1. Comparing algorithms for predictive data analyticsGoran Kirov, 2024, master's thesis Abstract: The master’s degree thesis is composed of theoretical and practical parts. The theoretical part describes the basics of predictive data analytics and machine learning algorithms for classification such as Logistic Regression, Decision Tree, Random Forest, SVM, and KNN. We also describe different evaluation metrics such as Recall, Precision, Accuracy, F1 Score, Cohen’s Kappa, Hamming Loss, and Jaccard Index that are used to measure the performance of these algorithms. Additionally, we record the time taken for the training and prediction processes to provide insights into algorithm scalability.
The key part master’s thesis is the practical part that compares these algorithms with a self-implemented tool that shows results for different evaluation metrics on seven datasets. First, we describe the implementation of an application for testing where we measure evaluation metrics scores. We tested these algorithms on all seven datasets using Python libraries such as scikit-learn. Finally, w
Keywords: data analytics, machine learning, classification, evaluation metrics
Published in DKUM: 15.01.2025; Views: 0; Downloads: 22
 Full text (2,68 MB) |
2. The role of visualization in estimating cardiovascular disease risk : scoping reviewAdrijana Svenšek, Mateja Lorber, Lucija Gosak, Katrien Verbert, Zalika Klemenc-Ketiš, Gregor Štiglic, 2024, review article Abstract: Background: Supporting and understanding the health of patients with chronic diseases and cardiovascular disease (CVD) risk is often a major challenge. Health data are often used in providing feedback to patients, and visualization plays an important role in facilitating the interpretation and understanding of data and, thus, influencing patients’ behavior. Visual analytics enable efficient analysis and understanding of large datasets in real time. Digital health technologies can promote healthy lifestyle choices and assist in estimating CVD risk. Objective: This review aims to present the most-used visualization techniques to estimate CVD risk. Methods: In this scoping review, we followed the Joanna Briggs Institute PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines. The search strategy involved searching databases, including PubMed, CINAHL Ultimate, MEDLINE, and Web of Science, and gray literature from Google Scholar. This review included English-language articles on digital health, mobile health, mobile apps, images, charts, and decision support systems for estimating CVD risk, as well as empirical studies, excluding irrelevant studies and commentaries, editorials, and systematic reviews. Results: We found 774 articles and screened them against the inclusion and exclusion criteria. The final scoping review included 17 studies that used different methodologies, including descriptive, quantitative, and population-based studies. Some prognostic models, such as the Framingham Risk Profile, World Health Organization and International Society of Hypertension risk prediction charts, Cardiovascular Risk Score, and a simplified Persian atherosclerotic CVD risk stratification, were simpler and did not require laboratory tests, whereas others, including the Joint British Societies recommendations on the prevention of CVD, Systematic Coronary Risk Evaluation, and Framingham-Registre Gironí del COR, were more complex and required laboratory testing–related results. The most frequently used prognostic risk factors were age, sex, and blood pressure (16/17, 94% of the studies); smoking status (14/17, 82%); diabetes status (11/17, 65%); family history (10/17, 59%); high-density lipoprotein and total cholesterol (9/17, 53%); and triglycerides and low-density lipoprotein cholesterol (6/17, 35%). The most frequently used visualization techniques in the studies were visual cues (10/17, 59%), followed by bar charts (5/17, 29%) and graphs (4/17, 24%). Conclusions: On the basis of the scoping review, we found that visualization is very rarely included in the prognostic models themselves even though technology-based interventions improve health care worker performance, knowledge, motivation, and compliance by integrating machine learning and visual analytics into applications to identify and respond to estimation of CVD risk. Visualization aids in understanding risk factors and disease outcomes, improving bioinformatics and biomedicine. However, evidence on mobile health’s effectiveness in improving CVD outcomes is limited.
Keywords: cardiovascular disease prevention, risk factors, visual analytics, visualization, mobile phone, PRISMA
Published in DKUM: 26.11.2024; Views: 0; Downloads: 1
Full text (435,60 KB) |
3. ROBOTIC PROCESS AUTOMATION (RPA) IN AUDITINGFilip Tashkovski, 2024, undergraduate thesis Abstract: Auditing, as a form of control (for example over financial management or compliance), has traditionally relied on manual processes that are time-consuming, labor-intensive and prone to human error. With the advent of robotic process automation (RPA), there has been a paradigm shift from manual to automated processes in audit processes as well. Automation dates back to the 1990s, which led to the creation of robotic process automation (RPA) tools. Today we are approaching or we are in the fourth industrial revolution, the era of universal automation. RPA refers to the use of software robots (or "bots") to automate repetitive rule-based activities previously performed by humans. As companies try to keep up with rapid technological improvements, incorporating RPA into audit processes provides a number of benefits that can radically change auditing. RPA has emerged as a transformative technology in auditing, changing established approaches with its ability to improve productivity, accuracy and compliance. One of the most significant benefits of RPA in auditing is its ability to increase efficiency. Traditional audit procedures can sometimes be time-consuming and labor-intensive, as auditors must manually collect and evaluate data from multiple sources. RPA accelerates these activities by automating common tasks such as data entry, coordination and report generation. For example, an RPA robot can be trained to collect financial data from multiple sources (eg from multiple companies) and verify its accuracy using established criteria. This not only reduces the time required to perform audits, but also eliminates the possibility of human error. In addition to efficiency, there is another key advantage: accuracy. RPA enables auditors to take proactive measures to reduce risk, thereby protecting the financial integrity and reputation of the organization. By automating mundane and repetitive activities, RPA allows auditors to focus on more strategic activities that deliver value to the business. Auditors (in the broadest sense) can spend more time evaluating data models, finding areas for improvement, and making strategic suggestions to management. The aim of this bachelor's degree thesis is to explore and demonstrate the application of RPA in audit procedures, highlighting its benefits such as increased productivity, improved quality of rapid processing of large databases, improved risk management, and cost savings. The thesis also discusses the challenges and considerations related to the implementation of RPA in audit practices. The history of RPA is detailed, revealing its use by different industries and their goals. The thesis defines all types of RPA tools and their advantages and weaknesses. It also distinguishes between artificial intelligence (AI) and RPA, as it can confuse the activities of RPA tools with AI.
Keywords: robotic process automation, RPA, monitoring, analytics, security, productivity, auditing, audit process.
Published in DKUM: 09.09.2024; Views: 25; Downloads: 14
Full text (1,64 MB) |
4. Assessing Perceived Trust and Satisfaction with Multiple Explanation Techniques in XAI-Enhanced Learning AnalyticsSaša Brdnik, Vili Podgorelec, Boštjan Šumak, 2023, original scientific article Abstract: This study aimed to observe the impact of eight explainable AI (XAI) explanation techniques on user trust and satisfaction in the context of XAI-enhanced learning analytics while comparing two groups of STEM college students based on their Bologna study level, using various established feature relevance techniques, certainty, and comparison explanations. Overall, the students reported the highest trust in local feature explanation in the form of a bar graph. Additionally, master's students presented with global feature explanations also reported high trust in this form of explanation. The highest measured explanation satisfaction was observed with the local feature explanation technique in the group of bachelor's and master's students, with master's students additionally expressing high satisfaction with the global feature importance explanation. A detailed overview shows that the two observed groups of students displayed consensus in favored explanation techniques when evaluating trust and explanation satisfaction. Certainty explanation techniques were perceived with lower trust and satisfaction than were local feature relevance explanation techniques. The correlation between itemized results was documented and measured with the Trust in Automation questionnaire and Explanation Satisfaction Scale questionnaire. Master's-level students self-reported an overall higher understanding of the explanations and higher overall satisfaction with explanations and perceived the explanations as less harmful.
Keywords: explainable artificial intelligence, learning analytics, XAI techniques, trust, explanation satisfaction
Published in DKUM: 12.02.2024; Views: 368; Downloads: 41
Full text (3,24 MB)
This document has many files! More... |
5. Analiza okoljskih podatkov z Oracle Analytics CloudEdin Šahinović, 2023, undergraduate thesis Abstract: Z analizo okoljskih podatkov, pridobljenih v sodelovanju z mednarodnim proizvodnim podjetjem, smo raziskovali in ocenili zmožnosti, funkcije, prednosti in slabosti orodja Oracle Analytics Cloud. Poleg samih funkcij smo se osredotočili na povezanost in pomembnost analize okoljskih podatkov z doseganjem ciljev zelenega slovenskega lokacijskega okvirja ter tudi evropskega zelenega dogovora. Ti cilji postajajo vedno bolj pomembni in regulirani, kar pa se odraža tudi pri prilagajanju poslovanja podjetij, ki veliko svojih resursov usmerjajo v optimizacijo energentov in področje trajnosti. Diplomska naloga se zato osredotoča na preprost prikaz okoljskih podatkov in njihovo predstavitev, kljub temu da je v ozadju podrobna analiza, izvedena v raziskovalnem orodju.
Keywords: Oracle Analytics Cloud, okoljski podatki, analiza, Evropski zeleni dogovor.
Published in DKUM: 08.08.2023; Views: 536; Downloads: 68
Full text (3,44 MB) |
6. Študij vezave peptidov na Fc regije protiteles : magistrsko deloŽan Smrekar, 2023, master's thesis Abstract: Z uporabo računalniških pristopov in simulacij lahko uspešno modeliramo interakcije, ki so ključne pri razumevanju delovanja in razvoju novih zdravilnih učinkovin. Tekom razvoja se pojavljajo novi razredi peptidnih zdravil. Peptidi so sestavljeni iz verig aminokislinskih preostankov in zajemajo prednosti tako majhnih molekul kot tudi tarčno specifičnost večjih struktur, kot so proteini. Za načrtovanje novih potencialnih struktur peptidov smo tako uporabili računalniške in bioinformacijske pristope, kot je molekulsko sidranje. V magistrski nalogi smo se osredotočili na Fc regijo protiteles kot receptor. Načrtovali in identificirali smo potencialne tetrapeptide s strukturo, ki je podobna eksperimentalnim podatkom.
Problema smo se lotili s pomočjo računalniških programov. Ustrezni receptor smo pridobili na prosto dostopnem spletnem mestu https://www.rcsb.org/ (PDB ID: 5U52), za pripravo knjižnice struktur tetrapeptidov in analizo rezultatov smo uporabili analitično platformo KNIME, za molekulsko sidranje smo uporabili programsko opremo CmDock in za grafični vpogled ciljnih struktur računalniški program PyMol.
Keywords: peptidi, Fc regija, molekulsko sidranje, KNIME Analytics Platform, PyMol, peptidno sidranje
Published in DKUM: 25.05.2023; Views: 642; Downloads: 90
Full text (2,74 MB) |
7. Prenova spletne trgovine Pikapolonica.siDare Vodušek, 2020, undergraduate thesis Abstract: Podjetje Pikapoka, d. o. o., želi optimizirati obdelavo spletnih naročil, saj se za njihovo
obdelavo porabi preveč časa, kar za podjetje pomeni ekonomsko izgubo. Največji
problem je v obdelavi naročil, predvsem v preverjanju zaloge po poslovalnicah, ki se
opravlja ročno, prek telefonov. To obremenjuje obe strani, tako poslovalnico, ki obdeluje
naročilo, kot poslovalnico, v katero se kliče. Uvedli smo ažuren podatek o zalogi iz vsake
poslovalnice, posledično pa se bo na spletno mesto lahko vpeljala tudi nova
funkcionalnost, in sicer izpis zaloge po poslovalnicah. Nov sistem bo omogočil boljšo
uporabniško izkušnjo in obdelovalcu naročila zmanjšal potreben čas za preverjanje
zaloge.
Keywords: spletna trgovina, SymetricDS, Google Analytics
Published in DKUM: 02.11.2020; Views: 1300; Downloads: 93
Full text (1,49 MB) |
8. Prenova spletne trgovine za industrijsko varilno tehnikoMihael Hack, 2019, undergraduate thesis Abstract: Za uspešno spletno stran in končne rezultate je v današnjem času potrebnega veliko več dela, predvsem zaradi vedno večjega števila konkurenčnih spletnih strani.
V diplomskem delu se pri komponentah spleta osredotočamo na grafično oblikovanje spletne strani, optimizacijo spletne strani, digitalni marketing, varnost in znake zaupanja. Izpostavljena tematika dela je neposodobljena spletna stran, ki ni bila spremenjena že nekaj let. Sprotno urejanje spletne strani je v spletnem svetu velikega pomena, saj lahko v nasprotnem primeru pade obisk spletnih uporabnikov. Obiskovalci strani zahtevajo aktualne informacije o novostih na trgu dela in zaradi takih potreb je potrebno izdelati spletno stran z dobrim SEO (angl. Search Engine Opitimization) sistemom, ki stranki omogoča hitro rešitev iskanja informacij z uporabo spletnega iskalnika.
Rešitev aktualne problematike je v prenovi spletne strani VTH-Hack in uporaba nove domene. Pred izdelavo nove spletne strani smo analizirali staro oziroma obstoječo spletno stran, analizirali konkurenco, analizirali ključne besede in določili osnove spletne strani. Za izdelavo spletne strani smo uporabili sistem za upravljanje vsebin WordPress. V WordPressu smo lahko s pomočjo izbrane teme in vtičniki oblikovali spletno stran po naših potrebah. Po končanem delu smo spletno stran objavili in jo prikazali javnosti ter dovolili orodju Google Analytics, da spremlja obiske posodobljene spletne strani. S tem je omogočeno spremljanje in analiza obiska spletne strani ter spremljanje izboljšav na podlagi rezultatov analize.
Keywords: optimizacija spletne strani, WordPress, Google Analytics, izdelava spletne strani, analiza spletne strani
Published in DKUM: 13.01.2020; Views: 1052; Downloads: 247
Full text (3,52 MB) |
9. Spletna analitika v digitalnem marketingu turizmaMojca Vogrič, 2019, bachelor thesis/paper Abstract: Pojav in razvoj interneta predstavljata korenite spremembe na področju marketinga, saj je s tem pridobil spletno podobo. Za boljše in učinkovitejše poslovne rezultate pa ima velik pomen oglaševanje. Da bi z oglaševanjem dosegli tudi cilj, to je nakup izdelka ali storitve, morajo podjetja s pomočjo spletne analitike izbrati pravilne poslovne odločitve in strategije.
V diplomski nalogi je obravnavana problematika, kdaj in kje je najbolj smiselno oglaševati. Cilj diplomske naloge je predvsem ugotoviti, kaj obiskovalce spletne strani najbolj zanima, da lahko na podlagi teh podatkov prilagodimo oglaševanje.
Najprej smo s pomočjo domače in tuje literature pridobili vse potrebne informacije in podatke, ki smo jih potrebovali za teoretični del diplomske naloge. Nato pa smo z zbranimi podatki iz podjetja Forward in s pomočjo orodja Google Analytics ugotovili, katere strani na spletnem mestu so najbolj obiskane in kdaj. Po podrobni analizi pridobljenih rezultatov smo prišli do zaključkov, na podlagi katerih smo naročniku svetovali, kako naj v prihodnosti oglašuje.
Keywords: spletni marketing, spletna analitika, Google Analytics
Published in DKUM: 08.05.2019; Views: 1573; Downloads: 206
Full text (2,42 MB) |
10. Pomen vizualne percepcije na spletni promet spletnega dnevnikaLarisa Fekonja, 2018, undergraduate thesis Abstract: V diplomski nalogi smo se osredotočili na percepcijo obstoječega spletnega dnevnika v namen zvišanja spletnega prometa. Glede na načela in dobre prakse percepcijskega oblikovanja spletnih strani smo omenjeni spletni dnevnik vizualno izboljšali. Glede na izbrane metrike uspešnosti smo nato z orodjem Google Analytics izmerili spletni promet pred in po izboljšavi. Pokazali smo, da imajo percepcijske izboljšave vpliv na sam promet spletnega mesta. V postopku merjenja smo namreč dosegli 45,19 % izboljšanje pri ogledih strani ter 59,24 % izboljšanje pri številu uporabnikov.
Keywords: spletni dnevnik, percepcija, percepcijsko oblikovanje, spletni promet, Google Analytics
Published in DKUM: 30.01.2019; Views: 1474; Downloads: 104
Full text (5,33 MB) |
