More than one decade 3D modeling in SolidWorks is taught at the Faculty of Mechanincal Engineering at the University of Belgrade (Serbia). As every new skill that has to be mastered, SolidWorks software package demands well-tailored teaching methodology. The best possible way of teaching would be one-on-one tutoring. One teacher per student, who would be absolutely focused on student's task completion, would provide the best results. Unfortunately, due to the lack of teaching staff and vast number of students this approach isn't possible. Instead, one teacher would present the 3D modeling task of interest on the video presenter to a group of 80 students. They would follow the whole presentation and only when the whole presentation ends, students would split into four classrooms with 20 computers each, and practice the presented tasks. During the last decade few major problems in these teaching methods were recognized. A new teaching approach was implemented. This paper presents a novel teaching methodology and achieved results in the teaching process improvement.
When measuring and analyzing site-specific yield known as the yield monitoring within a wider cycle of precise agriculture, about 30 parameters are measured from inertia for mapping yields. The most important parameters with the default three parameters that define the location (latitude, longitude and elevation) are mass grain yield and grain moisture. In addition to this data during the yield monitoring, the temperature of the grain, speed of the combine and delution of precision (DOP) were also observed in this paper. By simple statistical testing of the correlation between these parameters, the level of mutual influence was determined, among other things, the degree of influence of all mentioned and observed parameters on yield, in response to the research question whether the yield affects another parameter other than the location and physical and chemical properties of the land at that location. A different degree of influence was determined, but no significant additional impact on the yield was calculated by measuring and measuring the measurement itself. For the monitoring of the yield of seed wheat harvesting on the "Mladost" PKB, Tabla 2, the Class Lexion 450 harvester with an upgraded system for monitoring the AGL Technology manufacturer was used. For the statistical analysis, the parametric method of correlation within the software package SPSS Statistics v.21 was used.
Obećavajući koncept veštačke inteligencije koji beleži intenzivan razvoj u oblasti digitalne obrade slike je duboko učenje (Deep Learning-DL). Intenzivnije istraživanje u okviru ove oblasti beleži se poslednje dve decenije, a primenu poprima i u poljoprivrednoj industiji. U okviru ovog radu opisana je tehnologija DL koja predstavlja deo mašinskog učenja (Machine Learning-ML), bazirajući se na konvolucijske neuralne mreže (Convolution Neural Networks-CNN). Posebnu primenu zauzima u mašinskoj viziji gde omogućava mašinama da uče iz iskustva, prilagođavaju se novim tehnologijama i obavljaju ljudske zadatke. Ulazni podaci mogu biti iz raznovrsnih izvora: od klasičnih digitalnih snimaka kamere do satelitskih snimaka, kao i snimaka dobijenih pomoću hiperspektralnih, termalnih i infrared kamera. Sve je veća popularnost i upotreba dronova na poljoprivrednim površinama, a samom primenom ovih novih tehnologija dolazi se do ogromnog broja podataka koje je potrebno obraditi u realnom vremenu, stoga se i algoritmi DL sve više upotrebljavaju. U radu su prikazane dosadašnje primene CNN u primarnoj i preciznoj poljoprivredi kao i moguće primene DL u budućnosti. Ključne reči: precizna poljoprivreda, veštačka inteligencija, mašinski vid UVOD DL (Deep Learning) je posebna grana mašinskog učenja koja je najširu upotrebu našla u mašinskom vidu. Algoritmi DL su se pokazali neuporedivno preciznijim i bržim
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.