| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font
First page > Show document

Show document Help

Title:GRUČENJE UČENCEV PRI POUKU RAČUNALNIŠTVA
Authors:ID Kermavner, Barbara (Author)
ID Rizman Žalik, Krista (Mentor) More about this mentor... New window
Files:.pdf UNI_Kermavner_Barbara_2011.pdf (1,29 MB)
MD5: 62345CF704403144EDDB3D4E71FA9039
PID: 20.500.12556/dkum/5f35ff8c-23ca-4870-8680-2f23a4b40589
 
Language:Slovenian
Work type:Undergraduate thesis
Organization:FNM - Faculty of Natural Sciences and Mathematics
Abstract:Povod za nastanek seminarske diplomske naloge je bilo« srečanje« z gručenjem pri predmetu Informacijski sistemi. Z razvrščanjem se nezavedno srečujemo na vsakem koraku. Človeški možgani sistematično razvrščajo informacije, da dosežejo hitrejše razumevanje in boljše odzive, ter reakcije.. V diplomskem delu sem zapisala moje razmišljanje in raziskovanje na to temo. Uporabila sem moje področje, poučevanje učencev. V grobem lahko vrste gručenja delimo na hierarhične in delitvene tehnike. Primeri hiararhičnih tehnik so: metoda enojnega povezovanja, celostno povezovalna metoda, metoda povezovanja glede na povprečje, metoda mediane, metoda varovanca… K delitvenim tehnikam pa spadajo: k-means metoda, prilagodljiva K-means metoda, metoda povezovanja centroidov, metoda »fuzzy« c - means… Rezultat gručenja se lahko interpretira na različne načine, zato je izbira algoritma glede na primerjavo popolnoma odvisna od želenega cilja in vrste podatkov, objektov, ki jih je potrebno urediti. Gručenje ali razvrščanje v skupine srečujemo v medicini, genetiki, marketingu, biologiji… Vsaka razvrstitev objektov ali podatkov je z matematičnega vidika ekvivalenčna relacija. Z množico ekvivalenčnih relacij nad podatki dobimo podatkovno hierarhijo, nas pa zanima kakšno. Imeti moramo jasen cilj in dobro poznati podatke. Ti nam določajo izbiro ustreznih metod, med temi pa lahko stremimo k optimalnosti. Različne metode gručenja lahko ustvarjajo diskretne particije ali strogo ločene gruče v katerih vsak objekt pripada eni izmed gruč. Druge omogočajo dostop do »ubežnikov« , ki ne pripadajo nobeni od gruč, lahko pa se srečujemo tudi s pripadnostjo več gručam. Pri mojem delu, učim namreč na eni izmed osnovnih šoli v Ljubljani, pa bi lahko tak pregled rezultatov nalog pomagal kreirati skupine izbirnih predmetov ( ali nivojskih skupin pri angleščini, slovenščini in matematiki)..
Keywords:Gručenje, hierarhične tehnike, delitvene tehnike, metoda enojnega povezovanja, celostno povezovalna metoda, metoda povezovanja glede na povprečje, metoda mediane, metoda varovanca, k-means metoda, prilagodljiva K-means metoda, metoda povezovanja centroidov, metoda »fuzzy« c - means.
Place of publishing:Maribor
Publisher:[B. Kermavner]
Year of publishing:2011
PID:20.500.12556/DKUM-17884 New window
UDC:004(043.2)
COBISS.SI-ID:18409736 New window
NUK URN:URN:SI:UM:DK:JDDCTLHG
Publication date in DKUM:30.05.2011
Views:2347
Downloads:262
Metadata:XML DC-XML DC-RDF
Categories:FNM
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share



Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Secondary language

Language:English
Title:CLASTERING OF PUPILS AT THE COMPUTER SCIENCE LECTURE
Abstract:The catalyst for the emergence of a seminar thesis was "meeting" with the clustering in the subject Information Systems. The categorization of the unconscious we encounter at every step. The human brains are systematically classified information to achieve fasterand better understanding of the responses and reactions .. I wrote my thinking and research on this topic. I used my field, teaching the students. The type of clustering can be roughly divided into hierarchical and technical division.Examples of hierachical techniques are: , Complete Linkage Method, Average Linkage Method, Centroid Method,Median Method, Ward Method… Particional techniques are: K-MEANS method, adaptive K-MEANS method, "fuzzy" c - means ... The result of clustering can be interpreted in different ways, so the choice of the algorithm is the most important part of clustering . We use clustering in medicine, genetics, marketing, biology ... Any classification of objects or data, is an equivalence relation in mathematical point of view. With a multitude of equivalence relations over the data we get the datahierarchy, but we want to know what tipe of hierarchy . We must have a clear goal and a good knowledge of the data. Different clustering methods may generate discrete partition or clusterin in which each object belongs to one of the clusters. Others allow access to "outliers" that do not belong to one cluster, but we can also meet with the membership of severalclusters. In my work, I teach is the one of the primary school in Ljubljana, such a review of results can help create level groups in English,Slovenian and mathematics lecture.
Keywords:Clustering, hiarachical clustering, particionalno clustering, Johnson`s algorithem, Complete Linkage Method, Average Linkage Method, Centroid Method, Median Method, Ward Method, Divisive hiererchical metod, fuzzy C-means, mixture of Gaussians, EM algorithem, K-means, Adaptive K-means Method, Hard C-means method.


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica