1. Using generative AI to improve the performance and interpretability of rule-based diagnosis of Type 2 diabetes mellitusLeon Kopitar, Iztok Fister, Gregor Štiglic, 2024, original scientific article Abstract: Introduction: Type 2 diabetes mellitus is a major global health concern, but interpreting machine learning models for diagnosis remains challenging. This study investigates combining association rule mining with advanced natural language processing to improve both diagnostic accuracy and interpretability. This novel approach has not been explored before in using pretrained transformers for diabetes classification on tabular data. Methods: The study used the Pima Indians Diabetes dataset to investigate Type 2 diabetes mellitus. Python and Jupyter Notebook were employed for analysis, with the NiaARM framework for association rule mining. LightGBM and the dalex package were used for performance comparison and feature importance analysis, respectively. SHAP was used for local interpretability. OpenAI GPT version 3.5 was utilized for outcome prediction and interpretation. The source code is available on GitHub. Results: NiaARM generated 350 rules to predict diabetes. LightGBM performed better than the GPT-based model. A comparison of GPT and NiaARM rules showed disparities, prompting a similarity score analysis. LightGBM’s decision making leaned heavily on glucose, age, and BMI, as highlighted in feature importance rankings. Beeswarm plots demonstrated how feature values correlate with their influence on diagnosis outcomes. Discussion: Combining association rule mining with GPT for Type 2 diabetes mellitus classification yields limited effectiveness. Enhancements like preprocessing and hyperparameter tuning are required. Interpretation challenges and GPT’s dependency on provided rules indicate the necessity for prompt engineering and similarity score methods. Variations in feature importance rankings underscore the complexity of T2DM. Concerns regarding GPT’s reliability emphasize the importance of iterative approaches for improving prediction accuracy.
Keywords: GPT, association rule mining, classification, interpretability, diagnostics
Published in DKUM: 26.11.2024; Views: 0; Downloads: 6
 Full text (1,29 MB)
This document has many files! More... |
2. If at first you do not succeed : an overview of remedies available in the United States Courts of AppealsThomas Allan Heller, 2022, original scientific article Abstract: In the United States federal court system, from a procedural standpoint, it has been the historic policy that appeals to the Courts of Appeal lie only from final decisions by the district courts. This policy, dubbed the final judgment rule, is designed to prevent a piecemeal approach to appellate practice, and to enhance efficiency and fairness. Applied overly strictly, the rule can often lead to unfair results, and even irreparable harm. This article catalogues the primary exceptions to the final judgment rule, and discusses those instances when interlocutory appeals may be taken short of district court rulings disposing of all issues as to all parties, that is, final judgments.
Keywords: appeals, final judgment rule, collateral orders doctrine, interlocutory appeals, mandamus, appeal administrative orders, class actions
Published in DKUM: 17.06.2024; Views: 136; Downloads: 14
Full text (553,54 KB)
This document has many files! More... |
3. Time series numerical association rule mining variants in smart agricultureIztok Fister, Dušan Fister, Iztok Fister, Vili Podgorelec, Sancho Salcedo-Sanz, 2023, original scientific article Keywords: association rule mining, smart agriculture, optimization, evolutionary algotihms, internet of things
Published in DKUM: 12.06.2024; Views: 121; Downloads: 9
Full text (1,49 MB)
This document has many files! More... |
4. Action-Based Digital Characterization of a Game PlayerDamijan Novak, Domen Verber, Jani Dugonik, Iztok Fister, 2023, original scientific article Keywords: association rule mining, digital characterization, game agent, game player, real-time strategy games
Published in DKUM: 23.05.2024; Views: 131; Downloads: 7
Full text (9,40 MB)
This document has many files! More... |
5. Variable-length differential evolution for numerical and discrete association rule miningUroš Mlakar, Iztok Fister, Iztok Fister, 2023, original scientific article Abstract: This paper proposes a variable-length Differential Evolution for Association Rule Mining. The proposed algorithm includes a novel representation of individuals, which can encode both numerical and discrete attributes in their original or absolute complement of the original intervals. The fitness function used is comprised of a weighted sum of Support and Confidence Association Rule Mining metrics. The proposed algorithm was tested on fourteen publicly available, and commonly used datasets from the UC Irvine Machine Learning Repository. It is also compared to the nature inspired algorithms taken from the NiaARM framework, providing superior results. The implementation of the proposed algorithm follows the principles of Green Artificial Intelligence, where a smaller computational load is required for obtaining promising results, and thus lowering the carbon footprint.
Keywords: association rule mining, differential evolution, data mining, variable-lenght solution representation, green AI
Published in DKUM: 18.01.2024; Views: 341; Downloads: 25
Full text (2,39 MB)
This document has many files! More... |
6. K-vertex: a novel model for the cardinality constraints enforcement in graph databases : doctoral dissertationMartina Šestak, 2022, doctoral dissertation Abstract: 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.
Keywords: Graph database, K-vertex cardinality constraint, Cardinality, Business rule, Property graph data model, Property graph schema, Hypernode, Performance analysis, Fraud detection, Data classification
Published in DKUM: 10.08.2022; Views: 771; Downloads: 104
Full text (3,43 MB) |
7. uARMSolver: a framework for association rule miningIztok Fister, Iztok Fister, 2020, treatise, preliminary study, study Keywords: association rule mining, categorical attributes, numerical attributes, software framework, optimization
Published in DKUM: 17.03.2021; Views: 1446; Downloads: 41
Full text (462,21 KB)
This document has many files! More... |
8. An overview of the law of attorney fees in the United States : the American rule is not so simple after allThomas Allan Heller, 2018, original scientific article Abstract: It often is said that in the United States each party pays their own attorney’s fees, win or lose, absent a contractual provision to the contrary or some recognized ground in equity. This basic proposition, which is true as far as it goes, is based on the so-called American Rule, which provides that in the United States each side in a litigated case is responsible for paying their own attorney, regardless of the outcome of the case. On its face this proposition seems simple. On the contrary, however, the laws in the United States governing attorney’s fees are surprising quite complex. This article provides a general survey of the patchwork of laws, federal and to a lesser extent state, and the author will demonstrate that rules and laws governing attorney’s fees are often grounded in important public policy and fundamentally shape important issues, such as access to the courts and the legal system more generally. Unfortunately, many United States citizens have been priced out of the legal market under the current system.
Keywords: attorney’s fees, fee-shifting, fee arrangements, American Rule, court access
Published in DKUM: 03.08.2018; Views: 1085; Downloads: 157
Full text (457,99 KB)
This document has many files! More... |
9. ODGOVORNOST ZA NEPRAVOČASNI STEČAJ GOSPODARSKE DRUŽBE KOT POSLEDICA PONAREDITVE PODATKOV LETNEGA POROČILA Z VIDIKA ZAHTEV PRAVA EUKatarina Moravec, 2016, master's thesis Abstract: Insolventnost gospodarske družbe je stanje, za katerega pravo zahteva sprejem ustreznih ukrepov, kot so finančna reorganizacija, prisilna poravnava ali stečaj. Organi vodenja in nadzora so dolžni stanje insolventnosti zaznati dovolj zgodaj, nato pa brez nepotrebnega odlašanja nadaljevati z ukrepi, s katerimi zagotovijo stabilno finančno poslovanje gospodarske družbe. Namen hitrega delovanja je v varstvu interesov upnikov, saj lahko prav ti zaradi zavlačevanja sprejema prepotrebnih ukrepov izgubijo največ.
Stanje insolventnosti gospodarske družbe, kot ga določa 14. člen Zakona o finančnem poslovanju, postopkih zaradi insolventnosti in prisilnem prenehanju (v nadaljevanju: ZFPPIPP) se zazna najkasneje ob sestavi letnega poročila, kot enega najpomembnejših korporacijskopravnih aktov vsake gospodarske družbe in podjetnika. Na podlagi tega se lahko ugotovi zadolženost (prezadolženost) gospodarske družbe, strukturo dolgov, zavarovanja, kot tudi realno vrednost premoženja gospodarske družbe. Generalna klavzula v prvem odstavku 61. člena Zakona o gospodarskih družbah (v nadaljevanju: ZGD-1) zahteva, da je letno poročilo sestavljeno jasno in pregledno ter da izkazuje resničen in pošten prikaz premoženja in obveznosti gospodarske družbe, njenega finančnega položaja ter poslovnega izida. Če so podatki v letnem poročilu ponarejeni tako, da izkazujejo boljše premoženjsko stanje od dejanskega, se stanje insolventnosti ne zazna. Posledično to pomeni, da do pravočasnega sprejema ustreznih ukrepov, kot jih za primer insolventnosti gospodarske družbe določa ZFPPIPP ne pride, kar prinese odgovornost članov organov vodenja in nadzora. Zavlačevanje s predlaganjem stečaja je predvsem v interesu lastnikov gospodarske družbe, ki z odlaganjem pridobijo možnost, da iz gospodarske družbe umaknejo lastna sredstva in ustanovijo novo gospodarsko družbo, s čimer oškodujejo predvsem svoje upnike.
Keywords: finančno poslovanje gospodarske družbe, business judgement rule, letno poročilo, harmonizacija bilančnega prava, ponarejanje podatkov letnega poročila, insolventnost, nepravočasni stečaj, odgovornost članov organov vodenja in nadzora, stečajni upravitelj, revizor.
Published in DKUM: 06.03.2017; Views: 2139; Downloads: 207
Full text (642,46 KB) |
