izpis_h1_title_alt

SISTEMI ZA UPRAVLJANJE IDENTITET Z NADZOROM UPORABNIKOVEGA VEDENJA
ROŽAC, BORUT (Author), Kos, Andrej (Mentor) More about this mentor... This link opens in a new window, Košir, Andrej (Co-mentor)

.pdfPDF - Presentation file, Download (1,83 MB)

Abstract
V magistrskem delu je opisan primer uporabe dnevniških zapisov sistema za upravljanje identitet v povezavi z dnevniškimi zapisi strežnika DHCP in sistema za nadzor pristopa srednje velikega slovenskega podjetja, iz katerih je izdelan podatkovni model, na katerem so bile s pomočjo metod strojnega učenja napovedane ocene vedenjskega uspeha uporabnikov za samoiniciativnost. Značilke podatkovnega modela so bile predstavljene kot število ponovitev vzorcev določenih sekvenc dogodkov za posameznega uporabnika povezanih dnevniških zapisov v multinomskem podatkovnem zapisu in podatkovnem zapisu TF-IDF. Najbolj diskriminatorne vzorce sekvenc glede na oznako razreda smo za skupino vseh analiziranih uporabnikov poiskali s pomočjo testa Χ2 in njegovega Bonferronijevega popravka. V prvem in drugem poglavju sta predstavljena koncept digitalne identitete in sistemov za upravljanje identitet in glavna motivacija za napovedovanje vedenja uporabnikov s pomočjo metod strojnega učenja za napovedovanje uspeha uporabnikov sistemov za upravljanje identitet. V tretjem poglavju so na kratko opisani koncepti strojnega učenja, postopki učenja klasifikacijskih modelov, mere za ocenjevanje kakovosti klasifikacijskih modelov in na kratko postopki za izdelavo značilk. Opisani so tudi primeri uporabe metod strojnega učenje na področju analize dnevniških zapisov za potrebe odkrivanja vdorov v informacijske sisteme in primeri uporabe metod strojnega učenja na kadrovskem področju. Četrto poglavje opisuje postopek pridobivanja podatkov iz različni virov, njihovo pripravo in postopek izdelave podatkovnih modelov ter za to uporabljena orodja. V petem poglavju so opisani postopki napovedovanja uspeha uporabnikov z metodami strojnega učenje s predstavitvijo rezultatov. Delo je zaključeno s sklepom, v katerem so podani vzroki za slabe rezultate klasifikacije in predlogi za uporabo metod strojnega učenja za analizo dnevniških zapisov sistemov za upravljanje identitet za druge namene.

Language:Slovenian
Keywords:strojno učenje, klasifikacija, sistemi za upravljanje identitet, podatkovni model
Work type:Master's thesis (m2)
Organization:FE - Faculty of Electrical Engineering
Year:2016
Views:599
Downloads:441
Metadata:XML RDF-CHPDL DC-XML DC-RDF
 
Average score:(0 votes)
Your score:Voting is allowed only to logged in users.
:
Share:AddThis
AddThis uses cookies that require your consent. Edit consent...

Secondary language

Language:English
Title:IDENTITY MANAGEMENT SYSTEMS WITH CONTROL OF USERS´BEHAVIOR
Abstract:
This master thesis describes an example of applying machine learning methods on data model built from the most frequent sequences of events, occurring in log data of identity management system, connected with log data of DHCP server and access control system of medium sized Slovenian enterprise, with a goal of predicting employees’ performance for behavioral competence enthusiasm. Features were represented as a number of occurrences of different frequent sequence patterns for each user in multinomial and TF-IDF data format. Sequences with most discriminatory power based on class label, were extracted with Χ2 test and with Χ2 test with Bonferroni correction on all data. The first and the second chapter present a concept of digital identity, identity management systems and main motivations for predicting users’ behavior with machine learning methods based on identity management systems. The third chapter presents a concepts of machine learning, classification models training, feature generation process, and metrics for evaluation of classification models quality. The chapter also presents use cases of application of machine learning methods on analysis of log data, with a goal of intrusion detection in information systems, and application of machine learning methods in the field of human resource management. The fourth chapter describes process of data collection, preparation and data model building, and describes tools used in the thesis. The fifth chapter describes procedures for users’ performance prediction with machine learning methods with comments on results. The conclusion presents reasons for poor classification results and proposes other applications of analysis of identity management systems with machine learning methods.

Keywords:machine learning, classification, identity management systems, data model

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Comments

Leave comment

You have to log in to leave a comment.

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

Back