Pregled bibliografske jedinice broj: 654147
Comparison of artificial neural network and mathematical models for drying of apple slices pretreated with high intensity ultrasound
Comparison of artificial neural network and mathematical models for drying of apple slices pretreated with high intensity ultrasound // Bulgarian journal of agricultural science, 19 (2013), 6; 1372-1377 (međunarodna recenzija, članak, znanstveni)
CROSBI ID: 654147 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Comparison of artificial neural network and mathematical models for drying of apple slices pretreated with high intensity ultrasound
Autori
Karlović, Sven ; Bosiljkov, Tomislav ; Brnčić, Mladen ; Ježek, Damir ; Tripalo, Branko ; Dujmić, Filip ; Džineva, Iva
Izvornik
Bulgarian journal of agricultural science (1310-0351) 19
(2013), 6;
1372-1377
Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni
Ključne riječi
apple ; artificial neural network ; drying ; mathematical model ; ultrasound
Sažetak
In this paper artificial neural network model was compared to the traditional regression models for drying of food materials. High intensity ultrasound with amplitudes set to 25 %, 50 %, 75 % and 100 % of maximal was used for treatment of apple slices of different thickness. After 7 minutes of treatment, samples were dried in the infrared drier at two different temperatures. Four most often used regression models for drying available in literature were fitted based on experimental data, and their usability was tested on different experimental sets. For the creation of back-propagation neural network, 3 input parameters were used (amplitude of ultrasound, sample thickness and drying temperature) together with one output (moisture content). After training and validation of networks, statistical analysis was conducted and based on mean square error and correlation coefficient best network was selected. After assessment of networks and statistical results, neural networks show excellent fitting to experimental data, independently of used input parameters obtained in experiments. This is opposed to standard regression models, which had excellent fit to just one set of experimental data, and show inadequate fit even with introduced small changes in one or more input parameters.
Izvorni jezik
Engleski
Znanstvena područja
Prehrambena tehnologija
POVEZANOST RADA
Projekti:
058-0581846-0422 - Pripremanje sirovina i određivanje teksturalnih svojstava prehrambenih proizvoda (Ježek, Damir, MZOS ) ( CroRIS)
058-0581846-0717 - Primjena ultrazvuka u prehrambenoj tehnologiji i biotehnologiji (Tripalo, Branko, MZOS ) ( CroRIS)
Ustanove:
Prehrambeno-biotehnološki fakultet, Zagreb
Profili:
Tomislav Bosiljkov
(autor)
Sven Karlović
(autor)
Mladen Brnčić
(autor)
Filip Dujmić
(autor)
Branko Tripalo
(autor)
Damir Ježek
(autor)
Citiraj ovu publikaciju:
Časopis indeksira:
- Web of Science Core Collection (WoSCC)
- SCI-EXP, SSCI i/ili A&HCI
- Scopus