Browsing by Subject "big data"

Now showing 1 - 18 of 18

Access status: Open Access ,
Analityka kulturowa, czyli jak narzędzia »data science« zmieniły humanistykę
(Wydawnictwa AGH, 2022) Radomski, Andrzej
The article presents research paradigms that have radically changed the contemporary humanities. The most important of these is cultural analytics. It is based on Data Science methods. The author presents the assumptions of data science, and then the characteristics of digital humanities and cultural analytics. The second part of the article presents examples of research and projects conducted as part of cultural analysis. These are projects implemented at the DH Lab at Yale University, Software Studies Initiative, and Media Lab Katowice. Research conducted in these institutions transformed the humanities. Its characteristic features are the study of large data collections, research automation, the use of machine learning and knowledge visualization. The new humanities, the author claims, has become an exact science.
Access status: Restricted ,
Analiza wskaźników jakości energii elektrycznej z wykorzystaniem wybranych metod sztucznej inteligencji
(Data obrony: 2020-11-27) Wilczek, Gerald
Wydział Elektrotechniki, Automatyki, Informatyki i Inżynierii Biomedycznej
Access status: Restricted ,
Application of Big data and AI technologies for ancillary pricing in airline industry
(Data obrony: 2019-10-25) Biel, Michał Jan
Wydział Informatyki, Elektroniki i Telekomunikacji
Access status: Open Access ,
COVID-19 and instagram: an analysis of an Ibero-American infodemic
(Wydawnictwa AGH, 2022) Renó, Denis Porto; Martinez-Rolan, Xabier; Piñeiro-Otero, Teresa; Versuti, Andrea
Understanding the role of communication promoted by Ibero-American society during the Coronavirus pandemic is fundamental for building knowledge about the disease. In this scenario, Instagram occupies a privileged place, as it carries a diversity of possible languages. Furthermore, Instagram’s relevance in the social media landscape is growing. This article presents, from a study developed through big data analysis procedures, the first result of several that make up an international investigation on the subject. In the project stage, the quantitative volume of publications, the average publication per user and the participation of the different languages used in this analysis group were verified. It is hoped that further investigations can be developed based on the results presented here, especially due to the urgency of knowing the role of communication in the pandemic scenario in which we live.
Access status: Open Access ,
Data censoring with set-membership affine projection algorithm
(Wydawnictwa AGH, 2020) Karamali, Gholamreza; Zardadi, Akram; Moradi, Hamid Reza
In this work, we use the single-threshold and double-threshold set-membership affine projection algorithm to censor non-informative and irrelevant data in big data problems. For this purpose, we employ the probability distribution function of the additive noise in the desired signal and the excess of the meansquared error (EMSE) in steady-state to evaluate the threshold parameter of the single -threshold set-membership affine projection (ST-SM-AP) algorithm intending to obtain the desired update percentage. In addition, we propose the double-threshold set-membership affine projection (DT-SM-AP) algorithm to detect very large errors caused by unrelated data (such as outliers). The DT-SM-AP algorithm is capable of censoring non-informative and unrelated data in big data problems, and it will promote the misalignment and convergence speed of the learning procedure with low computational complexity. The synthetic examples and real-life experiments substantiate the superior performance of the proposed algorithms as compared to traditional algorithms.
Access status: Open Access ,
Formal verification of extension of istar to support big data projects
(Wydawnictwa AGH, 2021) Djeddi, Chabane; Zarour, Nacer Eddine; Charrel, Pierre-Jean
Identifying all of the correct requirements of any system is fundamental for its success. These requirements need to be engineered with precision in the early phases. Principally, late correction costs are estimated to be more than 200 times greater than the cost of corrections during requirements engineering (RE), especially in the big data area due to its importance and characteristics. A deep analysis of the big data literature suggests that current RE methods do not support the elicitation of big data project requirements. In this research, we present BiStar (an extension of iStar) to undertake big data characteris tics such as volume, variety, etc. As a first step, some missing concepts are identified that are not supported by the current methods of RE. Next, BiStar is presented to take big data-specific characteristics into account while dealing with the requirements. To ensure the integrity property of BiStar, formal proofs are made by performing a Bigraph-based description on iStar and BiStar. Fi nally, iStar and BiStar are applied on the same exemplary scenario. BiStar shows promising results, so it is more efficient for eliciting big data project requirements.
Access status: Restricted ,
Interactive application for the analysis of big data
(Data obrony: 2021-05-14) Reutowicz, Kamil Mieczysław
Wydział Inżynierii Mechanicznej i Robotyki
Access status: Open Access ,
Novel approach for big data classification based on hybrid parallel dimensionality reduction using spark cluster
(Wydawnictwa AGH, 2019) Ali, Ahmed Hussein; Abdullah, Mahmood Zaki
The big data concept has elicited studies on how to accurately and efficiently extract valuable information from such huge dataset. The major problem during big data mining is data dimensionality due to a large number of dimensions in such datasets. This major consequence of high data dimensionality is that it affects the accuracy of machine learning (ML) classifiers, it also results in time wastage due to the presence of several redundant features in the dataset. This problem can be possibly solved using a fast feature reduction method. Hence, this study presents a fast HP-PL which is a new hybrid parallel feature reduction framework that utilizes spark to facilitate feature reduction on shared/distributed-memory clusters. The evaluation of the proposed HP-PL on KDD99 dataset showed the algorithm to be significantly faster than the conventional feature reduction techniques. The proposed technique required >1 minute to select 4 dataset features from over 79 features and 3,000,000 samples on a 3-node cluster (total of 21 cores). For the comparative algorithm, more than 2 hours was required to achieve the same feat. In the proposed system, Hadoop’s distributed file system (HDFS) was used to achieve distributed storage while Apache Spark was used as the computing engine. The model development was based on a parallel model with full consideration of the high performance and throughput of distributed computing. Conclusively, the proposed HP-PL method can achieve good accuracy with less memory and time compared to the conventional methods of feature reduction. This tool can be publicly accessed at https://github.com/ahmed/Fast-HP-PL.
Access status: Open Access ,
Porównanie narzędzi do optymalizacji przetwarzania dużych zbiorów danych
(Data obrony: 2020-07-31) Zoń, Alicja
Wydział Fizyki i Informatyki Stosowanej
Access status: Restricted ,
Przetwarzanie i analiza strumienia rzeczywistych danych typu Big Data do prognozowania produkcji energii elektrycznej przez farmę wiatrową
(Data obrony: 2017-12-18) Nowobilski, Karol
Wydział Elektrotechniki, Automatyki, Informatyki i Inżynierii Biomedycznej
Access status: Open Access ,
Small farms as »data producers« for the needs of Agricultural Management Information System
(Wydawnictwa AGH, 2022) Zysk, Elżbieta; Mroczkowski, Tomasz; Dawidowicz, Agnieszka
In the face of current global threats, including the COVID-19 Pandemic, new technological solutions are needed. Globalization, progressing urbanization, the decreasing availability of cultivable land for food production, water contamination, flood risk and climate change, can all be viewed as potential threats to food safety. According to forecasts and trends, the future of both agricultural policy and agricultural innovation will be based on big data, data analytics and machine learning. Therefore, it is and will continue to be important to develop information systems dedicated to agricultural innovation and the management of food security challenges. The main aim of the study is a classification of data for a uniform AMIS from data from IREIS, GC and AIIS based on survey and expert interview data obtained. We propose to expand the range of data produced by small farmers while keeping in mind the protection of farmers and their rights and the possible benefits of the data provided. The literature recognizes the value of such data but it has not yet been legally regulated, protected, managed and, above all, properly used for agricultural and food security policy purposes. Therefore, we develop the idea of extended farmers' participation in the production of agricultural activity data. The research used a survey questionnaire and expert interviews. A viable AIIS needs current data that farmers already produce as well as additional data needs which we identify in our research. We propose an architecture of databases and describe their flow in the Agriculture Management Information System (AMIS).
Access status: Restricted ,
System analizy danych czasu rzeczywistego w oparciu o architekturę lambda
(Data obrony: 2019-07-03) Kryjak, Kamil
Wydział Elektrotechniki, Automatyki, Informatyki i Inżynierii Biomedycznej
Access status: Restricted ,
System przetwarzania danych w czasie rzeczywistym oparty o architekturę lambda
(Data obrony: 2020-07-13) Gródek, Bartłomiej
Wydział Elektrotechniki, Automatyki, Informatyki i Inżynierii Biomedycznej
Access status: Restricted ,
System rekomendacji treści WWW
(Data obrony: 2016-09-28) Porzycki, Krzysztof
Wydział Elektrotechniki, Automatyki, Informatyki i Inżynierii Biomedycznej
Access status: Open Access ,
The advent of the deep learning evolutionary algorithm EvoDN2 and its recent applications
(Wydawnictwa AGH, 2025) Chakraborti, Nirupam
The evolutionary deep learning algorithm EvoDN2 is an emerging strategy for data-driven intelligent learning and many-objective optimisation capable of handling a large volume of noisy and non-linear data. This article provides the essential details of this algorithm and highlights a number of its recent applications.
Access status: Restricted ,
Wykorzystanie standardowych narzędzi do obróbki danych tekstowych w przetwarzaniu wyników pomiarów GPS
(Data obrony: 2019-01-31) Łokaj, Agnieszka
Wydział Geologii, Geofizyki i Ochrony Środowiska
Celem niniejszej pracy było sprawdzenie narzędzi standardu POSIX, w obróbce masowych danych tekstowych. Zamierzono zbadać, czy stosowanie tradycyjnych narzędzi jest opłacalne z punktu widzenia czasu przygotowania programu, wygody jego tworzenia oraz wydajności kodu. W pracy zamieszczono projekt i implementację programu, na przykładzie wyników pomiarów GPS karetek pogotowia.
Access status: Restricted ,
Zapisywanie oraz analiza danych pochodzących z czujników samochodowych
(Data obrony: 2019-12-10) Konior, Przemysław
Wydział Inżynierii Metali i Informatyki Przemysłowej
Access status: Restricted ,
Zastosowanie technologii Big Data w zarządzaniu przedsiębiorstwem
(Data obrony: 2020-10-29) Manko, Iryna
Wydział Zarządzania