CCL

Összesen 5 találat.
#/oldal:
Részletezés:
Rendezés:

1.

001-es BibID:BIBFORM122768
Első szerző:Gál Zoltán (informatikus)
Cím:Deep Learning-Based Analysis of Ancient Greek Literary Texts in English Version: A Statistical Model Based on Word Frequency and Noise Probability for the Classification of Texts / Gál Zoltán, Tóth Erzsébet
Dátum:2024
ISSN:2061-2079
Megjegyzések:In our paper we intend to present a methodology that we elaborated for clustering texts based on the word frequency in the English translations of selected old Greek texts. We used the classification system of the ancient Library of Alexandria, devised by the prominent Greek scholar-poet, Callimachus in the 3rd century BC., as a basis for categorizing literary masterpieces. In our content analysis, we could determine a triplet of a, b, c values for describing a power function that appropriately fits a curve determined by the word frequencies in the texts. In addition, we have discovered 16 special features of the different texts that correspond to various token categories investigated in each text, such as part of speech of the word in the context, numerals, subordinate conjunction, symbols, etc. We have developed a cognitive model in which several hundred different subtexts were utilized for supervised learning with the aim of subtext class recognition. Concerning 200 subtexts, the triplet of a, b, c values, the classes of the subtexts, and their 16-dimensional feature vectors were learnt for the Recurrent Neural Network (RNN). It turned out that the Long-Short Term Memory RNN could efficiently predict which class a chosen subtext could be categorized into without considering the interpretation of the content. The influence of the non-zero error rate of new communication services on the meaning of the transferred texts was also investigated. The impact of the noise on the classification accuracy was found to be linear, dependent on the character error rate.
Tárgyszavak:Műszaki tudományok Informatikai tudományok idegen nyelvű folyóiratközlemény hazai lapban
folyóiratcikk
mélytanulás
ókori görög irodalmi szövegek
szövegklaszterezés
zajos szövegek
Pinakes
text classification
automatic content analysis
Recurrent Neural Network (RNN)
Long-Short Term Memory
Megjelenés:Infocommunications Journal. - 16 : Joint Special Issue on Cognitive Infocommunications and Cognitive Aspects of Virtual Reality (2024), p. 2-11. -
További szerzők:Tóth Erzsébet (1972-) (informatikus könyvtáros)
Pályázati támogatás:TKP2021-NKTA-34
Egyéb
Internet cím:Szerző által megadott URL
DOI
Intézményi repozitóriumban (DEA) tárolt változat
Borító:

2.

001-es BibID:BIBFORM062503
Első szerző:Gál Zoltán (informatikus)
Cím:VoIP LAN/MAN traffic analysis for NGN QoS management / Zoltán Gál
Dátum:2009
ISSN:0866-5583
Megjegyzések:Strict requirement is emphasized regarding QoS guarantees of the NGN (Next Generation Network) networks today. DiffServ mechanism is applied mostly for classification of protocol data units of real time and conventional information streams in LAN/MAN environment. The dependence of VoIP traffic characteristics of the delay and the jitter sensitive IP telephony vs. voice codec applied can be considered an exciting scientific question. We analyze Ethernet traffic generated by G.711, G.723, G.728 and Wideband (G.722) voice codecs. The self similar, fractal and multifractal properties of popular TCP based services (http, ftp, telnet, etc.) in LAN/MAN environment is well known for several decades. In this paper, we study the effect of UDP based current voice mechanisms on self similarity of the Ethernet data traffic. UDP traffics of the IP phones are evaluated in congested and congestionless environment using sophisticated methods of entropy and wavelet analysis. A new and efficient evaluation method, named ON/(ON+OFF) transformation is applied for characterization of VoIP traffic.
Tárgyszavak:Műszaki tudományok Informatikai tudományok idegen nyelvű folyóiratközlemény hazai lapban
NGN
TCP
UDP
codec
QoS
DiffServ
self similarity
wavelet
fractal
entropy
Megjelenés:Infocommunications Journal. - 64 : 2 (2009), p. 22-29. -
Internet cím:Szerző által megadott URL
Intézményi repozitóriumban (DEA) tárolt változat
Borító:

3.

001-es BibID:BIBFORM056731
Első szerző:Gál Zoltán (informatikus)
Cím:Internet of Things: application areas and research results of the FIRST project / Gál Zoltán, Almási Béla, Dabóczi Tamás, Vida Rolland, Oniga Stefan, Baran Sándor, Farkas István
Dátum:2014
ISSN:2061-2079
Megjegyzések:The FIRST/IoT project coordinated by the Faculty of Informatics, University of Debrecen, Hungary has important impact on the R&D work in this field. Six activity areas have been covered in the twenty-seven months long project. More than thirty researchers from half dozen Hungarian and other universities and research institutes have been involved in this activity. The results of this work are planned to be used for other international IoT projects in the following time period. Other institutes and individual researchers from abroad are invited to join to this open initiative and become partner. In the paper are presented the results and the most exciting aspects of the research activity.
Tárgyszavak:Műszaki tudományok Informatikai tudományok idegen nyelvű folyóiratközlemény hazai lapban
IoT
MPT
Sensor/Actuator
Big Data
Data Clusterization
Cyber-Physical Space
Bloom-filter
E-health
Ensemble Forecasting
Virtual Organization
Tárgyak Internete (IoT)
Megjelenés:Infocommunications Journal. - 6 : 3 (2014), p. 37-44. -
További szerzők:Almási Béla (1966-2015) (informatikus, matematikus) Dabóczi Tamás (1966-) (villamosmérnök) Vida Rolland (1974-) (villamosmérnök, informatikus) Oniga István László (1960-) (villamosmérnök) Baran Sándor (1973-) (matematikus, informatikus) Farkas István (1976-) (informatikus)
Pályázati támogatás:TÁMOP-4.2.2.C-11/1/KONV-2012-0001
TÁMOP
Tárgyak Internete és az IPv4/IPv6 rendszerekkel való integrációja
Internet cím:Szerző által megadott URL
Intézményi repozitóriumban (DEA) tárolt változat
Borító:

4.

001-es BibID:BIBFORM114470
035-os BibID:(WoS)001143123700008 (Scopus)85174808943
Első szerző:Talbi, Djamila (mérnök informatikus)
Cím:Decomposition Based Congestion Analysis of the Communication in B5G/6G TeraHertz High-Speed Networks / Djamila Talbi, Zoltán Gál
Dátum:2023
ISSN:2061-2079
Megjegyzések:The New MAC mechanism plays a key role in achieving the needed requirements of the B5G/6G radio technology and helps to avoid high-speed frequency issues and limitations. With the help of the ns-3 simulator, we generated 42 different cases for the purpose of analyzing the impact of the network load on the overall effective transmission rate. Therefore, the use of the data-adaptive decomposition method the Empirical Mode Decomposition (EMD) on our non-stationary system benefits in the extraction of the important meaningful components. However, due to the highlighted direction dependency finding of EMD, Ensembled EMD (EEMD) being direction independent shows better performance on our data series. The extracted trend based on the proposed method matches the fitting curve, while the fitting curve parameters can be clusterized into 2 main clusters congested and non-congested cases of the radio channel throughput signal.
Tárgyszavak:Műszaki tudományok Informatikai tudományok idegen nyelvű folyóiratközlemény hazai lapban
folyóiratcikk
Tera-Hertz technology
6G
Beyond 5G
Empirical Mode Decomposition
Ensemble Empirical Mode Decomposition
Intrinsic Mode Function
Megjelenés:Infocommunications Journal. - 15 : Special Issue (2023), p. 43-48. -
További szerzők:Gál Zoltán (1966-) (informatikus)
Pályázati támogatás:TKP2021-NKTA-34
Egyéb
Internet cím:Szerző által megadott URL
DOI
Intézményi repozitóriumban (DEA) tárolt változat
Borító:

5.

001-es BibID:BIBFORM122769
Első szerző:Tóth Erzsébet (informatikus könyvtáros)
Cím:Optimizing Text Clustering Efficiency through Flexible Latent Dirichlet Allocation Method: Exploring the Impact of Data Features and Threshold Modification / Tóth Erzsébet, Gál Zoltán
Dátum:2024
ISSN:2061-2079
Megjegyzések:A parallel corpus comprising Croatian EU legislative documents automatically translated into English spans 28 years and is enriched with metadata, including creation year and hierarchical classifier tags denoting descriptors, document types, and fields. However, nearly two-thirds of the approximately 1.5 thousand texts lack complete metadata, necessitating labor intensive manual efforts that pose challenges for human administration. This incompleteness issue can be observed in the case of official legal sites functioning as regular service provisioning databases. In response, this paper introduces an artificial cognitive and multilabel classification approach to expedite the tagging process with only a fraction of the manual effort. Leveraging the Latent Dirichlet Allocation (LDA) algorithm, our method assigns field values or tags to incompletely labeled documents. We implement a Flexible LDA variant, incorporating the influence of topics close to the most probable topic, regulated by a relative probability threshold (RPT). We evaluate the LDA prediction's dependence on document prefiltering and RPT values. Furthermore, we investigate the dependence of quantitative linguistic properties on the type and speciality of pre-processing tasks. Our algorithm, built on error-correcting optimizing codes, succesfully predicts a mixture of topic probabilities for these legal texts. This prediction is achieved by calculating the Hamming distance of binary feature vectors created using the legal fields of the EUROVOC multilingual thesaurus.
Tárgyszavak:Műszaki tudományok Informatikai tudományok idegen nyelvű folyóiratközlemény hazai lapban
folyóiratcikk
Latent Dirichlet Allocation algoritmus
több címkés osztályozás
Természetes nyelvű feldolgozás
jogi szövegek klaszterezése
Ellenőrzött tanulás
Megjelenés:Infocommunications Journal. - 16 : Joint Special Issue on Cognitive Infocommunications and Cognitive Aspects of Virtual Reality (2024), p. 58-66. -
További szerzők:Gál Zoltán (1966-) (informatikus)
Pályázati támogatás:TKP2021-NKTA-34
Egyéb
Internet cím:Szerző által megadott URL
DOI
Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Rekordok letöltése1 
Corvina könyvtári katalógus v10.1.21-SNAPSHOT © 2024 Monguz kft. Minden jog fenntartva.