20.500.12556/RUL-173259 Napovedovanje števila potnikov v slovenskem železniškem omrežju Passenger Number Forecasting in the Slovenian Railway Network V diplomskem delu obravnavamo problem zasedenosti vlakov. Cilj raziskave je bil razviti sistem za podporo pri načrtovanju in optimizaciji železniškega prometa. V ta namen smo oblikovali napovedni model za oceno števila potnikov na železniških postajah. Za učenje in testiranje smo uporabili podatke Slovenskih železnic, ki vključujejo večletne zapise o številu potnikov, čase prihodov in odhodov ter vozne rede. Podatke smo dopolnili z informacijami o vremenu, praznikih, šolskih počitnicah in drugih dejavnikih, ki vplivajo na potniški promet. Napovedni sistem temelji na metodi XGBoost. Njegovo uspešnost smo ovrednotili s primerjavo z dvema enostavnejšima modeloma: prvi je napovedoval povprečno število potnikov glede na postajo, drugi pa glede na postajo in dan v tednu. Število potnikov je dokaj stabilno, zato so trivialni modeli pogosto že dokaj dobri. Kljub temu je naš model pokazal boljše rezultate od obeh primerjalnih pristopov. The thesis addresses the problem of train occupancy, aiming to develop a system that supports the planning and optimization of railway traffic. To achieve this, we designed a predictive model to estimate passenger numbers at railway stations. For training and testing, we used data from Slovenian Railways, which include multi-year records of passenger entries and exits, train arrival and departure times, and schedules. The dataset was further enriched with information on weather, holidays, school breaks, and other factors that can influence passenger flow. The predictive system is based on the XGBoost method. Its performance was evaluated against two simpler models: the first predicted the average number of passengers per station, while the second considered both the station and the day of the week. Passenger numbers were found to be fairly stable, making simple models often reasonably effective. Nevertheless, our model consistently outperformed both baseline approaches. železniški promet napovedni model XGBoost strojno učenje railway traffic prediction model XGBoost machine learning true false false Slovenski jezik Angleški jezik Diplomsko delo/naloga 2025-09-15 10:55:04 2025-09-15 10:55:10 2025-11-07 03:50:08 0000-00-00 00:00:00 2025 0 0 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 38047 250506499 Urh_Zala_-_Napovedovanje_stevila_potnikov_v_slovenskem_zelezniskem_omrezju.pdf Urh_Zala_-_Napovedovanje_stevila_potnikov_v_slovenskem_zelezniskem_omrezju.pdf 1 C82A3EEA49F626ABE8D1D9FE83B0E96E d415cf82480b262bb20437239247e07acf3aaae1dfb806c6df4b0fdd1d8e8d9e 841cd5cd-9211-11f0-9328-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=217471 Fakulteta za računalništvo in informatiko 0 0 0