Temat: compressed - Katalog OPAC zbiorów

Skocz do pozycji: 1.

Tytuł:: Recognition of the numbers in the Polish language
Autorzy:: Plichta, A.
Gąciarz, T.
Krzywdziński, T.
Powiązania:: https://bibliotekanauki.pl/articles/308844.pdf
Data publikacji:: 2013
Wydawca:: Instytut Łączności - Państwowy Instytut Badawczy
Tematy:: Automatic Speech Recognition
compressed sensing
Sparse Classification
Opis:: Automatic Speech Recognition is one of the hottest research and application problems in today’s ICT technologies. Huge progress in the development of the intelligent mobile systems needs an implementation of the new services, where users can communicate with devices by sending audio commands. Those systems must be additionally integrated with the highly distributed infrastructures such as computational and mobile clouds, Wireless Sensor Networks (WSNs), and many others. This paper presents the recent research results for the recognition of the separate words and words in short contexts (limited to the numbers) articulated in the Polish language. Compressed Sensing Theory (CST) is applied for the first time as a methodology of speech recognition. The effectiveness of the proposed methodology is justified in numerical tests for both separate words and short sentences.
Źródło:: Journal of Telecommunications and Information Technology; 2013, 4; 70-78
1509-4553
1899-8852
Pojawia się w:: Journal of Telecommunications and Information Technology
Dostawca treści:: Biblioteka Nauki

Artykuł

Zmień widok

na półce

Skocz do pozycji: 2.

Tytuł:: High-resolution Direction of Arrival Estimation Method Based on Sparse Arrays with Minimum Number of Elements
Autorzy:: Mohammed, Jafar Ramadhan
Powiązania:: https://bibliotekanauki.pl/articles/1839475.pdf
Data publikacji:: 2021
Wydawca:: Instytut Łączności - Państwowy Instytut Badawczy
Tematy:: compressed sensing
direction of arrival
DOA
estimation
sparse array
Opis:: Regular fully filled antenna arrays have been widely used in direction of arrival (DOA) estimation. However, practical implementation of these arrays is rather complex and their resolutions are limited to the beamwidth of the array pattern. Therefore, higher resolution and simpler methods are desirable. In this paper, the compressed sensing method is first applied to an initial fully filled array to randomly select the most prominent and effective elements which are used to form the sparse array. To keep the dimension of the sparse array equal to that of the fully filled array, the first and the last elements were excluded from the sparseness process. In addition, some constraints on the sparse spectrum are applied to increase estimation accuracy. The optimization problem is then solved iteratively using the iterative reweighted l1 norm. Finally, a simple searching algorithm is used to detect peaks in the spectrum solution that correspond to the directions of the arriving signals. Compared with the existing scanned beam methods, such as the minimum variance distortionless response (MVDR) technique, and with subspace approaches, such as multiple signal classification (MUSIC) and ESPIRT algorithms, the proposed sparse array method offers better performance even with a lower number of array elements and in severely noisy environments. Effectiveness of the proposed sparse array method is verified via computer simulations.
Źródło:: Journal of Telecommunications and Information Technology; 2021, 1; 8-14
1509-4553
1899-8852
Pojawia się w:: Journal of Telecommunications and Information Technology
Dostawca treści:: Biblioteka Nauki

Artykuł

Zmień widok

na półce

Skocz do pozycji: 3.

Tytuł:: High-resolution Direction of Arrival Estimation Method Based on Sparse Arrays with Minimum Number of Elements
Autorzy:: Mohammed, Jafar Ramadhan
Powiązania:: https://bibliotekanauki.pl/articles/1839489.pdf
Data publikacji:: 2021
Wydawca:: Instytut Łączności - Państwowy Instytut Badawczy
Tematy:: compressed sensing
direction of arrival
DOA
estimation
sparse array
Opis:: Regular fully filled antenna arrays have been widely used in direction of arrival (DOA) estimation. However, practical implementation of these arrays is rather complex and their resolutions are limited to the beamwidth of the array pattern. Therefore, higher resolution and simpler methods are desirable. In this paper, the compressed sensing method is first applied to an initial fully filled array to randomly select the most prominent and effective elements which are used to form the sparse array. To keep the dimension of the sparse array equal to that of the fully filled array, the first and the last elements were excluded from the sparseness process. In addition, some constraints on the sparse spectrum are applied to increase estimation accuracy. The optimization problem is then solved iteratively using the iterative reweighted l1 norm. Finally, a simple searching algorithm is used to detect peaks in the spectrum solution that correspond to the directions of the arriving signals. Compared with the existing scanned beam methods, such as the minimum variance distortionless response (MVDR) technique, and with subspace approaches, such as multiple signal classification (MUSIC) and ESPIRT algorithms, the proposed sparse array method offers better performance even with a lower number of array elements and in severely noisy environments. Effectiveness of the proposed sparse array method is verified via computer simulations.
Źródło:: Journal of Telecommunications and Information Technology; 2021, 1; 8-14
1509-4553
1899-8852
Pojawia się w:: Journal of Telecommunications and Information Technology
Dostawca treści:: Biblioteka Nauki

Artykuł

Zmień widok

na półce

Skocz do pozycji: 4.

Tytuł:: Linear and Planar Array Pattern Nulling via Compressed Sensing
Autorzy:: Mohammed, Jafar Ramadhan
Thaher, Raad H.
Abdulqader, Ahmed Jameel
Powiązania:: https://bibliotekanauki.pl/articles/1839322.pdf
Data publikacji:: 2021
Wydawca:: Instytut Łączności - Państwowy Instytut Badawczy
Tematy:: compressed sensing
convex optimization
iterative re-weighted l1- norm minimization
linear array
planar array
Opis:: An optimization method based on compressed sensing is proposed for uniformly excited linear or planar antenna arrays to perturb excitation of the minimum number of array elements in such a way that the required number of nulls is obtained. First, the spares theory is relied upon to formulate the problem and then the convex optimization approach is adopted to find the optimum solution. The optimization process is further developed by using iterative re-weighted l1- norm minimization, helping select the least number of the sparse elements and impose the required constraints on the array radiation pattern. Furthermore, the nulls generated are wide enough to cancel a whole specific sidelobe. Simulation results demonstrate the effectiveness of the proposed method and the required nulls are placed with a minimum number of perturbed elements. Thus, in practical implementations of the proposed method, a highly limited number of attenuators and phase shifters is required compared to other, conventional methods.
Źródło:: Journal of Telecommunications and Information Technology; 2021, 3; 50-55
1509-4553
1899-8852
Pojawia się w:: Journal of Telecommunications and Information Technology
Dostawca treści:: Biblioteka Nauki

Artykuł

Zmień widok

na półce

Informacja

Wyszukujesz frazę "compressed" wg kryterium: Temat

Źródło danych

Dostawca treści

Kolekcja

Rok wydania

Wydawca

Temat

Autor

Typ dokumentu

Język