izvorni znanstveni rad
Municipal waste is a major environmental problem. It is well known that recycling can reduce the amount of general municipal waste. A major challenge is to increase the amount of recycled material in the waste. Computer technology allows us to operate a complex reward system linked to an embedded system for waste collection. An embedded system controlled by artificial intelligence helps to support a decision about the type of waste. This paper presents the design methodology, architecture, and initial results of the intelligent waste management application that uses a neural network to detect the type of waste. To achieve the best possible results with a neural network on collected data, we conducted experiments on ResNet and VGG neural network architectures of different depths using the transfer learning technique. The results show that the depth and complexity of the architecture were not critical for the accuracy of the neural network on our dataset. The best resulting neural network was used as the basis for waste-type decision-making. With this system, we expect a drastic reduction in incorrect waste disposal.
embedded systems; neural network; transfer learning; computer architecture; recycling; plastics; artificial intelligence
Razvojem virtualizacijskih tehnologija raste kompleksnost IT sustava, dok korisnici istovremeno zahtijevaju brži pristup resursima, napredne integracije i jednostavnost korištenja. Jedno od ključnih rješenja za ove izazove primjena je…
Ovaj rad istražuje i uspoređuje mogućnosti prosljeđivanja grafičkih kartica na Hyper-V i KVM hipervizorima prema virtualnim strojevima, detaljno opisujući metode, postupke i razlike u arhitekturi koje utječu na…
The ever-growing usage and adaptation of HTTP/3 in web traffic leverages Quick UDP Internet Connections (QUIC) as a transport protocol. QUIC is widely recognized for reduced latency, enhanced…
