Please use this identifier to cite or link to this item: http://dx.doi.org/10.25673/115645
Full metadata record
DC FieldValueLanguage
dc.contributor.authorKasianchuk, Nadiia-
dc.contributor.authorHarkava, Sofiia-
dc.contributor.authorOnishchenko, Sofiia-
dc.contributor.authorSolodka, Olesia-
dc.contributor.authorShyshko, Daria-
dc.contributor.authorSiemens, Eduard-
dc.contributor.authorFalfushynska, Halina-
dc.contributor.authorUstyianovych, Taras-
dc.date.accessioned2024-04-10T12:22:05Z-
dc.date.available2024-04-10T12:22:05Z-
dc.date.issued2024-
dc.identifier.urihttps://opendata.uni-halle.de//handle/1981185920/117600-
dc.identifier.urihttp://dx.doi.org/10.25673/115645-
dc.description.abstractAquatic ecosystems are crucial in maintaining environmental equilibrium and sustaining human well-being. However, the traditional manual methods used in hydrobiological research have limitations in providing a far-reaching understanding of these intricate ecosystems. Data science, machine learning, and deep learning techniques offer a variety of opportunities to overcome these limitations and unlock new insights into aquatic environments. This study highlights the impact of computational tools in areas such as taxonomic identification, metagenomic sequence analysis, and water quality prediction. Deep learning techniques have demonstrated superior accuracy in classifying organisms, including those previously unidentified by conventional methods. In metagenomic sequence analysis, machine learning aids in effectively ssembling DNA sequences, aligning them with known databases, and addressing challenges related to sequence repeats, errors, and missing data. Furthermore, predictive models have been developed to provide insights into water quality parameters, such as eutrophication events and heavy metal concentrations. These advancements lead to informed conservation measures and a deep understanding of the intricate relationships within aquatic ecosystems. However, challenges persist, including data quality issues, model interpretability, and the need for robust training datasets. Thus, data integration strategies designed specifically for environmental and genomic studies are necessary. Data fusion and imputation can help address data scarcity and provide a comprehensive view of hydrobiological processes. As the study of aquatic ecosystems continues to evolve, the synergy between computational methods and traditional hydrobiological techniques holds immense potential. By everaging the power of data science and cutting-edge technologies, researchers can gain a deep understanding of aquatic environments, monitor changes in biodiversity, and develop informed strategies for sustainable management amidst global environmental shifts.-
dc.language.isoeng-
dc.rights.urihttps://creativecommons.org/licenses/by-sa/4.0/-
dc.subjectInformationstechnik-
dc.subjectDatenverarbeitung-
dc.subject.ddc006.3-
dc.titleComputational Breakthroughs in Aquatic Taxonomy : The Role of Deep Learning and DNA Barcoding-
local.versionTypepublishedVersion-
local.publisher.universityOrInstitutionHochschule Anhalt-
local.openaccesstrue-
dc.identifier.ppn1884680585-
cbs.publication.displayform2024-
local.bibliographicCitation.year2024-
cbs.sru.importDate2024-04-10T12:20:14Z-
local.bibliographicCitationEnthalten in Proceedings of the 12th International Conference on Applied Innovations in IT - Köthen, Germany : Edition Hochschule Anhalt, 2024-
local.accessrights.dnbfree-
Appears in Collections:International Conference on Applied Innovations in IT (ICAIIT)

Files in This Item:
File Description SizeFormat 
2_3_ICAIIT_2024_Part_4_paper_11.pdf781.22 kBAdobe PDFThumbnail
View/Open