothing constraints are imposed onto the estimated low-rank factors.

5

Local fault detection of rolling element bearing components by spectrogram clustering with semi-binary NMF

Wodecki J., Zdunek R., Wyłomańska A., Zimroz R.

Diagnostyka

|

2017

|

Vol. 18, No. 1

3--8

EN

Information extraction is a very important problem nowadays. In diagnostics, it is particularly useful when one desires to isolate information about machine damage from a measured diagnostic signal. The method presented in this paper utilizes the idea that is based on a very important topic in numerical algebra, which is nonnegative matrix factorization. When applied to the matrix of multidimensional representation of the measured data, it can extract very useful information about the events which occur in the signal and are not recognizable otherwise. In the presented methodology, we use the algorithm called Semi-Binary Nonnegative Matrix Factorization (SB-NMF), and apply it to a time-frequency representation of the real-life vibration signal measured on faulty bearing operating in a belt conveyor driving station. Detected impulses of local damage are clearly identifiable. Performance of the algorithm is very satisfying in terms of time efficiency and output signal quality.

PL

Ekstrakcja informacji jest aktualnym kierunkiem badań. Jest ona szczególnie użyteczna, kiedy próbuje się wyizolować informację na temat uszkodzenia maszyny z zarejestrowanego sygnału diagnostycznego. Metoda zaprezentowana w niniejszej pracy bazuje na bardzo ważnym zagadnieniu algebry numerycznej, jakim jest nieujemna faktoryzacja macierzy. Kiedy jest ona zastosowana do analizy macierzy będącej wielowymiarową reprezentacją sygnału wejściowego, może wyizolować informację istotną z punktu widzenia procesów zachodzących w sygnale, a która nie jest rozpoznawalna w inny sposób. Przedstawiona metodologia korzysta z algorytmu znanego jako półbinarna nieujemna faktoryzacja macierzy, zastosowanego do reprezentacji czasowo-częstotliwościowej rzeczywistego sygnału drganiowego, zmierzonego na uszkodzonym łożysku pracującym w stacji napędowej przenośnika taśmowego. Wykryte impulsy związane z uszkodzeniem lokalnym zostały wyraźnie zidentyfikowane. Działanie algorytmu jest satysfakcjonujące w kwestii wydajności obliczeniowej oraz jakości otrzymanego wyniku.

6

Regularized nonnegative matrix factorization: Geometrical interpretation and application to spectral unmixing

Zdunek R.

International Journal of Applied Mathematics and Computer Science

|

2014

|

Vol. 24, no. 2

233--247

EN

Nonnegative Matrix Factorization (NMF) is an important tool in data spectral analysis. However, when a mixing matrix or sources are not sufficiently sparse, NMF of an observation matrix is not unique. Many numerical optimization algorithms, which assure fast convergence for specific problems, may easily get stuck into unfavorable local minima of an objective function, resulting in very low performance. In this paper, we discuss the Tikhonov regularized version of the Fast Combinatorial NonNegative Least Squares (FC-NNLS) algorithm (proposed by Benthem and Keenan in 2004), where the regularization parameter starts from a large value and decreases gradually with iterations. A geometrical analysis and justification of this approach are presented. The numerical experiments, carried out for various benchmarks of spectral signals, demonstrate that this kind of regularization, when applied to the FC-NNLS algorithm, is essential to obtain good performance.

7

Classification of Music Genres Based on Music Separation into Harmonic and Drum Components

Rosner A., Schuller B., Kostek B.

Archives of Acoustics

|

2014

|

Vol. 39, No. 4

629--638

EN

This article presents a study on music genre classification based on music separation into harmonic and drum components. For this purpose, audio signal separation is executed to extend the overall vector of parameters by new descriptors extracted from harmonic and/or drum music content. The study is performed using the ISMIS database of music files represented by vectors of parameters containing music features. The Support Vector Machine (SVM) classifier and co-training method adapted for the standard SVM are involved in genre classification. Also, some additional experiments are performed using reduced feature vectors, which improved the overall result. Finally, results and conclusions drawn from the study are presented, and suggestions for further work are outlined.

8

Online Blind Separation of Dependent Sources Using Nonnegative Matrix Factorization Based on KL Divergence

Li H., Shen Y., Wang J.

Przegląd Elektrotechniczny

|

2012

|

R. 88, nr 1b

278-281

EN

This paper proposes a novel online algorithm for nonnegative matrix factorization (NMF) based on the generalized Kullback-Leibler (KL) divergence criterion, aimed to overcome the high computation problem of large-scale data brought about by conventional batch NMF algorithms. It features stable updating the factors alternately for each new-coming observation, and provides an efficient solution for the blind separation of statistically dependent sources (i.e., the sources are mutually correlated). Our theoretic analysis is validated by simulation examples.

PL

Przedstawiono nowy algorytm do faktoryzacji nieujemnej macierzy bazujący na kryterium Kullback-Leibler, pozwalający usprawnić problem obliczeń dużej ilości danych. Algorytm sukcesywnie zmienia współczynniki i pozwala na ślepą separację statystycznie zależnych źródeł.

9

A Novel Traffic Prediction Scheme for Broadband Satellite Communications System

Gao Q., Li G.

Przegląd Elektrotechniczny

|

2012

|

R. 88, nr 5b

141-145

EN

Multi-user traffic prediction is an important issue in broadband satellite communications system. In view of multiple UTs (User Terminal) which are treated by a single ST (Satellite Terminal), a novel NMF-based (Nonnegative Matrix Factorization-based) multi-user traffic prediction method is proposed. Compared with previous prediction schemes, the new method can reduce computational complexity and remain comparable prediction accuracy. Simulation results based on real traffic data testify the validity of the proposed method.

PL

Przedstawiono metodę prognozowania przesyłu danych w satelitarnym szerokopasmowym systemie komunikacyjnym. Nowa metoda traktuje każdego z wielu użytkowników sieci jako pojedynczy terminal satelitarny.

10

A Nonnegative Subspace Approach for Packet Loss Concealment

Huang J., Zhang Y., Zhang X., Xia Z.

Przegląd Elektrotechniczny

|

2011

|

R. 87, nr 10

350-354

EN

This paper presents a nonnegative subspace approach for packet loss concealment problem. The magnitude spectrogram of speech signal is projected onto nonnegative subspace using nonnegative matrix factorization algorithm. Consequently, packet loss concealment problem is transformed to linear interpolation of the projective coefficients in nonnegative subspace. Simulation examples, objective tests show that packet loss concealment in the nonnegative subspace results in improved perceptual quality of speech compared to popular packet loss concealment algorithms.

PL

Zaprezentowano metodę subprzestrzeni dla rozwiązania problemu straty pakietu. Spektrogram amplitudowy sygnału mowy .jest poddawany projekcji do nieujemnej podprzestrzeni przy wykorzystaniu macierzy faktoryzacji. W rezultacie problem staje się możliwy do liniowej interpolacji. Osiągnięto dostrzegalną poprawę jakości przetwarzania sygnału mowy.