Naslov
A META-HEURISTIC MULTI-OBJECTIVE APPROACH TO THE MODEL SELECTION OF CONVOLUTION NEURAL NETWORKS FOR URINARY BLADDER CANCER DIAGNOSIS
(A META-HEURISTIC MULTI-OBJECTIVE APPROACH TO THE MODEL SELECTION OF CONVOLUTION NEURAL NETWORKS FOR URINARY BLADDER CANCER DIAGNOSIS)

Autori
Lorencin, Ivan ; Smolić, Klara ; Markić, Dean ; Španjol, Josip

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), ostalo

Izvornik
1st International Conference on Chemo and Bioinformatics / - Kragujevac, 2021, 1-4

Skup
1st International Conference on Chemo and BioInformatics (ICCBIKG 2021)

Mjesto i datum
Kragujevac, Srbija, 26.10.2021. - 27.10.2021

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Convolutional neural network, Discrete particle swarm algorithm, Genetic algorithm, Urinary bladder cancer

Sažetak
Bladder cancer is one of the most common malignancies of the urinary tract. It is characterized by high metastatic potential and a high recurrence rate, which significantly complicates diagnosis and treatment. In order to increase the accuracy of the diagnostic procedure, algorithms based on artificial intelligence are introduced. This paper presents the principle of selection of convolutional neural network (CNN) models based on a multi- objective approach that maximizes classification and generalization performance. Model selection is performed on two standard CNN architectures, AlexNet and VGG-16. Classification performances are measured by using ROC analysis and the resulting AUC value. On the other hand, generalization performances are evaluated by using a 5- fold cross-validation procedure. By using these two metrics, a multi-objective fitness function, used in meta-heuristic algorithms, is designed. The multi-objective search was performed using a Genetic algorithm (GA) and a Discrete Particle Swarm (D-PS) algorithm. From obtained results, it can be noticed that such an approach has resulted in CNN models that are defined with high classification and generalization performances. When a GA-based approach is used, fitness values up to 0.97 are achieved. On the other hand, by using the D-PS approach, fitness values up to 0.99 are achieved pointing towards the conclusion that such an approach has provided models with higher classification and generalization performances.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Računarstvo, Temeljne tehničke znanosti, Kliničke medicinske znanosti, Biotehnologija u biomedicini (prirodno područje, biomedicina i zdravstvo, biotehničko područje)

POVEZANOST RADA