Milan Zorman

Class imbalance remains a persistent challenge in supervised classification, particularly when the minority class represents rare but important observations. Common approaches address this problem through undersampling, synthetic oversampling, cost-sensitive learning, or decomposition of complex class distributions. This study introduces Hierarchical Majority Decomposition (HMD), an architecture in which the majority class is recursively partitioned into a binary tree of increasingly localized subclasses while the complete minority class remains intact. A supervised local classifier is associated with each internal majority node and distinguishes the minority class from the node’s two child majority subclasses. During top-down inference, a minority prediction terminates traversal, whereas a majority-subclass prediction simultaneously identifies the current observation as not yet recognized as minority and determines the branch in which the next minority comparison is performed. HMD was evaluated using six binary benchmark datasets with imbalance ratios ranging from approximately 3.2:1 to 42.0:1. An unrestricted decision tree was used as a controlled base learner, and all methods were evaluated using 5-fold stratified cross-validation repeated 10 times. HMD was compared with an untreated decision tree, a class-weighted decision tree, random undersampling, SMOTE, and a root-only flat majority decomposition. Increasing HMD inference depth increased minority recall relative to the untreated decision tree on all six datasets. The strongest effects were observed on Mammography, Climate Model Simulation Crashes, Oil Spill, and Ozone Level Detection. Importantly, the root-only decomposition generally remained close to the untreated decision tree, whereas deeper HMD inference produced substantially larger sensitivity increases, indicating that recursive minority comparison rather than majority decomposition alone is responsible for much of the observed effect. Random undersampling frequently achieved equal or greater minority recall and balanced accuracy, but often at a substantially greater loss of specificity and minority precision. The results demonstrate that a recursively decomposed majority class can be used as an active inference structure in which an unchanged minority class is repeatedly reconsidered against progressively localized majority contexts.

Področje umetne inteligence zaradi svoje interdisciplinarne narave zahteva strokovno znanje s področij matematike, statistike, računalništva in seveda domenskega znanja na področju uporabe. Umetna inteligenca se hitro razvija, nenehno se pojavljajo novi algoritmi in tehnike, ki zahtevajo stalno učenje. Izzivi poleg tehničnih vključujejo etične vidike, ublažitev pristranskosti in preglednost v postopkih odločanja. Široka uporaba umetne inteligence v različnih panogah zahteva različne nabore spretnosti in prilagodljivost. Umetna inteligenca tako ostaja zahtevno in dinamično področje. Pospeševalci uporabe umetne inteligence imajo ključno vlogo pri učinkoviti uporabi širokega nabora znanj . Ponujajo smernice za krmarjenje po zapletenem okolju tehnologij umetne inteligence in zagotavljajo usklajenost s predpisi EU, etičnimi standardi in družbenimi vrednotami. Pomagajo opredeliti priložnosti za uvedbo umetne inteligence, jih uskladiti s posebnimi potrebami in izzivi v EU ter spodbujati inovacije in gospodarsko rast. Preko platforme EU.FFICIENT (https://eufficient.eu/) lahko obstoječi in novi pospeševalci dostopajo do najnovejših praktičnih primerov in učnega gradiva, ki jim pomaga pridobiti nove spretnosti in znanja. Platforma EU.EFFICIENT združuje štiri tematske skupnosti, in sicer, Napredno proizvodnjo, Biomedicinsko tehniko, Mobilnost ter Umetno inteligenco in digitalne tehnologije. Z zagotavljanjem centralizirane platforme za soustvarjanje pospešujemo in izboljšujemo sodelovanje med akademskim svetom in industrijo ter tako ustvarjamo pozitiven vpliv na družbo.

Purpose: Collaborative robotics and autonomous driving are fairly new disciplines, still with a long way to go to achieve goals, set by the research community, manufacturers and users. For technologies like collaborative robotics and autonomous driving, which focus on closing the gap between humans and machines, the physical, psychological and emotional needs of human individuals becoming increasingly important in order to ensure effective and safe human–machine interaction. The authors' goal was to conceptualize ways to combine experience from both fields and transfer artificial intelligence knowledge from one to another. By identifying transferable meta-knowledge, the authors will increase quality of artificial intelligence applications and raise safety and contextual awareness for users and environment in both fields.Design/methodology/approach: First, the authors presented autonomous driving and collaborative robotics and autonomous driving and collaborative robotics' connection to artificial intelligence. The authors continued with advantages and challenges of both fields and identified potential topics for transferrable practices. Topics were divided into three time slots according to expected research timeline.Findings: The identified research opportunities seem manageable in the presented timeline. The authors' expectation was that autonomous driving and collaborative robotics will start moving closer in the following years and even merging in some areas like driverless and humanless transport and logistics.Originality/value: The authors' findings confirm the latest trends in autonomous driving and collaborative robotics and expand them into new research and collaboration opportunities for the next few years. The authors' research proposal focuses on those that should have the most positive impact to safety, complement, optimize and evolve human capabilities and increase productivity in line with social expectations. Transferring meta-knowledge between fields will increase progress and, in some cases, cut some shortcuts in achieving the aforementioned goals.

The 7th Student Computer Science Research Conference is an answer to the fact that modern PhD and already Master level Computer Science programs foster early research activity among the students. The prime goal of the conference is to become a place for students to present their research work and hence further encourage students for an early research. Besides the conference also wants to establish an environment where students from different institutions meet, let know each other, exchange the ideas, and nonetheless make friends and research colleagues. At last but not least, the conference is also meant to be meeting place for students with senior researchers from institutions others than their own. Konferenčni zbornik 7. študentske konferenece na področju računalništva in informatike 2021. Sedma Študentska konferenca na področju računalništva in informatike je odgovor na dejstvo, da so študenti 2. in 3. Bolonjske stopnje prisiljeni v raziskovalno delo že zelo zgodaj. Prvenstveni cilj te konference je nuditi možnost tem študentom, da predstavijo rezultate svojega raziskovalnega dela in jih vzpodbuditi za nadaljnje delo. Poleg tega želi konference vzpostaviti okolje, kjer se študenti iz različnih institucij srečujejo, spoznavajo, izmenjujejo ideje in na koncu koncev sklepajo prijateljstva, ki jim ostajajo v zrelih letih. Nenazadnje ta konferenca omogoča tudi, da se študenti srečujejo in navezujejo stike s starejšimi raziskovalci iz drugih institucij.

Acute pancreatitis (AP) is a disease with significant morbidity and mortality. The aim of this study was to evaluate the prognostic role of inflammatory markers, particularly interleukins (ILs), in the course of AP and to determine the frequency of etiologic factors of AP. We included patients with AP who were treated at our institution from May 1, 2012 to January 31, 2015. Different laboratory parameters, including ILs, and the severity scoring systems Ranson’s criteria and Bedside Index of Severity in Acute Pancreatitis (BISAP) were analyzed. AP was classified into mild and severe, and independent parameters were compared between these groups. The predictive performance of each parameter was evaluated using receiver operating characteristic (ROC) curves and the area under the ROC curve (AUC). A binomial logistic regression was performed to evaluate Ranson’s criteria and IL6, IL8, and IL10 (at admission and after 48 hours) in the course of AP. Overall, 96 patients were treated, 59 (61.5%) males and 37 (38.5%) females, average age 62.5 ± 16.8 years (range 22–91 years). The best predictor for the severity of AP was IL6, measured 48 hours after admission (AUC = 0.84). Other useful predictors of the severity of AP were lactate dehydrogenase (p < 0.001), serum glucose (p < 0.006), and difference in the platelet count (p < 0.001) between admission and after 48 hours (p < 0.001), hemoglobin (p < 0.027) and erythrocytes (p < 0.029). The major causes of AP were gallstones and alcohol consumption. According to our results, IL6 and Ranson score are important predictors of the severity of AP.

Code smells as symptoms of poor design and implementation choices. Many times they are the result of so called technical debt. Our study showed that the interest in code smells research is increasing. However, most of the publications are appearing in conference proceedings. Most of the research is done in G7 and other highly developed countries. Four main research themes were identified namely code smell detection, bad smell based refactoring, software development and anti patterns. The results show that code smells can also have a positive connotation, we can develop software which smells good and attracts various customers and good smelling code could also serve as a pattern for future software development.