1. Cephalometric landmark detection in lateral skull X-ray images by using improved spatialconfiguration-netMartin Šavc, Gašper Sedej, Božidar Potočnik, 2022, izvirni znanstveni članek Opis: Accurate automated localization of cephalometric landmarks in skull X-ray images is the
basis for planning orthodontic treatments, predicting skull growth, or diagnosing face discrepancies.
Such diagnoses require as many landmarks as possible to be detected on cephalograms. Today’s
best methods are adapted to detect just 19 landmarks accurately in images varying not too much.
This paper describes the development of the SCN-EXT convolutional neural network (CNN), which
is designed to localize 72 landmarks in strongly varying images. The proposed method is based
on the SpatialConfiguration-Net network, which is upgraded by adding replications of the simpler
local appearance and spatial configuration components. The CNN capacity can be increased without
increasing the number of free parameters simultaneously by such modification of an architecture.
The successfulness of our approach was confirmed experimentally on two datasets. The SCN-EXT
method was, with respect to its effectiveness, around 4% behind the state-of-the-art on the small ISBI
database with 250 testing images and 19 cephalometric landmarks. On the other hand, our method
surpassed the state-of-the-art on the demanding AUDAX database with 4695 highly variable testing
images and 72 landmarks statistically significantly by around 3%. Increasing the CNN capacity
as proposed is especially important for a small learning set and limited computer resources. Our
algorithm is already utilized in orthodontic clinical practice.
Ključne besede: detection of cephalometric landmarks, skull X-ray images, convolutional neural networks, deep learning, SpatialConfiguration-Net architecture, AUDAX database
Objavljeno v DKUM: 27.03.2025; Ogledov: 0; Prenosov: 5
 Celotno besedilo (2,46 MB)
Gradivo ima več datotek! Več... |
2. |
3. |
4. K-vertex: a novel model for the cardinality constraints enforcement in graph databases : doctoral dissertationMartina Šestak, 2022, doktorska disertacija Opis: The increasing number of network-shaped domains calls for the use of graph database technology, where there are continuous efforts to develop mechanisms to address domain challenges. Relationships as 'first-class citizens' in graph databases can play an important role in studying the structural and behavioural characteristics of the domain. In this dissertation, we focus on studying the cardinality constraints mechanism, which also exploits the edges of the underlying property graph. The results of our literature review indicate an obvious research gap when it comes to concepts and approaches for specifying and representing complex cardinality constraints for graph databases validated in practice.
To address this gap, we present a novel and comprehensive approach called the k-vertex cardinality constraints model for enforcing higher-order cardinality constraints rules on edges, which capture domain-related business rules of varying complexity. In our formal k-vertex cardinality constraint concept definition, we go beyond simple patterns formed between two nodes and employ more complex structures such as hypernodes, which consist of nodes connected by edges. We formally introduce the concept of k-vertex cardinality constraints and their properties as well as the property graph-based model used for their representation. Our k-vertex model includes the k-vertex cardinality constraint specification by following a pre-defined syntax followed by a visual representation through a property graph-based data model and a set of algorithms for the implementation of basic operations relevant for working with k-vertex cardinality constraints.
In the practical part of the dissertation, we evaluate the applicability of the k-vertex model on use cases by carrying two separate case studies where we present how the model can be implemented on fraud detection and data classification use cases. We build a set of relevant k-vertex cardinality constraints based on real data and explain how each step of our approach is to be done. The results obtained from the case studies prove that the k-vertex model is entirely suitable to represent complex business rules as cardinality constraints and can be used to enforce these cardinality constraints in real-world business scenarios. Next, we analyze the performance efficiency of our model on inserting new edges into graph databases with varying number of edges and outgoing node degree and compare it against the case when there is no cardinality constraints checking. The results of the statistical analysis confirm a stable performance of the k-vertex model on varying datasets when compared against a case with no cardinality constraints checking. The k-vertex model shows no significant performance effect on property graphs with varying complexity and it is able to serve as a cardinality constraints enforcement mechanism without large effects on the database performance.
Ključne besede: Graph database, K-vertex cardinality constraint, Cardinality, Business rule, Property graph data model, Property graph schema, Hypernode, Performance analysis, Fraud detection, Data classification
Objavljeno v DKUM: 10.08.2022; Ogledov: 771; Prenosov: 111
Celotno besedilo (3,43 MB) |
5. The influence of one's own database on the accuracy of forecasting future movements of investment portfolio valueVesna Trančar, 2017, izvirni znanstveni članek Opis: The main purpose of this article is to present the test results of the hypothesis that the use of one’s own (and foreign) database (used by investment portfolio managers to create indicators of individual stock analyses) has an effect on the accuracy of forecasting future movements of investment portfolio value. In addition to the use of different indicators and methods of stock analysis, the creation of an optimal investment portfolio requires assessment of the suitability and adequacy of the database used in investment portfolio managers′ decisionmaking process; in other words, it is necessary to determine which stocks are to be included in the specific investment portfolio and which are not. The problem of the selection and use of different databases is linked to the question of determining the importance of numerous relevant elements when creating an optimal investment portfolio.
Ključne besede: database, investment portfolio, investment portfolio managers, stocks
Objavljeno v DKUM: 14.11.2017; Ogledov: 1339; Prenosov: 373
Celotno besedilo (262,91 KB)
Gradivo ima več datotek! Več... |
6. Inference attacks and control on database structuresMuhamed Turkanović, Tatjana Welzer-Družovec, Marko Hölbl, 2015, izvirni znanstveni članek Opis: Today’s databases store information with sensitivity levels that range from public to highly sensitive, hence ensuring confidentiality can be highly important, but also requires costly control. This paper focuses on the inference problem on different database structures. It presents possible treats on privacy with relation to the inference, and control methods for mitigating these treats. The paper shows that using only access control, without any inference control is inadequate, since these models are unable to protect against indirect data access. Furthermore, it covers new inference problems which rise from the dimensions of new technologies like XML, semantics, etc.
Ključne besede: inference, attacks, database, security, semantics
Objavljeno v DKUM: 09.08.2017; Ogledov: 1482; Prenosov: 120
Celotno besedilo (322,91 KB)
Gradivo ima več datotek! Več... |
7. COMPARISON OF MYSQL, NEO4J AND APACHE HIVE DATABASE MANAGEMENT SYSTEMSMatjaž Moser, 2016, magistrsko delo/naloga Opis: In this work a comparison of three different database management systems (DBMS) is presented. In general a relational data model with a graph data model is compared. The three systems used are MySQL, Neo4j and Apache Hive. Neo4j is a member of the NoSQL database family and is a well-known graph database. The relational databases used in this work are MySQL and Apache Hive. The latter is not a classic relational model but since it is modelled as such it can be considered relational. MySQL is a well-known solution that has been on the market for several years now and is a standard solution for many data problems.
Within this work a detailed comparison of all three systems from different aspects of usage is made, both from our own experience as well as from preliminary research from other authors and sources. Additionally some practical information from our dataset with some simple mining techniques is extracted and the result of our work is visualised in an interactive web side using modern approaches to data visualisation.
Ključne besede: Neo4j, MySQL, Apache Hadoop/Hive, database comparison, data visualisation
Objavljeno v DKUM: 13.05.2016; Ogledov: 2573; Prenosov: 195
Celotno besedilo (1,02 MB) |
8. |
9. ZAGOTAVLJANJE RAZPOLOŽLJIVOSTI INFRASTRUKTURNIH STORITEVHinko Rosulnik, 2013, diplomsko delo Opis: Pomembnost zagotavljanja zanesljivosti in razpoložljivosti infrastrukturnih storitev predstavlja eno ključnih nalog informacijske in telekomunikacijske tehnologije.
Osnovna ideja zagotavljanja visoke razpoložljivosti infrastrukturnih rešitev je, da vse spremembe, ki se dogajajo v postopkih spremljanja poslovanja na primarni bazi, čim hitreje prenesejo tudi na nadomestno bazo, ki obstoja na neki oddaljeni lokaciji glede na primarno bazo. V normalnem delovanju uporabniki delajo na primarni bazi, medtem ko je nadomestna baza v stanju pripravljenosti. Vse spremembe na primarni bazi se samodejno prenašajo na nadomestno lokacijo in s posebnim avtomatiziranim postopkom vpisujejo v nadomestno bazo.
V primeru kakršnekoli nastale napake v postopkih izvajanja poslovanja na informacijskem področju mora sistem pravilno opredeliti vrsto in zahtevnost nastale napake. V zahtevnih primerih nastale napake mora biti računalniški sistem na nadomestni lokaciji sposoben v čim krajšem času avtomatizirano prevzeti vse funkcionalnosti, ki jih je pred napako nudil primarni sistem.
Ključne besede: Oracle
Oracle Data Guard
Primary database
Standby database
Objavljeno v DKUM: 10.12.2013; Ogledov: 1438; Prenosov: 87
Celotno besedilo (1,54 MB) |
10. PRIMERJAVA PRISTOPOV K RAZVOJU PODATKOVNEGA SLOJA Z ADO.NET ENTITY FRAMEWORKRok Avberšek, 2012, diplomsko delo Opis: V diplomskem delu se primerjajo postopki načrtovanja podatkovnih modelov v ogrodju Entity Framework. Na začetku se osredotoča na samo arhitekturo ogrodja ter prednosti, ki jih ponujajo tehnologije ADO.NET, ADO.NET Entity Framework in LINQ. Predstavljene so tri tehnike oz. poteki dela s principi baze prej, modela prej in kode prej. Vsak izmed postopkov načrtovanja je opremljen s kratkim primerom in obrazložitvijo delovanja ter prednostmi, ki jih ponuja. Naloga je zaključena z razčlenitvijo prednosti in slabosti posameznega postopka načrtovanja, vrsto aplikacije in želje posameznih razvijalcev.
Ključne besede: Microsoft, ADO.NET, LINQ, EDM, Visual, Studio, Code-First, Database-First, Model-First
Objavljeno v DKUM: 26.11.2012; Ogledov: 2163; Prenosov: 179
Celotno besedilo (2,24 MB) |
