Gelişmiş Arama

Basit öğe kaydını göster

dc.contributor.authorTasçı, Mustafa
dc.contributor.authorİstanbullu, Ayhan
dc.contributor.authorKosunalp, Selahattin
dc.contributor.authorIliev, Teodor
dc.contributor.authorStoyanov, Ivaylo
dc.contributor.authorBeloev, Ivan
dc.date.accessioned2024-07-03T10:13:45Z
dc.date.available2024-07-03T10:13:45Z
dc.date.issued2023en_US
dc.identifier.issn2079-9292
dc.identifier.urihttps://doi.org/10.3390/electronics12102285
dc.identifier.urihttps://hdl.handle.net/20.500.12462/14886
dc.descriptionİstanbullu, Ayhan (Balikesir Author)en_US
dc.description.abstractRice, as one of the significant grain products across the world, features a wide range of varieties in terms of usability and efficiency. It may be known with various varieties and regional names depending on the specific locations. To specify a particular rice type, different features are considered, such as shape and color. This study uses an available dataset in Turkey consisting of five different varieties: Ipsala, Arborio, Basmati, Jasmine, and Karacadag. The dataset introduces 75,000 grain images in total; each of the 5 varieties has 15,000 samples with a 256 x 256-pixel dimension. The main contribution of this paper is to create Quantized Neural Network (QNN) models to efficiently classify rice varieties with the purpose of reducing resource usage on edge devices. It is well-known that QNN is a successful method for alleviating high computational costs and power requirements in response to many Deep Learning (DL) algorithms. These advantages of the quantization process have the potential to provide an efficient environment for artificial intelligence applications on microcontroller-driven edge devices. For this purpose, we created eight different QNN networks using the MLP and Lenet-5-based deep learning models with varying quantization levels to be trained by the dataset. With the Lenet-5-based QNN network created at the W3A3 quantization level, a 99.87% classification accuracy level was achieved with only 23.1 Kb memory size used for the parameters. In addition to this tremendous benefit of memory usage, the number of billion transactions per second (GOPs) is 23 times less than similar classification studies.en_US
dc.language.isoengen_US
dc.publisherMDPIen_US
dc.relation.isversionof10.3390/electronics12102285en_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.rightsAttribution 3.0 United States*
dc.rights.urihttp://creativecommons.org/licenses/by/3.0/us/*
dc.subjectRice Classificationen_US
dc.subjectDeep Learningen_US
dc.subjectQuantized Neural Networken_US
dc.subjectLeNet-5en_US
dc.titleAn efficient classification of rice variety with quantized neural networksen_US
dc.typearticleen_US
dc.relation.journalElectronicsen_US
dc.contributor.departmentMühendislik Fakültesien_US
dc.contributor.authorID0000-0002-8073-8587en_US
dc.contributor.authorID0000-0002-7066-4238en_US
dc.contributor.authorID0000-0003-2214-8092en_US
dc.contributor.authorID0000-0001-9824-1504en_US
dc.contributor.authorID0000-0003-2014-1970en_US
dc.identifier.volume12en_US
dc.identifier.issue10en_US
dc.identifier.startpage1en_US
dc.identifier.endpage16en_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US


Bu öğenin dosyaları:

Thumbnail

Bu öğe aşağıdaki koleksiyon(lar)da görünmektedir.

Basit öğe kaydını göster

info:eu-repo/semantics/openAccess
Aksi belirtilmediği sürece bu öğenin lisansı: info:eu-repo/semantics/openAccess