Digital repository of Slovenian research organisations

Search the repository
A+ | A- | Help | SLO | ENG

There are two search modes available: simple and advanced. Simple search can include one or more words from the title, summary, keywords or full text, but does not allow the use of search operators. Advanced search allows to limit the number of search results by entering the search terms of different categories in the search window, as well as the use of Boolean search operators (AND, OR and AND NOT). In search results short formats of records are displayed and some data are displayed as links, which open a detailed description of the material (title link) or perform a new search (author or keyword link).

Help
Search in:
Options:
 


1991 - 2000 / 2000
First pagePrevious page191192193194195196197198199200Next pageLast page
1991.
Časovna študija sestojne inventure z aplikacijo MOTI na zasebni gozdni posesti
Andrej Ficko, Helena Smrekar, 2023, original scientific article

Abstract: Z razvojem digitalnih orodij postaja izvedba gozdne inventure na zasebni gozdni posesti dostopnejša, hitrejša in preglednejša. V raziskavi smo v okviru projekta EIP Digigozd na šestih gozdnih posestih proučevali porabo časa za merjenje sestojne temeljnice, števila dreves in zgornje sestojne višine s slovensko različico mobilne aplikacije MOTI ter hitrost učenja merilcev. Lastniki so izvedli meritve na 149 vzorčnih ploskvah v štirinajstih sestojih, pretežno debeljakih. Zbrane meritve smo analizirali na sestojni ravni, ravni posesti in skupaj. Pri skoraj vseh lastnikih se je izkazal negativen eksponentni učinek učenja na porabo časa za inventuro, ki je v povprečju znašala 10 min/ploskev. Na podlagi mešanega linearnega modela smo ugotovili, da ob upoštevanju razlik med lastniki in med sestoji na porabo časa značilno vpliva le zaporedna številka meritve. To pomeni, da vsaj v začetni fazi, ko merilec še ni izurjen, učenje prevladujoče vpliva na hitrost izvajanja meritev. Na podlagi časovne študije in izkušenj, ki smo jih pridobili v projektu, nameravamo nadaljevati z razvojem orodij za podporo pri gospodarjenju na zasebni gozdni posesti.
Keywords: časovna analiza, gozdna inventura, mobilne aplikacije, zasebna gozdna posest, gozdnogospodarsko načrtovanje, lastniki gozdov
Published in DiRROS: 03.10.2023; Views: 395; Downloads: 96
.pdf Full text (764,80 KB)

1992.
Makroskopske in mikroskopske značilnosti lesa : breza (Batula spp.)
Jožica Gričar, Peter Prislan, 2023, professional article

Keywords: anatomija lesa, značilnosti lesa, drevesne vrste
Published in DiRROS: 03.10.2023; Views: 1835; Downloads: 117
.pdf Full text (268,72 KB)

1993.
Sonaravnejše gospodarjenje z gozdovi
Boris Rantaša, Aleš Poljanec, 2023, preface, editorial, afterword

Keywords: gospodarjenje z gozdovi, sonaravnost, trajnost
Published in DiRROS: 03.10.2023; Views: 396; Downloads: 103
.pdf Full text (414,84 KB)

1994.
1995.
1996.
1997.
Objavljanje v odprtem dostopu – zakaj, kje in za koliko? : Predavanje na Petkovem kolokviju GIS, 29. 9. 2023
Maja Peteh, 2023, other monographs and other completed works

Keywords: odprta znanost, znanstvena komunikacija
Published in DiRROS: 29.09.2023; Views: 604; Downloads: 219
.pptx Full text (6,19 MB)
This document has many files! More...

1998.
1999.
Spatial arrangement of functional domains in OxyS stress response sRNA
Vesna Štih, Heinz Amenitsch, Janez Plavec, Peter Podbevšek, 2023, original scientific article

Published in DiRROS: 29.09.2023; Views: 453; Downloads: 80
.pdf Full text (6,89 MB)
This document has many files! More...

2000.
Models for forecasting the traffic flow within the city of Ljubljana
Gašper Petelin, Rok Hribar, Gregor Papa, 2023, original scientific article

Abstract: Efficient traffic management is essential in modern urban areas. The development of intelligent traffic flow prediction systems can help to reduce travel times and maximize road capacity utilization. However, accurately modeling complex spatiotemporal dependencies can be a difficult task, especially when real-time data collection is not possible. This study aims to tackle this challenge by proposing a solution that incorporates extensive feature engineering to combine historical traffic patterns with covariates such as weather data and public holidays. The proposed approach is assessed using a new real-world data set of traffic patterns collected in Ljubljana, Slovenia. The constructed models are evaluated for their accuracy and hyperparameter sensitivity, providing insights into their performance. By providing practical solutions for real-world scenarios, the proposed approach offers an effective means to improve traffic flow prediction without relying on real-time data.
Keywords: traffic modeling, time-series forecasting, traffic-count data set, machine learning, model comparison
Published in DiRROS: 28.09.2023; Views: 434; Downloads: 172
.pdf Full text (5,05 MB)
This document has many files! More...

Search done in 0.58 sec.
Back to top