Search the digital library catalog

Abstract: The goal of this study was to develop an automated monitoring system for the detection of pigs’ bodies, heads and tails. The aim in the first part of the study was to recognize individual pigs (in lying and standing positions) in groups and their body parts (head/ears, and tail) by using machine learning algorithms (feature pyramid network). In the second part of the study, the goal was to improve the detection of tail posture (tail straight and curled) during activity (standing/moving around) by the use of neural network analysis (YOLOv4). Our dataset (n = 583 images, 7579 pig posture) was annotated in Labelbox from 2D video recordings of groups (n = 12–15) of weaned pigs. The model recognized each individual pig’s body with a precision of 96% related to threshold intersection over union (IoU), whilst the precision for tails was 77% and for heads this was 66%, thereby already achieving human-level precision. The precision of pig detection in groups was the highest, while head and tail detection precision were lower. As the first study was relatively time-consuming, in the second part of the study, we performed a YOLOv4 neural network analysis using 30 annotated images of our dataset for detecting straight and curled tails. With this model, we were able to recognize tail postures with a high level of precision (90%).
Keywords: pig, welfare, image processing, object detection, deep learning, smart farming
Published in DKUM: 11.07.2024; Views: 87; Downloads: 5
Full text (48,11 MB)
This document has many files! More...

Abstract: Purpose: Foreign bodies in the upper gastrointestinal tract (GIT) rarely cause urgent problems in gastroenterology. The purpose of the study was to assess the percentage of patients in whom urgent endoscopic investigation revealed true foreign bodies in the upper GIT and to evaluate the success of emergency endoscopic procedures. Methods: The study includes patients in whom urgent endoscopic investigations of the upper GIT were performed in the period 1 January 1994 to 1 May 2008. Results: 8552 patients were investigated,average age 60,6 years (SD +/- 17,1 years, range 1 - 106 years), with 3276 (38 %) females and 5276 males (62 %). In 69 patients (0,8 %), "true" foreign bodies were detected in the esophagus or stomach. In these patients a total of 90 endoscopic investigations were performed: in 65/69 patients (94,2 %) the foreign bodies were removed endoscopically; in 4 (5,8 %) cases the endoscopic procedures were unsuccessful. Among the foreign bodiesremoved were a variety metal or plastic objects, such as coins, keys, screws, hooks, batteries, razor blades, needles, lighters, buttons and parts of kitchen, toilet or writting utensils. In patients with successful endoscopic removal of the objects, no significant complications were noted. In 4 patients (4/69, 5,8 %) mild hemorrhages from the region of the esophagogastric junction were observed. Conclusion: Endoscopic technologies allow successful removal of a variety of types of foreign bodies from the upper GIT.
Keywords: tujki, zgornja prebavna cev, endoskopija, odstranitev, zapleti
Published in DKUM: 19.04.2024; Views: 156; Downloads: 2
Full text (144,82 KB)
This document is also a collection of 1 document!

Abstract: Vsako dejanje v podjetništvu se začne z notranjimi vzgibi posameznika, njegovimi osebnimi vrednotami, motivacijo in motivi, ki ga nato ženejo k doseganju svojih ciljev. Motivi in spodbude za vstop v podjetništvo se razlikujejo od posameznika do posameznika, kot tudi od okolja, v katerem živijo. Podjetništvo zahteva od podjetnikov različne veščine, znanje, inovativnost, predvsem pa drugačen pristop pri iskanju rešitev zase, za družbo okoli sebe in okolje, v katerem živijo. Prav tu se stikajo področja, ki jih proučujemo v pričujočem delu – podjetništvo, motivacija in trajnostni razvoj, ki jih lahko skupaj prepoznamo kot rešitev za ohranitev sveta, ki ga poznamo in želimo obdržati. V magistrskem delu smo želeli ugotoviti, zakaj se podjetniki odločijo stremeti k trajnostnem razvoju v podjetništvu, kaj jih pri tem motivira in kaj zavira. Magistrsko delo je razdeljeno na dva sklopa, teoretičnega in empiričnega. V teoretičnem delu smo se osredotočili na posamezne koncepte in pripadajoče pojave. V empiričnem delu smo uporabili podatkovno bazo GEM za leto 2022 in s statističnimi testi ugotavljali povezanost med različnimi podjetniškimi motivi in upoštevanjem družbenih in/ali okoljskih vplivov poslovnih odločitev pri podjetnikih v celotni zgodnji podjetniški aktivnosti (TEA). Ugotovili smo, da pri nekaterih motivih ter upoštevanju družbenih in/ali okoljskih vplivov obstaja pozitivna povezava, medtem ko pri drugih ne.
Keywords: trajnostni razvoj, motivacija za podjetništvo, podjetništvo, trajnostno podjetništvo, GEM raziskava
Published in DKUM: 18.01.2024; Views: 424; Downloads: 86
Full text (1,91 MB)

Abstract: V diplomskem delu smo z namenom hitrejšega zaznavanja spremembe temperature v posodi na temperaturni NTK senzor, ki je nameščen na sredini posamezne tuljave, dodali temperaturno prevodno ploščico. Pri izbiri materiala, debeline in oblike smo morali biti pozorni, da je iz nemagnetnega materiala, da dobro prevaja toploto in da se v ploščici med segrevanjem posode inducira čim manj vrtinčnih tokov. Pomembna je tudi namestitev toplotno prevodne ploščice z namenom čim boljšega termalnega stika ploščice z NTK senzorjem in steklom, zato smo v diplomskem delu preizkusili več različnih postavitev ploščice na NTK senzor z uporabo toplotno prevodne paste, termalne blazinice in lista sljude. Z izboljšanim zaznavanjem temperature v posodi smo napisali tudi avtomatske algoritme za segrevanje vodnih jedi, topljenje, taljenje in pečenje hrane.
Keywords: nadzor temperature, indukcijsko kuhališče, toplotno prevodna ploščica, prenos toplote
Published in DKUM: 21.01.2022; Views: 1290; Downloads: 0

Abstract: 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.
Keywords: pig, pig annotation, behavior, welfare, machine learning
Published in DKUM: 08.09.2020; Views: 1051; Downloads: 184
Full text (1,40 MB)