| | SLO | ENG | Piškotki in zasebnost

Večja pisava | Manjša pisava

Iskanje po katalogu digitalne knjižnice Pomoč

Iskalni niz: išči po
išči po
išči po
išči po
* po starem in bolonjskem študiju

Opcije:
  Ponastavi


1 - 5 / 5
Na začetekNa prejšnjo stran1Na naslednjo stranNa konec
1.
The Digital Pig: Automatic Systems for Behavior Detection in Weaned Pigs
Anja Žnidar, 2020, diplomsko delo

Opis: In this bachelor's thesis, we used machine learning techniques to detect pigs in group pens, which would help to improve the welfare and comfort of pigs. Mask-RCNN was used for object segmentation. The implementation was based on Resnet101. The goal was to achieve the highest possible precision in detection of the pig's body, head, and tail. We predicted that the accuracy will be the highest for body detection and lower for head and tail detection. We also concluded that the difference in precision and recall will be less than 10% between hand-labeled bounding boxes and the predicted bounding boxes from our model. As predicted, body detection represented the highest results, as the accuracy of head and tail detection was lower. The difference between precision and recall was 10% for body detection and higher than 10% for head and tail detection. Precision of the body detection was 96%, as the whole body is easier to detect. The head detection precision score was 66%. Tail detection precision was 77%, which is a large difference compared to the percentage of head detection. The use of machine learning in livestock farming could be a potentially useful tool for detecting welfare in pigs, as it would reduce the frequency of aggressive behaviors and the number of injuries. In the future, we want to refine our model to achieve higher precision for head and tail detection. Once the algorithm has clearly detected all the pigs in the image, we will try to refine the model to detect different forms of behavior. This technology would help us to evaluate welfare, which would be improved if necessary.
Ključne besede: pig, pig annotation, behavior, welfare, machine learning
Objavljeno: 08.09.2020; Ogledov: 232; Prenosov: 72
.pdf Celotno besedilo (1,40 MB)

2.
OCENJEVANJE DOBREGA POČUTJA KRAV MOLZNIC S POMOČJO PROTOKOLA WELFARE QUALITY®
Janja Končar, 2016, diplomsko delo/naloga

Opis: V raziskavi smo za ocenjevanje dobrega počutja krav molznic uporabili protokol Welfare Quality®. Gre za hierarhično zgrajen sistem, pri katerem se ocenjujejo štiri ocenjevalna področja (OP; Krmljenje, Način reje, Zdravstveno stanje in Obnašanje). Posamezno OP preverimo z 2 do 4 merili, oceno posameznega merila pa določimo na osnovi manjšega števila meritev, ki jih v večji meri izvedemo na nivoju živali. Ocene OP združimo v skupno oceno primernosti reje in rejo uvrstimo v eno izmed kategorij dobrega počutja: odlično, dobro, sprejemljivo in nerazvrščeno. Protokol smo uporabili na dveh kmetijah, usmerjenih v prirejo mleka: na kmetiji B z vezano rejo krav (n = 15) in na kmetiji G s prosto rejo krav (n = 220). Za OP smo na kmetiji B na lestvici od 0 (najslabše stanje) do 100 (najboljše stanje) dobili ocene: 19,0 za OP Krmljenje, 9,4 za OP Način reje, 26,6 za OP Zdravstveno stanje in 45,8 za OP Obnašanje. Kmetija B se je na podlagi teh ocen uvrstila v najnižjo kategorijo (nerazvrščeno). Za kmetijo G smo dobili ocene 34,0 za OP Krmljenje, 44,7 za OP Način reje, 15,7 za OP Zdravstveno stanje in 59,2 za OP Obnašanje. Kmetija G se je na podlagi teh ocen uvrstila v kategorijo sprejemljivo. V raziskavi smo ugotovili nizko stopnjo dobrega počutja živali, ocenjenega po protokolu Welfare Quality®, na izbranih kmetijah z mlečno proizvodnjo kljub številnim razlikam med kmetijama (velikost črede, menedžment, način reje).
Ključne besede: dobro počutje živali, krave molznice, protokol Welfare Quality®
Objavljeno: 03.11.2016; Ogledov: 1384; Prenosov: 116
.pdf Celotno besedilo (487,03 KB)

3.
Breeding of laboratory mice for biomedical research
Maša Skelin, Marjan Rupnik, Marko Volk, 2010, izvirni znanstveni članek

Ključne besede: mouse breeding, husbandry, animal welfare, identification
Objavljeno: 10.07.2015; Ogledov: 642; Prenosov: 14
URL Povezava na celotno besedilo

4.
Microeconomic uncertainties facilitate cooperative alliances and social welfare
Matjaž Perc, 2007, izvirni znanstveni članek

Opis: We show that microeconomic chaotic variations of payoffs in the prisoner's dilemma game maintain cooperation over a broad range of defection temptation values where otherwise economic stalemate reigns. Thus, unpredictability at micro scales impedes mutual defection that inflicts social poverty.
Ključne besede: chaotic systems, game theory, microeconomic chaos, cooperation, social welfare
Objavljeno: 07.06.2012; Ogledov: 1243; Prenosov: 81
URL Povezava na celotno besedilo

5.
Flights towards defection in economic transactions
Matjaž Perc, 2007, izvirni znanstveni članek

Opis: We show that Lévy distributed variations of payoffs in the prisoner's dilemma game impede cooperation as the frequency of rare events increases. Lévy flights thus facilitate defection, but also uphold the evolutionary process, arguably maintaining a healthy level of competitiveness amongst the agents.
Ključne besede: chaotic systems, game theory, Lévy process, cooperation, social welfare
Objavljeno: 07.06.2012; Ogledov: 1343; Prenosov: 86
URL Povezava na celotno besedilo

Iskanje izvedeno v 0.16 sek.
Na vrh
Logotipi partnerjev Univerza v Mariboru Univerza v Ljubljani Univerza na Primorskem Univerza v Novi Gorici